system

Abstract

The system according to the embodiment aims to detect power harassment and sexual harassment remarks within the company in real time and respond immediately. [Solution] A system according to an embodiment includes an analysis unit, an alert unit, and a reporting unit. The analysis unit monitors the content of internal emails or phone calls in real time. The alert unit immediately issues an alert to the relevant parties based on problematic statements detected by the analysis unit. If an alert issued by the alert unit is ignored, the reporting unit automatically reports the issue to the human resources department or an appropriate department.

Description

[Technical Field]

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

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

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

[0004] Conventional technology had the problem of making it difficult to detect power harassment or sexual harassment remarks within the company in real time and respond immediately.

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

[0006] The system according to the embodiment includes an analysis unit, an alert unit, and a reporting unit. The analysis unit monitors the content of internal emails or phone calls in real time. The alert unit immediately issues an alert to the relevant parties based on problematic statements detected by the analysis unit. The reporting unit automatically reports to the human resources department or an appropriate department if an alert issued by the alert unit is ignored. [Effects of the Invention]

[0007] The system according to the embodiment can detect power harassment and sexual harassment remarks within the company in real time and respond immediately. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) The power harassment and sexual harassment prevention system according to an embodiment of the present invention utilizes a generation AI that is constantly connected to internal emails and employee mobile phone calls. If any problematic comments are made, the AI ​​immediately alerts the relevant parties. Specifically, the system consists of the following steps: First, a generation AI is installed to monitor internal emails and phone calls in real time. The generation AI uses natural language processing technology to analyze emails and phone calls and detect comments that constitute power harassment or sexual harassment. For example, the generation AI detects offensive language or inappropriate comments. Next, if the generation AI detects a problematic comment, it immediately alerts the relevant parties. This alert appears as a pop-up message or a voice notification during emails or phone calls. For example, a message such as "That comment is inappropriate. Please change your comment." Furthermore, if the problematic comment continues despite the alert, the generation AI automatically reports it to the human resources department or other appropriate department. This report includes information about the content of the problematic comment and the person who made it. For example, a report such as "Mr. / Ms. X made an inappropriate comment. Details are as follows." This system can prevent power harassment and sexual harassment from occurring and contribute to improving organizational productivity. For example, creating an environment where employees can work with peace of mind will improve work efficiency and team performance. This means that a power harassment and sexual harassment prevention system can prevent power harassment and sexual harassment from occurring and contribute to improving organizational productivity.

[0029] A power harassment and sexual harassment prevention system according to an embodiment includes an analysis unit, an alert unit, and a reporting unit. The analysis unit monitors internal emails and phone calls in real time. The analysis unit analyzes emails and phone calls using, for example, natural language processing technology to detect statements that constitute power harassment or sexual harassment. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to break down words in emails and phone calls, grammatical analysis to analyze sentence structure, and semantic analysis to understand the meaning of the sentence. The analysis unit combines these technologies to detect statements that constitute power harassment or sexual harassment with high accuracy. The alert unit immediately issues an alert to the person involved based on the problematic statement detected by the analysis unit. The alert unit displays the alert, for example, as a pop-up message or a voice notification. The pop-up message is displayed in the center of the screen to attract the user's attention. The voice notification can convey the alert audibly through a speaker. For example, the alert unit can display a message such as, "That statement is inappropriate. Please revise your statement." The reporting unit automatically notifies the human resources department or the appropriate department if an alert is ignored by the alert unit. The reporting unit issues a report that includes, for example, the content of the problematic remark and information about the person who made it. The report may include the date and time of the remark, the name of the person who made it, and the content of the remark. For example, the reporting unit may issue a report such as, "Mr. / Ms. XX made an inappropriate remark. Details are as follows." As a result, the power harassment and sexual harassment prevention system according to the embodiment can prevent the occurrence of power harassment and sexual harassment and contribute to improving organizational productivity.

[0030] The analysis unit can analyze emails and phone calls using natural language processing technology to detect statements that constitute power harassment or sexual harassment. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. The analysis unit can, for example, use morphological analysis to break down words in emails and phone calls, use grammatical analysis to analyze sentence structure, and use semantic analysis to understand the meaning of the sentence. For example, the analysis unit can use morphological analysis to break down words in emails and phone calls, use grammatical analysis to analyze sentence structure, and use semantic analysis to understand the meaning of the sentence. This improves the accuracy of detecting problematic statements by using natural language processing technology. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input emails and phone calls into a generation AI, which can then use natural language processing technology to detect problematic statements.

[0031] The alert unit can display the alert as a pop-up message or a voice notification. The pop-up message can be displayed, for example, in the center of the screen to attract the user's attention. For example, the alert unit can display a message such as, "That comment is inappropriate. Please change your comment." The alert unit can also display the alert as a voice notification. For example, the alert unit can play a voice message such as, "That comment is inappropriate. Please change your comment." from a speaker. This allows for a variety of alert display methods, thereby effectively alerting the user. Some or all of the above-described processing in the alert unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the alert unit can request the generation AI to generate an alert message, and the generation AI can generate and display an appropriate message.

[0032] The reporting unit can make a report that includes the content of the problematic remark or information about the person who made the remark. The report can include, for example, the date and time of the remark, the name of the person who made the remark, and the content of the remark. For example, the reporting unit can make a report with the content, "Mr. / Ms. XX made an inappropriate remark. Details are as follows." By including detailed information in the report content, an appropriate response can be made promptly. Some or all of the above-mentioned processing in the reporting unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the reporting unit can request a generation AI to generate the content of the report, and the generation AI can generate appropriate content and make the report.

[0033] The analysis unit may include a standard setting unit that sets standards for detecting problematic remarks based on corporate policies or laws and regulations. The standard setting unit may set standards for detecting problematic remarks based on, for example, a corporate code of conduct or ethical code, or laws and regulations such as the Labor Standards Act and the Anti-Harassment Act. For example, the standard setting unit may set standards for detecting offensive language or inappropriate comments as problematic remarks based on the corporate code of conduct. The standard setting unit may also set standards for detecting remarks that constitute power harassment or sexual harassment as problematic remarks based on the Labor Standards Act and the Anti-Harassment Act. This improves the accuracy of detecting problematic remarks by setting standards based on corporate policies and laws and regulations. Some or all of the above-described processing by the standard setting unit may be performed using, or without, a generation AI. For example, the standard setting unit may input data for setting standards into the generation AI, which may then set appropriate standards.

[0034] The analysis unit can improve the accuracy of detecting problematic statements by referring to past statement history. The analysis unit can, for example, refer to the statement history of users who have made problematic statements in the past and detect similar statement patterns. It can also improve detection accuracy by extracting specific keywords or phrases from the past statement history. Furthermore, it can analyze the past statement history to understand trends in problematic statements and reflect them in the analysis. By referring to the past statement history, the accuracy of detecting problematic statements can be improved. Some or all of the above-described processing in the analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input past statement history data into a generation AI, which can then analyze the statement patterns to detect problematic statements.

[0035] The analysis unit can dynamically change the detection criteria for problematic statements based on the context of the statement. For example, the analysis unit can analyze the context before and after the statement to increase the likelihood of the statement being problematic. The analysis unit can also dynamically change the importance of specific keywords depending on the context of the statement. Furthermore, the detection criteria for problematic statements can be adjusted in real time, taking into account the context of the statement. This improves the accuracy of detecting problematic statements by taking into account the context of the statement. The analysis of the context may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the analysis unit can input context data before and after the statement into the generation AI, which can then analyze the context and dynamically change the detection criteria for problematic statements.

[0036] The analysis unit can adjust the accuracy of the analysis based on the speaker's job position or title. For example, if the speaker is a superior, the generation AI can increase the analysis accuracy by taking into account the influence of the comment. Furthermore, if the speaker is a subordinate, the generation AI can maintain normal analysis accuracy by taking into account the influence of the comment. Furthermore, if the speaker is a colleague, the generation AI can fine-tune the analysis accuracy by taking into account the influence of the comment. This improves the analysis accuracy by taking into account the speaker's job position or title. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the speaker's job position or title data into the generation AI, which can analyze the influence of the comment and adjust the analysis accuracy.

[0037] The analysis unit can change the analysis criteria based on the time or location of the statement. For example, if a statement is made at night, the generation AI can carefully analyze the content of the statement. Also, if a statement is made during a meeting, the generation AI can analyze the statement by increasing its importance. Furthermore, if a statement is made outside the office, the generation AI can adjust the analysis criteria by taking into account the context of the statement. This improves the accuracy of the analysis by taking into account the time and location of the statement. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input data on the time and location of the statement into the generation AI, which can then analyze the context of the statement and change the analysis criteria.

[0038] The alert unit can select the optimal alert method by referring to past alert history. The alert unit can, for example, preferentially display alert methods that were effective in the past. The alert unit can also select the optimal alert method for a specific user from past alert history. Furthermore, the alert unit can analyze past alert history and suggest the most effective alert method. In this way, the optimal alert method is selected by referring to past alert history. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI, for example. For example, the alert unit can input past alert history data into the generation AI, which can then select the optimal alert method.

[0039] The alert unit can adjust the level of detail of the alert based on the importance of the statement. For example, in the case of a seriously problematic statement, the generation AI can display a detailed alert. Furthermore, in the case of a slightly problematic statement, the generation AI can display a concise alert. Furthermore, the generation AI can dynamically adjust the level of detail of the alert according to the importance of the statement. This allows appropriate attention to be given by adjusting the level of detail of the alert according to the importance of the statement. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input statement importance data to the generation AI, which can then adjust the level of detail of the alert.

[0040] The alert unit can customize the content of the alert based on the attribute information of the speaker. For example, if the speaker is a superior, the generation AI can display the alert using appropriate honorific language. Furthermore, if the speaker is a subordinate, the generation AI can display the alert in a friendly tone. Furthermore, if the speaker is a colleague, the generation AI can display the alert in a casual tone. In this way, by customizing the content of the alert according to the attribute information of the speaker, more appropriate attention can be given. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input attribute information data of the speaker into the generation AI, which can then customize the content of the alert.

[0041] The alert unit can apply a different alert method depending on the category of the remark. For example, in the case of a power harassment remark, the generation AI can display an alert in a stern tone. In addition, in the case of a sexual harassment remark, the generation AI can immediately display an alert. Furthermore, in the case of other problematic remarks, the generation AI can display an alert in an appropriate tone. In this way, by changing the alert method depending on the category of the remark, appropriate attention can be given. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input category data of the remark into the generation AI, which can select an appropriate alert method.

[0042] The reporting unit can improve the accuracy of reporting by referring to past reporting history. The reporting unit can, for example, prioritize the use of reporting methods that have been effective in the past. The reporting unit can also select the optimal reporting method for a specific user from the past reporting history. Furthermore, the past reporting history can be analyzed and the most effective reporting method can be suggested. As a result, by referring to the past reporting history, the accuracy of reporting is improved. Some or all of the above-mentioned processing in the reporting unit may be performed using, or without, the generation AI, for example. For example, the reporting unit can input past reporting history data into the generation AI, which can then select the optimal reporting method.

[0043] The reporting unit can dynamically change the reporting criteria based on the context of the statement. The reporting unit can, for example, analyze the context before and after the statement and adjust the reporting criteria. The reporting unit can also dynamically change the importance of specific keywords depending on the context of the statement. Furthermore, the reporting criteria can be adjusted in real time by taking the context of the statement into consideration. This improves the accuracy of reporting by taking the context of the statement into consideration. The analysis of the context can be performed, for example, using a generation AI or without using a generation AI. For example, the reporting unit can input context data before and after the statement into a generation AI, which can then analyze the context and dynamically change the reporting criteria.

[0044] The reporting unit can customize the content of the report based on the speaker's job title or position. For example, if the speaker is a superior, the generation AI can create the report content using appropriate honorific language. Furthermore, if the speaker is a subordinate, the generation AI can create the report content in a friendly tone. Furthermore, if the speaker is a colleague, the generation AI can create the report content in a casual tone. In this way, customizing the content of the report according to the speaker's job title or position allows for more appropriate reporting. Some or all of the above-mentioned processing in the reporting unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reporting unit can input the speaker's job title or position data into the generation AI, which can then customize the content of the report.

[0045] The reporting unit can change the reporting criteria based on the time or location of the comment. For example, if a comment is made at night, the generation AI can tighten the reporting criteria. Also, if a comment is made during a meeting, the generation AI can raise the reporting criteria. Furthermore, if a comment is made outside the office, the generation AI can adjust the reporting criteria. This improves the accuracy of reporting by taking into account the time and location of the comment. Some or all of the above-mentioned processing in the reporting unit may be performed using, or without, the generation AI. For example, the reporting unit can input data on the time and location of the comment into the generation AI, and the generation AI can change the reporting criteria.

[0046] The standard setting unit can improve the accuracy of the standards by referring to past problematic utterance data. The standard setting unit can, for example, analyze past problematic utterance data and reflect frequently occurring keywords and phrases in the standards. Also, it can add utterances in specific situations or contexts from the past problematic utterance data to the standards. Furthermore, it can dynamically adjust the accuracy of the standards by referring to past problematic utterance data. In this way, the accuracy of the standards is improved by referring to past problematic utterance data. Some or all of the above-mentioned processing in the standard setting unit can be performed, for example, using a generation AI or can be performed without using a generation AI. For example, the standard setting unit can input past problematic utterance data into a generation AI, which can analyze the data and improve the accuracy of the standards.

[0047] The standard setting unit can dynamically update the standards in response to changes in corporate policies and laws and regulations. For example, the standard setting unit can automatically update the standards when corporate policies change. The standard setting unit can also dynamically adjust the standards in response to amendments to laws and regulations. Furthermore, the standard setting unit can update the standards to reflect changes in corporate policies and laws and regulations in real time. This allows the latest standards to be always applied by dynamically updating the standards in response to changes in corporate policies and laws and regulations. Some or all of the above-mentioned processing in the standard setting unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the standard setting unit can input data on changes in corporate policies and laws and regulations into the generation AI, which can then dynamically update the standards.

[0048] The standard setting unit can customize the standards based on the industry or size of the company. For example, the standard setting unit can set strict standards for large companies. Also, the standard setting unit can set flexible standards for small and medium-sized companies. Furthermore, the standard setting unit can customize appropriate standards according to a specific industry. In this way, by customizing the standards according to the industry and size of the company, more appropriate standards can be set. Some or all of the above-mentioned processing in the standard setting unit may be performed using, or without, the generation AI, for example. For example, the standard setting unit can input data on the industry and size of the company into the generation AI, which can then customize the standards.

[0049] The standard setting unit can apply different standards depending on the category of the remark. For example, the standard setting unit can apply strict standards to remarks that constitute power harassment. Furthermore, in the case of remarks that constitute sexual harassment, the standard setting unit can apply standards that immediately address the remarks. Furthermore, in the case of other problematic remarks, the standard setting unit can apply appropriate standards. In this way, appropriate standards are applied by changing the standards depending on the category of the remark. Some or all of the above-mentioned processing in the standard setting unit may be performed using, or without, a generation AI. For example, the standard setting unit can input category data of the remarks into the generation AI, which can then select appropriate standards.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The analysis unit can improve the accuracy of detecting problematic statements by referring to past statement history. For example, it can detect similar statement patterns by referring to the statement history of users who have made problematic statements in the past. It can also improve detection accuracy by extracting specific keywords or phrases from the past statement history. Furthermore, it can analyze the past statement history to understand trends in problematic statements and reflect them in the analysis. In this way, by referring to the past statement history, the accuracy of detecting problematic statements is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input past statement history data into a generation AI, which can analyze statement patterns to detect problematic statements.

[0052] The analysis unit can dynamically change the detection criteria for problematic statements based on the context of the statement. For example, the analysis unit can analyze the context before and after the statement to increase the likelihood of the statement being problematic. The analysis unit can also dynamically change the importance of specific keywords depending on the context of the statement. Furthermore, the analysis unit can adjust the detection criteria for problematic statements in real time, taking into account the context of the statement. This improves the accuracy of detecting problematic statements by taking into account the context of the statement. The analysis of the context may be performed, for example, using or without the generation AI. For example, the analysis unit can input context data before and after the statement into the generation AI, which can then analyze the context and dynamically change the detection criteria for problematic statements.

[0053] The analysis unit can adjust the accuracy of the analysis based on the speaker's job position or title. For example, if the speaker is a superior, the generation AI can increase the analysis accuracy by taking into account the influence of the comment. Also, if the speaker is a subordinate, the generation AI can maintain normal analysis accuracy by taking into account the influence of the comment. Furthermore, if the speaker is a colleague, the generation AI can fine-tune the analysis accuracy by taking into account the influence of the comment. In this way, the analysis accuracy is improved by taking into account the speaker's job position or title. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the speaker's job position or title data into the generation AI, which can analyze the influence of the comment and adjust the analysis accuracy.

[0054] The alert unit can select the optimal alert method by referring to past alert history. For example, it can preferentially display alert methods that were effective in the past. It can also select the optimal alert method for a specific user from past alert history. It can also analyze past alert history and suggest the most effective alert method. In this way, the optimal alert method is selected by referring to past alert history. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, a generation AI, for example. For example, the alert unit can input past alert history data into the generation AI, which can then select the optimal alert method.

[0055] The alert unit can adjust the level of detail of the alert based on the importance of the statement. For example, in the case of a serious problematic statement, the generation AI can display a detailed alert. In addition, in the case of a minor problematic statement, the generation AI can display a concise alert. Furthermore, the generation AI can dynamically adjust the level of detail of the alert according to the importance of the statement. As a result, by adjusting the level of detail of the alert according to the importance of the statement, appropriate attention can be given. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input statement importance data into the generation AI, which can then adjust the level of detail of the alert.

[0056] The alert unit can customize the content of the alert based on the speaker's attribute information. For example, if the speaker is a superior, the generation AI can display the alert using appropriate honorific language. Furthermore, if the speaker is a subordinate, the generation AI can display the alert in a friendly tone. Furthermore, if the speaker is a colleague, the generation AI can display the alert in a casual tone. In this way, by customizing the content of the alert according to the speaker's attribute information, more appropriate attention can be given. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input the speaker's attribute information data into the generation AI, which can then customize the content of the alert.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The analysis unit monitors internal emails or phone call content in real time. The analysis unit uses natural language processing technology to analyze emails and phone call content and detect comments that constitute power harassment or sexual harassment. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to break down words in emails and phone call content, grammatical analysis to analyze the structure of sentences, and semantic analysis to understand the meaning of sentences. By combining these technologies, it is possible to detect comments that constitute power harassment or sexual harassment with a high degree of accuracy. Step 2: The alerting unit immediately issues an alert to the person involved based on the problematic remarks detected by the analysis unit. The alerting unit displays the alert as a pop-up message or a voice notification. For example, it can display a message saying, "That remark is inappropriate. Please revise your remark." Step 3: If the alert is ignored by the Alert Department, the Reporting Department will automatically notify the Human Resources Department or the appropriate department. The Reporting Department will make a report that includes the content of the problematic remark and information about the person who made it. The report will include the date and time of the remark, the name of the person who made it, and the content of the remark. For example, a report can be made with the content, "Mr. / Ms. XX made an inappropriate remark. Details are as follows."

[0059] (Example 2) The power harassment and sexual harassment prevention system according to an embodiment of the present invention utilizes a generation AI that is constantly connected to internal emails and employee mobile phone calls. If any problematic comments are made, the AI ​​immediately alerts the relevant parties. Specifically, the system consists of the following steps: First, a generation AI is installed to monitor internal emails and phone calls in real time. The generation AI uses natural language processing technology to analyze emails and phone calls and detect comments that constitute power harassment or sexual harassment. For example, the generation AI detects offensive language or inappropriate comments. Next, if the generation AI detects a problematic comment, it immediately alerts the relevant parties. This alert appears as a pop-up message or a voice notification during emails or phone calls. For example, a message such as "That comment is inappropriate. Please change your comment." Furthermore, if the problematic comment continues despite the alert, the generation AI automatically reports it to the human resources department or other appropriate department. This report includes information about the content of the problematic comment and the person who made it. For example, a report such as "Mr. / Ms. X made an inappropriate comment. Details are as follows." This system can prevent power harassment and sexual harassment from occurring and contribute to improving organizational productivity. For example, creating an environment where employees can work with peace of mind will improve work efficiency and team performance. This means that a power harassment and sexual harassment prevention system can prevent power harassment and sexual harassment from occurring and contribute to improving organizational productivity.

[0060] A power harassment and sexual harassment prevention system according to an embodiment includes an analysis unit, an alert unit, and a reporting unit. The analysis unit monitors internal emails and phone calls in real time. The analysis unit analyzes emails and phone calls using, for example, natural language processing technology to detect statements that constitute power harassment or sexual harassment. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to break down words in emails and phone calls, grammatical analysis to analyze sentence structure, and semantic analysis to understand the meaning of the sentence. The analysis unit combines these technologies to detect statements that constitute power harassment or sexual harassment with high accuracy. The alert unit immediately issues an alert to the person involved based on the problematic statement detected by the analysis unit. The alert unit displays the alert, for example, as a pop-up message or a voice notification. The pop-up message is displayed in the center of the screen to attract the user's attention. The voice notification can convey the alert audibly through a speaker. For example, the alert unit can display a message such as, "That statement is inappropriate. Please revise your statement." The reporting unit automatically notifies the human resources department or the appropriate department if an alert is ignored by the alert unit. The reporting unit issues a report that includes, for example, the content of the problematic remark and information about the person who made it. The report may include the date and time of the remark, the name of the person who made it, and the content of the remark. For example, the reporting unit may issue a report such as, "Mr. / Ms. XX made an inappropriate remark. Details are as follows." As a result, the power harassment and sexual harassment prevention system according to the embodiment can prevent the occurrence of power harassment and sexual harassment and contribute to improving organizational productivity.

[0061] The analysis unit can analyze emails and phone calls using natural language processing technology to detect statements that constitute power harassment or sexual harassment. Natural language processing technology includes, for example, morphological analysis, grammatical analysis, and semantic analysis. The analysis unit can, for example, use morphological analysis to break down words in emails and phone calls, use grammatical analysis to analyze sentence structure, and use semantic analysis to understand the meaning of the sentence. For example, the analysis unit can use morphological analysis to break down words in emails and phone calls, use grammatical analysis to analyze sentence structure, and use semantic analysis to understand the meaning of the sentence. This improves the accuracy of detecting problematic statements by using natural language processing technology. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input emails and phone calls into a generation AI, which can then use natural language processing technology to detect problematic statements.

[0062] The alert unit can display the alert as a pop-up message or a voice notification. The pop-up message can be displayed, for example, in the center of the screen to attract the user's attention. For example, the alert unit can display a message such as, "That comment is inappropriate. Please change your comment." The alert unit can also display the alert as a voice notification. For example, the alert unit can play a voice message such as, "That comment is inappropriate. Please change your comment." from a speaker. This allows for a variety of alert display methods, thereby effectively alerting the user. Some or all of the above-described processing in the alert unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the alert unit can request the generation AI to generate an alert message, and the generation AI can generate and display an appropriate message.

[0063] The reporting unit can make a report that includes the content of the problematic remark or information about the person who made the remark. The report can include, for example, the date and time of the remark, the name of the person who made the remark, and the content of the remark. For example, the reporting unit can make a report with the content, "Mr. / Ms. XX made an inappropriate remark. Details are as follows." By including detailed information in the report content, an appropriate response can be made promptly. Some or all of the above-mentioned processing in the reporting unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the reporting unit can request a generation AI to generate the content of the report, and the generation AI can generate appropriate content and make the report.

[0064] The analysis unit may include a standard setting unit that sets standards for detecting problematic remarks based on corporate policies or laws and regulations. The standard setting unit may set standards for detecting problematic remarks based on, for example, a corporate code of conduct or ethical code, or laws and regulations such as the Labor Standards Act and the Anti-Harassment Act. For example, the standard setting unit may set standards for detecting offensive language or inappropriate comments as problematic remarks based on the corporate code of conduct. The standard setting unit may also set standards for detecting remarks that constitute power harassment or sexual harassment as problematic remarks based on the Labor Standards Act and the Anti-Harassment Act. This improves the accuracy of detecting problematic remarks by setting standards based on corporate policies and laws and regulations. Some or all of the above-described processing by the standard setting unit may be performed using, or without, a generation AI. For example, the standard setting unit may input data for setting standards into the generation AI, which may then set appropriate standards.

[0065] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, if the user is angry, the generation AI can detect the increase in emotions and improve the accuracy of the analysis. Furthermore, if the user is relaxed, the generation AI can detect the stability of emotions and maintain normal analysis accuracy. Furthermore, if the user is nervous, the generation AI can detect emotional fluctuations and fine-tune the accuracy of the analysis. This allows for more appropriate analysis by adjusting the analysis accuracy according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI, or without the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI, which can estimate the emotion and adjust the accuracy of the analysis.

[0066] The analysis unit can improve the accuracy of detecting problematic statements by referring to past statement history. The analysis unit can, for example, refer to the statement history of users who have made problematic statements in the past and detect similar statement patterns. It can also improve detection accuracy by extracting specific keywords or phrases from the past statement history. Furthermore, it can analyze the past statement history to understand trends in problematic statements and reflect them in the analysis. By referring to the past statement history, the accuracy of detecting problematic statements can be improved. Some or all of the above-described processing in the analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input past statement history data into a generation AI, which can then analyze the statement patterns to detect problematic statements.

[0067] The analysis unit can dynamically change the detection criteria for problematic statements based on the context of the statement. For example, the analysis unit can analyze the context before and after the statement to increase the likelihood of the statement being problematic. The analysis unit can also dynamically change the importance of specific keywords depending on the context of the statement. Furthermore, the detection criteria for problematic statements can be adjusted in real time, taking into account the context of the statement. This improves the accuracy of detecting problematic statements by taking into account the context of the statement. The analysis of the context may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the analysis unit can input context data before and after the statement into the generation AI, which can then analyze the context and dynamically change the detection criteria for problematic statements.

[0068] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated user emotions. For example, if the user is angry, the generation AI can detect the heightened emotions and prioritize displaying the analysis results. Also, if the user is relaxed, the generation AI can detect emotional stability and display the analysis results with normal priority. Furthermore, if the user is nervous, the generation AI can detect emotional fluctuations and fine-tune the priority of the analysis results. Thus, by prioritizing the analysis results according to the user's emotions, important analysis results are displayed with priority. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI, which can then estimate the emotion and prioritize the analysis results.

[0069] The analysis unit can adjust the accuracy of the analysis based on the speaker's job position or title. For example, if the speaker is a superior, the generation AI can increase the analysis accuracy by taking into account the influence of the comment. Furthermore, if the speaker is a subordinate, the generation AI can maintain normal analysis accuracy by taking into account the influence of the comment. Furthermore, if the speaker is a colleague, the generation AI can fine-tune the analysis accuracy by taking into account the influence of the comment. This improves the analysis accuracy by taking into account the speaker's job position or title. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the speaker's job position or title data into the generation AI, which can analyze the influence of the comment and adjust the analysis accuracy.

[0070] The analysis unit can change the analysis criteria based on the time or location of the statement. For example, if a statement is made at night, the generation AI can carefully analyze the content of the statement. Also, if a statement is made during a meeting, the generation AI can analyze the statement by increasing its importance. Furthermore, if a statement is made outside the office, the generation AI can adjust the analysis criteria by taking into account the context of the statement. This improves the accuracy of the analysis by taking into account the time and location of the statement. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input data on the time and location of the statement into the generation AI, which can then analyze the context of the statement and change the analysis criteria.

[0071] The alert unit can estimate the user's emotions and adjust the way the alert is expressed based on the estimated user emotions. For example, if the user is angry, the generation AI can display the alert in a calm tone. If the user is relaxed, the generation AI can display the alert in a gentle tone. If the user is nervous, the generation AI can display the alert in a soft tone. This allows for more effective alerting by adjusting the way the alert is expressed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the alert unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the alert unit can input the user's emotion data into the generation AI, which can estimate the emotion and adjust the way the alert is expressed.

[0072] The alert unit can select the optimal alert method by referring to past alert history. The alert unit can, for example, preferentially display alert methods that were effective in the past. The alert unit can also select the optimal alert method for a specific user from past alert history. Furthermore, the alert unit can analyze past alert history and suggest the most effective alert method. In this way, the optimal alert method is selected by referring to past alert history. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI, for example. For example, the alert unit can input past alert history data into the generation AI, which can then select the optimal alert method.

[0073] The alert unit can adjust the level of detail of the alert based on the importance of the statement. For example, in the case of a seriously problematic statement, the generation AI can display a detailed alert. Furthermore, in the case of a slightly problematic statement, the generation AI can display a concise alert. Furthermore, the generation AI can dynamically adjust the level of detail of the alert according to the importance of the statement. This allows appropriate attention to be given by adjusting the level of detail of the alert according to the importance of the statement. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input statement importance data to the generation AI, which can then adjust the level of detail of the alert.

[0074] The alert unit can estimate the user's emotions and adjust the timing of the alert based on the estimated user emotions. For example, if the user is angry, the generation AI can immediately display an alert. Also, if the user is relaxed, the generation AI can display an alert at an appropriate time. Furthermore, if the user is nervous, the generation AI can carefully adjust the timing of the alert. This allows for more effective attention by adjusting the timing of the alert according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the alert unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the alert unit can input the user's emotion data into the generation AI, which then estimates the emotion and adjusts the timing of the alert.

[0075] The alert unit can customize the content of the alert based on the attribute information of the speaker. For example, if the speaker is a superior, the generation AI can display the alert using appropriate honorific language. Furthermore, if the speaker is a subordinate, the generation AI can display the alert in a friendly tone. Furthermore, if the speaker is a colleague, the generation AI can display the alert in a casual tone. In this way, by customizing the content of the alert according to the attribute information of the speaker, more appropriate attention can be given. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input attribute information data of the speaker into the generation AI, which can then customize the content of the alert.

[0076] The alert unit can apply a different alert method depending on the category of the remark. For example, in the case of a power harassment remark, the generation AI can display an alert in a stern tone. In addition, in the case of a sexual harassment remark, the generation AI can immediately display an alert. Furthermore, in the case of other problematic remarks, the generation AI can display an alert in an appropriate tone. In this way, by changing the alert method depending on the category of the remark, appropriate attention can be given. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input category data of the remark into the generation AI, which can select an appropriate alert method.

[0077] The reporting unit can estimate the user's emotions and adjust the content of the report based on the estimated user emotions. For example, if the user is angry, the generation AI can create the report content in a calm tone. If the user is relaxed, the generation AI can create the report content in a gentle tone. If the user is nervous, the generation AI can create the report content in a gentle tone. This allows the report content to be adjusted according to the user's emotions, resulting in a more appropriate report. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reporting unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reporting unit can input the user's emotion data into the generation AI, which then estimates the emotion and adjusts the content of the report.

[0078] The reporting unit can improve the accuracy of reporting by referring to past reporting history. The reporting unit can, for example, prioritize the use of reporting methods that have been effective in the past. The reporting unit can also select the optimal reporting method for a specific user from the past reporting history. Furthermore, the past reporting history can be analyzed and the most effective reporting method can be suggested. As a result, by referring to the past reporting history, the accuracy of reporting is improved. Some or all of the above-mentioned processing in the reporting unit may be performed using, or without, the generation AI, for example. For example, the reporting unit can input past reporting history data into the generation AI, which can then select the optimal reporting method.

[0079] The reporting unit can dynamically change the reporting criteria based on the context of the statement. The reporting unit can, for example, analyze the context before and after the statement and adjust the reporting criteria. The reporting unit can also dynamically change the importance of specific keywords depending on the context of the statement. Furthermore, the reporting criteria can be adjusted in real time by taking the context of the statement into consideration. This improves the accuracy of reporting by taking the context of the statement into consideration. The analysis of the context can be performed, for example, using a generation AI or without using a generation AI. For example, the reporting unit can input context data before and after the statement into a generation AI, which can then analyze the context and dynamically change the reporting criteria.

[0080] The reporting unit can estimate the user's emotions and determine the priority of reports based on the estimated user emotions. For example, if the user is angry, the generation AI can increase the priority of the report. Also, if the user is relaxed, the generation AI can make reports with normal priority. Furthermore, if the user is nervous, the generation AI can fine-tune the priority of the report. As a result, by determining the priority of reports according to the user's emotions, important reports are given priority. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reporting unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reporting unit can input the user's emotion data into the generation AI, which can estimate the emotion and determine the priority of the report.

[0081] The reporting unit can customize the content of the report based on the speaker's job title or position. For example, if the speaker is a superior, the generation AI can create the report content using appropriate honorific language. Furthermore, if the speaker is a subordinate, the generation AI can create the report content in a friendly tone. Furthermore, if the speaker is a colleague, the generation AI can create the report content in a casual tone. In this way, customizing the content of the report according to the speaker's job title or position allows for more appropriate reporting. Some or all of the above-mentioned processing in the reporting unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reporting unit can input the speaker's job title or position data into the generation AI, which can then customize the content of the report.

[0082] The reporting unit can change the reporting criteria based on the time or location of the comment. For example, if a comment is made at night, the generation AI can tighten the reporting criteria. Also, if a comment is made during a meeting, the generation AI can raise the reporting criteria. Furthermore, if a comment is made outside the office, the generation AI can adjust the reporting criteria. This improves the accuracy of reporting by taking into account the time and location of the comment. Some or all of the above-mentioned processing in the reporting unit may be performed using, or without, the generation AI. For example, the reporting unit can input data on the time and location of the comment into the generation AI, and the generation AI can change the reporting criteria.

[0083] The standard setting unit can estimate the user's emotions and adjust the standard setting method based on the estimated user's emotions. For example, if the user is angry, the standard setting unit can set stricter standards taking into account the user's heightened emotions. Furthermore, if the user is relaxed, the standard setting unit can set normal standards taking into account emotional stability. Furthermore, if the user is nervous, the standard setting unit can fine-tune the standards taking into account emotional fluctuations. This allows for more appropriate standards to be set by adjusting the standard setting method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the standard setting unit can be performed using, for example, the generation AI, or without the generation AI. For example, the standard setting unit can input the user's emotion data into the generation AI, which can then estimate the emotion and adjust the standard setting method.

[0084] The standard setting unit can improve the accuracy of the standards by referring to past problematic utterance data. The standard setting unit can, for example, analyze past problematic utterance data and reflect frequently occurring keywords and phrases in the standards. Also, it can add utterances in specific situations or contexts from the past problematic utterance data to the standards. Furthermore, it can dynamically adjust the accuracy of the standards by referring to past problematic utterance data. In this way, the accuracy of the standards is improved by referring to past problematic utterance data. Some or all of the above-mentioned processing in the standard setting unit can be performed, for example, using a generation AI or can be performed without using a generation AI. For example, the standard setting unit can input past problematic utterance data into a generation AI, which can analyze the data and improve the accuracy of the standards.

[0085] The standard setting unit can dynamically update the standards in response to changes in corporate policies and laws and regulations. For example, the standard setting unit can automatically update the standards when corporate policies change. The standard setting unit can also dynamically adjust the standards in response to amendments to laws and regulations. Furthermore, the standard setting unit can update the standards to reflect changes in corporate policies and laws and regulations in real time. This allows the latest standards to be always applied by dynamically updating the standards in response to changes in corporate policies and laws and regulations. Some or all of the above-mentioned processing in the standard setting unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the standard setting unit can input data on changes in corporate policies and laws and regulations into the generation AI, which can then dynamically update the standards.

[0086] The standard setting unit can estimate the user's emotions and determine the priority of standard setting based on the estimated user's emotions. For example, if the user is angry, the standard setting unit can increase the priority of standard setting taking into account the user's heightened emotions. Furthermore, if the user is relaxed, the standard setting unit can set standards at a normal priority taking into account emotional stability. Furthermore, if the user is nervous, the standard setting priority can be fine-tuned taking into account emotional fluctuations. Thus, by determining the priority of standard setting according to the user's emotions, important standards are prioritized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the standard setting unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the standard setting unit can input the user's emotion data into the generation AI, which can then estimate the emotion and determine the priority of standard setting.

[0087] The standard setting unit can customize the standards based on the industry or size of the company. For example, the standard setting unit can set strict standards for large companies. Also, the standard setting unit can set flexible standards for small and medium-sized companies. Furthermore, the standard setting unit can customize appropriate standards according to a specific industry. In this way, by customizing the standards according to the industry and size of the company, more appropriate standards can be set. Some or all of the above-mentioned processing in the standard setting unit may be performed using, or without, the generation AI, for example. For example, the standard setting unit can input data on the industry and size of the company into the generation AI, which can then customize the standards.

[0088] The standard setting unit can apply different standards depending on the category of the remark. For example, the standard setting unit can apply strict standards to remarks that constitute power harassment. Furthermore, in the case of remarks that constitute sexual harassment, the standard setting unit can apply standards that immediately address the remarks. Furthermore, in the case of other problematic remarks, the standard setting unit can apply appropriate standards. In this way, appropriate standards are applied by changing the standards depending on the category of the remark. Some or all of the above-mentioned processing in the standard setting unit may be performed using, or without, a generation AI. For example, the standard setting unit can input category data of the remarks into the generation AI, which can then select appropriate standards. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, alert unit, and reporting unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14, and monitors internal emails and phone calls in real time and analyzes them using natural language processing technology. The alert unit is realized, for example, by the control unit 46A of the smart device 14, and displays an alert as a pop-up message or audio notification when a problematic comment is detected. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically reports the HR department or an appropriate department if the alert is ignored. === Hard Collateral 1-2 === Each of the multiple elements, including the analysis unit, alert unit, and reporting unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214, and monitors internal emails and phone call content in real time and analyzes them using natural language processing technology. The alert unit is realized, for example, by the control unit 46A of the smart glasses 214, and displays an alert as a pop-up message or voice notification when a problematic statement is detected. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically reports the human resources department or an appropriate department if the alert is ignored. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, alert unit, and reporting unit is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset terminal 314, and monitors internal emails and phone call content in real time and analyzes them using natural language processing technology. The alert unit is realized, for example, by the control unit 46A of the headset terminal 314, and displays an alert as a pop-up message or audio notification when a problematic statement is detected. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically reports the human resources department or an appropriate department if the alert is ignored. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, alert unit, and reporting unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414, and monitors internal emails and phone call content in real time and analyzes them using natural language processing technology. The alert unit is realized, for example, by the control unit 46A of the robot 414, and displays an alert as a pop-up message or audio notification when a problematic statement is detected. The reporting unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically reports the human resources department or an appropriate department when the alert is ignored.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, if the user is angry, the generation AI can detect the heightened emotions and increase the accuracy of the analysis. Also, if the user is relaxed, the generation AI can detect emotional stability and maintain normal analysis accuracy. Furthermore, if the user is nervous, the generation AI can detect emotional fluctuations and fine-tune the analysis accuracy. This allows for more appropriate analysis by adjusting the analysis accuracy according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI, or without the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI, which can then estimate the emotion and adjust the analysis accuracy.

[0091] The analysis unit can improve the accuracy of detecting problematic statements by referring to past statement history. For example, it can detect similar statement patterns by referring to the statement history of users who have made problematic statements in the past. It can also improve detection accuracy by extracting specific keywords or phrases from the past statement history. Furthermore, it can analyze the past statement history to understand trends in problematic statements and reflect them in the analysis. In this way, by referring to the past statement history, the accuracy of detecting problematic statements is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input past statement history data into a generation AI, which can analyze statement patterns to detect problematic statements.

[0092] The analysis unit can dynamically change the detection criteria for problematic statements based on the context of the statement. For example, the analysis unit can analyze the context before and after the statement to increase the likelihood of the statement being problematic. The analysis unit can also dynamically change the importance of specific keywords depending on the context of the statement. Furthermore, the analysis unit can adjust the detection criteria for problematic statements in real time, taking into account the context of the statement. This improves the accuracy of detecting problematic statements by taking into account the context of the statement. The analysis of the context may be performed, for example, using or without the generation AI. For example, the analysis unit can input context data before and after the statement into the generation AI, which can then analyze the context and dynamically change the detection criteria for problematic statements.

[0093] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated user emotions. For example, if the user is angry, the generation AI can detect the heightened emotions and prioritize displaying the analysis results. Also, if the user is relaxed, the generation AI can detect the emotional stability and display the analysis results with normal priority. Furthermore, if the user is nervous, the generation AI can detect emotional fluctuations and fine-tune the priority of the analysis results. Thus, by prioritizing the analysis results according to the user's emotions, important analysis results are displayed with priority. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, the generation AI, or without the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI, which can then estimate the emotion and prioritize the analysis results.

[0094] The analysis unit can adjust the accuracy of the analysis based on the speaker's job position or title. For example, if the speaker is a superior, the generation AI can increase the analysis accuracy by taking into account the influence of the comment. Also, if the speaker is a subordinate, the generation AI can maintain normal analysis accuracy by taking into account the influence of the comment. Furthermore, if the speaker is a colleague, the generation AI can fine-tune the analysis accuracy by taking into account the influence of the comment. In this way, the analysis accuracy is improved by taking into account the speaker's job position or title. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input the speaker's job position or title data into the generation AI, which can analyze the influence of the comment and adjust the analysis accuracy.

[0095] The alert unit can estimate the user's emotions and adjust the way the alert is expressed based on the estimated user emotions. For example, if the user is angry, the generation AI can display the alert in a calm tone. Furthermore, if the user is relaxed, the generation AI can display the alert in a gentle tone. Furthermore, if the user is nervous, the generation AI can display the alert in a gentle tone. This allows for more effective alerting by adjusting the way the alert is expressed based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the alert unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the alert unit can input the user's emotion data into the generation AI, which then estimates the emotion and adjusts the way the alert is expressed.

[0096] The alert unit can select the optimal alert method by referring to past alert history. For example, it can preferentially display alert methods that were effective in the past. It can also select the optimal alert method for a specific user from past alert history. It can also analyze past alert history and suggest the most effective alert method. In this way, the optimal alert method is selected by referring to past alert history. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, a generation AI, for example. For example, the alert unit can input past alert history data into the generation AI, which can then select the optimal alert method.

[0097] The alert unit can adjust the level of detail of the alert based on the importance of the statement. For example, in the case of a serious problematic statement, the generation AI can display a detailed alert. In addition, in the case of a minor problematic statement, the generation AI can display a concise alert. Furthermore, the generation AI can dynamically adjust the level of detail of the alert according to the importance of the statement. As a result, by adjusting the level of detail of the alert according to the importance of the statement, appropriate attention can be given. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input statement importance data into the generation AI, which can then adjust the level of detail of the alert.

[0098] The alert unit can estimate the user's emotions and adjust the timing of the alert based on the estimated user emotions. For example, if the user is angry, the generation AI can immediately display an alert. Furthermore, if the user is relaxed, the generation AI can display an alert at an appropriate time. Furthermore, if the user is nervous, the generation AI can carefully adjust the timing of the alert. This allows for more effective alerting by adjusting the timing of the alert according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the alert unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the alert unit can input the user's emotion data into the generation AI, which then estimates the emotion and adjusts the timing of the alert.

[0099] The alert unit can customize the content of the alert based on the speaker's attribute information. For example, if the speaker is a superior, the generation AI can display the alert using appropriate honorific language. Furthermore, if the speaker is a subordinate, the generation AI can display the alert in a friendly tone. Furthermore, if the speaker is a colleague, the generation AI can display the alert in a casual tone. In this way, by customizing the content of the alert according to the speaker's attribute information, more appropriate attention can be given. Some or all of the above-mentioned processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input the speaker's attribute information data into the generation AI, which can then customize the content of the alert.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The analysis unit monitors internal emails or phone call content in real time. The analysis unit uses natural language processing technology to analyze emails and phone call content and detect comments that constitute power harassment or sexual harassment. Natural language processing technology includes morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to break down words in emails and phone call content, grammatical analysis to analyze the structure of sentences, and semantic analysis to understand the meaning of sentences. By combining these technologies, it is possible to detect comments that constitute power harassment or sexual harassment with a high degree of accuracy. Step 2: The alerting unit immediately issues an alert to the person involved based on the problematic remarks detected by the analysis unit. The alerting unit displays the alert as a pop-up message or a voice notification. For example, it can display a message saying, "That remark is inappropriate. Please revise your remark." Step 3: If the alert is ignored by the Alert Department, the Reporting Department will automatically notify the Human Resources Department or the appropriate department. The Reporting Department will make a report that includes the content of the problematic remark and information about the person who made it. The report will include the date and time of the remark, the name of the person who made it, and the content of the remark. For example, a report can be made with the content, "Mr. / Ms. XX made an inappropriate remark. Details are as follows."

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0104] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0105] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0157] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0158] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0159] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0162] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0163] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0164] 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.

[0165] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0166] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0167] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0168] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0170] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0171] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0172] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0173] [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An analysis unit that monitors internal emails or phone calls in real time, an alert unit that immediately issues an alert to the person concerned based on the problematic statement detected by the analysis unit; a reporting unit that automatically reports to a human resources department or an appropriate department when the alert is ignored by the alert unit; Equipped with A system characterized by:

2. The analysis unit Analyze emails and phone calls using natural language processing technology to detect statements that constitute power harassment or sexual harassment 2. The system of claim 1.

3. The alert unit Display alerts as pop-up messages or sound notifications 2. The system of claim 1.

4. The reporting unit Report the problematic comment and include information about the commenter.

2. The system of claim 1.

5. The analysis unit A standard setting unit is provided to set standards for detecting problematic statements based on company policy or laws and regulations.

2. The system of claim 1.

6. The analysis unit Estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions.

2. The system of claim 1.

7. The analysis unit Improve the accuracy of detecting problematic statements by referencing past statement history 2. The system of claim 1.

8. The analysis unit Dynamically change the detection criteria for problematic statements based on the context of the statement 2. The system of claim 1.

Images