System

Abstract

An object of the system according to the embodiment is to detect a sign of a moral harassment from the content of a conversation or a message in real time and to immediately cope with the disaster.SOLUTION: A system includes an analysis unit, a detection unit, and a warning unit. The analysis unit analyzes the content of the conversation or the message in real time using the generated AI. The detection unit detects a sign of moral harassment from the conversation or the message analyzed by the analysis unit. The warning unit issues a warning based on the sign of moral harassment detected by the detection unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology had the problem of making it difficult to detect signs of moral harassment in real time from the content of conversations and messages and respond immediately.

[0005] The system according to the embodiment aims to detect signs of moral harassment in real time from the content of conversations and messages and respond immediately. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a detection unit, and a warning unit. The analysis unit analyzes the content of conversations or messages in real time using a generation AI. The detection unit detects signs of moral harassment from the conversations or messages analyzed by the analysis unit. The warning unit issues a warning based on the signs of moral harassment detected by the detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect signs of moral harassment in real time from the content of conversations and messages and respond immediately. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The moral harassment detection system according to an embodiment of the present invention is a system in which a generation AI analyzes the content of conversations and messages in real time, detects signs of moral harassment, and issues a warning. As a result, the moral harassment detection system can detect signs of moral harassment early and issue a warning immediately, thereby quickly stopping moral harassment.

[0029] A moral harassment detection system according to an embodiment includes an analysis unit, a detection unit, and a warning unit. The analysis unit uses a generation AI to analyze the content of conversations and messages in real time. For example, the generation AI analyzes the content of conversations and messages using a text generation AI (e.g., GPT-3 or BERT). The generation AI is fine-tuned to detect specific keywords and phrases. For example, it detects offensive language such as "You're useless" or "You're no good anyway," as well as repeatedly used negative expressions. The detection unit detects signs of moral harassment from the conversations and messages analyzed by the analysis unit. For example, it detects specific keywords and phrases containing signs of moral harassment based on the data analyzed by the generation AI. The detection unit can also use natural language processing technology to detect signs of moral harassment. For example, the generation AI analyzes the degree of word correspondence and sentence structure similarity between the summary and the model answer and calculates a similarity score. The warning unit issues a warning based on the signs of moral harassment detected by the detection unit. For example, the warning unit issues a warning directly to a user who is committing moral harassment. For example, a message such as "That statement may constitute moral harassment. Please reconsider your statement" is displayed. A warning is also issued to the victim, and support is provided as needed. For example, a message such as "The current conversation shows signs of moral harassment. If you need support, please contact us here" is displayed. In this way, the moral harassment detection system according to the embodiment can detect signs of moral harassment in real time and immediately issue a warning, thereby quickly stopping moral harassment.

[0030] The analysis unit understands the context of the conversation and can detect signs of moral harassment based on context, rather than simply detecting keywords. For example, the generation AI analyzes the context of the conversation, understanding not only the meaning of words but also the context surrounding them. For example, it determines whether the phrase "You're useless" is used jokingly or with serious, aggressive intent. The analysis unit also analyzes the flow of the conversation and, if a specific keyword is used repeatedly, takes that context into account to detect signs of moral harassment. For example, if the phrase "it's impossible" is used repeatedly, it analyzes the intention behind it. To understand the context of the conversation, the generation AI also references past conversation history and learns patterns of interactions between specific users. For example, if a specific user consistently uses aggressive language, it can detect signs of moral harassment based on that pattern. This enables more accurate detection of moral harassment by detecting signs of moral harassment based on context.

[0031] The analysis unit analyzes the tone of the conversation and the intonation of the voice, and can detect signs of moral harassment not only from text but also from voice data. For example, the analysis unit uses a generation AI to analyze voice data and detect signs of moral harassment based on the tone and intonation of the conversation. For example, if tones of anger or irritation are included, a warning is issued based on the voice data. The analysis unit also understands the intention behind the emphasis when a specific phrase is emphasized through analysis of the voice data. For example, if the phrase "You're really useless" is emphasized, it analyzes that intention. The analysis unit also analyzes the intonation of the conversation and detects signs of moral harassment when a specific emotion is strongly expressed. For example, if strong emotions of anger or irritation are sensed from the voice data, a warning is issued based on that data. This allows for more comprehensive detection of moral harassment by detecting signs of moral harassment from voice data as well.

[0032] The analysis unit can expand the scope of its analysis of conversations and messages to include not only text messages but also video conferences and telephone conversations. For example, the analysis unit uses a generative AI to analyze video conference video data and detect signs of moral harassment by considering not only the content of the conversation but also facial expressions and gestures. For example, if aggressive facial expressions or gestures are observed, a warning is issued based on that data. The analysis unit also analyzes audio data from telephone conversations and detects signs of moral harassment based on the tone and intonation of the conversation. For example, if a tone of anger or irritation is included, a warning is issued based on that audio data. The analysis unit can also analyze video conference and telephone conversation data in real time to build a system that detects signs of moral harassment in the same way as text messages. For example, the content of the conversation can be integrated with video and audio data for analysis. This allows for a wider range of moral harassment detection to be possible by expanding the analysis to include video conferences and telephone conversations.

[0033] The analysis unit can realize global moral harassment detection using a multilingual generation AI to accommodate different languages ​​and cultural spheres. For example, the analysis unit makes the generation AI multilingual and analyzes conversations and messages in different languages. For example, it can support multiple languages ​​such as English, French, and Chinese. The analysis unit also learns definitions and expressions of moral harassment in different cultural spheres and performs moral harassment detection taking cultural background into account. For example, it detects expressions that are considered offensive in a particular cultural sphere. The analysis unit also uses a multilingual generation AI to build a global moral harassment detection system. For example, it analyzes conversations between users from different languages ​​and cultural spheres and detects signs of moral harassment. This multilingual support makes global moral harassment detection possible.

[0034] The warning unit personalizes the warning message based on the user's past behavior and speech history, enabling more effective warnings to be issued. For example, the warning unit uses a generation AI to analyze the user's past behavior and speech history and personalize the warning message based on that data. For example, a stronger warning may be issued for a user who has repeatedly made similar statements in the past. The warning unit also adjusts the content of the warning message based on the user's speech history. For example, if a specific phrase or word is used repeatedly, a specific warning for that phrase may be issued. The warning unit also customizes the tone and content of the warning message based on the user's past behavior data. For example, more specific suggestions for improvement may be made for users who have received warnings in the past. This allows for more effective warnings to be issued by personalizing the warning message based on the user's past behavior and speech history.

[0035] The warning unit monitors the user's reaction after the warning is issued, evaluates the effectiveness of the warning in real time, and can adjust the content of the warning as necessary. For example, the generation AI in the warning unit monitors the user's reaction after the warning is issued in real time and evaluates the effectiveness of the warning based on that data. For example, it analyzes whether the user accepted the warning. The warning unit also builds a system that adjusts the content of the warning based on user reaction data. For example, it issues a stronger warning to users who ignore the warning. The warning unit also monitors the user's behavior after the warning is issued and evaluates the effectiveness of the warning. For example, it analyzes whether the user's comments have improved after receiving the warning. In this way, the user's reaction after the warning is issued can be monitored and the effectiveness of the warning can be evaluated in real time, allowing the content of the warning to be adjusted as necessary.

[0036] The warning unit can provide a wider variety of communication methods by transmitting warning messages not only as text but also as audio or video messages. For example, the warning unit may build a system in which a generation AI transmits warning messages not only as text but also as audio messages. For example, the warning message may be transmitted by audio using speech synthesis technology. The warning unit may also develop a system that transmits warning messages using video messages. For example, the warning content may be explained in a video to make it easier to understand visually. The warning unit may also provide a choice between transmitting warning messages in text, audio, or video format, allowing users to receive the warning in the format most acceptable to them. In this way, transmitting warning messages through a wider variety of communication methods improves the ease with which users accept warnings.

[0037] When issuing a warning, the warning unit can simultaneously provide information on specific examples of moral harassment and how to deal with it, thereby deepening the user's understanding. For example, the warning unit can build a system in which a generation AI provides specific examples of moral harassment along with a warning message. For example, it can present specific examples based on past cases. The warning unit can also add information on how to deal with the warning message, allowing the user to understand specific actions to prevent moral harassment. For example, it can present ways to improve communication skills. The warning unit can also provide information on the definition and impact of moral harassment along with the warning message, deepening the user's understanding. For example, it can explain how moral harassment affects victims. In this way, by providing specific examples and how to deal with the situation when issuing a warning, the user's understanding can be deepened and moral harassment can be prevented from recurring.

[0038] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0039] The analysis unit can learn a user's behavioral patterns and predict signs of moral harassment. For example, if a particular user frequently uses aggressive language, the analysis unit can learn that pattern and predict future occurrences of moral harassment. The analysis unit can also issue a warning before signs of moral harassment appear based on the user's behavioral history. For example, it can analyze past data and identify patterns in which moral harassment is likely to occur under certain circumstances. The analysis unit can also send preventative messages based on the user's behavioral patterns before signs of moral harassment appear. For example, it can display a message such as, "Your recent comments seem to have become more aggressive. Please try to respond calmly." This allows the system to learn a user's behavioral patterns and predict signs of moral harassment, allowing early action to be taken.

[0040] The analysis unit can analyze a user's social network and identify relationships that pose a high risk of moral harassment. For example, it can analyze the frequency and content of messages between users and determine whether a particular relationship poses a high risk of moral harassment. The analysis unit can also send preventative messages to relationships that pose a high risk of moral harassment based on the user's social network. For example, it can display a message such as, "You need to be careful about this relationship. Please try to respond calmly." The analysis unit can also analyze a user's social network and provide support to relationships that pose a high risk of moral harassment. For example, it can display a message such as, "This relationship needs support. Please contact us." In this way, by analyzing a user's social network and identifying relationships that pose a high risk of moral harassment, it is possible to take measures early.

[0041] The analysis unit can send preventive messages before signs of moral harassment appear based on the user's behavioral history. For example, it can analyze past data and identify patterns in which moral harassment is likely to occur under certain circumstances. The analysis unit can also issue warnings before signs of moral harassment appear based on the user's behavioral history. For example, it can issue a stronger warning to a user who has repeatedly made similar statements in the past. The analysis unit can also send preventive messages before signs of moral harassment appear based on the user's behavioral history. For example, it can display a message such as, "Your recent comments seem to have become more aggressive. Please try to respond calmly." This allows for early countermeasures to be taken by sending preventive messages before signs of moral harassment appear based on the user's behavioral history.

[0042] The warning unit can personalize the warning message based on the user's past behavior and speech history, thereby issuing a more effective warning. For example, a stronger warning can be issued to a user who has repeatedly made similar statements in the past. The warning unit also adjusts the content of the warning message based on the user's speech history. For example, if a specific phrase or word is used repeatedly, a specific warning can be issued for that phrase. The warning unit also customizes the tone and content of the warning message based on the user's past behavior data. For example, more specific suggestions for improvement can be made to a user who has received a warning in the past. In this way, more effective warnings can be issued by personalizing the warning message based on the user's past behavior and speech history.

[0043] The warning unit monitors the user's reaction after issuing a warning, evaluates the effectiveness of the warning in real time, and can adjust the content of the warning as necessary. For example, the generation AI monitors the user's reaction after issuing a warning in real time and evaluates the effectiveness of the warning based on that data. For example, it analyzes whether the user accepted the warning. The warning unit also builds a system that adjusts the content of the warning based on user reaction data. For example, it issues a stronger warning to users who ignore the warning. The warning unit also monitors the user's behavior after issuing a warning and evaluates the effectiveness of the warning. For example, it analyzes whether the user's comments improved after receiving the warning. In this way, the system can monitor the user's reaction after issuing a warning and evaluate the effectiveness of the warning in real time, thereby adjusting the content of the warning as necessary.

[0044] The processing flow of the first embodiment will be briefly explained below.

[0045] Step 1: The analysis unit uses the generation AI to analyze the content of conversations and messages in real time. For example, the generation AI uses text generation AI (e.g., GPT-3 or BERT) to analyze the content of conversations and messages. The generation AI is also fine-tuned to detect specific keywords and phrases. For example, it detects offensive language such as "You're useless" or "You'll never get anywhere" and repeated negative expressions. Step 2: The detection unit detects signs of moral harassment from the conversations and messages analyzed by the analysis unit. For example, it detects specific keywords and phrases that contain signs of moral harassment based on the data analyzed by the generation AI. The detection unit can also use natural language processing technology to detect signs of moral harassment. For example, the generation AI analyzes the degree of word agreement and sentence structure similarity between the summary and the model answer and calculates a similarity score. Step 3: The warning unit issues a warning based on the signs of moral harassment detected by the detection unit. For example, the warning unit may issue a warning directly to a user who is committing moral harassment. For example, a message such as "That comment may constitute moral harassment. Please reconsider your comment" is displayed. A warning is also sent to the victim, and support is provided if necessary. For example, a message such as "The current conversation shows signs of moral harassment. If you need support, please contact us" is displayed.

[0046] (Example 2) The moral harassment detection system according to an embodiment of the present invention is a system in which a generation AI analyzes the content of conversations and messages in real time, detects signs of moral harassment, and issues a warning. As a result, the moral harassment detection system can detect signs of moral harassment early and issue a warning immediately, thereby quickly stopping moral harassment.

[0047] A moral harassment detection system according to an embodiment includes an analysis unit, a detection unit, and a warning unit. The analysis unit uses a generation AI to analyze the content of conversations and messages in real time. For example, the generation AI analyzes the content of conversations and messages using a text generation AI (e.g., GPT-3 or BERT). The generation AI is fine-tuned to detect specific keywords and phrases. For example, it detects offensive language such as "You're useless" or "You're no good anyway," as well as repeatedly used negative expressions. The detection unit detects signs of moral harassment from the conversations and messages analyzed by the analysis unit. For example, it detects specific keywords and phrases containing signs of moral harassment based on the data analyzed by the generation AI. The detection unit can also use natural language processing technology to detect signs of moral harassment. For example, the generation AI analyzes the degree of word correspondence and sentence structure similarity between the summary and the model answer and calculates a similarity score. The warning unit issues a warning based on the signs of moral harassment detected by the detection unit. For example, the warning unit issues a warning directly to a user who is committing moral harassment. For example, a message such as "That statement may constitute moral harassment. Please reconsider your statement" is displayed. A warning is also issued to the victim, and support is provided as needed. For example, a message such as "The current conversation shows signs of moral harassment. If you need support, please contact us here" is displayed. In this way, the moral harassment detection system according to the embodiment can detect signs of moral harassment in real time and immediately issue a warning, thereby quickly stopping moral harassment.

[0048] The analysis unit understands the context of the conversation and can detect signs of moral harassment based on context, rather than simply detecting keywords. For example, the generation AI analyzes the context of the conversation, understanding not only the meaning of words but also the context surrounding them. For example, it determines whether the phrase "You're useless" is used jokingly or with serious, aggressive intent. The analysis unit also analyzes the flow of the conversation and, if a specific keyword is used repeatedly, takes that context into account to detect signs of moral harassment. For example, if the phrase "it's impossible" is used repeatedly, it analyzes the intention behind it. To understand the context of the conversation, the generation AI also references past conversation history and learns patterns of interactions between specific users. For example, if a specific user consistently uses aggressive language, it can detect signs of moral harassment based on that pattern. This enables more accurate detection of moral harassment by detecting signs of moral harassment based on context.

[0049] The analysis unit analyzes the tone of the conversation and the intonation of the voice, and can detect signs of moral harassment not only from text but also from voice data. For example, the analysis unit uses a generation AI to analyze voice data and detect signs of moral harassment based on the tone and intonation of the conversation. For example, if tones of anger or irritation are included, a warning is issued based on the voice data. The analysis unit also understands the intention behind the emphasis when a specific phrase is emphasized through analysis of the voice data. For example, if the phrase "You're really useless" is emphasized, it analyzes that intention. The analysis unit also analyzes the intonation of the conversation and detects signs of moral harassment when a specific emotion is strongly expressed. For example, if strong emotions of anger or irritation are sensed from the voice data, a warning is issued based on that data. This allows for more comprehensive detection of moral harassment by detecting signs of moral harassment from voice data as well.

[0050] The analysis unit uses the emotion estimation function to analyze changes in a user's emotions during a conversation in real time and can detect sudden changes in emotions as signs of moral harassment. For example, the analysis unit uses the generation AI's emotion estimation function to analyze changes in a user's emotions during a conversation in real time. For example, if a user's emotions suddenly become stronger, such as anger or sadness, the analysis unit detects this change as a sign of moral harassment. The analysis unit also analyzes the cause of sudden changes in emotions during a conversation. For example, if a specific phrase or word causes a change in emotion, the analysis unit identifies the cause. The analysis unit also uses the emotion estimation function to learn patterns of sudden changes in a user's emotions during a conversation. For example, if a specific user consistently causes changes in emotion, the analysis unit detects signs of moral harassment based on this pattern. This allows for earlier detection of sudden changes in emotions as signs of moral harassment, enabling moral harassment to be discovered.

[0051] The analysis unit can expand the scope of its analysis of conversations and messages to include not only text messages but also video conferences and telephone conversations. For example, the analysis unit uses a generative AI to analyze video conference video data and detect signs of moral harassment by considering not only the content of the conversation but also facial expressions and gestures. For example, if aggressive facial expressions or gestures are observed, a warning is issued based on that data. The analysis unit also analyzes audio data from telephone conversations and detects signs of moral harassment based on the tone and intonation of the conversation. For example, if a tone of anger or irritation is included, a warning is issued based on that audio data. The analysis unit can also analyze video conference and telephone conversation data in real time to build a system that detects signs of moral harassment in the same way as text messages. For example, the content of the conversation can be integrated with video and audio data for analysis. This allows for a wider range of moral harassment detection to be possible by expanding the analysis to include video conferences and telephone conversations.

[0052] The analysis unit can realize global moral harassment detection using a multilingual generation AI to accommodate different languages ​​and cultural spheres. For example, the analysis unit makes the generation AI multilingual and analyzes conversations and messages in different languages. For example, it can support multiple languages ​​such as English, French, and Chinese. The analysis unit also learns definitions and expressions of moral harassment in different cultural spheres and performs moral harassment detection taking cultural background into account. For example, it detects expressions that are considered offensive in a particular cultural sphere. The analysis unit also uses a multilingual generation AI to build a global moral harassment detection system. For example, it analyzes conversations between users from different languages ​​and cultural spheres and detects signs of moral harassment. This multilingual support makes global moral harassment detection possible.

[0053] The analysis unit uses the emotion estimation function to estimate the emotion of the user when inputting a conversation in real time and make suggestions to elicit positive emotions. The analysis unit, for example, uses the emotion estimation function to estimate the emotion of the user when inputting a conversation in real time. For example, if the user is feeling anger or irritation, the analysis unit makes suggestions to alleviate those emotions. The analysis unit also provides an interface for eliciting positive emotions based on the emotion estimation data when the user inputs a conversation. For example, the analysis unit presents encouraging messages and success stories. The analysis unit also uses the emotion estimation function to provide advice for eliciting positive emotions when the user inputs a conversation. For example, the analysis unit displays appropriate words of encouragement or praise according to the input content. In this way, by estimating the user's emotion in real time and making suggestions to elicit positive emotions, it is possible to prevent the occurrence of moral harassment.

[0054] The warning unit personalizes the warning message based on the user's past behavior and speech history, enabling more effective warnings to be issued. For example, the warning unit uses a generation AI to analyze the user's past behavior and speech history and personalize the warning message based on that data. For example, a stronger warning may be issued for a user who has repeatedly made similar statements in the past. The warning unit also adjusts the content of the warning message based on the user's speech history. For example, if a specific phrase or word is used repeatedly, a specific warning for that phrase may be issued. The warning unit also customizes the tone and content of the warning message based on the user's past behavior data. For example, more specific suggestions for improvement may be made for users who have received warnings in the past. This allows for more effective warnings to be issued by personalizing the warning message based on the user's past behavior and speech history.

[0055] The warning unit monitors the user's reaction after the warning is issued, evaluates the effectiveness of the warning in real time, and can adjust the content of the warning as necessary. For example, the generation AI in the warning unit monitors the user's reaction after the warning is issued in real time and evaluates the effectiveness of the warning based on that data. For example, it analyzes whether the user accepted the warning. The warning unit also builds a system that adjusts the content of the warning based on user reaction data. For example, it issues a stronger warning to users who ignore the warning. The warning unit also monitors the user's behavior after the warning is issued and evaluates the effectiveness of the warning. For example, it analyzes whether the user's comments have improved after receiving the warning. In this way, the user's reaction after the warning is issued can be monitored and the effectiveness of the warning can be evaluated in real time, allowing the content of the warning to be adjusted as necessary.

[0056] The warning unit can use the emotion estimation function to analyze the emotions of the user who received the warning and automatically generate a follow-up message to alleviate any negative reactions. The warning unit, for example, uses the emotion estimation function to analyze the emotions of the user who received the warning in real time. For example, if the user feels anger or irritation after receiving the warning, the warning unit automatically generates a follow-up message to alleviate those emotions. The warning unit also provides a specific follow-up message to alleviate any negative reactions based on the user's emotion data. For example, it provides an encouraging message or a suggestion for improvement after the warning. The warning unit also uses the emotion estimation function to monitor changes in the emotions of the user who received the warning and adjusts the follow-up message based on the data. For example, it provides a message that improves the user's emotions after the warning. In this way, by analyzing the emotions of the user who received the warning and automatically generating a follow-up message to alleviate any negative reactions, the psychological burden on the user can be reduced.

[0057] The warning unit can provide a wider variety of communication methods by transmitting warning messages not only as text but also as audio or video messages. For example, the warning unit may build a system in which a generation AI transmits warning messages not only as text but also as audio messages. For example, the warning message may be transmitted by audio using speech synthesis technology. The warning unit may also develop a system that transmits warning messages using video messages. For example, the warning content may be explained in a video to make it easier to understand visually. The warning unit may also provide a choice between transmitting warning messages in text, audio, or video format, allowing users to receive the warning in the format most acceptable to them. In this way, transmitting warning messages through a wider variety of communication methods improves the ease with which users accept warnings.

[0058] When issuing a warning, the warning unit can simultaneously provide information on specific examples of moral harassment and how to deal with it, thereby deepening the user's understanding. For example, the warning unit can build a system in which a generation AI provides specific examples of moral harassment along with a warning message. For example, it can present specific examples based on past cases. The warning unit can also add information on how to deal with the warning message, allowing the user to understand specific actions to prevent moral harassment. For example, it can present ways to improve communication skills. The warning unit can also provide information on the definition and impact of moral harassment along with the warning message, deepening the user's understanding. For example, it can explain how moral harassment affects victims. In this way, by providing specific examples and how to deal with the situation when issuing a warning, the user's understanding can be deepened and moral harassment can be prevented from recurring.

[0059] The warning unit can use the emotion estimation function to monitor the emotions of a user who has received a warning in real time and continuously provide optimal follow-up. The warning unit, for example, uses the emotion estimation function to develop a system that monitors the emotions of a user who has received a warning in real time. For example, the warning unit analyzes the user's facial expressions and voice and calculates an emotion score. The warning unit also builds a system that continuously provides follow-up messages after a warning based on the user's emotional response data. For example, the warning unit periodically sends messages that improve the user's emotions after a warning. The warning unit also develops a system that collects emotion estimation data in real time and dynamically adjusts follow-up messages according to changes in the user's emotions. For example, if the user's emotions are negative, the warning unit sends an encouraging message. In this way, the emotions of a user who has received a warning can be monitored in real time and optimal follow-up can be continuously provided, thereby reducing the user's psychological burden and preventing recurrence of moral harassment.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The analysis unit can learn a user's behavioral patterns and predict signs of moral harassment. For example, if a particular user frequently uses aggressive language, the analysis unit can learn that pattern and predict future occurrences of moral harassment. The analysis unit can also issue a warning before signs of moral harassment appear based on the user's behavioral history. For example, it can analyze past data and identify patterns in which moral harassment is likely to occur under certain circumstances. The analysis unit can also send preventative messages based on the user's behavioral patterns before signs of moral harassment appear. For example, it can display a message such as, "Your recent comments seem to have become more aggressive. Please try to respond calmly." This allows the system to learn a user's behavioral patterns and predict signs of moral harassment, allowing early action to be taken.

[0062] The analysis unit can monitor the user's stress level and issue a warning when stress increases. For example, it can analyze the user's input speed and typing strength to estimate the stress level. The analysis unit can also analyze the user's biometric data (heart rate, electrodermal activity, etc.) to monitor the stress level in real time. For example, if the heart rate increases suddenly, it can issue a warning based on that data. The analysis unit can also make suggestions for relaxation when the user's stress level increases. For example, it can display a message such as, "Take a deep breath and relax." In this way, by monitoring the user's stress level and issuing a warning when stress increases, it is possible to prevent moral harassment from occurring.

[0063] The analysis unit can analyze a user's social network and identify relationships that pose a high risk of moral harassment. For example, it can analyze the frequency and content of messages between users and determine whether a particular relationship poses a high risk of moral harassment. The analysis unit can also send preventative messages to relationships that pose a high risk of moral harassment based on the user's social network. For example, it can display a message such as, "You need to be careful about this relationship. Please try to respond calmly." The analysis unit can also analyze a user's social network and provide support to relationships that pose a high risk of moral harassment. For example, it can display a message such as, "This relationship needs support. Please contact us." In this way, by analyzing a user's social network and identifying relationships that pose a high risk of moral harassment, it is possible to take measures early.

[0064] The analysis unit uses the user's emotion estimation function to analyze changes in the user's emotions during a conversation in real time and detect sudden changes in emotions as signs of moral harassment. For example, if the user's emotions suddenly become stronger, such as anger or sadness, the analysis unit detects this change as a sign of moral harassment. The analysis unit also analyzes the cause of sudden changes in emotions during a conversation. For example, if a specific phrase or word causes a change in emotion, the analysis unit identifies the cause. The analysis unit also uses the emotion estimation function to learn patterns of sudden changes in the user's emotions during a conversation. For example, if a specific user consistently causes changes in emotion, the analysis unit detects signs of moral harassment based on that pattern. This allows moral harassment to be discovered earlier by detecting sudden changes in emotions as signs of moral harassment.

[0065] The analysis unit can monitor the user's health condition and issue a warning if the health condition deteriorates. For example, it can analyze the user's sleep data and exercise data to estimate the user's health condition. The analysis unit can also make suggestions for relaxation when the user's health condition deteriorates. For example, it can display a message such as, "Take a break and relax." The analysis unit can also monitor the user's health condition and provide support when the health condition deteriorates. For example, it can display a message such as, "Your health condition is deteriorating. Please contact us." In this way, by monitoring the user's health condition and issuing a warning when the health condition deteriorates, it is possible to prevent moral harassment from occurring.

[0066] The analysis unit can send preventive messages before signs of moral harassment appear based on the user's behavioral history. For example, it can analyze past data and identify patterns in which moral harassment is likely to occur under certain circumstances. The analysis unit can also issue warnings before signs of moral harassment appear based on the user's behavioral history. For example, it can issue a stronger warning to a user who has repeatedly made similar statements in the past. The analysis unit can also send preventive messages before signs of moral harassment appear based on the user's behavioral history. For example, it can display a message such as, "Your recent comments seem to have become more aggressive. Please try to respond calmly." This allows for early countermeasures to be taken by sending preventive messages before signs of moral harassment appear based on the user's behavioral history.

[0067] The analysis unit uses the emotion estimation function to estimate the user's emotions in real time when they input conversations and make suggestions to bring out positive emotions. For example, if the user is feeling angry or irritated, the analysis unit makes suggestions to alleviate those emotions. The analysis unit also provides an interface for bringing out positive emotions based on the emotion estimation data when the user inputs conversations. For example, it presents encouraging messages and success stories. The analysis unit also uses the emotion estimation function to provide advice for bringing out positive emotions when the user inputs conversations. For example, it displays appropriate words of encouragement or praise based on the input content. In this way, by estimating the user's emotions in real time and making suggestions to bring out positive emotions, it is possible to prevent the occurrence of moral harassment.

[0068] The warning unit can personalize the warning message based on the user's past behavior and speech history, thereby issuing a more effective warning. For example, a stronger warning can be issued to a user who has repeatedly made similar statements in the past. The warning unit also adjusts the content of the warning message based on the user's speech history. For example, if a specific phrase or word is used repeatedly, a specific warning can be issued for that phrase. The warning unit also customizes the tone and content of the warning message based on the user's past behavior data. For example, more specific suggestions for improvement can be made to a user who has received a warning in the past. In this way, more effective warnings can be issued by personalizing the warning message based on the user's past behavior and speech history.

[0069] The warning unit monitors the user's reaction after issuing a warning, evaluates the effectiveness of the warning in real time, and can adjust the content of the warning as necessary. For example, the generation AI monitors the user's reaction after issuing a warning in real time and evaluates the effectiveness of the warning based on that data. For example, it analyzes whether the user accepted the warning. The warning unit also builds a system that adjusts the content of the warning based on user reaction data. For example, it issues a stronger warning to users who ignore the warning. The warning unit also monitors the user's behavior after issuing a warning and evaluates the effectiveness of the warning. For example, it analyzes whether the user's comments improved after receiving the warning. In this way, the system can monitor the user's reaction after issuing a warning and evaluate the effectiveness of the warning in real time, thereby adjusting the content of the warning as necessary.

[0070] The warning unit can use the emotion estimation function to analyze the emotions of the user who received the warning and automatically generate a follow-up message to alleviate any negative reactions. For example, the emotion estimation function is used to analyze the emotions of the user who received the warning in real time. For example, if the user feels anger or irritation after receiving the warning, a follow-up message to alleviate those emotions is automatically generated. The warning unit also provides a specific follow-up message to alleviate any negative reactions based on the user's emotion data. For example, an encouraging message or suggestions for improvement are provided after the warning. The warning unit also uses the emotion estimation function to monitor changes in the emotions of the user who received the warning and adjust the follow-up message based on the data. For example, a message is provided that improves the user's emotions after the warning. In this way, the psychological burden on the user can be reduced by analyzing the emotions of the user who received the warning and automatically generating a follow-up message to alleviate any negative reactions.

[0071] The processing flow of the second embodiment will be briefly explained below.

[0072] Step 1: The analysis unit uses the generation AI to analyze the content of conversations and messages in real time. For example, the generation AI uses text generation AI (e.g., GPT-3 or BERT) to analyze the content of conversations and messages. The generation AI is also fine-tuned to detect specific keywords and phrases. For example, it detects offensive language such as "You're useless" or "You'll never get anywhere" and repeated negative expressions. Step 2: The detection unit detects signs of moral harassment from the conversations and messages analyzed by the analysis unit. For example, it detects specific keywords and phrases that contain signs of moral harassment based on the data analyzed by the generation AI. The detection unit can also use natural language processing technology to detect signs of moral harassment. For example, the generation AI analyzes the degree of word agreement and sentence structure similarity between the summary and the model answer and calculates a similarity score. Step 3: The warning unit issues a warning based on the signs of moral harassment detected by the detection unit. For example, the warning unit may issue a warning directly to a user who is committing moral harassment. For example, a message such as "That comment may constitute moral harassment. Please reconsider your comment" is displayed. A warning is also sent to the victim, and support is provided if necessary. For example, a message such as "The current conversation shows signs of moral harassment. If you need support, please contact us" is displayed.

[0073] 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.

[0074] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0075] 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.

[0076] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] 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).

[0082] 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.

[0083] 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.

[0084] 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.

[0085] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0086] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0092] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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).

[0097] 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.

[0098] 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.

[0099] 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.

[0100] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0101] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0107] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0109] The 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.

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

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

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

[0113] 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.

[0114] 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.

[0115] 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.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0117] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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."

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0140] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An analysis unit that uses generative AI to analyze the content of conversations or messages in real time; a detection unit that detects signs of moral harassment from the conversation or the message analyzed by the analysis unit; a warning unit that issues a warning based on the signs of moral harassment detected by the detection unit. A system characterized by:

2. The analysis unit Analyze the tone and intonation of the conversation to detect signs of moral harassment not only from text but also from voice data.

2. The system of claim 1.

3. The analysis unit Expand conversation or message analysis beyond text messages to include video conferences and phone conversations 2. The system of claim 1.

4. The warning unit Personalize warning messages based on users' past behavior and speech history to deliver more effective warnings 2. The system of claim 1.

5. The analysis unit The system analyzes changes in the user's emotions in real time during the conversation and detects sudden changes in emotions as signs of moral harassment.

2. The system of claim 1.

Images