system

Abstract

The system according to this embodiment aims to detect harassment in internal company communications and to intervene automatically. [Solution] The system according to the embodiment comprises a monitoring unit, a detection unit, and an intervention unit. The monitoring unit monitors internal company communications. The detection unit detects harassment from communications monitored by the monitoring unit. The intervention unit automatically intervenes in response to harassment detected by the detection unit.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , , , , ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to effectively detect harassment in in-house communication and respond promptly.

[0005] The system according to the embodiment aims to detect harassment in in-house communication and automatically intervene.

Means for Solving the Problems

[0006] The system according to the embodiment includes a monitoring unit, a detection unit, and an intervention unit. The monitoring unit monitors in-house communication. The detection unit detects harassment from the communication monitored by the monitoring unit. The intervention unit automatically intervenes in the harassment detected by the detection unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect harassment in internal company communications and intervene automatically. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The agent system according to an embodiment of the present invention is a system that monitors employee communication and automatically intervenes when harassment is detected. This agent system improves psychological safety and maximizes work efficiency by monitoring employee communication and automatically intervening when harassment is detected. For example, the agent system patrols internal communications such as chats and video conferences and checks for remarks that could lead to harassment. Next, when it finds communication that could lead to harassment, it issues a warning. For example, it displays a message such as, "This remark may lead to harassment. Please be careful!" This helps to raise awareness of unintentional harassment. Furthermore, it provides a function to save the communication when harassment is detected and submit it to a consultation service with a single button. For example, it can save chat logs or video conference recordings when harassment occurs and submit them to a consultation service as needed. This allows for securing evidence and responding quickly. It also has a function to statistically analyze harassment trends and report them for each organization. For example, if harassment is occurring frequently in a particular department, the trend can be analyzed and used to consider organizational improvements. This can improve the psychological safety of the entire organization. This system improves psychological safety, maximizes work efficiency, and minimizes the risk of legal liability and damage to the company's image. For example, a reduction in harassment reduces employee stress and creates an environment where employees can concentrate on their work. It also enables a swift response to harassment, improving the company's credibility. In this way, the agent system can improve psychological safety and maximize work efficiency by monitoring employee communication, detecting harassment, and automatically intervening.

[0029] The agent system according to this embodiment comprises a monitoring unit, a detection unit, and an intervention unit. The monitoring unit monitors employee communication. The monitoring unit, for example, patrols internal communications such as chats and video conferences and checks for remarks that could lead to harassment. The monitoring unit makes a judgment by comprehensively considering the context and communications across multiple channels. For example, if a particular employee repeatedly makes aggressive remarks, it determines whether those remarks constitute harassment. The detection unit detects harassment from communications monitored by the monitoring unit. The detection unit, for example, uses natural language processing technology to detect remarks that constitute harassment. The detection unit statistically analyzes harassment trends and reports them for each organization. For example, if harassment is frequent in a particular department, the trend can be analyzed and used to consider organizational improvements. The intervention unit automatically intervenes in response to harassment detected by the detection unit. For example, if the intervention unit finds communication that could lead to harassment, it issues a warning. For example, it displays a message such as, "This remark may lead to harassment. Please be careful!" The intervention unit saves communications when harassment is detected and can submit them to a consultation service with a single button click. For example, it can save chat logs or video conference recordings from when harassment occurs and submit them to the consultation service as needed. This ensures that evidence is secured and allows for a swift response. As a result, the agent system according to this embodiment can improve psychological safety and maximize work efficiency by monitoring employee communications, detecting harassment, and automatically intervening.

[0030] The monitoring department monitors employee communication. For example, the monitoring department patrols internal communications such as chat and video conferences to check for remarks that could lead to harassment. Specifically, the monitoring department analyzes chat text data and video conference audio data in real time to detect specific keywords and phrases. This includes using natural language processing technology to analyze the intent and emotion of remarks. For example, if aggressive words or insulting expressions are included, the monitoring department comprehensively evaluates the surrounding context and tone of the remarks to determine whether the remarks constitute harassment. In addition, the monitoring department monitors multiple communication channels in an integrated manner to check whether a particular employee consistently engages in aggressive behavior across different channels. For example, by comparing remarks in chat and video conferences, if consistent harassing behavior is observed, appropriate action will be taken against that employee. Furthermore, by accumulating historical data and analyzing long-term trends, the monitoring department can understand the frequency and patterns of harassment occurrences in specific employees or departments. This allows the monitoring department to contribute not only to real-time monitoring but also to long-term risk management and the development of preventive measures.

[0031] The detection unit detects harassment from communications monitored by the monitoring unit. For example, the detection unit uses natural language processing technology to detect harassing remarks. Specifically, it analyzes text and audio data to identify remarks containing aggressive or insulting language. This involves using machine learning algorithms to learn from past harassment cases and build a model to determine whether a new remark constitutes harassment. For example, if a remark contains specific keywords or phrases, it is likely to be considered harassment. The detection unit also analyzes the emotion and tone of remarks to more accurately understand the intent behind them. For instance, the same words may be considered harassing depending on the tone and context, so these factors are comprehensively evaluated. Furthermore, the detection unit statistically analyzes harassment trends and reports them for each organization. For example, if harassment is frequent in a particular department, the trend can be analyzed and used to consider organizational improvements. In this way, the detection unit contributes to the early detection and prevention of harassment, improving psychological safety throughout the organization.

[0032] The intervention unit automatically intervenes in response to harassment detected by the detection unit. For example, if the intervention unit finds communication that could lead to harassment, it will issue a warning. Specifically, if a statement constituting harassment is detected, it will immediately send a warning message to the employee in question. For example, it will display a message such as, "This statement may lead to harassment. Please be careful!" to make the employee aware that their behavior is inappropriate. The intervention unit can also save the communication at the time harassment is detected and submit it to the consultation desk with a single click. Specifically, it will automatically save chat logs and video conference recordings when harassment occurs and provide an interface for submitting them to the consultation desk as needed. This ensures that evidence is secured and a swift response is possible. Furthermore, the intervention unit can also provide educational programs and counseling to the employee in question to prevent the recurrence of harassment. For example, if harassing behavior is repeated, a special training session will be set up for that employee to learn about the impact of harassment and prevention measures. The intervention unit can also regularly review the occurrence of harassment and propose improvement measures for the entire organization. This allows the intervention department to detect harassment early and respond quickly, thereby improving psychological safety throughout the organization.

[0033] The monitoring department can patrol internal communications such as chats and video conferences, and make judgments by comprehensively considering the context and communications across multiple channels. For example, if a particular employee repeatedly makes aggressive remarks, the monitoring department can determine whether those remarks constitute harassment. This improves the accuracy of harassment detection by comprehensively considering the context and communications across multiple channels. Some or all of the above processing in the monitoring department may be performed using, for example, generative AI, or not. For example, the monitoring department can input chat and video conference data into a generative AI and have the generative AI perform a comprehensive judgment of the context and communications across multiple channels.

[0034] The intervention unit can issue a warning when it detects communication that could lead to harassment. For example, when the intervention unit detects communication that could lead to harassment, it will issue a warning. For example, it may display a message such as, "This statement may lead to harassment. Please be careful!" This can encourage awareness of unintentional harassment. Some or all of the above processing in the intervention unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the intervention unit can input data on communication that could lead to harassment into a generative AI and have the generative AI generate a warning message.

[0035] The intervention unit can save communications when harassment is detected and submit them to a consultation service with the push of a button. For example, the intervention unit can save communications when harassment is detected and submit them to a consultation service with the push of a button. For example, it can save chat logs and video conference recordings from when harassment occurs and submit them to a consultation service as needed. This ensures evidence is secured and allows for a swift response. Some or all of the above processing in the intervention unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the intervention unit can input chat logs and video conference recordings from when harassment occurs into a generative AI and have the generative AI perform saving and submission to a consultation service.

[0036] The detection unit can statistically analyze harassment trends and report them for each organization. For example, if harassment is frequent in a particular department, the detection unit can analyze the trends and use the findings to consider organizational improvements. This can improve the overall psychological safety of the organization. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input harassment trend data into a generative AI and have the generative AI perform statistical analysis and reporting.

[0037] The monitoring unit can analyze the frequency of occurrence of specific keywords and phrases during monitoring and assess the likelihood of harassment. For example, the monitoring unit will rate the likelihood of harassment highly if certain aggressive words or phrases are used frequently. The monitoring unit analyzes the frequency of occurrence of words that indicate negative emotions and finds signs of harassment. The monitoring unit monitors words and phrases that are repeatedly used against specific users and assesses the likelihood of harassment. This allows for a high assessment of the likelihood of harassment by analyzing the frequency of occurrence of specific keywords and phrases. Some or all of the above processing in the monitoring unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the monitoring unit can input data on specific keywords and phrases into a generative AI and have the generative AI perform frequency analysis and assess the likelihood of harassment.

[0038] The monitoring unit can detect similar patterns by referring to past harassment cases during monitoring. For example, the monitoring unit can refer to a database of past harassment cases and detect similar behavioral patterns. The monitoring unit uses a model learned from past cases to find signs of new harassment. The monitoring unit compares past cases with current communication, finds similarities, and issues a warning. In this way, by referring to past harassment cases, similar behavioral patterns can be detected and warnings can be issued. Some or all of the above processing in the monitoring unit may be performed using, for example, generative AI, or without generative AI. For example, the monitoring unit can input data on past harassment cases into a generative AI and have the generative AI perform the detection of similar patterns.

[0039] The monitoring unit can apply different monitoring standards based on the user's job duties and position during monitoring. For example, the monitoring unit may apply stricter monitoring standards to users in management positions. For new employees, it may apply monitoring standards that emphasize support. For specific project teams, it may apply monitoring standards that are appropriate to the importance of the project. This allows for appropriate monitoring by applying different monitoring standards based on the user's job duties and position. Some or all of the above processes in the monitoring unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the monitoring unit can input data on the user's job duties and position into a generative AI and have the generative AI apply different monitoring standards.

[0040] The monitoring unit can analyze users' social media activity and monitor related communications during monitoring. For example, the monitoring unit can analyze users' social media posts and assess their potential impact on internal communications. The monitoring unit can focus its monitoring on internal communications of users who frequently post negative comments on social media. The monitoring unit can analyze social media trends and monitor related communications within the company. This allows the monitoring unit to monitor relevant communications within the company by analyzing users' social media activity. Some or all of the above processes in the monitoring unit may be performed using, for example, generative AI, or not using generative AI. For example, the monitoring unit can input data on users' social media activity into a generative AI and have the generative AI perform monitoring of related communications.

[0041] The detection unit can analyze the tone and context of communication to assess the possibility of harassment upon detection. For example, the detection unit assesses communication containing an aggressive tone or negative context as potentially harassing. The detection unit analyzes the context and determines whether specific words constitute harassment. The detection unit detects changes in tone and context to find signs of harassment. In this way, the possibility of harassment can be assessed by analyzing the tone and context of communication. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input data on the tone and context of communication into a generative AI and have the generative AI perform the assessment of the possibility of harassment.

[0042] The detection unit can detect similar patterns by referring to past harassment cases during detection. For example, the detection unit can refer to a database of past harassment cases and detect similar behavioral patterns. The detection unit uses a model learned from past cases to find signs of new harassment. The detection unit compares past cases with current communication, finds similarities, and issues a warning. In this way, by referring to past harassment cases, similar behavioral patterns can be detected and warnings can be issued. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input data of past harassment cases into a generative AI and have the generative AI perform the detection of similar patterns.

[0043] The detection unit can apply different detection criteria based on the user's job duties and position during detection. For example, the detection unit applies stricter detection criteria to users in management positions. For new employees, it applies detection criteria that emphasize support. For specific project teams, it applies detection criteria that are appropriate to the importance of the project. This allows for appropriate detection by applying different detection criteria based on the user's job duties and position. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the detection unit can input data on the user's job duties and position into a generative AI and have the generative AI apply different detection criteria.

[0044] The detection unit can analyze a user's social media activity and detect relevant communications during detection. For example, the detection unit analyzes a user's social media posts and evaluates their potential impact on internal communications. The detection unit focuses on detecting internal communications of users who frequently post negative comments on social media. The detection unit analyzes social media trends and detects relevant communications within the company. In this way, relevant communications within the company can be detected by analyzing a user's social media activity. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input data on the user's social media activity into a generative AI and have the generative AI perform the detection of relevant communications.

[0045] The intervention unit can apply different intervention methods depending on the type and severity of the harassment during an intervention. For example, for mild harassment, the intervention unit displays a warning message. For moderate harassment, the intervention unit encourages reporting to a supervisor. For serious harassment, the intervention unit immediately reports to the human resources department. This allows for appropriate responses by applying different intervention methods depending on the type and severity of the harassment. Some or all of the above processing in the intervention unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intervention unit can input data on the type and severity of harassment into a generative AI and have the generative AI execute the application of different intervention methods.

[0046] The intervention unit can select the optimal intervention method by referring to past intervention cases during the intervention. For example, the intervention unit can refer to past intervention cases and select the optimal intervention method for similar cases. The intervention unit applies an effective intervention method based on past success cases. The intervention unit analyzes past failure cases and adjusts the intervention method to avoid repeating the same mistakes. In this way, the optimal intervention method can be selected by referring to past intervention cases. Some or all of the above processes in the intervention unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intervention unit can input data on past intervention cases into a generative AI and have the generative AI perform the selection of the optimal intervention method.

[0047] The intervention unit can apply different intervention methods based on the user's job duties and position at the time of intervention. For example, the intervention unit may apply stricter intervention methods to users in management positions. For new employees, it may apply support-oriented intervention methods. For specific project teams, it may apply intervention methods appropriate to the importance of the project. This allows for appropriate intervention by applying different intervention methods based on the user's job duties and position. Some or all of the above processing in the intervention unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the intervention unit can input data on the user's job duties and position into a generative AI and have the generative AI execute the application of different intervention methods.

[0048] The intervention unit can analyze a user's social media activity and intervene in relevant communications at the time of intervention. For example, the intervention unit can analyze a user's social media posts and assess their potential impact on internal communications. The intervention unit can intervene in internal communications of users who frequently post negative comments on social media. The intervention unit can analyze social media trends and intervene in relevant communications within the company. This allows for appropriate intervention in relevant communications within the company by analyzing a user's social media activity. Some or all of the above processing in the intervention unit may be performed using, for example, generative AI, or without generative AI. For example, the intervention unit can input data on a user's social media activity into a generative AI and have the generative AI perform interventions on relevant communications.

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

[0050] The monitoring unit can analyze the frequency and patterns of user communication to detect abnormal behavior. For example, if a particular user suddenly increases the frequency of their communication, the unit will detect this anomaly and issue a warning. The monitoring unit analyzes the timing and recipients of user communication patterns to detect unusual behavior. Furthermore, the monitoring unit can analyze the content of user communication to identify sudden changes or abnormal patterns. As a result, by analyzing the frequency and patterns of communication, abnormal behavior can be detected early, and appropriate responses can be taken.

[0051] The detection unit can analyze the content of user communications and assess the risk of harassment related to specific topics. For example, if there is a high risk of harassment in communications related to a particular project or task, it can assess the risk and issue a warning. The detection unit analyzes the frequency of negative remarks related to specific topics to find signs of harassment. Furthermore, the detection unit can analyze the tone and context of communications related to specific topics to assess the risk of harassment. This allows for more appropriate responses by assessing the risk of harassment related to specific topics.

[0052] The intervention unit can analyze the content of user communications and adjust its intervention methods for specific topics. For example, if there is a high risk of harassment in communications related to a particular project or task, it will issue a warning about that topic. If there are many negative comments on a particular topic, the intervention unit will provide support resources related to that topic. Furthermore, the intervention unit can analyze the tone and context of communications on a particular topic and select an appropriate intervention method. This allows for more effective intervention by adjusting the intervention method for specific topics.

[0053] The monitoring unit can analyze the content of user communications and evaluate the frequency of occurrence of specific keywords and phrases. For example, if certain aggressive words or phrases are used frequently, it can evaluate their frequency and issue a warning. The monitoring unit can analyze the frequency of words indicating negative emotions to identify signs of harassment. Furthermore, the monitoring unit can monitor words and phrases repeatedly used towards specific users and assess the potential for harassment. This allows for a high assessment of the potential for harassment by analyzing the frequency of occurrence of specific keywords and phrases.

[0054] The intervention unit can analyze the content of user communication and select the optimal intervention method by referring to past intervention cases. For example, it can refer to past intervention cases and select the optimal intervention method for similar cases. The intervention unit applies effective intervention methods based on past successes. Furthermore, the intervention unit can analyze past failures and adjust the intervention method to avoid repeating the same mistakes. In this way, the optimal intervention method can be selected by referring to past intervention cases.

[0055] The following briefly describes the processing flow for example form 1.

[0056] Step 1: The monitoring department monitors employee communication. The monitoring department patrols internal communications such as chats and video conferences to check for any remarks that could lead to harassment. The monitoring department makes a comprehensive judgment based on the context and communication across multiple channels. For example, if a particular employee repeatedly makes aggressive remarks, the monitoring department will determine whether those remarks constitute harassment. Step 2: The detection unit detects harassment from communications monitored by the monitoring unit. The detection unit uses natural language processing technology to detect statements that constitute harassment. The detection unit statistically analyzes harassment trends and reports them for each organization. For example, if harassment is frequent in a particular department, the trends can be analyzed and used to consider organizational improvements. Step 3: The intervention unit automatically intervenes in response to harassment detected by the detection unit. When the intervention unit finds communication that could lead to harassment, it issues a warning. For example, it displays a message such as, "This statement may lead to harassment. Please be careful!" The intervention unit saves the communication at the time harassment is detected and can submit it to a consultation service with a single button click. For example, it can save chat logs or video conference recordings from when harassment occurred and submit them to a consultation service as needed.

[0057] (Example of form 2) The agent system according to an embodiment of the present invention is a system that monitors employee communication and automatically intervenes when harassment is detected. This agent system improves psychological safety and maximizes work efficiency by monitoring employee communication and automatically intervening when harassment is detected. For example, the agent system patrols internal communications such as chats and video conferences and checks for remarks that could lead to harassment. Next, when it finds communication that could lead to harassment, it issues a warning. For example, it displays a message such as, "This remark may lead to harassment. Please be careful!" This helps to raise awareness of unintentional harassment. Furthermore, it provides a function to save the communication when harassment is detected and submit it to a consultation service with a single button. For example, it can save chat logs or video conference recordings when harassment occurs and submit them to a consultation service as needed. This allows for securing evidence and responding quickly. It also has a function to statistically analyze harassment trends and report them for each organization. For example, if harassment is occurring frequently in a particular department, the trend can be analyzed and used to consider organizational improvements. This can improve the psychological safety of the entire organization. This system improves psychological safety, maximizes work efficiency, and minimizes the risk of legal liability and damage to the company's image. For example, a reduction in harassment reduces employee stress and creates an environment where employees can concentrate on their work. It also enables a swift response to harassment, improving the company's credibility. In this way, the agent system can improve psychological safety and maximize work efficiency by monitoring employee communication, detecting harassment, and automatically intervening.

[0058] The agent system according to this embodiment comprises a monitoring unit, a detection unit, and an intervention unit. The monitoring unit monitors employee communication. The monitoring unit, for example, patrols internal communications such as chats and video conferences and checks for remarks that could lead to harassment. The monitoring unit makes a judgment by comprehensively considering the context and communications across multiple channels. For example, if a particular employee repeatedly makes aggressive remarks, it determines whether those remarks constitute harassment. The detection unit detects harassment from communications monitored by the monitoring unit. The detection unit, for example, uses natural language processing technology to detect remarks that constitute harassment. The detection unit statistically analyzes harassment trends and reports them for each organization. For example, if harassment is frequent in a particular department, the trend can be analyzed and used to consider organizational improvements. The intervention unit automatically intervenes in response to harassment detected by the detection unit. For example, if the intervention unit finds communication that could lead to harassment, it issues a warning. For example, it displays a message such as, "This remark may lead to harassment. Please be careful!" The intervention unit saves communications when harassment is detected and can submit them to a consultation service with a single button click. For example, it can save chat logs or video conference recordings from when harassment occurs and submit them to the consultation service as needed. This ensures that evidence is secured and allows for a swift response. As a result, the agent system according to this embodiment can improve psychological safety and maximize work efficiency by monitoring employee communications, detecting harassment, and automatically intervening.

[0059] The monitoring department monitors employee communication. For example, the monitoring department patrols internal communications such as chat and video conferences to check for remarks that could lead to harassment. Specifically, the monitoring department analyzes chat text data and video conference audio data in real time to detect specific keywords and phrases. This includes using natural language processing technology to analyze the intent and emotion of remarks. For example, if aggressive words or insulting expressions are included, the monitoring department comprehensively evaluates the surrounding context and tone of the remarks to determine whether the remarks constitute harassment. In addition, the monitoring department monitors multiple communication channels in an integrated manner to check whether a particular employee consistently engages in aggressive behavior across different channels. For example, by comparing remarks in chat and video conferences, if consistent harassing behavior is observed, appropriate action will be taken against that employee. Furthermore, by accumulating historical data and analyzing long-term trends, the monitoring department can understand the frequency and patterns of harassment occurrences in specific employees or departments. This allows the monitoring department to contribute not only to real-time monitoring but also to long-term risk management and the development of preventive measures.

[0060] The detection unit detects harassment from communications monitored by the monitoring unit. For example, the detection unit uses natural language processing technology to detect harassing remarks. Specifically, it analyzes text and audio data to identify remarks containing aggressive or insulting language. This involves using machine learning algorithms to learn from past harassment cases and build a model to determine whether a new remark constitutes harassment. For example, if a remark contains specific keywords or phrases, it is likely to be considered harassment. The detection unit also analyzes the emotion and tone of remarks to more accurately understand the intent behind them. For instance, the same words may be considered harassing depending on the tone and context, so these factors are comprehensively evaluated. Furthermore, the detection unit statistically analyzes harassment trends and reports them for each organization. For example, if harassment is frequent in a particular department, the trend can be analyzed and used to consider organizational improvements. In this way, the detection unit contributes to the early detection and prevention of harassment, improving psychological safety throughout the organization.

[0061] The intervention unit automatically intervenes in response to harassment detected by the detection unit. For example, if the intervention unit finds communication that could lead to harassment, it will issue a warning. Specifically, if a statement constituting harassment is detected, it will immediately send a warning message to the employee in question. For example, it will display a message such as, "This statement may lead to harassment. Please be careful!" to make the employee aware that their behavior is inappropriate. The intervention unit can also save the communication at the time harassment is detected and submit it to the consultation desk with a single click. Specifically, it will automatically save chat logs and video conference recordings when harassment occurs and provide an interface for submitting them to the consultation desk as needed. This ensures that evidence is secured and a swift response is possible. Furthermore, the intervention unit can also provide educational programs and counseling to the employee in question to prevent the recurrence of harassment. For example, if harassing behavior is repeated, a special training session will be set up for that employee to learn about the impact of harassment and prevention measures. The intervention unit can also regularly review the occurrence of harassment and propose improvement measures for the entire organization. This allows the intervention department to detect harassment early and respond quickly, thereby improving psychological safety throughout the organization.

[0062] The monitoring department can patrol internal communications such as chats and video conferences, and make judgments by comprehensively considering the context and communications across multiple channels. For example, if a particular employee repeatedly makes aggressive remarks, the monitoring department can determine whether those remarks constitute harassment. This improves the accuracy of harassment detection by comprehensively considering the context and communications across multiple channels. Some or all of the above processing in the monitoring department may be performed using, for example, generative AI, or not. For example, the monitoring department can input chat and video conference data into a generative AI and have the generative AI perform a comprehensive judgment of the context and communications across multiple channels.

[0063] The intervention unit can issue a warning when it detects communication that could lead to harassment. For example, when the intervention unit detects communication that could lead to harassment, it will issue a warning. For example, it may display a message such as, "This statement may lead to harassment. Please be careful!" This can encourage awareness of unintentional harassment. Some or all of the above processing in the intervention unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the intervention unit can input data on communication that could lead to harassment into a generative AI and have the generative AI generate a warning message.

[0064] The intervention unit can save communications when harassment is detected and submit them to a consultation service with the push of a button. For example, the intervention unit can save communications when harassment is detected and submit them to a consultation service with the push of a button. For example, it can save chat logs and video conference recordings from when harassment occurs and submit them to a consultation service as needed. This ensures evidence is secured and allows for a swift response. Some or all of the above processing in the intervention unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the intervention unit can input chat logs and video conference recordings from when harassment occurs into a generative AI and have the generative AI perform saving and submission to a consultation service.

[0065] The detection unit can statistically analyze harassment trends and report them for each organization. For example, if harassment is frequent in a particular department, the detection unit can analyze the trends and use the findings to consider organizational improvements. This can improve the overall psychological safety of the organization. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input harassment trend data into a generative AI and have the generative AI perform statistical analysis and reporting.

[0066] The monitoring unit can estimate the user's emotions and adjust the monitoring frequency based on the estimated emotions. For example, if the user is stressed, the monitoring unit can increase the monitoring frequency to detect problems early. If the user is relaxed, the monitoring unit can reduce the monitoring frequency to respect privacy. If the user is in a hurry, the monitoring unit can focus its monitoring on important communications. This allows for early problem detection and respect for privacy by adjusting the monitoring frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using or without a generative AI. For example, the monitoring unit can input user emotion data into a generative AI and have the generative AI adjust the monitoring frequency.

[0067] The monitoring unit can analyze the frequency of occurrence of specific keywords and phrases during monitoring and assess the likelihood of harassment. For example, the monitoring unit will rate the likelihood of harassment highly if certain aggressive words or phrases are used frequently. The monitoring unit analyzes the frequency of occurrence of words that indicate negative emotions and finds signs of harassment. The monitoring unit monitors words and phrases that are repeatedly used against specific users and assesses the likelihood of harassment. This allows for a high assessment of the likelihood of harassment by analyzing the frequency of occurrence of specific keywords and phrases. Some or all of the above processing in the monitoring unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the monitoring unit can input data on specific keywords and phrases into a generative AI and have the generative AI perform frequency analysis and assess the likelihood of harassment.

[0068] The monitoring unit can detect similar patterns by referring to past harassment cases during monitoring. For example, the monitoring unit can refer to a database of past harassment cases and detect similar behavioral patterns. The monitoring unit uses a model learned from past cases to find signs of new harassment. The monitoring unit compares past cases with current communication, finds similarities, and issues a warning. In this way, by referring to past harassment cases, similar behavioral patterns can be detected and warnings can be issued. Some or all of the above processing in the monitoring unit may be performed using, for example, generative AI, or without generative AI. For example, the monitoring unit can input data on past harassment cases into a generative AI and have the generative AI perform the detection of similar patterns.

[0069] The monitoring unit can estimate the user's emotions and determine the priority of communications to monitor based on the estimated emotions. For example, if the user is stressed, the monitoring unit will prioritize monitoring that user's communications. If the user is relaxed, the monitoring unit will prioritize monitoring other important communications. If the user is in a hurry, the monitoring unit will prioritize monitoring important conversations or meetings. This allows for prioritizing important communications by determining the priority of communications to monitor based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using or without a generative AI. For example, the monitoring unit can input user emotion data into a generative AI and have the generative AI determine the priority of communications to monitor.

[0070] The monitoring unit can apply different monitoring standards based on the user's job duties and position during monitoring. For example, the monitoring unit may apply stricter monitoring standards to users in management positions. For new employees, it may apply monitoring standards that emphasize support. For specific project teams, it may apply monitoring standards that are appropriate to the importance of the project. This allows for appropriate monitoring by applying different monitoring standards based on the user's job duties and position. Some or all of the above processes in the monitoring unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the monitoring unit can input data on the user's job duties and position into a generative AI and have the generative AI apply different monitoring standards.

[0071] The monitoring unit can analyze users' social media activity and monitor related communications during monitoring. For example, the monitoring unit can analyze users' social media posts and assess their potential impact on internal communications. The monitoring unit can focus its monitoring on internal communications of users who frequently post negative comments on social media. The monitoring unit can analyze social media trends and monitor related communications within the company. This allows the monitoring unit to monitor relevant communications within the company by analyzing users' social media activity. Some or all of the above processes in the monitoring unit may be performed using, for example, generative AI, or not using generative AI. For example, the monitoring unit can input data on users' social media activity into a generative AI and have the generative AI perform monitoring of related communications.

[0072] The detection unit can estimate the user's emotions and adjust the harassment detection criteria based on the estimated emotions. For example, if the user is stressed, the detection unit will tighten the harassment detection criteria. If the user is relaxed, the detection unit will loosen the harassment detection criteria. If the user is in a hurry, the detection unit will focus on detecting harassment in important communications. This allows for more appropriate harassment detection by adjusting the harassment detection criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using a generative AI, or not. For example, the detection unit can input user emotion data into a generative AI and have the generative AI adjust the harassment detection criteria.

[0073] The detection unit can analyze the tone and context of communication to assess the possibility of harassment upon detection. For example, the detection unit assesses communication containing an aggressive tone or negative context as potentially harassing. The detection unit analyzes the context and determines whether specific words constitute harassment. The detection unit detects changes in tone and context to find signs of harassment. In this way, the possibility of harassment can be assessed by analyzing the tone and context of communication. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input data on the tone and context of communication into a generative AI and have the generative AI perform the assessment of the possibility of harassment.

[0074] The detection unit can detect similar patterns by referring to past harassment cases during detection. For example, the detection unit can refer to a database of past harassment cases and detect similar behavioral patterns. The detection unit uses a model learned from past cases to find signs of new harassment. The detection unit compares past cases with current communication, finds similarities, and issues a warning. In this way, by referring to past harassment cases, similar behavioral patterns can be detected and warnings can be issued. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input data of past harassment cases into a generative AI and have the generative AI perform the detection of similar patterns.

[0075] The detection unit can estimate the user's emotions and adjust the display method of the detection results based on the estimated user emotions. For example, if the user is stressed, the detection unit provides a concise and highly visible display method. If the user is relaxed, the detection unit provides a display method that includes detailed information. If the user is in a hurry, the detection unit provides a display method that gets straight to the point. In this way, by adjusting the display method of the detection results based on the user's emotions, a display method that is easy for the user to understand can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the detection unit may be performed using a generative AI, for example, or without a generative AI. For example, the detection unit can input user emotion data into a generative AI and have the generative AI adjust the display method of the detection results.

[0076] The detection unit can apply different detection criteria based on the user's job duties and position during detection. For example, the detection unit applies stricter detection criteria to users in management positions. For new employees, it applies detection criteria that emphasize support. For specific project teams, it applies detection criteria that are appropriate to the importance of the project. This allows for appropriate detection by applying different detection criteria based on the user's job duties and position. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the detection unit can input data on the user's job duties and position into a generative AI and have the generative AI apply different detection criteria.

[0077] The detection unit can analyze a user's social media activity and detect relevant communications during detection. For example, the detection unit analyzes a user's social media posts and evaluates their potential impact on internal communications. The detection unit focuses on detecting internal communications of users who frequently post negative comments on social media. The detection unit analyzes social media trends and detects relevant communications within the company. In this way, relevant communications within the company can be detected by analyzing a user's social media activity. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can input data on the user's social media activity into a generative AI and have the generative AI perform the detection of relevant communications.

[0078] The intervention unit can estimate the user's emotions and adjust its intervention method based on the estimated emotions. For example, if the user is stressed, the intervention unit will give a gentle warning. If the user is relaxed, the intervention unit will give a direct warning. If the user is in a hurry, the intervention unit will give a concise and quick warning. This allows for more appropriate intervention by adjusting the intervention method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the intervention unit may be performed using a generative AI, or not. For example, the intervention unit can input user emotion data into a generative AI and have the generative AI adjust the intervention method.

[0079] The intervention unit can apply different intervention methods depending on the type and severity of the harassment during an intervention. For example, for mild harassment, the intervention unit displays a warning message. For moderate harassment, the intervention unit encourages reporting to a supervisor. For serious harassment, the intervention unit immediately reports to the human resources department. This allows for appropriate responses by applying different intervention methods depending on the type and severity of the harassment. Some or all of the above processing in the intervention unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intervention unit can input data on the type and severity of harassment into a generative AI and have the generative AI execute the application of different intervention methods.

[0080] The intervention unit can select the optimal intervention method by referring to past intervention cases during the intervention. For example, the intervention unit can refer to past intervention cases and select the optimal intervention method for similar cases. The intervention unit applies an effective intervention method based on past success cases. The intervention unit analyzes past failure cases and adjusts the intervention method to avoid repeating the same mistakes. In this way, the optimal intervention method can be selected by referring to past intervention cases. Some or all of the above processes in the intervention unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intervention unit can input data on past intervention cases into a generative AI and have the generative AI perform the selection of the optimal intervention method.

[0081] The intervention unit can estimate the user's emotions and adjust the timing of interventions based on the estimated emotions. For example, if the user is stressed, the intervention unit can intervene early to prevent problems. If the user is relaxed, the intervention unit can intervene at the appropriate time. If the user is in a hurry, the intervention unit can intervene quickly to resolve the problem. In this way, problems can be prevented by adjusting the timing of interventions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the intervention unit may be performed using a generative AI, or not using a generative AI. For example, the intervention unit can input user emotion data into a generative AI and have the generative AI adjust the timing of interventions.

[0082] The intervention unit can apply different intervention methods based on the user's job duties and position at the time of intervention. For example, the intervention unit may apply stricter intervention methods to users in management positions. For new employees, it may apply support-oriented intervention methods. For specific project teams, it may apply intervention methods appropriate to the importance of the project. This allows for appropriate intervention by applying different intervention methods based on the user's job duties and position. Some or all of the above processing in the intervention unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the intervention unit can input data on the user's job duties and position into a generative AI and have the generative AI execute the application of different intervention methods.

[0083] The intervention unit can analyze a user's social media activity and intervene in relevant communications at the time of intervention. For example, the intervention unit can analyze a user's social media posts and assess their potential impact on internal communications. The intervention unit can intervene in internal communications of users who frequently post negative comments on social media. The intervention unit can analyze social media trends and intervene in relevant communications within the company. This allows for appropriate intervention in relevant communications within the company by analyzing a user's social media activity. Some or all of the above processing in the intervention unit may be performed using, for example, generative AI, or without generative AI. For example, the intervention unit can input data on a user's social media activity into a generative AI and have the generative AI perform interventions on relevant communications.

[0084] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0085] The monitoring unit can analyze the tone of users' communications in real time and detect signs of harassment early based on changes in tone. For example, if a user's remarks suddenly become aggressive, the unit can detect this change and issue a warning. The monitoring unit also performs sentiment analysis of users' voice tone and text, and issues a warning if negative tones increase. Furthermore, the monitoring unit can monitor users' communication tone over the long term, analyze patterns of tone changes, and assess the risk of harassment. This allows for early detection of signs of harassment based on changes in tone and enables appropriate responses.

[0086] The detection unit can detect signs of harassment by analyzing not only the content of the user's communication but also nonverbal elements. For example, it can analyze facial expressions and gestures during video conferences to detect aggressive attitudes or behaviors indicating discomfort. The detection unit can also analyze the user's voice characteristics, such as tone, speed, and pauses, to find signs of harassment. Furthermore, the detection unit can analyze the user's body movements and posture to detect signs of tension or stress. By analyzing nonverbal elements in this way, signs of harassment can be detected more accurately.

[0087] The intervention unit can estimate the user's emotions and personalize the intervention based on those emotions. For example, if the user is stressed, it will provide a gentle reminder. If the user is relaxed, it will provide a direct reminder. If the user is in a hurry, it will provide a concise and quick reminder. Furthermore, the intervention unit can provide appropriate support resources according to the user's emotions. For example, it can provide mental health support information to a stressed user. This personalization of the intervention based on the user's emotions makes the intervention more effective.

[0088] The monitoring unit can estimate the user's emotions and adjust the scope of monitoring based on those estimates. For example, if a user is stressed, the system will focus on monitoring that user's communications. If the user is relaxed, the monitoring scope will be broadened to include the communications of other users. If a user is in a hurry, important conversations and meetings will be prioritized for monitoring. This allows for prioritizing important communications by adjusting the scope of monitoring based on the user's emotions.

[0089] The detection unit can estimate the user's emotions and adjust the harassment detection criteria based on those emotions. For example, if the user is stressed, the harassment detection criteria are tightened. If the user is relaxed, the criteria are loosened. If the user is in a hurry, harassment detection is limited to important communications. By adjusting the harassment detection criteria based on the user's emotions, more appropriate harassment detection becomes possible.

[0090] The monitoring unit can analyze the frequency and patterns of user communication to detect abnormal behavior. For example, if a particular user suddenly increases the frequency of their communication, the unit will detect this anomaly and issue a warning. The monitoring unit analyzes the timing and recipients of user communication patterns to detect unusual behavior. Furthermore, the monitoring unit can analyze the content of user communication to identify sudden changes or abnormal patterns. As a result, by analyzing the frequency and patterns of communication, abnormal behavior can be detected early, and appropriate responses can be taken.

[0091] The detection unit can analyze the content of user communications and assess the risk of harassment related to specific topics. For example, if there is a high risk of harassment in communications related to a particular project or task, it can assess the risk and issue a warning. The detection unit analyzes the frequency of negative remarks related to specific topics to find signs of harassment. Furthermore, the detection unit can analyze the tone and context of communications related to specific topics to assess the risk of harassment. This allows for more appropriate responses by assessing the risk of harassment related to specific topics.

[0092] The intervention unit can analyze the content of user communications and adjust its intervention methods for specific topics. For example, if there is a high risk of harassment in communications related to a particular project or task, it will issue a warning about that topic. If there are many negative comments on a particular topic, the intervention unit will provide support resources related to that topic. Furthermore, the intervention unit can analyze the tone and context of communications on a particular topic and select an appropriate intervention method. This allows for more effective intervention by adjusting the intervention method for specific topics.

[0093] The monitoring unit can analyze the content of user communications and evaluate the frequency of occurrence of specific keywords and phrases. For example, if certain aggressive words or phrases are used frequently, it can evaluate their frequency and issue a warning. The monitoring unit can analyze the frequency of words indicating negative emotions to identify signs of harassment. Furthermore, the monitoring unit can monitor words and phrases repeatedly used towards specific users and assess the potential for harassment. This allows for a high assessment of the potential for harassment by analyzing the frequency of occurrence of specific keywords and phrases.

[0094] The intervention unit can analyze the content of user communication and select the optimal intervention method by referring to past intervention cases. For example, it can refer to past intervention cases and select the optimal intervention method for similar cases. The intervention unit applies effective intervention methods based on past successes. Furthermore, the intervention unit can analyze past failures and adjust the intervention method to avoid repeating the same mistakes. In this way, the optimal intervention method can be selected by referring to past intervention cases.

[0095] The following briefly describes the processing flow for example form 2.

[0096] Step 1: The monitoring department monitors employee communication. The monitoring department patrols internal communications such as chats and video conferences to check for any remarks that could lead to harassment. The monitoring department makes a comprehensive judgment based on the context and communication across multiple channels. For example, if a particular employee repeatedly makes aggressive remarks, the monitoring department will determine whether those remarks constitute harassment. Step 2: The detection unit detects harassment from communications monitored by the monitoring unit. The detection unit uses natural language processing technology to detect statements that constitute harassment. The detection unit statistically analyzes harassment trends and reports them for each organization. For example, if harassment is frequent in a particular department, the trends can be analyzed and used to consider organizational improvements. Step 3: The intervention unit automatically intervenes in response to harassment detected by the detection unit. When the intervention unit finds communication that could lead to harassment, it issues a warning. For example, it displays a message such as, "This statement may lead to harassment. Please be careful!" The intervention unit saves the communication at the time harassment is detected and can submit it to a consultation service with a single button click. For example, it can save chat logs or video conference recordings from when harassment occurred and submit them to a consultation service as needed.

[0097] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0098] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0099] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0100] Each of the multiple elements described above, including the monitoring unit, detection unit, and intervention unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the monitoring unit is implemented by the control unit 46A of the smart device 14 and patrols internal communications such as chats and video conferences to check for any remarks that could lead to harassment. The detection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and uses natural language processing technology to detect remarks that constitute harassment. The intervention unit is implemented, for example, by the control unit 46A of the smart device 14 and, when it finds communications that could lead to harassment, it issues a warning and provides a function to submit them to a consultation service if necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0101] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0102] As shown in Figure 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.

[0103] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0104] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0105] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0107] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0108] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0109] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0110] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0111] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0112] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0113] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0115] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements described above, including the monitoring unit, detection unit, and intervention unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the monitoring unit is implemented by the control unit 46A of the smart glasses 214 and patrols internal communications such as chats and video conferences to check for any remarks that could lead to harassment. The detection unit is implemented by the identification processing unit 290 of the data processing unit 12 and uses natural language processing technology to detect remarks that constitute harassment. The intervention unit is implemented by the control unit 46A of the smart glasses 214 and, when it finds communications that could lead to harassment, it issues a warning and provides a function to submit them to a consultation service if necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0121] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements, including the monitoring unit, detection unit, and intervention unit described above, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the monitoring unit is implemented by the control unit 46A of the headset terminal 314 and patrols internal communications such as chats and video conferences to check for any remarks that could lead to harassment. The detection unit is implemented by the identification processing unit 290 of the data processing unit 12 and uses natural language processing technology to detect remarks that constitute harassment. The intervention unit is implemented by the control unit 46A of the headset terminal 314 and, when it finds communications that could lead to harassment, it issues a warning and provides a function to submit them to a consultation service if necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0133] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0134] As shown in Figure 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.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0137] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0141] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0142] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0143] Storage 32 stores the data generation model 58 and the 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 emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0144] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0145] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0146] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0147] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0148] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements, including the monitoring unit, detection unit, and intervention unit described above, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the monitoring unit is implemented by the control unit 46A of the robot 414 and patrols internal communications such as chats and video conferences to check for any remarks that could lead to harassment. The detection unit is implemented by the identification processing unit 290 of the data processing unit 12 and uses natural language processing technology to detect remarks that constitute harassment. The intervention unit is implemented by the control unit 46A of the robot 414 and, when it finds communications that could lead to harassment, it issues a warning and provides a function to submit them to a consultation service if necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0150] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0151] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0152] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0153] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0154] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0155] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has 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 ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0157] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0158] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to 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] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0161] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0162] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0163] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0164] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0165] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0166] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0167] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0168] (Note 1) The monitoring department, which monitors internal communications, A detection unit that detects harassment from communications monitored by the aforementioned monitoring unit, The system includes an intervention unit that automatically intervenes in response to harassment detected by the detection unit. A system characterized by the following features. (Note 2) The aforementioned monitoring unit, We monitor internal communications such as chats and video conferences, and make judgments based on a comprehensive assessment of the context and communications across multiple channels. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned intervention unit is When we find communication that could lead to harassment, we issue a warning. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned intervention unit is It saves communications when harassment is detected and can be submitted to a consultation service with a single button click. The system described in Appendix 1, characterized by the features described herein. (Note 5) The detection unit is Statistically analyze harassment trends and report them for each organization. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned monitoring unit, It estimates the user's emotions and adjusts the monitoring frequency based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned monitoring unit, During monitoring, the frequency of specific keywords and phrases is analyzed to assess the potential for harassment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned monitoring unit, During monitoring, similar patterns are detected by referring to past harassment cases. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned monitoring unit, It estimates the user's emotions and determines the priority of monitoring communications based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned monitoring unit, During monitoring, different monitoring criteria are applied based on the user's job duties and position. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned monitoring unit, During monitoring, the system analyzes users' social media activity and monitors relevant communications. The system described in Appendix 1, characterized by the features described herein. (Note 12) The detection unit is The system estimates user emotions and adjusts harassment detection criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The detection unit is Upon detection, the tone and context of the communication are analyzed to assess the possibility of harassment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The detection unit is During detection, similar patterns are identified by referring to past harassment cases. The system described in Appendix 1, characterized by the features described herein. (Note 15) The detection unit is It estimates the user's emotions and adjusts how the detection results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The detection unit is When detection occurs, different detection criteria are applied based on the user's job title or position. The system described in Appendix 1, characterized by the features described herein. (Note 17) The detection unit is During detection, the system analyzes the user's social media activity and identifies relevant communications. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned intervention unit is It estimates the user's emotions and adjusts the intervention method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned intervention unit is When intervening, different intervention methods will be applied depending on the type and severity of the harassment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned intervention unit is During intervention, the optimal intervention method is selected by referring to past intervention cases. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned intervention unit is It estimates the user's emotions and adjusts the timing of interventions based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned intervention unit is During intervention, different intervention methods are applied based on the user's job duties and position. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned intervention unit is During intervention, the system analyzes the user's social media activity and intervenes in relevant communications. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The monitoring department, which monitors internal communications, A detection unit that detects harassment from communications monitored by the aforementioned monitoring unit, The system includes an intervention unit that automatically intervenes in response to harassment detected by the detection unit. A system characterized by the following features.

2. The aforementioned monitoring unit, We monitor internal communications such as chats and video conferences, and make judgments based on a comprehensive assessment of the context and communications across multiple channels. The system according to feature 1.

3. The aforementioned intervention unit is When we find communication that could lead to harassment, we issue a warning. The system according to feature 1.

4. The aforementioned intervention unit is It saves communications when harassment is detected and can be submitted to a consultation service with a single button click. The system according to feature 1.

5. The detection unit is Statistically analyze harassment trends and report them for each organization. The system according to feature 1.

6. The aforementioned monitoring unit, It estimates the user's emotions and adjusts the monitoring frequency based on the estimated emotions. The system according to feature 1.

7. The aforementioned monitoring unit, During monitoring, the frequency of specific keywords and phrases is analyzed to assess the potential for harassment. The system according to feature 1.

8. The aforementioned monitoring unit, During monitoring, similar patterns are detected by referring to past harassment cases. The system according to feature 1.

Images