system

Abstract

The system according to the embodiment aims to detect verbal abuse in real time and immediately alert the user. [Solution] A system according to an embodiment includes a collection unit, an analysis unit, and an alert unit. The collection unit monitors conversations in real time. The analysis unit analyzes the audio data collected by the collection unit and detects statements of moral harassment. The alert unit issues an alert to the user when such statements are detected by the analysis unit.

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 moral harassment language in real time and respond immediately.

[0005] The system according to the embodiment aims to detect verbal abuse in real time and immediately alert the user. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and an alert unit. The collection unit monitors conversations in real time. The analysis unit analyzes the audio data collected by the collection unit and detects statements of moral harassment. The alert unit issues an alert to the user when such statements are detected by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect verbal abuse in real time and immediately alert the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A moral harassment detection system according to an embodiment of the present invention monitors conversations in real time, and a generation AI detects potentially moral harassment statements and issues an alert. The moral harassment detection system monitors conversations in real time, and the generation AI compares the results with numerous past cases of moral harassment to detect potentially moral harassment statements. For example, a moral harassment detection system constantly monitors conversations at work or home and collects audio data. This audio data is input into a generation AI. The generation AI then analyzes the input audio data. The generation AI compares the results with numerous past cases of moral harassment to detect potentially moral harassment statements. For example, the system can detect offensive phrases such as "You're useless" and "How many times do I have to tell you?" If such phrases are detected, an alert is issued to the user. For example, a warning message can be displayed on a smartphone or PC screen or a voice message can be used to warn the user. This allows the user to immediately recognize the occurrence of moral harassment and take appropriate action. The moral harassment detection system can also estimate a user's emotions and adjust the timing of conversation collection and the method of displaying alerts based on the estimated emotions. For example, if a user is feeling stressed, the collection frequency can be increased, allowing for early detection of signs of moral harassment. This enables the moral harassment detection system to detect and prevent moral harassment early. This allows the moral harassment detection system to monitor user conversations in real time, detect phrases that may be moral harassment, and issue an alert. For example, by constantly monitoring conversations at work or at home, it can detect signs of moral harassment early and take appropriate action. This allows users to maintain a healthy communication environment.

[0029] A moral harassment detection system according to an embodiment includes a collection unit, an analysis unit, and an alert unit. The collection unit monitors conversations in real time. For example, the collection unit constantly monitors conversations at work or at home and collects audio data. The collection unit can also use a generation AI to convert the audio data into a format that is easier to analyze. For example, the collection unit can convert the audio data into text data. The analysis unit uses a generation AI to analyze the audio data collected by the collection unit. The analysis unit compares countless past cases of moral harassment to detect potentially moral harassment phrases. For example, the analysis unit can detect aggressive phrases such as "You're useless" or "How many times do I have to tell you?" The alert unit issues an alert to the user when such phrases are detected by the analysis unit. For example, the alert unit can display a warning message on a smartphone or PC screen or issue an audio warning. This enables early detection and prevention of moral harassment by detecting potentially moral harassment phrases in real time and issuing an alert to the user. Furthermore, the alert unit can estimate the user's emotions and adjust the alert display method based on the estimated emotions. For example, if the user is feeling stressed, a simple and highly visible alert can be displayed. This allows for more effective alerts to be provided according to the user's emotions.

[0030] The collection unit can periodically monitor conversations at work or at home and collect voice data. For example, the collection unit can constantly monitor conversations at work or at home and collect voice data. The collection unit can also use a generation AI to convert the voice data into a format that is easy to analyze. For example, the collection unit can convert the voice data into text data. By constantly monitoring conversations at work or at home, signs of moral harassment can be detected early. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the collection unit can input voice data into the generation AI and have the generation AI generate text data from the voice data.

[0031] The analysis unit uses the generation AI to analyze the voice data and compare past cases of moral harassment with numerous other cases to detect moral harassment phrases. The analysis unit uses the generation AI to analyze the voice data collected by the collection unit. The analysis unit compares countless past cases of moral harassment to detect phrases that may be moral harassment. For example, the analysis unit can detect offensive words such as "You're useless" or "How many times do I have to tell you?". This allows the use of the generation AI to detect phrases that may be moral harassment with high accuracy. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input voice data into the generation AI and have the generation AI detect moral harassment phrases.

[0032] The alert unit can display a warning message on the screen of the smartphone or PC and warn the user by voice. The alert unit issues an alert to the user when detected by the analysis unit. The alert unit can, for example, display a warning message on the screen of the smartphone or PC and warn the user by voice. This allows the user to immediately recognize the occurrence of moral harassment by issuing visual and auditory alerts. Some or all of the above-mentioned 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 cause the generation AI to generate a warning message.

[0033] The collection unit can analyze the user's past conversation history and select an appropriate collection method. For example, the collection unit can identify time periods during which the user frequently experienced moral harassment in the past and focus on collecting conversations from those time periods. The collection unit can also prioritize collecting conversations with specific people from the user's past conversation history. Furthermore, the collection unit can analyze the user's past conversation history and prioritize collecting conversations containing specific keywords. In this way, by analyzing the past conversation history, it is possible to prioritize collecting conversations with people or times during which moral harassment is more likely to occur. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, a generation AI, or can be performed without using the generation AI. For example, the collection unit can input the past conversation history into the generation AI and have the generation AI select the optimal collection method.

[0034] When collecting conversations, the collection unit can filter them based on the user's current environment or situation. For example, when the user is at work, the collection unit prioritizes collecting conversations at work. Also, when the user is at home, the collection unit can prioritize collecting conversations at home. Furthermore, when the user is in a public place, the collection unit can limit collection of conversations in consideration of privacy. This makes it possible to collect more relevant conversations by filtering conversations according to the user's environment and situation. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit can input the user's environmental data into the generation AI and have the generation AI perform filtering.

[0035] When collecting conversations, the collection unit can select an appropriate collection means depending on the user's input method. For example, if the user is using voice input, the collection unit prioritizes collecting voice data. Also, if the user is using text input, the collection unit can also prioritize collecting text data. Furthermore, if the user is using image input, the collection unit can analyze image data to collect related conversations. This allows for efficient collection of conversations by selecting the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the collection unit can input the user's input data into the generation AI and have the generation AI select the optimal collection means.

[0036] When collecting conversations, the collection unit can prioritize collecting highly relevant conversations based on the user's geographical location information. For example, when the user is in a specific location, the collection unit prioritizes collecting conversations at that location. Furthermore, when the user is traveling, the collection unit can also prioritize collecting conversations at the user's destination. Furthermore, when the user is in a specific area, the collection unit can also prioritize collecting conversations in that area. This makes it possible to prioritize collecting highly relevant conversations taking the user's geographical location information into consideration. Some or all of the above-described processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to collect highly relevant conversations.

[0037] When collecting conversations, the collection unit can analyze the user's social media activities and collect related conversations. For example, the collection unit collects related conversations based on the content posted by the user on social media. The collection unit can also collect related conversations by referring to the activities of the user's friends on social media. Furthermore, the collection unit can collect related conversations based on the user's check-in information on social media. In this way, highly relevant conversations can be collected by analyzing the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the user's social media data into the generation AI and cause the generation AI to collect related conversations.

[0038] When collecting conversations, the collection unit can customize the collection method based on the user's past feedback. The collection unit, for example, adjusts the collection method based on feedback provided by the user in the past. The collection unit can also prioritize collection of specific conversations based on the user's past feedback. Furthermore, the collection unit can analyze the user's past feedback and suggest an optimal collection method. This makes it possible to provide an optimal collection method by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit can input the user's feedback data into the generation AI and have the generation AI customize the collection method.

[0039] During analysis, the analysis unit can adjust the level of detail of the analysis based on the priority of the conversation. For example, in the case of an important conversation, the analysis unit allows the generation AI to perform a detailed analysis. In addition, in the case of a normal conversation, the analysis unit can also allow the generation AI to perform a concise analysis. Furthermore, in the case of a conversation where there is a high possibility of moral harassment, the analysis unit can also allow the generation AI to perform a particularly detailed analysis. In this way, by adjusting the level of detail of the analysis according to the importance of the conversation, analysis can be performed efficiently. 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 conversation data to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0040] During analysis, the analysis unit can apply different analysis algorithms depending on the type of conversation. For example, in the case of a conversation at work, the analysis unit can apply an algorithm that causes the generation AI to detect workplace-specific moral harassment. In addition, in the case of a conversation at home, the analysis unit can also apply an algorithm that causes the generation AI to detect home-specific moral harassment. Furthermore, in the case of a conversation in a public place, the analysis unit can also apply an algorithm that causes the generation AI to detect public-specific moral harassment. This allows for the application of an appropriate analysis algorithm depending on the type of conversation, thereby improving the accuracy of moral harassment detection. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the analysis unit can input conversation data into the generation AI and have the generation AI apply an appropriate analysis algorithm.

[0041] During analysis, the analysis unit can improve the accuracy of the analysis based on the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm using the generation AI based on the user's past analysis results. The analysis unit can also learn specific patterns from the user's past analysis results to improve the analysis accuracy. Furthermore, the analysis unit can analyze the user's past analysis results and suggest an optimal analysis method. This allows the analysis accuracy to be improved by referring to the past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input past analysis results into the generation AI and have the generation AI improve the analysis accuracy.

[0042] During analysis, the analysis unit can determine the analysis priority based on the time the conversation occurred. For example, the analysis unit prioritizes analysis of recent conversations. The analysis unit can also prioritize analysis of conversations that occurred during a specific time period. Furthermore, the analysis unit can also prioritize analysis of conversations within a period specified by the user. This allows for efficient analysis by determining the analysis priority based on the time the conversation occurred. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input conversation data into a generation AI and have the generation AI determine the analysis priority.

[0043] During analysis, the analysis unit can adjust the order of analysis based on the relationships between conversations. For example, the analysis unit prioritizes analysis of conversations that are likely to be moral harassment. The analysis unit can also prioritize analysis of specific conversations specified by the user. Furthermore, the analysis unit can group and analyze highly related conversations. This allows for efficient analysis by adjusting the order of analysis based on the relationships between the conversations. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input conversation data into a generation AI and have the generation AI adjust the order of analysis.

[0044] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's knowledge level. For example, if the user has specialized knowledge, the analysis unit can provide analysis results using detailed technical terminology. Alternatively, if the user does not have specialized knowledge, the analysis unit can provide analysis results using concise, easy-to-understand language. Furthermore, the analysis unit can select appropriate technical terminology according to the user's level of expertise to provide analysis results. By adjusting the use of technical terminology in the analysis according to the user's level of expertise, more understandable analysis results can be provided. Some or all of the above-described 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 the user's knowledge level data into the generation AI and have the generation AI execute the use of technical terminology.

[0045] When an alert occurs, the alert unit can select an appropriate alert method based on the user's past reaction history. For example, the alert unit selects the optimal alert method based on the alert method to which the user has responded in the past. The alert unit can also preferentially select a specific alert method based on the user's past reaction history. Furthermore, the alert unit can analyze the user's past reaction history and suggest the optimal alert method. This makes it possible to provide the optimal alert method by referring to the user's past reaction history. Some or all of the above-described processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input the user's reaction history data into the generation AI and have the generation AI select the optimal alert method.

[0046] When an alert occurs, the alert unit can customize the alert content based on the user's current situation. For example, when the user is at work, the alert unit displays alert content appropriate for the workplace. Furthermore, when the user is at home, the alert unit can also display alert content appropriate for the home. Furthermore, when the user is in a public place, the alert unit can display alert content that takes privacy into consideration. This allows for customizing the alert content according to the user's current situation, making it possible to provide more appropriate alerts. Some or all of the above-described processing in the alert unit may be performed using, or without, a generation AI. For example, the alert unit can input the user's current situation data into the generation AI and have the generation AI customize the alert content.

[0047] When an alert occurs, the alert unit can improve the alert method based on user feedback. The alert unit can adjust the alert method based on, for example, feedback provided by the user in the past. The alert unit can also preferentially select a specific alert method based on the user's past feedback. Furthermore, the alert unit can analyze the user's past feedback and suggest an optimal alert method. This makes it possible to provide a more effective alert method by reflecting the user's feedback. Some or all of the above-described processing in the alert unit can be performed using, or without, a generation AI. For example, the alert unit can input user feedback data into the generation AI and have the generation AI improve the alert method.

[0048] When an alert occurs, the alert unit can select an appropriate alert method based on the user's geographical location information. For example, if the user is in a specific location, the alert unit selects an alert method appropriate for that location. Furthermore, if the user is moving, the alert unit can also select an alert method appropriate for the user's destination. Furthermore, if the user is in a specific area, the alert unit can also select an alert method appropriate for that area. This makes it possible to provide an optimal alert method by taking the user's geographical location information into consideration. Some or all of the above-described processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input the user's geographical location information into the generation AI and cause the generation AI to select the optimal alert method.

[0049] When an alert occurs, the alert unit can analyze the user's social media activity and suggest alert content. The alert unit can, for example, suggest relevant alert content based on the content posted by the user on social media. The alert unit can also suggest relevant alert content based on the activity of the user's friends on social media. Furthermore, the alert unit can also suggest relevant alert content based on the user's social media check-in information. In this way, by analyzing the user's social media activity, highly relevant alert content can be provided. Some or all of the above-mentioned processing in the alert unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the alert unit can input the user's social media data into the generation AI and have the generation AI suggest alert content.

[0050] When an alert occurs, the alert unit can customize the alert method based on the user's past feedback. The alert unit adjusts the alert method based on, for example, feedback provided by the user in the past. The alert unit can also preferentially select a specific alert method based on the user's past feedback. Furthermore, the alert unit can analyze the user's past feedback and suggest an optimal alert method. This makes it possible to provide a more effective alert method by reflecting the user's past feedback. Some or all of the above-described processing in the alert unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the alert unit can input user feedback data into the generation AI and have the generation AI customize the alert method.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The moral harassment detection system can further include a schedule acquisition unit that acquires the user's schedule information. The schedule acquisition unit works in conjunction with the user's calendar app or schedule management tool to acquire the user's schedule. The analysis unit can prioritize analysis of conversations that occur before and after specific important meetings or events based on the acquired schedule information. For example, it can perform a detailed analysis of conversations that occur immediately before an important meeting to detect signs of moral harassment early. It can also focus on analysis of conversations that occur during times when the user is likely to feel stressed (for example, Monday mornings or Friday evenings). This makes it possible to utilize the user's schedule information to improve the accuracy of moral harassment detection.

[0053] The moral harassment detection system can further include a location information acquisition unit that acquires the user's location information. The location information acquisition unit acquires location information from the user's smartphone or GPS device and provides it to the analysis unit. When the user is in a specific location, the analysis unit can prioritize analysis of conversations at that location. For example, when the user is at work, the analysis unit can focus on analyzing conversations at work. Also, when the user is at home, the analysis unit can analyze conversations at home in detail. Furthermore, when the user is in a public place, the analysis unit can analyze conversations at that place while taking privacy into consideration. This makes it possible to utilize location information to improve the accuracy of moral harassment detection.

[0054] The moral harassment detection system can further include a history analysis unit that analyzes the user's past moral harassment detection history. The history analysis unit analyzes previously detected cases of moral harassment and provides this data to the analysis unit. The analysis unit can prioritize analysis of conversations with similar patterns based on the past moral harassment detection history. For example, if a specific phrase was detected as moral harassment in the past, the analysis unit can analyze in detail conversations in which that phrase was used again. Furthermore, if moral harassment occurred in a specific time period or situation in the past, the analysis can also focus on conversations in that time period and situation. This makes it possible to prevent the recurrence of moral harassment by utilizing the past moral harassment detection history.

[0055] The moral harassment detection system may further include a health data acquisition unit that acquires the user's health data. The health data acquisition unit acquires health data from the user's fitness tracker or smartwatch and provides this data to the analysis unit. The analysis unit estimates the user's physical condition based on the health data, and if the user is feeling unwell, it can prioritize analyzing the conversations that occurred. For example, if it detects that the user is not getting enough sleep, it can analyze the conversations that occurred that day in detail. Also, if it detects that the user is not exercising enough, it can focus on analyzing the conversations that occurred at that time. This makes it possible to utilize health data to improve the accuracy of moral harassment detection.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The collection unit monitors conversations in real time and collects voice data. For example, it can constantly monitor conversations at work or at home and collect voice data. The collection unit can also use generative AI to convert the voice data into a format that is easier to analyze. For example, it can convert the voice data into text data. Step 2: The analysis unit analyzes the audio data collected by the collection unit and detects statements that could be considered moral harassment. The analysis unit uses generative AI to compare countless past cases of moral harassment and detect statements that could be considered moral harassment. For example, it can detect offensive words such as "You're useless" and "How many times do I have to tell you?" Step 3: The alert unit issues an alert to the user when the analysis unit detects a problem. The alert unit can, for example, display a warning message on the screen of a smartphone or PC, or alert the user by voice. Furthermore, the alert unit can estimate the user's emotions and adjust the way the alert is displayed based on the estimated emotions. For example, if the user is feeling stressed, a simple, highly visible alert can be displayed.

[0058] (Example 2) A moral harassment detection system according to an embodiment of the present invention monitors conversations in real time, and a generation AI detects potentially moral harassment statements and issues an alert. The moral harassment detection system monitors conversations in real time, and the generation AI compares the results with numerous past cases of moral harassment to detect potentially moral harassment statements. For example, a moral harassment detection system constantly monitors conversations at work or home and collects audio data. This audio data is input into a generation AI. The generation AI then analyzes the input audio data. The generation AI compares the results with numerous past cases of moral harassment to detect potentially moral harassment statements. For example, the system can detect offensive phrases such as "You're useless" and "How many times do I have to tell you?" If such phrases are detected, an alert is issued to the user. For example, a warning message can be displayed on a smartphone or PC screen or a voice message can be used to warn the user. This allows the user to immediately recognize the occurrence of moral harassment and take appropriate action. The moral harassment detection system can also estimate a user's emotions and adjust the timing of conversation collection and the method of displaying alerts based on the estimated emotions. For example, if a user is feeling stressed, the collection frequency can be increased, allowing for early detection of signs of moral harassment. This enables the moral harassment detection system to detect and prevent moral harassment early. This allows the moral harassment detection system to monitor user conversations in real time, detect phrases that may be moral harassment, and issue an alert. For example, by constantly monitoring conversations at work or at home, it can detect signs of moral harassment early and take appropriate action. This allows users to maintain a healthy communication environment.

[0059] A moral harassment detection system according to an embodiment includes a collection unit, an analysis unit, and an alert unit. The collection unit monitors conversations in real time. For example, the collection unit constantly monitors conversations at work or at home and collects audio data. The collection unit can also use a generation AI to convert the audio data into a format that is easier to analyze. For example, the collection unit can convert the audio data into text data. The analysis unit uses a generation AI to analyze the audio data collected by the collection unit. The analysis unit compares countless past cases of moral harassment to detect potentially moral harassment phrases. For example, the analysis unit can detect aggressive phrases such as "You're useless" or "How many times do I have to tell you?" The alert unit issues an alert to the user when such phrases are detected by the analysis unit. For example, the alert unit can display a warning message on a smartphone or PC screen or issue an audio warning. This enables early detection and prevention of moral harassment by detecting potentially moral harassment phrases in real time and issuing an alert to the user. Furthermore, the alert unit can estimate the user's emotions and adjust the alert display method based on the estimated emotions. For example, if the user is feeling stressed, a simple and highly visible alert can be displayed. This allows for more effective alerts to be provided according to the user's emotions.

[0060] The collection unit can periodically monitor conversations at work or at home and collect voice data. For example, the collection unit can constantly monitor conversations at work or at home and collect voice data. The collection unit can also use a generation AI to convert the voice data into a format that is easy to analyze. For example, the collection unit can convert the voice data into text data. By constantly monitoring conversations at work or at home, signs of moral harassment can be detected early. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the collection unit can input voice data into the generation AI and have the generation AI generate text data from the voice data.

[0061] The analysis unit uses the generation AI to analyze the voice data and compare past cases of moral harassment with numerous other cases to detect moral harassment phrases. The analysis unit uses the generation AI to analyze the voice data collected by the collection unit. The analysis unit compares countless past cases of moral harassment to detect phrases that may be moral harassment. For example, the analysis unit can detect offensive words such as "You're useless" or "How many times do I have to tell you?". This allows the use of the generation AI to detect phrases that may be moral harassment with high accuracy. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input voice data into the generation AI and have the generation AI detect moral harassment phrases.

[0062] The alert unit can display a warning message on the screen of the smartphone or PC and warn the user by voice. The alert unit issues an alert to the user when detected by the analysis unit. The alert unit can, for example, display a warning message on the screen of the smartphone or PC and warn the user by voice. This allows the user to immediately recognize the occurrence of moral harassment by issuing visual and auditory alerts. Some or all of the above-mentioned 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 cause the generation AI to generate a warning message.

[0063] The collection unit can analyze the user's emotions and adjust the timing of conversation collection based on the analyzed user emotions. For example, when the user is feeling stressed, the collection unit causes the generation AI to increase the frequency of conversation collection, thereby detecting signs of moral harassment early. Furthermore, when the user is relaxed, the collection unit can also cause the generation AI to reduce the frequency of conversation collection and collect only when necessary. Furthermore, when the user is in a hurry, the collection unit can also cause the generation AI to prioritize collecting important conversations in a short time. This allows for more effective detection of signs of moral harassment by adjusting the timing of conversation collection 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 collection unit can be performed using, for example, the generation AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI adjust the collection timing.

[0064] The collection unit can analyze the user's past conversation history and select an appropriate collection method. For example, the collection unit can identify time periods during which the user frequently experienced moral harassment in the past and focus on collecting conversations from those time periods. The collection unit can also prioritize collecting conversations with specific people from the user's past conversation history. Furthermore, the collection unit can analyze the user's past conversation history and prioritize collecting conversations containing specific keywords. In this way, by analyzing the past conversation history, it is possible to prioritize collecting conversations with people or times during which moral harassment is more likely to occur. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, a generation AI, or can be performed without using the generation AI. For example, the collection unit can input the past conversation history into the generation AI and have the generation AI select the optimal collection method.

[0065] When collecting conversations, the collection unit can filter them based on the user's current environment or situation. For example, when the user is at work, the collection unit prioritizes collecting conversations at work. Also, when the user is at home, the collection unit can prioritize collecting conversations at home. Furthermore, when the user is in a public place, the collection unit can limit collection of conversations in consideration of privacy. This makes it possible to collect more relevant conversations by filtering conversations according to the user's environment and situation. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit can input the user's environmental data into the generation AI and have the generation AI perform filtering.

[0066] When collecting conversations, the collection unit can select an appropriate collection means depending on the user's input method. For example, if the user is using voice input, the collection unit prioritizes collecting voice data. Also, if the user is using text input, the collection unit can also prioritize collecting text data. Furthermore, if the user is using image input, the collection unit can analyze image data to collect related conversations. This allows for efficient collection of conversations by selecting the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the collection unit can input the user's input data into the generation AI and have the generation AI select the optimal collection means.

[0067] The collection unit can analyze the user's emotions and determine the priority of conversations to be collected based on the analyzed user's emotions. For example, when the user is stressed, the collection unit causes the generation AI to prioritize collection of conversations that are likely to be moral harassment. Furthermore, when the user is relaxed, the collection unit can also cause the generation AI to prioritize collection of normal conversations. Furthermore, when the user is in a hurry, the collection unit can also cause the generation AI to prioritize collection of important conversations that can be completed quickly. This allows conversations that are likely to be moral harassment to be collected preferentially by determining the priority of conversations 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-described processing in the collection unit can be performed using, for example, the generation AI, or without the generation AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of conversations to be collected.

[0068] When collecting conversations, the collection unit can prioritize collecting highly relevant conversations based on the user's geographical location information. For example, when the user is in a specific location, the collection unit prioritizes collecting conversations at that location. Furthermore, when the user is traveling, the collection unit can also prioritize collecting conversations at the user's destination. Furthermore, when the user is in a specific area, the collection unit can also prioritize collecting conversations in that area. This makes it possible to prioritize collecting highly relevant conversations taking the user's geographical location information into consideration. Some or all of the above-described processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to collect highly relevant conversations.

[0069] When collecting conversations, the collection unit can analyze the user's social media activities and collect related conversations. For example, the collection unit collects related conversations based on the content posted by the user on social media. The collection unit can also collect related conversations by referring to the activities of the user's friends on social media. Furthermore, the collection unit can collect related conversations based on the user's check-in information on social media. In this way, highly relevant conversations can be collected by analyzing the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the user's social media data into the generation AI and cause the generation AI to collect related conversations.

[0070] When collecting conversations, the collection unit can customize the collection method based on the user's past feedback. The collection unit, for example, adjusts the collection method based on feedback provided by the user in the past. The collection unit can also prioritize collection of specific conversations based on the user's past feedback. Furthermore, the collection unit can analyze the user's past feedback and suggest an optimal collection method. This makes it possible to provide an optimal collection method by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, the generation AI. For example, the collection unit can input the user's feedback data into the generation AI and have the generation AI customize the collection method.

[0071] The analysis unit can analyze the user's emotions and adjust the way the analysis is presented based on the analyzed user's emotions. For example, if the user is feeling stressed, the analysis unit can have the generation AI provide a concise and easy-to-understand analysis result. Furthermore, if the user is relaxed, the analysis unit can have the generation AI provide a detailed analysis result. Furthermore, if the user is in a hurry, the analysis unit can have the generation AI provide an analysis result that focuses on the main points. This allows for more appropriate analysis results to be provided by adjusting the way the analysis is presented 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 and have the generation AI adjust the way the analysis is presented.

[0072] During analysis, the analysis unit can adjust the level of detail of the analysis based on the priority of the conversation. For example, in the case of an important conversation, the analysis unit allows the generation AI to perform a detailed analysis. In addition, in the case of a normal conversation, the analysis unit can also allow the generation AI to perform a concise analysis. Furthermore, in the case of a conversation where there is a high possibility of moral harassment, the analysis unit can also allow the generation AI to perform a particularly detailed analysis. In this way, by adjusting the level of detail of the analysis according to the importance of the conversation, analysis can be performed efficiently. 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 conversation data to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0073] During analysis, the analysis unit can apply different analysis algorithms depending on the type of conversation. For example, in the case of a conversation at work, the analysis unit can apply an algorithm that causes the generation AI to detect workplace-specific moral harassment. In addition, in the case of a conversation at home, the analysis unit can also apply an algorithm that causes the generation AI to detect home-specific moral harassment. Furthermore, in the case of a conversation in a public place, the analysis unit can also apply an algorithm that causes the generation AI to detect public-specific moral harassment. This allows for the application of an appropriate analysis algorithm depending on the type of conversation, thereby improving the accuracy of moral harassment detection. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the analysis unit can input conversation data into the generation AI and have the generation AI apply an appropriate analysis algorithm.

[0074] During analysis, the analysis unit can improve the accuracy of the analysis based on the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm using the generation AI based on the user's past analysis results. The analysis unit can also learn specific patterns from the user's past analysis results to improve the analysis accuracy. Furthermore, the analysis unit can analyze the user's past analysis results and suggest an optimal analysis method. This allows the analysis accuracy to be improved by referring to the past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, or without, the generation AI. For example, the analysis unit can input past analysis results into the generation AI and have the generation AI improve the analysis accuracy.

[0075] The analysis unit can analyze the user's emotions and adjust the length of the analysis based on the analyzed user's emotions. For example, if the user is feeling stressed, the analysis unit can cause the generation AI to perform a short, concise analysis. Furthermore, if the user is relaxed, the analysis unit can cause the generation AI to perform a detailed analysis. Furthermore, if the user is in a hurry, the analysis unit can cause the generation AI to perform a concise analysis. This allows for adjusting the length of the analysis according to the user's emotions, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, such as 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-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 and have the generation AI adjust the length of the analysis.

[0076] During analysis, the analysis unit can determine the analysis priority based on the time the conversation occurred. For example, the analysis unit prioritizes analysis of recent conversations. The analysis unit can also prioritize analysis of conversations that occurred during a specific time period. Furthermore, the analysis unit can also prioritize analysis of conversations within a period specified by the user. This allows for efficient analysis by determining the analysis priority based on the time the conversation occurred. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input conversation data into a generation AI and have the generation AI determine the analysis priority.

[0077] During analysis, the analysis unit can adjust the order of analysis based on the relationships between conversations. For example, the analysis unit prioritizes analysis of conversations that are likely to be moral harassment. The analysis unit can also prioritize analysis of specific conversations specified by the user. Furthermore, the analysis unit can group and analyze highly related conversations. This allows for efficient analysis by adjusting the order of analysis based on the relationships between the conversations. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input conversation data into a generation AI and have the generation AI adjust the order of analysis.

[0078] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's knowledge level. For example, if the user has specialized knowledge, the analysis unit can provide analysis results using detailed technical terminology. Alternatively, if the user does not have specialized knowledge, the analysis unit can provide analysis results using concise, easy-to-understand language. Furthermore, the analysis unit can select appropriate technical terminology according to the user's level of expertise to provide analysis results. By adjusting the use of technical terminology in the analysis according to the user's level of expertise, more understandable analysis results can be provided. Some or all of the above-described 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 the user's knowledge level data into the generation AI and have the generation AI execute the use of technical terminology.

[0079] The alert unit can analyze the user's emotions and adjust the alert display method based on the analyzed user's emotions. For example, if the user is feeling stressed, the alert unit can display a simple, highly visible alert. Furthermore, if the user is relaxed, the alert unit can also display an alert that includes detailed information. Furthermore, if the user is in a hurry, the alert unit can display an alert that focuses on the main points. This allows for more effective alerts by adjusting the alert display method 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 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 and have the generation AI adjust the alert display method.

[0080] When an alert occurs, the alert unit can select an appropriate alert method based on the user's past reaction history. For example, the alert unit selects the optimal alert method based on the alert method to which the user has responded in the past. The alert unit can also preferentially select a specific alert method based on the user's past reaction history. Furthermore, the alert unit can analyze the user's past reaction history and suggest the optimal alert method. This makes it possible to provide the optimal alert method by referring to the user's past reaction history. Some or all of the above-described processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input the user's reaction history data into the generation AI and have the generation AI select the optimal alert method.

[0081] When an alert occurs, the alert unit can customize the alert content based on the user's current situation. For example, when the user is at work, the alert unit displays alert content appropriate for the workplace. Furthermore, when the user is at home, the alert unit can also display alert content appropriate for the home. Furthermore, when the user is in a public place, the alert unit can display alert content that takes privacy into consideration. This allows for customizing the alert content according to the user's current situation, making it possible to provide more appropriate alerts. Some or all of the above-described processing in the alert unit may be performed using, or without, a generation AI. For example, the alert unit can input the user's current situation data into the generation AI and have the generation AI customize the alert content.

[0082] When an alert occurs, the alert unit can improve the alert method based on user feedback. The alert unit can adjust the alert method based on, for example, feedback provided by the user in the past. The alert unit can also preferentially select a specific alert method based on the user's past feedback. Furthermore, the alert unit can analyze the user's past feedback and suggest an optimal alert method. This makes it possible to provide a more effective alert method by reflecting the user's feedback. Some or all of the above-described processing in the alert unit can be performed using, or without, a generation AI. For example, the alert unit can input user feedback data into the generation AI and have the generation AI improve the alert method.

[0083] The alert unit can analyze the user's emotions and determine the priority of alerts based on the analyzed user's emotions. For example, if the user is feeling stressed, the alert unit can prioritize alerts that are likely to be moral harassment. The alert unit can also prioritize normal alerts when the user is relaxed. Furthermore, the alert unit can prioritize important alerts when the user is in a hurry. By determining the priority of alerts according to the user's emotions, more important alerts can be provided preferentially. 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 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 and have the generation AI determine the priority of alerts.

[0084] When an alert occurs, the alert unit can select an appropriate alert method based on the user's geographical location information. For example, if the user is in a specific location, the alert unit selects an alert method appropriate for that location. Furthermore, if the user is moving, the alert unit can also select an alert method appropriate for the user's destination. Furthermore, if the user is in a specific area, the alert unit can also select an alert method appropriate for that area. This makes it possible to provide an optimal alert method by taking the user's geographical location information into consideration. Some or all of the above-described processing in the alert unit may be performed using, or without, the generation AI. For example, the alert unit can input the user's geographical location information into the generation AI and cause the generation AI to select the optimal alert method.

[0085] When an alert occurs, the alert unit can analyze the user's social media activity and suggest alert content. The alert unit can, for example, suggest relevant alert content based on the content posted by the user on social media. The alert unit can also suggest relevant alert content based on the activity of the user's friends on social media. Furthermore, the alert unit can also suggest relevant alert content based on the user's social media check-in information. In this way, by analyzing the user's social media activity, highly relevant alert content can be provided. Some or all of the above-mentioned processing in the alert unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the alert unit can input the user's social media data into the generation AI and have the generation AI suggest alert content.

[0086] When an alert occurs, the alert unit can customize the alert method based on the user's past feedback. The alert unit adjusts the alert method based on, for example, feedback provided by the user in the past. The alert unit can also preferentially select a specific alert method based on the user's past feedback. Furthermore, the alert unit can analyze the user's past feedback and suggest an optimal alert method. This makes it possible to provide a more effective alert method by reflecting the user's past feedback. Some or all of the above-described processing in the alert unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the alert unit can input user feedback data into the generation AI and have the generation AI customize the alert method. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, and alert unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit monitors conversations in real time using the camera 42 and microphone 38B of the smart device 14 and collects audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected audio data, and detects potentially moral harassment-related statements. The alert unit is realized, for example, by the control unit 46A of the smart device 14, and issues an alert to the user when such statements are detected. The alert unit can, for example, display a warning message using the display 40A or speaker 40B of the smart device 14, or issue an audio warning. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, and alert 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 collection unit monitors conversations in real time using the camera 42 and microphone 238 of the smart glasses 214 and collects audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected audio data, and detects potentially moral harassment-related statements. The alert unit is realized, for example, by the control unit 46A of the smart glasses 214, and issues an alert to the user when such statements are detected. The alert unit can, for example, use the speaker 240 of the smart glasses 214 to issue an audio warning. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, and alert unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit monitors conversations in real time using the camera 42 and microphone 238 of the headset-type terminal 314 and collects audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected audio data, and detects words that may be moral harassment. The alert unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and issues an alert to the user when such words are detected. The alert unit can, for example, use the speaker 240 of the headset-type terminal 314 to issue an audio warning. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, and alert unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit monitors conversations in real time using the camera 42 and microphone 238 of the robot 414 and collects audio data. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected audio data, and detects words that may be moral harassment. The alert unit is realized, for example, by the control unit 46A of the robot 414, and issues an alert to the user when such words are detected. The alert unit can, for example, use the speaker 240 of the robot 414 to issue an audio warning.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The moral harassment detection system can further include a biometric information acquisition unit that acquires the user's biometric information. The biometric information acquisition unit monitors the user's biometric information, such as heart rate and electrodermal activity, in real time and provides this data to the analysis unit. The analysis unit estimates the user's stress level based on this biometric information, and if stress is high, can prioritize analysis of conversations that are likely to be moral harassment. For example, if the user's heart rate suddenly increases, the analysis can focus on the conversation immediately before that. Also, if the electrodermal activity is abnormally high, the conversation at that time can be analyzed in detail. This makes it possible to utilize the user's biometric information to more accurately detect moral harassment.

[0089] The moral harassment detection system can further include a schedule acquisition unit that acquires the user's schedule information. The schedule acquisition unit works in conjunction with the user's calendar app or schedule management tool to acquire the user's schedule. The analysis unit can prioritize analysis of conversations that occur before and after specific important meetings or events based on the acquired schedule information. For example, it can perform a detailed analysis of conversations that occur immediately before an important meeting to detect signs of moral harassment early. It can also focus on analysis of conversations that occur during times when the user is likely to feel stressed (for example, Monday mornings or Friday evenings). This makes it possible to utilize the user's schedule information to improve the accuracy of moral harassment detection.

[0090] The moral harassment detection system can further include a voice tone analysis unit that analyzes the user's voice tone. The voice tone analysis unit analyzes the tone, pitch, speed, etc. of the user's voice and provides this data to the analysis unit. The analysis unit estimates the user's emotions based on changes in voice tone, and can prioritize analysis of conversations where the user is emotional. For example, if the user's voice suddenly gets higher in pitch or their speaking speed increases, the analysis unit can analyze that conversation in detail. Also, if the user's voice tone gets lower and their speaking speed decreases, the analysis unit can also focus on analyzing that conversation. This makes it possible to utilize voice tone to detect moral harassment with higher accuracy.

[0091] The moral harassment detection system can further include a location information acquisition unit that acquires the user's location information. The location information acquisition unit acquires location information from the user's smartphone or GPS device and provides it to the analysis unit. When the user is in a specific location, the analysis unit can prioritize analysis of conversations at that location. For example, when the user is at work, the analysis unit can focus on analyzing conversations at work. Also, when the user is at home, the analysis unit can analyze conversations at home in detail. Furthermore, when the user is in a public place, the analysis unit can analyze conversations at that place while taking privacy into consideration. This makes it possible to utilize location information to improve the accuracy of moral harassment detection.

[0092] The moral harassment detection system can further include a social media analysis unit that analyzes the user's social media activity. The social media analysis unit analyzes the user's social media posts and the activities of their friends and provides this data to the analysis unit. The analysis unit estimates the user's emotions based on their social media activity, and if the user is emotionally charged, it can prioritize analyzing that conversation. For example, if a user posts something negative on social media, it can analyze the conversation immediately after in detail. Also, if a friend's activity is affecting the user, it can focus on analyzing the conversation at that time. This makes it possible to utilize social media activity to more accurately detect moral harassment.

[0093] The moral harassment detection system can further include a history analysis unit that analyzes the user's past moral harassment detection history. The history analysis unit analyzes previously detected cases of moral harassment and provides this data to the analysis unit. The analysis unit can prioritize analysis of conversations with similar patterns based on the past moral harassment detection history. For example, if a specific phrase was detected as moral harassment in the past, the analysis unit can analyze in detail conversations in which that phrase was used again. Furthermore, if moral harassment occurred in a specific time period or situation in the past, the analysis can also focus on conversations in that time period and situation. This makes it possible to prevent the recurrence of moral harassment by utilizing the past moral harassment detection history.

[0094] The moral harassment detection system may further include a health data acquisition unit that acquires the user's health data. The health data acquisition unit acquires health data from the user's fitness tracker or smartwatch and provides this data to the analysis unit. The analysis unit estimates the user's physical condition based on the health data, and if the user is feeling unwell, it can prioritize analyzing the conversations that occurred. For example, if it detects that the user is not getting enough sleep, it can analyze the conversations that occurred that day in detail. Also, if it detects that the user is not exercising enough, it can focus on analyzing the conversations that occurred at that time. This makes it possible to utilize health data to improve the accuracy of moral harassment detection.

[0095] The moral harassment detection system can further include a message analysis unit that analyzes the user's emails and messages. The message analysis unit analyzes the content of the user's emails and messaging apps and provides this data to the analysis unit. The analysis unit estimates the user's emotions based on the content of the emails and messages, and can prioritize analysis of conversations where the user is emotional. For example, if a user receives an email with negative content, the system can analyze in detail the conversation that follows. Also, if the user sends a message that makes the user feel stressed, the system can focus on analyzing the conversation at that time. This makes it possible to utilize the content of emails and messages to more accurately detect moral harassment.

[0096] The moral harassment detection system can further include a music analysis unit that analyzes the user's music playback history. The music analysis unit analyzes the genre and lyrics of the music the user is listening to and provides this data to the analysis unit. The analysis unit can estimate the user's emotions based on the music playback history, and prioritize analysis of conversations that involve emotional excitement. For example, if the user is listening to a sad song, the system can analyze in detail the conversation that follows. Also, if the user is listening to an intense song, the system can focus on analyzing the conversation at that time. This makes it possible to utilize music playback history to more accurately detect moral harassment.

[0097] The moral harassment detection system can further include a purchase history analysis unit that analyzes the user's purchase history. The purchase history analysis unit analyzes the user's online shopping and in-store purchase history and provides this data to the analysis unit. The analysis unit can estimate the user's emotions based on the purchase history, and if the user is emotionally charged, prioritize analyzing the conversation that occurred during that time. For example, if a user makes an impulse purchase to relieve stress, the analysis unit can analyze the conversation immediately after in detail. Also, if a user frequently purchases a particular product, the analysis unit can focus on analyzing the conversation at that time. This makes it possible to utilize purchase history to more accurately detect moral harassment.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The collection unit monitors conversations in real time and collects voice data. For example, it can constantly monitor conversations at work or at home and collect voice data. The collection unit can also use generative AI to convert the voice data into a format that is easier to analyze. For example, it can convert the voice data into text data. Step 2: The analysis unit analyzes the audio data collected by the collection unit and detects statements that could be considered moral harassment. The analysis unit uses generative AI to compare countless past cases of moral harassment and detect statements that could be considered moral harassment. For example, it can detect offensive words such as "You're useless" and "How many times do I have to tell you?" Step 3: The alert unit issues an alert to the user when the analysis unit detects a problem. The alert unit can, for example, display a warning message on the screen of a smartphone or PC, or alert the user by voice. Furthermore, the alert unit can estimate the user's emotions and adjust the way the alert is displayed based on the estimated emotions. For example, if the user is feeling stressed, a simple, highly visible alert can be displayed.

[0100] 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.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] 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.

[0103] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

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

[0105] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0106] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0107] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0108] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0109] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0110] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0111] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0112] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0113] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0114] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. 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.

[0115] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0116] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0118] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0119] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0134] 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.

[0135] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the 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.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 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.

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

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] [Explanation of symbols]

[0172] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that monitors conversations in real time; an analysis unit that analyzes the voice data collected by the collection unit and detects verbal abuse; an alert unit that issues an alert to a user when the analysis unit detects the error. A system characterized by:

2. The collecting unit Regularly monitor conversations at work and at home and collect audio data 2. The system of claim 1.

3. The analysis unit Analyze voice data using generative AI and compare past cases of moral harassment with numerous other cases to detect moral harassment phrases.

2. The system of claim 1.

4. The alert unit A warning message is displayed on the smartphone or PC screen and a voice prompt is given to warn the user.

2. The system of claim 1.

5. The collecting unit Analyze user emotions and adjust the timing of conversation collection based on the analyzed user emotions.

2. The system of claim 1.

6. The collecting unit Analyze the user's past conversation history and select the appropriate collection method 2. The system of claim 1.

7. The collecting unit When collecting conversations, filter them based on the user's current environment or situation 2. The system of claim 1.

8. The collecting unit When collecting conversations, select the appropriate collection method depending on the user's input method.

2. The system of claim 1.

Images