System

Abstract

An object of a system according to an embodiment is to eliminate the risk of leakage of private information and to provide environments in which generated AI can be safely utilized.SOLUTION: A system includes a masking unit, an alert unit, and an imitation unit. The masking unit masks the personal information. The alert unit alerts the presence or absence of personal information at the time of input to the prompt. The simulator simulates data.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] With conventional technology, there was a risk of personal information being leaked when using generative AI, and security was not sufficiently ensured.

[0005] The system according to the embodiment aims to eliminate the risk of personal information leakage and provide an environment in which generative AI can be used safely. [Means for solving the problem]

[0006] The system according to the embodiment includes a masking unit, an alert unit, and a simulation unit. The masking unit masks personal information. The alert unit alerts the user of the presence or absence of personal information when inputting to a prompt. The simulation unit simulates data. [Effects of the Invention]

[0007] The system according to the embodiment can eliminate the risk of personal information leakage and provide an environment in which generative AI can be used safely. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The security system according to the embodiment of the present invention is a system that eliminates security and personal information risks and provides an environment in which generative AI can be used with a high degree of freedom. This allows companies and local governments to safely use generative AI.

[0029] A security system according to an embodiment includes a masking unit, an alert unit, and a simulation unit. The masking unit masks personal information. For example, the masking unit masks personal information such as names, addresses, and phone numbers as "***" or "XXXX." The masking unit can understand the context and perform appropriate masking using natural language processing technology. For example, the generation AI analyzes input data and uses natural language processing technology to understand the context. The alert unit alerts whether personal information is present when a prompt is entered. For example, the alert unit displays an alert such as "This prompt contains personal information. Do you want to continue?" The alert unit can also detect personal information contained in the prompt with high accuracy using a machine learning model. For example, the generation AI uses a machine learning model to improve the accuracy of detecting personal information when analyzing the prompt. The simulation unit simulates data. For example, the simulation unit converts actual customer data into pseudo data, and the generation AI then uses the pseudo data to perform analysis. Furthermore, the simulation unit can develop an algorithm that completely removes personal information while preserving the statistical characteristics of the original data when the generation AI generates pseudo data. For example, personal information is deleted while maintaining the distribution and correlation of the original data. As a result, the security system according to the embodiment can eliminate security and personal information risks and provide an environment in which the generation AI can be used with a high degree of freedom. For example, companies and local governments can safely input data containing personal information into the generation AI for analysis and proposals. Furthermore, by checking the presence or absence of personal information when entering data into a prompt, the risk of accidentally entering personal information can be reduced. Furthermore, data simulation allows data to be safely analyzed even outside of secure environments.

[0030] The masking unit uses natural language processing technology to understand the context and appropriately mask personal information. For example, the masking unit uses natural language processing technology to analyze input data and understand the context. For example, it analyzes how names and addresses are used in the context and performs appropriate masking. It uses natural language processing technology to understand the meaning of the entire sentence and identify parts that contain personal information. For example, based on the context, the sentence "Tanaka-san's address is Shibuya-ku, Tokyo" can be masked as "***-san's address is ***-ku." Context analysis is performed to automatically detect and mask phrases that may contain personal information. For example, the sentence "My phone number is 090-1234-5678" can be masked as "My phone number is ***-****-****." This allows for understanding the context and performing appropriate masking, preventing the leakage of personal information.

[0031] The masking unit provides a reverse masking function, allowing data to be restored when necessary. The masking unit provides, for example, a reverse masking function for restoring masked data to its original state. For example, the masking unit makes it possible to access the original data through specific authentication. Using the reverse masking function, a system is built for restoring the original data when necessary. For example, data before masking stored in a database is restored. A security protocol is set up to restore the masked data, allowing only authenticated users to access the original data. For example, two-factor authentication is used to restore data. This allows the original data to be restored when necessary.

[0032] The masking unit can automatically detect and mask personal information contained in image or audio data. The masking unit uses, for example, image recognition technology to automatically detect and mask personal information contained in image data. For example, it blurs personal information such as faces and name tags. It uses audio analysis technology to automatically detect and mask personal information contained in audio data. For example, it silences parts containing names and addresses. It builds a system that analyzes image and audio data and identifies and masks parts containing personal information. For example, it hides specific phrases in audio data with beeps. This makes it possible to automatically mask personal information contained in image and audio data.

[0033] The masking unit uses the masked data to allow the generation AI to generate a new dataset, thereby ensuring data diversity. In the masking unit, for example, the generation AI generates a new dataset based on the masked data. For example, masked names and addresses are randomly generated to diversify the dataset. A system is constructed in which the generation AI generates a new dataset from the masked data, ensuring data diversity. For example, different patterns of masked data are generated. The generation AI generates diverse datasets based on the masked data, thereby improving data diversity. For example, masked data to be used in different contexts is generated. In this way, data diversity can be ensured using the masked data.

[0034] The alert unit can use a machine learning model to detect personal information included in prompts with high accuracy. The alert unit, for example, uses a machine learning model to build a system that detects personal information included in prompts with high accuracy. For example, it automatically identifies personal information such as name and address. When the generation AI analyzes the prompt, it uses a machine learning model to improve the accuracy of detecting personal information. For example, it learns from past data and identifies patterns of personal information. A system is developed that uses a machine learning model to detect personal information included in prompts with high accuracy and display an alert. For example, it highlights the parts that include personal information. This makes it possible to detect personal information included in prompts with high accuracy.

[0035] The alert unit can highlight specific parts of the personal information when an alert is displayed, allowing the user to easily correct it. The alert unit, for example, builds a system that highlights specific parts of the personal information included in a prompt when an alert is displayed, allowing the user to easily correct it. For example, the part containing the name or address is highlighted in color. The part containing the personal information is highlighted, allowing the user to easily correct that part. For example, clicking on the highlighted part switches to correction mode. When an alert is displayed, the specific part of the personal information is highlighted, and an interface is provided that allows the user to easily correct it. For example, correction suggestions are displayed in the highlighted part. This makes it possible to highlight specific parts of the personal information, allowing the user to easily correct it.

[0036] The alert unit can detect not only personal information but also confidential information and commercial secrets during prompt input and display an alert. For example, a system is constructed in which the alert unit detects not only personal information but also confidential information and commercial secrets during prompt input and displays an alert. For example, a warning is displayed if confidential corporate information is included. An algorithm is developed to detect confidential information and commercial secrets, and an alert is displayed during prompt input. For example, specific keywords and phrases are detected. A function is added to detect personal information, confidential information, and commercial secrets during prompt input and display an alert. For example, different alerts are displayed depending on the type of information detected. This makes it possible to detect not only personal information but also confidential information and commercial secrets and display an alert.

[0037] The alert unit can allow the user to select an option when an alert is displayed and provide an option to automatically mask personal information. For example, the alert unit builds a system that allows the user to select an option when an alert is displayed and provides an option to automatically mask personal information. For example, the options "mask" and "ignore" are displayed. The user can select an option when an alert is displayed and provide an option to automatically mask personal information. For example, masking is performed automatically when an option is clicked. An interface is developed that allows the user to select an option when an alert is displayed and provides an option to automatically mask personal information. For example, when an option is selected, the masking method is displayed. This allows the user to select an option and provides an option to automatically mask personal information.

[0038] The pseudo-compilation unit can develop an algorithm that completely removes personal information while preserving the statistical properties of the original data when the generation AI generates pseudo data. The pseudo-compilation unit, for example, develops an algorithm that completely removes personal information while preserving the statistical properties of the original data when the generation AI generates pseudo data. For example, it deletes personal information while maintaining the distribution and correlation of the original data. An algorithm for completely removing personal information while preserving the statistical properties of the original data is developed and incorporated into the generation AI. For example, it deletes personal information while maintaining the mean value and standard deviation of the data. An algorithm that completely removes personal information while preserving the statistical properties of the original data when the generation AI generates pseudo data is developed. For example, it deletes personal information while maintaining the distribution and correlation of the data. This makes it possible to develop an algorithm that completely removes personal information while preserving the statistical properties of the original data.

[0039] The simulation unit can visualize the process of generating pseudo data, allowing the user to understand the process. The simulation unit, for example, builds a system that visualizes the process of generating pseudo data, allowing the user to understand the process. For example, it displays the data conversion process in a graph or chart. It visualizes the process of generating pseudo data, providing an interface to enable the user to understand the process. For example, it displays the data conversion steps one by one. It develops a system that visualizes the process of generating pseudo data, allowing the user to understand the process. For example, it displays a comparison of the data before and after conversion. In this way, it is possible to visualize the process of generating pseudo data, allowing the user to understand the process.

[0040] The simulation unit can integrate different data sources to create a more diverse dataset. The simulation unit, for example, builds a system that integrates different data sources and creates a more diverse dataset when generating pseudo data. For example, it collects and integrates data from multiple databases. It develops an algorithm that integrates different data sources and creates a more diverse dataset when generating pseudo data. For example, it integrates data from different industries or fields. It develops a system that integrates different data sources and creates a more diverse dataset when generating pseudo data. For example, it integrates data in different formats and generates pseudo data. This makes it possible to integrate different data sources and create a more diverse dataset.

[0041] The simulation unit can provide a simulation environment using pseudo data, allowing the user to try out various scenarios without using actual data. The simulation unit, for example, provides a simulation environment using pseudo data, building a system that allows the user to try out various scenarios without using actual data. For example, simulating a marketing scenario. A simulation environment using pseudo data is provided, allowing the user to try out various scenarios without using actual data. For example, simulating a risk assessment scenario. A simulation environment using pseudo data is provided, allowing the user to try out various scenarios without using actual data, developing a system. For example, simulating an economic scenario. This provides a simulation environment using pseudo data, allowing the user to try out various scenarios without using actual data.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The security system may further include a data classification unit. The data classification unit can automatically classify input data and perform different processing depending on the level of confidentiality. For example, the data classification unit may classify data into personal information, confidential information, general information, etc., and apply appropriate security measures to each. The data classification unit may analyze the characteristics of data using a machine learning algorithm and classify it into an appropriate category. For example, a company's internal documents may be classified as confidential information so that only users with specific access rights can view them. The data classification unit may also classify data in real time and quickly identify security risks. This allows the security system to provide flexible security measures according to the level of confidentiality of the data.

[0044] The security system may further include a data encryption unit. The data encryption unit can encrypt input data to enhance security. For example, the data encryption unit may encrypt data using encryption algorithms such as AES or RSA to protect against unauthorized access. The data encryption unit can automatically encrypt data when it is sent or received, ensuring the security of communications. For example, it may encrypt data exchanged over a company's internal network to prevent external attacks. The data encryption unit may also encrypt data when it is stored, reducing the risk of data leaks. This allows the security system to enhance security through data encryption and protect personal and confidential information.

[0045] The security system may further include an access control unit. The access control unit may manage user access rights and perform appropriate access control. For example, the access control unit may set access rights according to the user's position and authority, and restrict access to specific data. The access control unit may work in conjunction with an authentication system to grant access rights based on the user's authentication information. For example, two-factor authentication may be used to authenticate users, and only authenticated users may access confidential information. The access control unit may also record access logs and detect and monitor unauthorized access. This allows the security system to appropriately manage user access rights and ensure data security.

[0046] The security system can further include a data backup unit. The data backup unit can periodically back up data and reduce the risk of data loss. For example, the data backup unit can back up data using cloud storage and restore the data in the event of a disaster or system failure. The data backup unit can set a backup schedule and automatically perform backups. For example, it can back up data late at night every day to protect the latest data. The data backup unit can also check the integrity of the backed up data and prevent data corruption. In this way, the security system can reduce the risk of data loss and ensure data safety through data backup.

[0047] The security system can further include a data audit unit. The data audit unit can monitor data usage and detect unauthorized access or operations. For example, the data audit unit can analyze access logs and operation logs to detect abnormal patterns. The data audit unit can use machine learning algorithms to detect anomalies and issue alerts in real time. For example, it can display a warning if a large amount of data is accessed during an unusual time period. The data audit unit can also generate audit reports on a regular basis to visualize the security status. This allows the security system to monitor data usage, quickly detect unauthorized access or operations, and take countermeasures.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The masking unit masks personal information. For example, personal information such as names, addresses, and phone numbers can be masked as "***" or "XXXX." The masking unit also uses natural language processing technology to understand the context and perform appropriate masking. Step 2: The alert unit alerts the user to the presence or absence of personal information when entering information into the prompt. For example, it displays an alert such as "This prompt contains personal information. Do you want to continue?". The alert unit also uses a machine learning model to detect personal information contained in the prompt with high accuracy. Step 3: The pseudo-computing unit simulates the data. For example, it converts actual customer data into pseudo-data, which is then used by the generation AI for analysis. The pseudo-computing unit can also develop algorithms that completely remove personal information while preserving the statistical properties of the original data.

[0050] (Example 2) The security system according to the embodiment of the present invention is a system that eliminates security and personal information risks and provides an environment in which generative AI can be used with a high degree of freedom. This allows companies and local governments to safely use generative AI.

[0051] A security system according to an embodiment includes a masking unit, an alert unit, and a simulation unit. The masking unit masks personal information. For example, the masking unit masks personal information such as names, addresses, and phone numbers as "***" or "XXXX." The masking unit can understand the context and perform appropriate masking using natural language processing technology. For example, the generation AI analyzes input data and uses natural language processing technology to understand the context. The alert unit alerts whether personal information is present when a prompt is entered. For example, the alert unit displays an alert such as "This prompt contains personal information. Do you want to continue?" The alert unit can also detect personal information contained in the prompt with high accuracy using a machine learning model. For example, the generation AI uses a machine learning model to improve the accuracy of detecting personal information when analyzing the prompt. The simulation unit simulates data. For example, the simulation unit converts actual customer data into pseudo data, and the generation AI then uses the pseudo data to perform analysis. Furthermore, the simulation unit can develop an algorithm that completely removes personal information while preserving the statistical characteristics of the original data when the generation AI generates pseudo data. For example, personal information is deleted while maintaining the distribution and correlation of the original data. As a result, the security system according to the embodiment can eliminate security and personal information risks and provide an environment in which the generation AI can be used with a high degree of freedom. For example, companies and local governments can safely input data containing personal information into the generation AI for analysis and proposals. Furthermore, by checking the presence or absence of personal information when entering data into a prompt, the risk of accidentally entering personal information can be reduced. Furthermore, data simulation allows data to be safely analyzed even outside of secure environments.

[0052] The masking unit uses natural language processing technology to understand the context and appropriately mask personal information. For example, the masking unit uses natural language processing technology to analyze input data and understand the context. For example, it analyzes how names and addresses are used in the context and performs appropriate masking. It uses natural language processing technology to understand the meaning of the entire sentence and identify parts that contain personal information. For example, based on the context, the sentence "Tanaka-san's address is Shibuya-ku, Tokyo" can be masked as "***-san's address is ***-ku." Context analysis is performed to automatically detect and mask phrases that may contain personal information. For example, the sentence "My phone number is 090-1234-5678" can be masked as "My phone number is ***-****-****." This allows for understanding the context and performing appropriate masking, preventing the leakage of personal information.

[0053] The masking unit provides a reverse masking function, allowing data to be restored when necessary. The masking unit provides, for example, a reverse masking function for restoring masked data to its original state. For example, the masking unit makes it possible to access the original data through specific authentication. Using the reverse masking function, a system is built for restoring the original data when necessary. For example, data before masking stored in a database is restored. A security protocol is set up to restore the masked data, allowing only authenticated users to access the original data. For example, two-factor authentication is used to restore data. This allows the original data to be restored when necessary.

[0054] The masking unit can use the emotion estimation function to mask personal information while preserving the emotional nuances of data entered by a user. The masking unit, for example, uses the emotion estimation function to analyze the emotional nuances of data entered by a user and mask the personal information. For example, sentences with positive emotions are masked with the same tone. A system is constructed using the emotion estimation function to mask personal information while preserving the emotional tone of input data. For example, the masking method is adjusted based on the emotion score. The user's emotional state is analyzed and personal information is masked so as not to impair the emotion. For example, sentences with negative emotions are masked with the same tone. This makes it possible to mask personal information while preserving the emotional nuances.

[0055] The masking unit can automatically detect and mask personal information contained in image or audio data. The masking unit uses, for example, image recognition technology to automatically detect and mask personal information contained in image data. For example, it blurs personal information such as faces and name tags. It uses audio analysis technology to automatically detect and mask personal information contained in audio data. For example, it silences parts containing names and addresses. It builds a system that analyzes image and audio data and identifies and masks parts containing personal information. For example, it hides specific phrases in audio data with beeps. This makes it possible to automatically mask personal information contained in image and audio data.

[0056] The masking unit uses the masked data to allow the generation AI to generate a new dataset, thereby ensuring data diversity. In the masking unit, for example, the generation AI generates a new dataset based on the masked data. For example, masked names and addresses are randomly generated to diversify the dataset. A system is constructed in which the generation AI generates a new dataset from the masked data, ensuring data diversity. For example, different patterns of masked data are generated. The generation AI generates diverse datasets based on the masked data, thereby improving data diversity. For example, masked data to be used in different contexts is generated. In this way, data diversity can be ensured using the masked data.

[0057] The masking unit can use the emotion estimation function to analyze the emotional tone of data entered by a user and propose a masking method for eliciting positive emotions. The masking unit, for example, uses the emotion estimation function to analyze the emotional tone of data entered by a user and propose a masking method for eliciting positive emotions. For example, a masking method that emphasizes positive expressions is provided. A system is constructed using the emotion estimation function to analyze the emotional tone of input data and propose a masking method for eliciting positive emotions. For example, the masking method is adjusted based on the emotion score. The user's emotional state is analyzed and a masking method for eliciting positive emotions is proposed. For example, sentences with negative emotions are masked with a positive tone. This makes it possible to propose a masking method for eliciting positive emotions.

[0058] The alert unit can use a machine learning model to detect personal information included in prompts with high accuracy. The alert unit, for example, uses a machine learning model to build a system that detects personal information included in prompts with high accuracy. For example, it automatically identifies personal information such as name and address. When the generation AI analyzes the prompt, it uses a machine learning model to improve the accuracy of detecting personal information. For example, it learns from past data and identifies patterns of personal information. A system is developed that uses a machine learning model to detect personal information included in prompts with high accuracy and display an alert. For example, it highlights the parts that include personal information. This makes it possible to detect personal information included in prompts with high accuracy.

[0059] The alert unit can highlight specific parts of the personal information when an alert is displayed, allowing the user to easily correct it. The alert unit, for example, builds a system that highlights specific parts of the personal information included in a prompt when an alert is displayed, allowing the user to easily correct it. For example, the part containing the name or address is highlighted in color. The part containing the personal information is highlighted, allowing the user to easily correct that part. For example, clicking on the highlighted part switches to correction mode. When an alert is displayed, the specific part of the personal information is highlighted, and an interface is provided that allows the user to easily correct it. For example, correction suggestions are displayed in the highlighted part. This makes it possible to highlight specific parts of the personal information, allowing the user to easily correct it.

[0060] The alert unit can use the emotion estimation function to analyze the emotional state of the user when inputting a prompt, and provide an alert display method for reducing stress. The alert unit, for example, uses the emotion estimation function to analyze the emotional state of the user when inputting a prompt, and provide an alert display method for reducing stress. For example, an alert is displayed in a gentle tone. A system is constructed that analyzes the emotional state of a user in real time and provides an alert display method for reducing stress. For example, a positive message is displayed. The emotion estimation function is used to analyze the emotional state of the user when inputting a prompt, and provide an alert display method for reducing stress. For example, relaxing music is played when the alert is displayed. This makes it possible to provide an alert display method for reducing stress for the user.

[0061] The alert unit can detect not only personal information but also confidential information and commercial secrets during prompt input and display an alert. For example, a system is constructed in which the alert unit detects not only personal information but also confidential information and commercial secrets during prompt input and displays an alert. For example, a warning is displayed if confidential corporate information is included. An algorithm is developed to detect confidential information and commercial secrets, and an alert is displayed during prompt input. For example, specific keywords and phrases are detected. A function is added to detect personal information, confidential information, and commercial secrets during prompt input and display an alert. For example, different alerts are displayed depending on the type of information detected. This makes it possible to detect not only personal information but also confidential information and commercial secrets and display an alert.

[0062] The alert unit can allow the user to select an option when an alert is displayed and provide an option to automatically mask personal information. For example, the alert unit builds a system that allows the user to select an option when an alert is displayed and provides an option to automatically mask personal information. For example, the options "mask" and "ignore" are displayed. The user can select an option when an alert is displayed and provide an option to automatically mask personal information. For example, masking is performed automatically when an option is clicked. An interface is developed that allows the user to select an option when an alert is displayed and provides an option to automatically mask personal information. For example, when an option is selected, the masking method is displayed. This allows the user to select an option and provides an option to automatically mask personal information.

[0063] The alert unit can use the emotion estimation function to monitor the emotional response of the user when entering a prompt in real time, and provide feedback to elicit positive emotions. The alert unit, for example, uses the emotion estimation function to monitor the emotional response of the user when entering a prompt in real time, and provide feedback to elicit positive emotions. For example, a positive message is displayed. A system is constructed that analyzes the user's emotional response in real time and provides feedback to elicit positive emotions. For example, feedback according to an emotion score is displayed. The emotion estimation function can be used to monitor the emotional response of the user when entering a prompt in real time, and provide feedback to elicit positive emotions. For example, an encouraging message according to the input content is displayed. In this way, the user's emotional response can be monitored and feedback to elicit positive emotions can be provided.

[0064] The pseudo-compilation unit can develop an algorithm that completely removes personal information while preserving the statistical properties of the original data when the generation AI generates pseudo data. The pseudo-compilation unit, for example, develops an algorithm that completely removes personal information while preserving the statistical properties of the original data when the generation AI generates pseudo data. For example, it deletes personal information while maintaining the distribution and correlation of the original data. An algorithm for completely removing personal information while preserving the statistical properties of the original data is developed and incorporated into the generation AI. For example, it deletes personal information while maintaining the mean value and standard deviation of the data. An algorithm that completely removes personal information while preserving the statistical properties of the original data when the generation AI generates pseudo data is developed. For example, it deletes personal information while maintaining the distribution and correlation of the data. This makes it possible to develop an algorithm that completely removes personal information while preserving the statistical properties of the original data.

[0065] The simulation unit can visualize the process of generating pseudo data, allowing the user to understand the process. The simulation unit, for example, builds a system that visualizes the process of generating pseudo data, allowing the user to understand the process. For example, it displays the data conversion process in a graph or chart. It visualizes the process of generating pseudo data, providing an interface to enable the user to understand the process. For example, it displays the data conversion steps one by one. It develops a system that visualizes the process of generating pseudo data, allowing the user to understand the process. For example, it displays a comparison of the data before and after conversion. In this way, it is possible to visualize the process of generating pseudo data, allowing the user to understand the process.

[0066] The simulation unit can use the emotion estimation function to evaluate the emotional impact that the analysis results based on the pseudo data have on the user and make adjustments to elicit positive results. The simulation unit, for example, uses the emotion estimation function to evaluate the emotional impact that the analysis results based on the pseudo data have on the user and make adjustments to elicit positive results. For example, it adjusts the method of presenting the analysis results. It builds a system that analyzes the user's emotional reactions in real time and makes adjustments so that the analysis results based on the pseudo data have a positive impact. For example, it provides feedback according to the emotion score. It uses the emotion estimation function to evaluate the emotional impact that the analysis results based on the pseudo data have on the user and make adjustments to elicit positive results. For example, it adjusts the method of displaying the analysis results. This makes it possible to evaluate the emotional impact that the analysis results based on the pseudo data have on the user and make adjustments to elicit positive results.

[0067] The simulation unit can integrate different data sources to create a more diverse dataset. The simulation unit, for example, builds a system that integrates different data sources and creates a more diverse dataset when generating pseudo data. For example, it collects and integrates data from multiple databases. It develops an algorithm that integrates different data sources and creates a more diverse dataset when generating pseudo data. For example, it integrates data from different industries or fields. It develops a system that integrates different data sources and creates a more diverse dataset when generating pseudo data. For example, it integrates data in different formats and generates pseudo data. This makes it possible to integrate different data sources and create a more diverse dataset.

[0068] The simulation unit can provide a simulation environment using pseudo data, allowing the user to try out various scenarios without using actual data. The simulation unit, for example, provides a simulation environment using pseudo data, building a system that allows the user to try out various scenarios without using actual data. For example, simulating a marketing scenario. A simulation environment using pseudo data is provided, allowing the user to try out various scenarios without using actual data. For example, simulating a risk assessment scenario. A simulation environment using pseudo data is provided, allowing the user to try out various scenarios without using actual data, developing a system. For example, simulating an economic scenario. This provides a simulation environment using pseudo data, allowing the user to try out various scenarios without using actual data.

[0069] The simulation unit can use the emotion estimation function to monitor the emotional impact that analysis results based on pseudo data have on the user in real time and propose an optimal analysis method. The simulation unit, for example, uses the emotion estimation function to monitor the emotional impact that analysis results based on pseudo data have on the user in real time and build a system that proposes an optimal analysis method. For example, it proposes an analysis method based on the emotion score. It analyzes the user's emotional response in real time and proposes an optimal analysis method so that analysis results based on pseudo data have a positive impact. For example, it adjusts the analysis method based on the emotion score. It uses the emotion estimation function to monitor the emotional impact that analysis results based on pseudo data have on the user in real time and proposes an optimal analysis method. For example, it adjusts the display method of the analysis results. In this way, it is possible to monitor the emotional impact that analysis results based on pseudo data have on the user in real time and propose an optimal analysis method.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The security system may further include a data classification unit. The data classification unit can automatically classify input data and perform different processing depending on the level of confidentiality. For example, the data classification unit may classify data into personal information, confidential information, general information, etc., and apply appropriate security measures to each. The data classification unit may analyze the characteristics of data using a machine learning algorithm and classify it into an appropriate category. For example, a company's internal documents may be classified as confidential information so that only users with specific access rights can view them. The data classification unit may also classify data in real time and quickly identify security risks. This allows the security system to provide flexible security measures according to the level of confidentiality of the data.

[0072] The security system may further include a data encryption unit. The data encryption unit can encrypt input data to enhance security. For example, the data encryption unit may encrypt data using encryption algorithms such as AES or RSA to protect against unauthorized access. The data encryption unit can automatically encrypt data when it is sent or received, ensuring the security of communications. For example, it may encrypt data exchanged over a company's internal network to prevent external attacks. The data encryption unit may also encrypt data when it is stored, reducing the risk of data leaks. This allows the security system to enhance security through data encryption and protect personal and confidential information.

[0073] The security system may further include an access control unit. The access control unit may manage user access rights and perform appropriate access control. For example, the access control unit may set access rights according to the user's position and authority, and restrict access to specific data. The access control unit may work in conjunction with an authentication system to grant access rights based on the user's authentication information. For example, two-factor authentication may be used to authenticate users, and only authenticated users may access confidential information. The access control unit may also record access logs and detect and monitor unauthorized access. This allows the security system to appropriately manage user access rights and ensure data security.

[0074] The security system can further include a data backup unit. The data backup unit can periodically back up data and reduce the risk of data loss. For example, the data backup unit can back up data using cloud storage and restore the data in the event of a disaster or system failure. The data backup unit can set a backup schedule and automatically perform backups. For example, it can back up data late at night every day to protect the latest data. The data backup unit can also check the integrity of the backed up data and prevent data corruption. In this way, the security system can reduce the risk of data loss and ensure data safety through data backup.

[0075] The security system can further include a data audit unit. The data audit unit can monitor data usage and detect unauthorized access or operations. For example, the data audit unit can analyze access logs and operation logs to detect abnormal patterns. The data audit unit can use machine learning algorithms to detect anomalies and issue alerts in real time. For example, it can display a warning if a large amount of data is accessed during an unusual time period. The data audit unit can also generate audit reports on a regular basis to visualize the security status. This allows the security system to monitor data usage, quickly detect unauthorized access or operations, and take countermeasures.

[0076] The security system can further use emotion estimation to adjust security measures based on the user's emotional state. For example, if the user is feeling stressed, the system can change security settings with a simple operation. The emotion estimation function can be used to analyze the user's emotional state in real time and suggest appropriate security measures. For example, if the user is feeling anxious, the system can highlight important alerts. The emotion estimation function can also be used to provide feedback according to the user's emotional state to raise security awareness. For example, if the user is relaxed, educational content about security can be provided. This allows the security system to flexibly adjust security measures based on the user's emotional state, strengthening security while reducing user stress.

[0077] The security system can further use the emotion estimation function to adjust the way alerts are displayed based on the user's emotional state. For example, if the user is nervous, the alert can be displayed in a calm tone. The emotion estimation function can be used to analyze the user's emotional state in real time and adjust the way alerts are displayed. For example, if the user is feeling angry, the alert can be displayed in a calm tone. The emotion estimation function can also be used to customize the content of alerts according to the user's emotional state. For example, if the user is feeling anxious, the alert can include specific countermeasures. This allows the security system to adjust the way alerts are displayed based on the user's emotional state, allowing the user to receive important information while reducing stress.

[0078] The security system can further use the emotion estimation function to adjust the data masking method based on the user's emotional state. For example, if the user has positive emotions, the masking method can be made more flexible. The emotion estimation function can be used to analyze the user's emotional state in real time and adjust the data masking method. For example, if the user has negative emotions, the masking method can be made more strict. The emotion estimation function can also be used to suggest a masking method according to the user's emotional state. For example, if the user is relaxed, the masking method can be simplified. In this way, the security system can adjust the data masking method based on the user's emotional state and protect personal information while taking the user's emotions into consideration.

[0079] The security system can further use the emotion estimation function to adjust the pseudo data generation method based on the user's emotional state. For example, if the user is feeling stressed, the pseudo data can be generated quickly. The emotion estimation function can be used to analyze the user's emotional state in real time and adjust the pseudo data generation method. For example, if the user is feeling impatient, the pseudo data generation can be simplified. The emotion estimation function can also be used to suggest a pseudo data generation method according to the user's emotional state. For example, if the user is relaxed, detailed pseudo data can be generated. In this way, the security system can adjust the pseudo data generation method based on the user's emotional state, ensuring data diversity while reducing user stress.

[0080] The security system can further use the emotion estimation function to provide security education content based on the user's emotional state. For example, if the user is relaxed, detailed security education content can be provided. The emotion estimation function can be used to analyze the user's emotional state in real time and provide appropriate security education content. For example, if the user is feeling anxious, concise security education content can be provided. The emotion estimation function can also be used to provide feedback according to the user's emotional state to raise security awareness. For example, if the user is feeling positive, security success stories can be introduced. In this way, the security system can provide appropriate security education content based on the user's emotional state and raise the user's security awareness.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The masking unit masks personal information. For example, personal information such as names, addresses, and phone numbers can be masked as "***" or "XXXX." The masking unit also uses natural language processing technology to understand the context and perform appropriate masking. Step 2: The alert unit alerts the user to the presence or absence of personal information when entering information into the prompt. For example, it displays an alert such as "This prompt contains personal information. Do you want to continue?". The alert unit also uses a machine learning model to detect personal information contained in the prompt with high accuracy. Step 3: The pseudo-computing unit simulates the data. For example, it converts actual customer data into pseudo-data, which is then used by the generation AI for analysis. The pseudo-computing unit can also develop algorithms that completely remove personal information while preserving the statistical properties of the original data.

[0083] 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.

[0084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] 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.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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).

[0092] 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.

[0093] 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.

[0094] 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.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0097] 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.

[0098] 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.

[0099] 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 AI 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.

[0100] 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.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0109] 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.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0111] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] 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.

[0113] 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.

[0114] 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 AI 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.

[0115] 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.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] 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.

[0129] 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.

[0130] 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 AI 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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."

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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, in order to avoid confusion and to 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.

[0149] 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]

[0150] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a masking unit that masks personal information; An alert section that alerts you to the presence or absence of personal information when entering information into a prompt; a simulation unit for simulation of data; A system characterized by:

2. The masking portion is Using natural language processing technology to understand the context and appropriately mask the personal information 2. The system of claim 1.

3. The masking portion is Provides reverse masking functionality to restore said data if necessary 2. The system of claim 1.

4. The masking portion is Masking personal information while preserving the emotional nuance of the data entered by a user 2. The system of claim 1.

5. The masking portion is Automatically detect and mask the personal information contained in image or audio data 2. The system of claim 1.

Images