System

Abstract

An object of a system according to an embodiment is to detect a fraudulent word or a fraudulent action in real time and visualize a text having no problem.SOLUTION: A system according to an embodiment includes a monitoring unit, a detection unit, a notification unit, a word cloud unit, and a visualization unit. The monitoring unit monitors an input text in real time. The detection unit detects a fraudulent word or fraudulent activity from the text monitored by the monitoring unit. The notification unit notifies an alert by mail on the basis of the fraudulent word or the fraudulent action detected by the detection unit. The word cloud unit forms a word cloud from the unproblematic text monitored by the monitoring unit. The visualization unit visualizes the word cloud generated by the word cloud unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the challenge of simultaneously detecting malicious words and malicious behavior in real time and visualizing non-problematic text.

[0005] The system according to the embodiment aims to detect fraudulent words and fraudulent behavior in real time and visualize non-problematic text. [Means for solving the problem]

[0006] The system according to the embodiment includes a monitoring unit, a detection unit, a notification unit, a word cloud unit, and a visualization unit. The monitoring unit monitors input text in real time. The detection unit detects fraudulent words or fraudulent behavior from the text monitored by the monitoring unit. The notification unit sends an alert by email based on the fraudulent words or fraudulent behavior detected by the detection unit. The word cloud unit creates a word cloud from non-problematic text monitored by the monitoring unit. The visualization unit visualizes the word cloud created by the word cloud unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect fraudulent words and fraudulent behavior in real time and visualize non-problematic text. [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 system according to an embodiment of the present invention is a fraud detection and survey service system that utilizes a keylogger system, a word cloud system, and text mining. This system installs a keylogger mechanism on employees' PCs and monitors input text in real time. If fraudulent words or actions are detected, an alert is sent via email. Meanwhile, non-problematic input behavior is visualized as a word cloud. Furthermore, by adding text mining functionality, it can replace traditional surveys. This system monitors input text in real time using a keylogger installed on employees' PCs, detects fraudulent words and actions, and sends an alert. Furthermore, by visualizing non-problematic input behavior as a word cloud, overall trends can be grasped. For example, traditional surveys can be replaced by analyzing employee opinions and feedback using natural language processing technology and displaying them as a word cloud.

[0029] A fraud detection system according to an embodiment includes a monitoring unit, a detection unit, a notification unit, a word cloud unit, and a visualization unit. The monitoring unit is installed on an employee's PC and monitors input text in real time. For example, the monitoring unit can use a keylogger to record and monitor all text input by employees in real time. The monitoring unit can also analyze the input text and detect specific keywords or patterns. The detection unit detects fraudulent words and actions from the text monitored by the monitoring unit. For example, the detection unit can detect fraudulent words based on a list of prohibited words. The detection unit can also detect fraudulent behavior such as spam and harassment. The detection unit can also use AI to learn fraudulent behavior patterns and improve detection accuracy. The notification unit sends an alert via email based on the fraudulent words and actions detected by the detection unit. For example, the notification unit can automatically send an email containing details of the detected fraudulent words and actions. The notification unit can also adjust the notification method depending on the importance of the alert. The word cloud unit creates a word cloud of non-problematic text monitored by the monitoring unit. For example, the word cloud unit can use a text mining algorithm to extract frequently occurring words and visually display them. The word cloud unit can also use natural language processing technology to analyze the content of text and display it as a word cloud. The visualization unit visualizes the word cloud generated by the word cloud unit. For example, the visualization unit can display the generated word cloud as a graph or chart, providing it in a visually easy-to-understand format. The visualization unit can also customize the display method of the word cloud to display it according to the user's needs. As a result, the fraud detection system according to the embodiment can monitor input text in real time, detect fraudulent words and actions, notify an alert, and visualize non-problematic text as a word cloud.

[0030] The monitoring unit is installed on employees' PCs and can monitor entered text in real time. The monitoring unit can use a keylogger, for example, to record all text entered by employees and monitor it in real time. The monitoring unit can also analyze entered text and detect specific keywords or patterns. For example, the monitoring unit can issue an alert if a specific keyword is entered. The monitoring unit can also learn patterns of entered text and detect abnormal patterns. Thus, by installing it on employees' PCs, it is possible to monitor entered text in real time.

[0031] The detection unit can detect fraudulent words and actions from text monitored by the monitoring unit. The detection unit can detect fraudulent words based on, for example, a list of prohibited words. The detection unit can also detect fraudulent behavior such as spam and harassment. For example, the detection unit can detect text containing specific keywords and identify them as fraudulent words. The detection unit can also use AI to learn patterns of fraudulent behavior and improve detection accuracy. Furthermore, the detection unit can analyze text in real time and immediately detect fraudulent behavior. This makes it possible to detect fraudulent words and actions from text monitored by the monitoring unit.

[0032] The notification unit can send an alert by email based on the abusive words and actions detected by the detection unit. The notification unit can, for example, automatically send an email including details of the detected abusive words and actions. The notification unit can also adjust the notification method depending on the importance of the alert. For example, the notification unit can immediately notify high-priority alerts and later notify low-priority alerts. The notification unit can also customize the content of the alert and notify in a format that is easy for the recipient to understand. Furthermore, the notification unit can save the history of alerts and refer to it later. This makes it possible to send an alert by email based on the abusive words and actions detected by the detection unit.

[0033] The word cloud unit can create a word cloud of non-problematic text monitored by the monitoring unit. The word cloud unit can extract frequently occurring words and visually display them using, for example, a text mining algorithm. The word cloud unit can also analyze the content of the text and display it as a word cloud using natural language processing technology. For example, the word cloud unit can display particularly important words in the text in a larger font and less frequently occurring words in a smaller font. The word cloud unit can also display different colors or fonts depending on the text category. Furthermore, the word cloud unit can customize the word cloud display method according to the user's needs. In this way, the non-problematic text monitored by the monitoring unit can be created as a word cloud.

[0034] The visualization unit can visualize the word cloud generated by the word cloud unit. For example, the visualization unit can display the generated word cloud as a graph or chart, providing it in a visually easy-to-understand format. The visualization unit can also customize the display method of the word cloud to provide a display that meets the user's needs. For example, the visualization unit can change the color or font of the word cloud to provide a visually appealing display. The visualization unit can also adjust the display size of the word cloud to provide an optimal display according to the screen size. Furthermore, the visualization unit can filter the display content of the word cloud to customize the display based on specific categories or keywords. In this way, the word cloud generated by the word cloud unit can be visualized.

[0035] The word cloud section can use a text mining algorithm to extract and visually display frequently occurring words. For example, the word cloud section can use Term Frequency-Inverse Document Frequency (TF-IDF) to extract important words within a text. The word cloud section can also use Latent Dirichlet Allocation (LDA) to extract and visually display topics within the text. For example, the word cloud section can calculate the frequency of words within the text and highlight frequently occurring words. The word cloud section can also display the text using different colors or fonts depending on the text category. Furthermore, the word cloud section can analyze the content of the text and extract and display specific keywords or phrases. This allows the text mining algorithm to extract and visually display frequently occurring words.

[0036] The visualization unit can use natural language processing technology to analyze employee opinions and feedback and display them as a word cloud. For example, the visualization unit can use morphological analysis to segment words in text and extract frequently occurring words. The visualization unit can also use grammatical analysis to analyze the structure of text and extract important words and phrases. For example, the visualization unit can extract nouns and verbs in text and display them as a word cloud. The visualization unit can also use semantic analysis to understand the meaning of text and extract important information. Furthermore, the visualization unit can analyze the content of the text and generate a word cloud based on a specific theme or topic. This makes it possible to use natural language processing technology to analyze employee opinions and feedback and display them as a word cloud.

[0037] The monitoring unit can analyze the user's past input history and select the optimal monitoring method. The monitoring unit can customize the monitoring method based on, for example, text patterns frequently entered by the user in the past. The monitoring unit can also intensify monitoring during specific time periods based on the user's past input history. For example, if the user inputs a lot of text during a specific time period, the monitoring unit can intensify monitoring during that time period. The monitoring unit can also analyze the user's past input history and select a monitoring method for detecting an abnormal pattern. For example, the monitoring unit can extract an abnormal pattern from the past input history and perform monitoring based on that pattern. In this way, the optimal monitoring method can be selected by analyzing the user's past input history. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI.

[0038] The monitoring unit can perform filtering based on the user's current work. For example, if the user is creating a document, the monitoring unit can perform monitoring based on the text content. Furthermore, if the user is sending an email, the monitoring unit can perform monitoring based on the recipient and content. For example, if the user sends an email containing a specific keyword, the monitoring unit can focus on monitoring that email. Furthermore, if the user is browsing the web, the monitoring unit can perform monitoring based on the content of the site accessed. For example, if the user accesses a site in a specific category, the monitoring unit can focus on monitoring the content of that site. This allows appropriate monitoring by filtering based on the user's current work. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI.

[0039] The monitoring unit can select the optimal monitoring means depending on the user's input method. For example, if the user uses voice input, the monitoring unit can perform monitoring using voice recognition technology. Furthermore, if the user uses text input, the monitoring unit can perform monitoring using text analysis technology. For example, if the user uses voice input, the monitoring unit can analyze the voice data and detect specific keywords or phrases. Furthermore, if the user uses image input, the monitoring unit can perform monitoring using image recognition technology. For example, if the user uses image input, the monitoring unit can analyze the image data and detect specific patterns or objects. This allows for effective monitoring by selecting the optimal monitoring means depending on the user's input method. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI.

[0040] The monitoring unit can prioritize monitoring highly relevant text in consideration of the user's geographical location information. For example, when the user is in a specific area, the monitoring unit can prioritize monitoring text related to that area. Furthermore, when the user is moving, the monitoring unit can also monitor related text based on the user's current location. For example, when the user is in a specific area, the monitoring unit can focus on monitoring keywords and phrases related to that area. Furthermore, when the user stays in a specific location for a long time, the monitoring unit can prioritize monitoring text related to that location. In this way, highly relevant text can be prioritized in consideration of the user's geographical location information. Some or all of the above-described processing in the monitoring unit may be performed, for example, using AI or without using AI.

[0041] The monitoring unit can analyze the user's social media activity and monitor related text. The monitoring unit can monitor related text based on, for example, content posted by the user on social media. The monitoring unit can also monitor related text with reference to the activities of the user's friends on social media. For example, if the user posts on social media containing a specific keyword, the monitoring unit can focus on monitoring text related to the keyword. The monitoring unit can also monitor related text based on the user's check-in information on social media. In this way, the user's social media activity can be analyzed and related text can be monitored. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI.

[0042] The monitoring unit can customize the monitoring method by reflecting the user's past feedback. The monitoring unit can adjust the monitoring method based on, for example, feedback provided by the user in the past. The monitoring unit can also strengthen specific monitoring items based on the user's past feedback. For example, if the user has provided feedback on a specific keyword in the past, the monitoring unit can strengthen monitoring related to that keyword. The monitoring unit can also analyze the user's past feedback and suggest an optimal monitoring method. In this way, the monitoring method can be customized by reflecting the user's past feedback, making it possible to provide an optimal monitoring method. Some or all of the above-described processing in the monitoring unit may be performed, for example, using AI or without using AI.

[0043] The detection unit can optimize the detection algorithm by referring to past fraudulent behavior data. The detection unit can, for example, adjust the detection algorithm based on the past fraudulent behavior data. The detection unit can also extract specific patterns from the past fraudulent behavior data and reflect them in the detection algorithm. For example, the detection unit can analyze the past fraudulent behavior data and extract specific keywords or behavioral patterns. The detection unit can also improve the accuracy of the detection algorithm based on the extracted patterns. Furthermore, the detection unit can dynamically optimize the detection algorithm by referring to the past fraudulent behavior data in real time. In this way, the detection algorithm can be optimized by referring to the past fraudulent behavior data. Some or all of the above-described processing in the detection unit may be performed, for example, using AI or without using AI.

[0044] The detection unit can perform detection taking into account user attribute information. The detection unit can adjust detection criteria based on, for example, the user's occupation or job title. The detection unit can also optimize the detection algorithm based on the user's age and gender. For example, the detection unit can focus on monitoring specific keywords or behavioral patterns depending on the user's occupation. The detection unit can also adjust parameters of the detection algorithm based on the user's age and gender. Furthermore, the detection unit can customize the detection algorithm based on the user's past behavioral history. In this way, detection can be performed taking into account the user's attribute information, thereby enabling more accurate detection. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI.

[0045] The detection unit can weight detection based on the frequency of user input. For example, if the user inputs frequently, the detection unit can set a high weight for detection. Furthermore, if the user inputs infrequently, the detection unit can set a low weight for detection. For example, the detection unit can analyze the frequency of user input and assign a high weight to frequently input keywords or phrases. Furthermore, the detection unit can assign a low weight to infrequently input keywords or phrases. Furthermore, the detection unit can monitor the frequency of user input in real time and dynamically adjust the weight. In this way, appropriate detection can be performed by weighting detection based on the frequency of user input. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI.

[0046] The detection unit can perform detection by taking into account the geographic distribution of text. The detection unit can adjust the detection algorithm based on, for example, fraudulent behavior that occurs frequently in a specific region. The detection unit can also strengthen detection in a specific region based on the geographic distribution. For example, the detection unit can extract keywords or behavioral patterns that occur frequently in a specific region and strengthen detection in that region. The detection unit can also analyze the geographic distribution and propose an optimal detection method. In this way, by performing detection by taking into account the geographic distribution of text, it is possible to strengthen detection in a specific region. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or without using AI.

[0047] The detection unit can improve the accuracy of detection by referring to related literature. The detection unit can, for example, optimize the detection algorithm based on the related literature. The detection unit can also extract the latest fraudulent behavior patterns from the related literature and reflect them in the detection algorithm. For example, the detection unit can learn the latest fraudulent behavior patterns by referring to the related literature. The detection unit can also adjust the parameters of the detection algorithm based on the related literature. Furthermore, the detection unit can dynamically optimize the detection algorithm by referring to the related literature in real time. In this way, the accuracy of the detection algorithm can be improved by referring to the related literature. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or without using AI.

[0048] The detection unit can perform detection taking into account the market value of the text. For example, the detection unit can prioritize detection of text with high market value. The detection unit can also exclude text with low market value from detection. For example, the detection unit can analyze the market value of the text and focus on detecting keywords and phrases with high market value. The detection unit can also filter out text with low market value and exclude it from detection. Furthermore, the detection unit can evaluate the market value of the text in real time and dynamically adjust the detection criteria. In this way, important text can be detected with priority by taking the market value of the text into consideration. Some or all of the above-described processing in the detection unit may be performed, for example, using AI or without using AI.

[0049] The notification unit can select the optimal notification method by referring to past notification history. The notification unit can select the optimal notification method based on, for example, the past notification history. The notification unit can also enhance a specific notification method based on the past notification history. For example, the notification unit can analyze the past notification history and select the optimal notification method for a specific keyword or phrase. The notification unit can also adjust the timing and frequency of notifications based on the past notification history. Furthermore, the notification unit can dynamically optimize the notification method by referring to the past notification history in real time. In this way, the optimal notification method can be selected by referring to the past notification history. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or without using AI.

[0050] The notification unit can customize the notification content based on the user's current situation. For example, when the user is in a meeting, the notification unit can provide a quiet notification method. Furthermore, when the user is on the move, the notification unit can provide concise notification content. For example, when the user is in a meeting, the notification unit can notify the user by vibrating or in silent mode. Furthermore, when the user is on the move, the notification unit can notify the user by a short message or a notification that focuses on the main points. Furthermore, when the user is on a break, the notification unit can provide detailed notification content. In this way, by customizing the notification content based on the user's current situation, appropriate notification can be provided. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or without using AI.

[0051] The notification unit can improve the notification method by reflecting user feedback. The notification unit can adjust the notification method based on, for example, feedback provided by the user in the past. The notification unit can also enhance a specific notification method based on the user's past feedback. For example, if the user has provided feedback on a specific notification method in the past, the notification unit can improve the notification method. The notification unit can also analyze the user's past feedback and suggest an optimal notification method. In this way, the notification method can be improved by reflecting the user's feedback, thereby providing an optimal notification method. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or without using AI.

[0052] The notification unit can select the optimal notification method taking into account the user's geographical location information. For example, when the user is in a specific area, the notification unit can prioritize displaying notifications related to that area. Furthermore, when the user is moving, the notification unit can also display related notifications based on the user's current location. For example, when the user is in a specific area, the notification unit can prioritize notifications related to keywords and phrases related to that area. Furthermore, when the user is staying in a specific location for a long time, the notification unit can prioritize displaying notifications related to that location. In this way, by selecting the optimal notification method taking into account the user's geographical location information, it is possible to provide highly relevant notifications. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or without using AI.

[0053] The notification unit can customize the notification content by analyzing the user's social media activity. The notification unit can display relevant notifications based on, for example, content posted by the user on social media. The notification unit can also display relevant notifications by referring to the activities of the user's friends on social media. For example, if the user posts on social media containing a specific keyword, the notification unit can prioritize notifications related to the keyword. The notification unit can also display relevant notifications based on the user's check-in information on social media. In this way, the notification content can be customized by analyzing the user's social media activity, thereby providing relevant notifications. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or without AI.

[0054] The notification unit can customize the notification method by reflecting the user's past feedback. The notification unit can adjust the notification method based on, for example, feedback provided by the user in the past. The notification unit can also enhance a specific notification method based on the user's past feedback. For example, if the user has provided feedback on a specific notification method in the past, the notification unit can improve the notification method. The notification unit can also analyze the user's past feedback and suggest an optimal notification method. In this way, the notification method can be customized by reflecting the user's past feedback, thereby providing an optimal notification method. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or without using AI.

[0055] The word cloud unit can adjust the level of detail of the word cloud based on the importance of the text. For example, the word cloud unit can generate a detailed word cloud based on text with high importance. The word cloud unit can also generate a simple word cloud based on text with low importance. For example, the word cloud unit can analyze the importance of the text and extract frequently occurring keywords and phrases. The word cloud unit can also display keywords with high importance in a larger size and keywords with low importance in a smaller size. Furthermore, the word cloud unit can adjust the color and font based on the importance of the text to provide a visually easy-to-understand display. In this way, by adjusting the level of detail of the word cloud based on the importance of the text, an appropriate word cloud can be generated. Some or all of the above-described processing in the word cloud unit may be performed, for example, using AI or without AI.

[0056] The word cloud unit can apply different algorithms depending on the category of the text. For example, the word cloud unit can apply a business algorithm to business-related text. The word cloud unit can also apply an entertainment algorithm to entertainment-related text. For example, the word cloud unit can analyze the category of the text and select an algorithm according to the category. The word cloud unit can also apply an education algorithm to education-related text. Furthermore, the word cloud unit can adjust colors and fonts based on the text category to provide a visually easy-to-understand display. In this way, by applying different algorithms depending on the text category, an appropriate word cloud can be generated. Some or all of the above-mentioned processing in the word cloud unit may be performed using, for example, AI, or may be performed without using AI.

[0057] The word cloud unit can improve the accuracy of generation by referring to the user's past word cloud results. For example, the word cloud unit can adjust the generation algorithm based on the user's past word cloud results. The word cloud unit can also extract specific patterns from the user's past word cloud results and reflect them in the generation algorithm. For example, the word cloud unit can analyze past word cloud results and extract frequently occurring keywords or phrases. The word cloud unit can also improve the accuracy of the generation algorithm based on the extracted patterns. Furthermore, the word cloud unit can refer to past word cloud results in real time and dynamically optimize the generation algorithm. This can improve the accuracy of generation by referring to the user's past word cloud results. Some or all of the above-described processing in the word cloud unit may be performed, for example, using AI or without AI.

[0058] The word cloud unit can determine the priority of word clouds based on the time of text submission. The word cloud unit can determine the priority of word clouds based on, for example, the most recent text. The word cloud unit can also determine the priority of word clouds based on older text. For example, the word cloud unit can analyze the time of text submission and prioritize displaying the most recent text. The word cloud unit can also filter older text and adjust the display priority. Furthermore, the word cloud unit can evaluate the time of text submission in real time and dynamically adjust the priority. In this way, by determining the priority of word clouds based on the time of text submission, the most recent information can be prioritized and displayed. Some or all of the above-described processing in the word cloud unit can be performed, for example, using AI or without AI.

[0059] The word cloud unit can adjust the order of the word cloud based on the relevance of the text. The word cloud unit can, for example, determine the order of the word cloud based on highly relevant text. The word cloud unit can also determine the order of the word cloud based on less relevant text. For example, the word cloud unit can analyze the relevance of the text and prioritize displaying highly relevant keywords and phrases. The word cloud unit can also filter less relevant keywords and phrases and adjust the display order. Furthermore, the word cloud unit can evaluate the relevance of the text in real time and dynamically adjust the order. In this way, by adjusting the order of the word cloud based on the relevance of the text, highly relevant information can be prioritized and displayed. Some or all of the above-described processing in the word cloud unit may be performed, for example, using AI or without AI.

[0060] The word cloud unit can adjust the use of technical terms in the word cloud according to the user's level of expertise. For example, the word cloud unit can provide a word cloud that uses a lot of technical terms to a user with high expertise. The word cloud unit can also provide a word cloud with less technical terms to a user with low expertise. For example, the word cloud unit can analyze the user's level of expertise and adjust the use of technical terms. The word cloud unit can also select keywords and phrases to display based on the user's level of expertise. Furthermore, the word cloud unit can evaluate the user's level of expertise in real time and dynamically adjust the use of technical terms. In this way, appropriate information can be provided by adjusting the use of technical terms in the word cloud according to the user's level of expertise. Some or all of the above-described processing in the word cloud unit can be performed, for example, using AI or without AI.

[0061] The visualization unit can select the optimal display method by referring to the user's past operation history. The visualization unit can select the optimal display method based on, for example, the user's past operation history. The visualization unit can also enhance a specific display method based on the user's past operation history. For example, the visualization unit can analyze the user's past operation history and select the optimal display method for a specific keyword or phrase. The visualization unit can also adjust the timing and frequency of display based on the past operation history. Furthermore, the visualization unit can refer to the past operation history in real time and dynamically optimize the display method. In this way, the optimal display method can be selected by referring to the user's past operation history. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without using AI.

[0062] The visualization unit can customize the display content according to the user's current task. For example, when the user is creating a document, the visualization unit can display related information. Furthermore, when the user is sending an email, the visualization unit can also display related information. For example, when the user is creating a document, the visualization unit can display keywords and phrases related to the document content. Furthermore, when the user is browsing the web, the visualization unit can display related information based on the content of the accessed site. Furthermore, the visualization unit can evaluate the user's current task in real time and dynamically customize the display content. This allows the display content to be customized according to the user's current task, thereby providing appropriate information. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI, or may be performed without using AI.

[0063] The visualization unit can improve the display method by reflecting user feedback. The visualization unit can adjust the display method based on, for example, feedback provided by the user in the past. The visualization unit can also enhance a specific display method based on the user's past feedback. For example, if the user provided feedback on a specific display method in the past, the visualization unit can improve the display method. The visualization unit can also analyze the user's past feedback and suggest an optimal display method. In this way, the display method can be improved by reflecting the user's feedback, thereby providing an optimal display method. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without using AI.

[0064] The visualization unit can select the optimal display method by taking into account the user's device information. For example, if the user is using a smartphone, the visualization unit can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the visualization unit can also provide a display method optimized for a large screen. For example, the visualization unit can analyze the user's device information and select a display method that matches the type of device. Furthermore, if the user is using a smartwatch, the visualization unit can also provide a simple and highly visible display method. Furthermore, the visualization unit can evaluate the device information in real time and dynamically optimize the display method. In this way, the optimal display method can be selected by taking into account the user's device information, thereby providing the optimal display method. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without using AI.

[0065] The visualization unit can make the display content multilingual according to the user's language setting. The visualization unit can automatically set the display content based on, for example, the language setting of the user's device. The visualization unit can also provide a language switching function when the user uses multiple languages. For example, the visualization unit can analyze the user's language setting and provide display content according to the set language. Furthermore, when the user selects a specific language, the visualization unit can provide display content in that language. Furthermore, the visualization unit can evaluate the language setting in real time and dynamically make the display content multilingual. This makes it possible to provide appropriate information by making the display content multilingual according to the user's language setting. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without AI.

[0066] The visualization unit can customize the display content based on the user's occupation and lifestyle. For example, if the user is a businessman, the visualization unit can prioritize displaying business-related information. Furthermore, if the user is a student, the visualization unit can prioritize displaying education-related information. For example, the visualization unit can analyze the user's occupation information and provide display content according to the occupation. Furthermore, the visualization unit can analyze the user's lifestyle and provide display content according to the lifestyle. Furthermore, the visualization unit can evaluate the occupation and lifestyle information in real time and dynamically customize the display content. In this way, appropriate information can be provided by customizing the display content based on the user's occupation and lifestyle. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without using AI.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] The notification unit can send alerts at optimal timing, taking into account the user's schedule information. For example, if the user is in a meeting, the alert can be temporarily suspended and the notification can be sent after the meeting ends. Also, if the user is on a break, an alert can be sent immediately, encouraging a prompt response. Furthermore, by obtaining the user's schedule information in real time and sending notifications at optimal timing, the burden on the user can be reduced.

[0069] The word cloud unit can generate a customized word cloud based on a user's interests. For example, if a user is interested in a particular topic, it can prioritize displaying words related to that topic. It can also analyze the user's past search history and browsing history to generate a word cloud based on their interests. Furthermore, by reflecting user feedback and continuously improving the content of the word cloud display, it is possible to provide more personalized information.

[0070] The visualization unit can adjust the display method taking into account the remaining battery level of the user's device. For example, when the battery level is low, a simple, energy-saving display method can be provided. When the battery level is sufficient, a display method including detailed information can be provided. Furthermore, by monitoring the remaining battery level in real time and dynamically adjusting the display method, the battery life of the user's device can be extended.

[0071] The notification unit can analyze the user's past alert response history and select the optimal notification method. For example, it can identify patterns of alerts that were immediately responded to in the past and adjust the notification method based on those patterns. It can also analyze patterns of alerts that were ignored in the past and select a notification method that avoids those patterns. Furthermore, by referencing the past alert response history in real time and dynamically optimizing the notification method, the burden on the user can be reduced.

[0072] The visualization unit can select the optimal display layout by referring to the user's past operation history. For example, it can identify layouts that have been frequently used in the past and display those layouts preferentially. It can also analyze layouts that have been avoided in the past and select a display method that avoids those layouts. Furthermore, by referring to the past operation history in real time and dynamically optimizing the display layout, it is possible to improve the user's operation efficiency.

[0073] The processing flow of the first embodiment will be briefly explained below.

[0074] Step 1: The monitoring unit is installed on the employee's PC and monitors the text entered in real time. For example, the monitoring unit can use a keylogger to record all text entered by the employee and monitor it in real time. The monitoring unit can also analyze the text entered and detect specific keywords or patterns. Step 2: The detection unit detects fraudulent words and actions from the text monitored by the monitoring unit. For example, the detection unit can detect fraudulent words based on a list of prohibited words. The detection unit can also detect fraudulent behavior such as spam and harassment. Furthermore, the detection unit can use AI to learn patterns of fraudulent behavior and improve detection accuracy. Step 3: The notification unit sends an email alert based on the malicious words and actions detected by the detection unit. For example, the notification unit can automatically send an email containing details of the detected malicious words and actions. The notification unit can also adjust the notification method depending on the importance of the alert. Step 4: The word cloud unit creates a word cloud from the non-problematic text monitored by the monitoring unit. For example, the word cloud unit can use a text mining algorithm to extract frequently occurring words and display them visually. The word cloud unit can also use natural language processing technology to analyze the content of the text and display it as a word cloud. Step 5: The visualization unit visualizes the word cloud generated by the word cloud unit. For example, the visualization unit can display the generated word cloud as a graph or chart, providing it in a visually easy-to-understand format. The visualization unit can also customize the display method of the word cloud to display it according to the user's needs.

[0075] (Example 2) The system according to an embodiment of the present invention is a fraud detection and survey service system that utilizes a keylogger system, a word cloud system, and text mining. This system installs a keylogger mechanism on employees' PCs and monitors input text in real time. If fraudulent words or actions are detected, an alert is sent via email. Meanwhile, non-problematic input behavior is visualized as a word cloud. Furthermore, by adding text mining functionality, it can replace traditional surveys. This system monitors input text in real time using a keylogger installed on employees' PCs, detects fraudulent words and actions, and sends an alert. Furthermore, by visualizing non-problematic input behavior as a word cloud, overall trends can be grasped. For example, traditional surveys can be replaced by analyzing employee opinions and feedback using natural language processing technology and displaying them as a word cloud.

[0076] A fraud detection system according to an embodiment includes a monitoring unit, a detection unit, a notification unit, a word cloud unit, and a visualization unit. The monitoring unit is installed on an employee's PC and monitors input text in real time. For example, the monitoring unit can use a keylogger to record and monitor all text input by employees in real time. The monitoring unit can also analyze the input text and detect specific keywords or patterns. The detection unit detects fraudulent words and actions from the text monitored by the monitoring unit. For example, the detection unit can detect fraudulent words based on a list of prohibited words. The detection unit can also detect fraudulent behavior such as spam and harassment. The detection unit can also use AI to learn fraudulent behavior patterns and improve detection accuracy. The notification unit sends an alert via email based on the fraudulent words and actions detected by the detection unit. For example, the notification unit can automatically send an email containing details of the detected fraudulent words and actions. The notification unit can also adjust the notification method depending on the importance of the alert. The word cloud unit creates a word cloud of non-problematic text monitored by the monitoring unit. For example, the word cloud unit can use a text mining algorithm to extract frequently occurring words and visually display them. The word cloud unit can also use natural language processing technology to analyze the content of text and display it as a word cloud. The visualization unit visualizes the word cloud generated by the word cloud unit. For example, the visualization unit can display the generated word cloud as a graph or chart, providing it in a visually easy-to-understand format. The visualization unit can also customize the display method of the word cloud to display it according to the user's needs. As a result, the fraud detection system according to the embodiment can monitor input text in real time, detect fraudulent words and actions, notify an alert, and visualize non-problematic text as a word cloud.

[0077] The monitoring unit is installed on employees' PCs and can monitor entered text in real time. The monitoring unit can use a keylogger, for example, to record all text entered by employees and monitor it in real time. The monitoring unit can also analyze entered text and detect specific keywords or patterns. For example, the monitoring unit can issue an alert if a specific keyword is entered. The monitoring unit can also learn patterns of entered text and detect abnormal patterns. Thus, by installing it on employees' PCs, it is possible to monitor entered text in real time.

[0078] The detection unit can detect fraudulent words and actions from text monitored by the monitoring unit. The detection unit can detect fraudulent words based on, for example, a list of prohibited words. The detection unit can also detect fraudulent behavior such as spam and harassment. For example, the detection unit can detect text containing specific keywords and identify them as fraudulent words. The detection unit can also use AI to learn patterns of fraudulent behavior and improve detection accuracy. Furthermore, the detection unit can analyze text in real time and immediately detect fraudulent behavior. This makes it possible to detect fraudulent words and actions from text monitored by the monitoring unit.

[0079] The notification unit can send an alert by email based on the abusive words and actions detected by the detection unit. The notification unit can, for example, automatically send an email including details of the detected abusive words and actions. The notification unit can also adjust the notification method depending on the importance of the alert. For example, the notification unit can immediately notify high-priority alerts and later notify low-priority alerts. The notification unit can also customize the content of the alert and notify in a format that is easy for the recipient to understand. Furthermore, the notification unit can save the history of alerts and refer to it later. This makes it possible to send an alert by email based on the abusive words and actions detected by the detection unit.

[0080] The word cloud unit can create a word cloud of non-problematic text monitored by the monitoring unit. The word cloud unit can extract frequently occurring words and visually display them using, for example, a text mining algorithm. The word cloud unit can also analyze the content of the text and display it as a word cloud using natural language processing technology. For example, the word cloud unit can display particularly important words in the text in a larger font and less frequently occurring words in a smaller font. The word cloud unit can also display different colors or fonts depending on the text category. Furthermore, the word cloud unit can customize the word cloud display method according to the user's needs. In this way, the non-problematic text monitored by the monitoring unit can be created as a word cloud.

[0081] The visualization unit can visualize the word cloud generated by the word cloud unit. For example, the visualization unit can display the generated word cloud as a graph or chart, providing it in a visually easy-to-understand format. The visualization unit can also customize the display method of the word cloud to provide a display that meets the user's needs. For example, the visualization unit can change the color or font of the word cloud to provide a visually appealing display. The visualization unit can also adjust the display size of the word cloud to provide an optimal display according to the screen size. Furthermore, the visualization unit can filter the display content of the word cloud to customize the display based on specific categories or keywords. In this way, the word cloud generated by the word cloud unit can be visualized.

[0082] The word cloud section can use a text mining algorithm to extract and visually display frequently occurring words. For example, the word cloud section can use Term Frequency-Inverse Document Frequency (TF-IDF) to extract important words within a text. The word cloud section can also use Latent Dirichlet Allocation (LDA) to extract and visually display topics within the text. For example, the word cloud section can calculate the frequency of words within the text and highlight frequently occurring words. The word cloud section can also display the text using different colors or fonts depending on the text category. Furthermore, the word cloud section can analyze the content of the text and extract and display specific keywords or phrases. This allows the text mining algorithm to extract and visually display frequently occurring words.

[0083] The visualization unit can use natural language processing technology to analyze employee opinions and feedback and display them as a word cloud. For example, the visualization unit can use morphological analysis to segment words in text and extract frequently occurring words. The visualization unit can also use grammatical analysis to analyze the structure of text and extract important words and phrases. For example, the visualization unit can extract nouns and verbs in text and display them as a word cloud. The visualization unit can also use semantic analysis to understand the meaning of text and extract important information. Furthermore, the visualization unit can analyze the content of the text and generate a word cloud based on a specific theme or topic. This makes it possible to use natural language processing technology to analyze employee opinions and feedback and display them as a word cloud.

[0084] The monitoring unit can estimate the user's emotions and adjust the monitoring frequency based on the estimated user emotions. The monitoring unit can estimate the user's emotions using, for example, an emotion analysis algorithm. For example, the monitoring unit can analyze the user's input text and calculate an emotion score. The monitoring unit can also estimate the user's emotions by analyzing the user's facial expressions and voice. For example, the monitoring unit can analyze the user's facial expression data captured by a camera and estimate the user's emotions. The monitoring unit can also analyze the user's voice data recorded by a microphone and estimate the user's emotions. The monitoring unit can also adjust the monitoring frequency based on the estimated user emotions. For example, if the user is feeling stressed, the monitoring frequency can be set low to reduce the burden on the user. If the user is relaxed, the monitoring frequency can be set high to collect detailed data. Thus, by adjusting the monitoring frequency based on the user's emotions, the user's burden can be reduced and detailed data can be collected. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the monitoring unit may be performed using AI, or may be performed without using AI.

[0085] The monitoring unit can analyze the user's past input history and select the optimal monitoring method. The monitoring unit can customize the monitoring method based on, for example, text patterns frequently entered by the user in the past. The monitoring unit can also intensify monitoring during specific time periods based on the user's past input history. For example, if the user inputs a lot of text during a specific time period, the monitoring unit can intensify monitoring during that time period. The monitoring unit can also analyze the user's past input history and select a monitoring method for detecting an abnormal pattern. For example, the monitoring unit can extract an abnormal pattern from the past input history and perform monitoring based on that pattern. In this way, the optimal monitoring method can be selected by analyzing the user's past input history. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI.

[0086] The monitoring unit can perform filtering based on the user's current work. For example, if the user is creating a document, the monitoring unit can perform monitoring based on the text content. Furthermore, if the user is sending an email, the monitoring unit can perform monitoring based on the recipient and content. For example, if the user sends an email containing a specific keyword, the monitoring unit can focus on monitoring that email. Furthermore, if the user is browsing the web, the monitoring unit can perform monitoring based on the content of the site accessed. For example, if the user accesses a site in a specific category, the monitoring unit can focus on monitoring the content of that site. This allows appropriate monitoring by filtering based on the user's current work. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI.

[0087] The monitoring unit can select the optimal monitoring means depending on the user's input method. For example, if the user uses voice input, the monitoring unit can perform monitoring using voice recognition technology. Furthermore, if the user uses text input, the monitoring unit can perform monitoring using text analysis technology. For example, if the user uses voice input, the monitoring unit can analyze the voice data and detect specific keywords or phrases. Furthermore, if the user uses image input, the monitoring unit can perform monitoring using image recognition technology. For example, if the user uses image input, the monitoring unit can analyze the image data and detect specific patterns or objects. This allows for effective monitoring by selecting the optimal monitoring means depending on the user's input method. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI.

[0088] The monitoring unit can estimate the user's emotions and determine the priority of text to monitor based on the estimated user's emotions. The monitoring unit can estimate the user's emotions using, for example, an emotion analysis algorithm. For example, the monitoring unit can analyze the user's input text and calculate an emotion score. The monitoring unit can also estimate emotions by analyzing the user's facial expressions and voice. For example, the monitoring unit can analyze the user's facial expression data captured with a camera to estimate emotions. The monitoring unit can also analyze the user's voice data recorded with a microphone to estimate emotions. The monitoring unit can also determine the priority of text to monitor based on the estimated user's emotions. For example, if the user is feeling stressed, it can prioritize monitoring of text with high importance. On the other hand, if the user is relaxed, it can monitor all texts equally. Thus, by determining the priority of text to monitor based on the user's emotions, it is possible to prioritize monitoring of important text. Emotion estimation is realized using, for example, an emotion estimation function using an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the monitoring unit may be performed using AI, or may be performed without using AI.

[0089] The monitoring unit can prioritize monitoring highly relevant text in consideration of the user's geographical location information. For example, when the user is in a specific area, the monitoring unit can prioritize monitoring text related to that area. Furthermore, when the user is moving, the monitoring unit can also monitor related text based on the user's current location. For example, when the user is in a specific area, the monitoring unit can focus on monitoring keywords and phrases related to that area. Furthermore, when the user stays in a specific location for a long time, the monitoring unit can prioritize monitoring text related to that location. In this way, highly relevant text can be prioritized in consideration of the user's geographical location information. Some or all of the above-described processing in the monitoring unit may be performed, for example, using AI or without using AI.

[0090] The monitoring unit can analyze the user's social media activity and monitor related text. The monitoring unit can monitor related text based on, for example, content posted by the user on social media. The monitoring unit can also monitor related text with reference to the activities of the user's friends on social media. For example, if the user posts on social media containing a specific keyword, the monitoring unit can focus on monitoring text related to the keyword. The monitoring unit can also monitor related text based on the user's check-in information on social media. In this way, the user's social media activity can be analyzed and related text can be monitored. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI.

[0091] The monitoring unit can customize the monitoring method by reflecting the user's past feedback. The monitoring unit can adjust the monitoring method based on, for example, feedback provided by the user in the past. The monitoring unit can also strengthen specific monitoring items based on the user's past feedback. For example, if the user has provided feedback on a specific keyword in the past, the monitoring unit can strengthen monitoring related to that keyword. The monitoring unit can also analyze the user's past feedback and suggest an optimal monitoring method. In this way, the monitoring method can be customized by reflecting the user's past feedback, making it possible to provide an optimal monitoring method. Some or all of the above-described processing in the monitoring unit may be performed, for example, using AI or without using AI.

[0092] The detection unit can estimate a user's emotions and adjust the detection criteria for malicious words and actions based on the estimated user emotions. The detection unit can estimate a user's emotions using, for example, an emotion analysis algorithm. For example, the detection unit can analyze a user's input text and calculate an emotion score. The detection unit can also estimate emotions by analyzing a user's facial expressions and voice. For example, the detection unit can analyze a user's facial expression data captured with a camera to estimate emotions. The detection unit can also analyze a user's voice data recorded with a microphone to estimate emotions. The detection unit can also adjust the detection criteria for malicious words and actions based on the estimated user emotions. For example, if a user is stressed, the detection criteria can be relaxed to reduce false positives. On the other hand, if a user is relaxed, the detection criteria can be tightened to perform more detailed detection. Thus, by adjusting the detection criteria for malicious words and actions based on the user's emotions, false positives can be reduced. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using AI, or may be performed without using AI.

[0093] The detection unit can optimize the detection algorithm by referring to past fraudulent behavior data. The detection unit can, for example, adjust the detection algorithm based on the past fraudulent behavior data. The detection unit can also extract specific patterns from the past fraudulent behavior data and reflect them in the detection algorithm. For example, the detection unit can analyze the past fraudulent behavior data and extract specific keywords or behavioral patterns. The detection unit can also improve the accuracy of the detection algorithm based on the extracted patterns. Furthermore, the detection unit can dynamically optimize the detection algorithm by referring to the past fraudulent behavior data in real time. In this way, the detection algorithm can be optimized by referring to the past fraudulent behavior data. Some or all of the above-described processing in the detection unit may be performed, for example, using AI or without using AI.

[0094] The detection unit can perform detection taking into account user attribute information. The detection unit can adjust detection criteria based on, for example, the user's occupation or job title. The detection unit can also optimize the detection algorithm based on the user's age and gender. For example, the detection unit can focus on monitoring specific keywords or behavioral patterns depending on the user's occupation. The detection unit can also adjust parameters of the detection algorithm based on the user's age and gender. Furthermore, the detection unit can customize the detection algorithm based on the user's past behavioral history. In this way, detection can be performed taking into account the user's attribute information, thereby enabling more accurate detection. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI.

[0095] The detection unit can weight detection based on the frequency of user input. For example, if the user inputs frequently, the detection unit can set a high weight for detection. Furthermore, if the user inputs infrequently, the detection unit can set a low weight for detection. For example, the detection unit can analyze the frequency of user input and assign a high weight to frequently input keywords or phrases. Furthermore, the detection unit can assign a low weight to infrequently input keywords or phrases. Furthermore, the detection unit can monitor the frequency of user input in real time and dynamically adjust the weight. In this way, appropriate detection can be performed by weighting detection based on the frequency of user input. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI.

[0096] The detection unit can estimate a user's emotion and adjust the display method of the detection result based on the estimated user's emotion. The detection unit can estimate the user's emotion using, for example, an emotion analysis algorithm. For example, the detection unit can analyze the user's input text and calculate an emotion score. The detection unit can also estimate the emotion by analyzing the user's facial expression and voice. For example, the detection unit can analyze the user's facial expression data captured by a camera to estimate the emotion. The detection unit can also analyze the user's voice data recorded by a microphone to estimate the emotion. The detection unit can also adjust the display method of the detection result based on the estimated user's emotion. For example, if the user is nervous, a simple, highly visible display method can be provided. On the other hand, if the user is relaxed, a display method including detailed information can be provided. As a result, by adjusting the display method of the detection result based on the user's emotion, a highly visible display method can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using AI, for example, or may be performed without using AI.

[0097] The detection unit can perform detection by taking into account the geographic distribution of text. The detection unit can adjust the detection algorithm based on, for example, fraudulent behavior that occurs frequently in a specific region. The detection unit can also strengthen detection in a specific region based on the geographic distribution. For example, the detection unit can extract keywords or behavioral patterns that occur frequently in a specific region and strengthen detection in that region. The detection unit can also analyze the geographic distribution and propose an optimal detection method. In this way, by performing detection by taking into account the geographic distribution of text, it is possible to strengthen detection in a specific region. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or without using AI.

[0098] The detection unit can improve the accuracy of detection by referring to related literature. The detection unit can, for example, optimize the detection algorithm based on the related literature. The detection unit can also extract the latest fraudulent behavior patterns from the related literature and reflect them in the detection algorithm. For example, the detection unit can learn the latest fraudulent behavior patterns by referring to the related literature. The detection unit can also adjust the parameters of the detection algorithm based on the related literature. Furthermore, the detection unit can dynamically optimize the detection algorithm by referring to the related literature in real time. In this way, the accuracy of the detection algorithm can be improved by referring to the related literature. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or without using AI.

[0099] The detection unit can perform detection taking into account the market value of the text. For example, the detection unit can prioritize detection of text with high market value. The detection unit can also exclude text with low market value from detection. For example, the detection unit can analyze the market value of the text and focus on detecting keywords and phrases with high market value. The detection unit can also filter out text with low market value and exclude it from detection. Furthermore, the detection unit can evaluate the market value of the text in real time and dynamically adjust the detection criteria. In this way, important text can be detected with priority by taking the market value of the text into consideration. Some or all of the above-described processing in the detection unit may be performed, for example, using AI or without using AI.

[0100] The notification unit can estimate the user's emotion and adjust the alert notification method based on the estimated user's emotion. The notification unit can estimate the user's emotion using, for example, an emotion analysis algorithm. For example, the notification unit can analyze the user's input text and calculate an emotion score. The notification unit can also estimate the emotion by analyzing the user's facial expression and voice. For example, the notification unit can analyze the user's facial expression data captured with a camera and estimate the emotion. The notification unit can also analyze the user's voice data recorded with a microphone and estimate the emotion. The notification unit can also adjust the alert notification method based on the estimated user's emotion. For example, if the user is nervous, the alert can be notified in a calm tone. On the other hand, if the user is relaxed, the alert can be notified in a bright tone. This allows for appropriate notification by adjusting the alert notification method based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the notification unit may be performed using AI, for example, or may be performed without using AI.

[0101] The notification unit can select the optimal notification method by referring to past notification history. The notification unit can select the optimal notification method based on, for example, the past notification history. The notification unit can also enhance a specific notification method based on the past notification history. For example, the notification unit can analyze the past notification history and select the optimal notification method for a specific keyword or phrase. The notification unit can also adjust the timing and frequency of notifications based on the past notification history. Furthermore, the notification unit can dynamically optimize the notification method by referring to the past notification history in real time. In this way, the optimal notification method can be selected by referring to the past notification history. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or without using AI.

[0102] The notification unit can customize the notification content based on the user's current situation. For example, when the user is in a meeting, the notification unit can provide a quiet notification method. Furthermore, when the user is on the move, the notification unit can provide concise notification content. For example, when the user is in a meeting, the notification unit can notify the user by vibrating or in silent mode. Furthermore, when the user is on the move, the notification unit can notify the user by a short message or a notification that focuses on the main points. Furthermore, when the user is on a break, the notification unit can provide detailed notification content. In this way, by customizing the notification content based on the user's current situation, appropriate notification can be provided. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or without using AI.

[0103] The notification unit can improve the notification method by reflecting user feedback. The notification unit can adjust the notification method based on, for example, feedback provided by the user in the past. The notification unit can also enhance a specific notification method based on the user's past feedback. For example, if the user has provided feedback on a specific notification method in the past, the notification unit can improve the notification method. The notification unit can also analyze the user's past feedback and suggest an optimal notification method. In this way, the notification method can be improved by reflecting the user's feedback, thereby providing an optimal notification method. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or without using AI.

[0104] The notification unit can estimate a user's emotion and determine the priority of notifications based on the estimated user's emotion. The notification unit can estimate the user's emotion using, for example, an emotion analysis algorithm. For example, the notification unit can analyze the user's input text and calculate an emotion score. The notification unit can also estimate the emotion by analyzing the user's facial expression and voice. For example, the notification unit can analyze the user's facial expression data captured with a camera and estimate the emotion. The notification unit can also analyze the user's voice data recorded with a microphone and estimate the emotion. The notification unit can also determine the priority of notifications based on the estimated user's emotion. For example, if the user is nervous, notifications with high importance can be displayed with priority. On the other hand, if the user is relaxed, all notifications can be displayed equally. In this way, by determining the priority of notifications based on the user's emotion, important notifications can be displayed with priority. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the notification unit may be performed using AI, for example, or may be performed without using AI.

[0105] The notification unit can select the optimal notification method taking into account the user's geographical location information. For example, when the user is in a specific area, the notification unit can prioritize displaying notifications related to that area. Furthermore, when the user is moving, the notification unit can also display related notifications based on the user's current location. For example, when the user is in a specific area, the notification unit can prioritize notifications related to keywords and phrases related to that area. Furthermore, when the user is staying in a specific location for a long time, the notification unit can prioritize displaying notifications related to that location. In this way, by selecting the optimal notification method taking into account the user's geographical location information, it is possible to provide highly relevant notifications. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or without using AI.

[0106] The notification unit can customize the notification content by analyzing the user's social media activity. The notification unit can display relevant notifications based on, for example, content posted by the user on social media. The notification unit can also display relevant notifications by referring to the activities of the user's friends on social media. For example, if the user posts on social media containing a specific keyword, the notification unit can prioritize notifications related to the keyword. The notification unit can also display relevant notifications based on the user's check-in information on social media. In this way, the notification content can be customized by analyzing the user's social media activity, thereby providing relevant notifications. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or without AI.

[0107] The notification unit can customize the notification method by reflecting the user's past feedback. The notification unit can adjust the notification method based on, for example, feedback provided by the user in the past. The notification unit can also enhance a specific notification method based on the user's past feedback. For example, if the user has provided feedback on a specific notification method in the past, the notification unit can improve the notification method. The notification unit can also analyze the user's past feedback and suggest an optimal notification method. In this way, the notification method can be customized by reflecting the user's past feedback, thereby providing an optimal notification method. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or without using AI.

[0108] The word cloud unit can estimate a user's emotion and adjust a word cloud generation method based on the estimated user's emotion. The word cloud unit can estimate a user's emotion using, for example, an emotion analysis algorithm. For example, the word cloud unit can analyze a user's input text and calculate an emotion score. The word cloud unit can also estimate an emotion by analyzing a user's facial expression or voice. For example, the word cloud unit can analyze a user's facial expression data captured with a camera and estimate an emotion. The word cloud unit can also analyze a user's voice data recorded with a microphone and estimate an emotion. The word cloud unit can also adjust a word cloud generation method based on the estimated user's emotion. For example, if a user is stressed, a simple word cloud can be generated. On the other hand, if a user is relaxed, a detailed word cloud can be generated. Thus, an appropriate word cloud can be generated by adjusting the word cloud generation method based on the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the word cloud section may be performed using AI, for example, or may be performed without using AI.

[0109] The word cloud unit can adjust the level of detail of the word cloud based on the importance of the text. For example, the word cloud unit can generate a detailed word cloud based on text with high importance. The word cloud unit can also generate a simple word cloud based on text with low importance. For example, the word cloud unit can analyze the importance of the text and extract frequently occurring keywords and phrases. The word cloud unit can also display keywords with high importance in a larger size and keywords with low importance in a smaller size. Furthermore, the word cloud unit can adjust the color and font based on the importance of the text to provide a visually easy-to-understand display. In this way, by adjusting the level of detail of the word cloud based on the importance of the text, an appropriate word cloud can be generated. Some or all of the above-described processing in the word cloud unit may be performed, for example, using AI or without AI.

[0110] The word cloud unit can apply different algorithms depending on the category of the text. For example, the word cloud unit can apply a business algorithm to business-related text. The word cloud unit can also apply an entertainment algorithm to entertainment-related text. For example, the word cloud unit can analyze the category of the text and select an algorithm according to the category. The word cloud unit can also apply an education algorithm to education-related text. Furthermore, the word cloud unit can adjust colors and fonts based on the text category to provide a visually easy-to-understand display. In this way, by applying different algorithms depending on the text category, an appropriate word cloud can be generated. Some or all of the above-mentioned processing in the word cloud unit may be performed using, for example, AI, or may be performed without using AI.

[0111] The word cloud unit can improve the accuracy of generation by referring to the user's past word cloud results. For example, the word cloud unit can adjust the generation algorithm based on the user's past word cloud results. The word cloud unit can also extract specific patterns from the user's past word cloud results and reflect them in the generation algorithm. For example, the word cloud unit can analyze past word cloud results and extract frequently occurring keywords or phrases. The word cloud unit can also improve the accuracy of the generation algorithm based on the extracted patterns. Furthermore, the word cloud unit can refer to past word cloud results in real time and dynamically optimize the generation algorithm. This can improve the accuracy of generation by referring to the user's past word cloud results. Some or all of the above-described processing in the word cloud unit may be performed, for example, using AI or without AI.

[0112] The word cloud unit can estimate a user's emotion and adjust the display method of the word cloud based on the estimated user's emotion. The word cloud unit can estimate a user's emotion using, for example, an emotion analysis algorithm. For example, the word cloud unit can analyze a user's input text and calculate an emotion score. The word cloud unit can also estimate an emotion by analyzing a user's facial expression or voice. For example, the word cloud unit can analyze a user's facial expression data captured with a camera and estimate an emotion. The word cloud unit can also analyze a user's voice data recorded with a microphone and estimate an emotion. The word cloud unit can also adjust the display method of the word cloud based on the estimated user's emotion. For example, if the user is nervous, a simple, highly visible display method can be provided. On the other hand, if the user is relaxed, a display method including detailed information can be provided. Thus, by adjusting the display method of the word cloud based on the user's emotion, a highly visible display method can be provided. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the word cloud section may be performed using AI, or may be performed without using AI.

[0113] The word cloud unit can determine the priority of word clouds based on the time of text submission. The word cloud unit can determine the priority of word clouds based on, for example, the most recent text. The word cloud unit can also determine the priority of word clouds based on older text. For example, the word cloud unit can analyze the time of text submission and prioritize displaying the most recent text. The word cloud unit can also filter older text and adjust the display priority. Furthermore, the word cloud unit can evaluate the time of text submission in real time and dynamically adjust the priority. In this way, by determining the priority of word clouds based on the time of text submission, the most recent information can be prioritized and displayed. Some or all of the above-described processing in the word cloud unit can be performed, for example, using AI or without AI.

[0114] The word cloud unit can adjust the order of the word cloud based on the relevance of the text. The word cloud unit can, for example, determine the order of the word cloud based on highly relevant text. The word cloud unit can also determine the order of the word cloud based on less relevant text. For example, the word cloud unit can analyze the relevance of the text and prioritize displaying highly relevant keywords and phrases. The word cloud unit can also filter less relevant keywords and phrases and adjust the display order. Furthermore, the word cloud unit can evaluate the relevance of the text in real time and dynamically adjust the order. In this way, by adjusting the order of the word cloud based on the relevance of the text, highly relevant information can be prioritized and displayed. Some or all of the above-described processing in the word cloud unit may be performed, for example, using AI or without AI.

[0115] The word cloud unit can adjust the use of technical terms in the word cloud according to the user's level of expertise. For example, the word cloud unit can provide a word cloud that uses a lot of technical terms to a user with high expertise. The word cloud unit can also provide a word cloud with less technical terms to a user with low expertise. For example, the word cloud unit can analyze the user's level of expertise and adjust the use of technical terms. The word cloud unit can also select keywords and phrases to display based on the user's level of expertise. Furthermore, the word cloud unit can evaluate the user's level of expertise in real time and dynamically adjust the use of technical terms. In this way, appropriate information can be provided by adjusting the use of technical terms in the word cloud according to the user's level of expertise. Some or all of the above-described processing in the word cloud unit can be performed, for example, using AI or without AI.

[0116] The visualization unit can estimate a user's emotion and adjust the display method of the visualization based on the estimated user's emotion. The visualization unit can estimate the user's emotion using, for example, an emotion analysis algorithm. For example, the visualization unit can analyze the user's input text and calculate an emotion score. The visualization unit can also estimate the emotion by analyzing the user's facial expression or voice. For example, the visualization unit can analyze the user's facial expression data captured with a camera and estimate the emotion. The visualization unit can also analyze the user's voice data recorded with a microphone and estimate the emotion. The visualization unit can also adjust the display method of the visualization based on the estimated user's emotion. For example, if the user is nervous, a simple, highly visible display method can be provided. On the other hand, if the user is relaxed, a display method including detailed information can be provided. In this way, by adjusting the display method of the visualization based on the user's emotion, a highly visible display method can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI.

[0117] The visualization unit can select the optimal display method by referring to the user's past operation history. The visualization unit can select the optimal display method based on, for example, the user's past operation history. The visualization unit can also enhance a specific display method based on the user's past operation history. For example, the visualization unit can analyze the user's past operation history and select the optimal display method for a specific keyword or phrase. The visualization unit can also adjust the timing and frequency of display based on the past operation history. Furthermore, the visualization unit can refer to the past operation history in real time and dynamically optimize the display method. In this way, the optimal display method can be selected by referring to the user's past operation history. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without using AI.

[0118] The visualization unit can customize the display content according to the user's current task. For example, when the user is creating a document, the visualization unit can display related information. Furthermore, when the user is sending an email, the visualization unit can also display related information. For example, when the user is creating a document, the visualization unit can display keywords and phrases related to the document content. Furthermore, when the user is browsing the web, the visualization unit can display related information based on the content of the accessed site. Furthermore, the visualization unit can evaluate the user's current task in real time and dynamically customize the display content. This allows the display content to be customized according to the user's current task, thereby providing appropriate information. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI, or may be performed without using AI.

[0119] The visualization unit can improve the display method by reflecting user feedback. The visualization unit can adjust the display method based on, for example, feedback provided by the user in the past. The visualization unit can also enhance a specific display method based on the user's past feedback. For example, if the user provided feedback on a specific display method in the past, the visualization unit can improve the display method. The visualization unit can also analyze the user's past feedback and suggest an optimal display method. In this way, the display method can be improved by reflecting the user's feedback, thereby providing an optimal display method. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without using AI.

[0120] The visualization unit can estimate a user's emotion and adjust the visualization operation procedure based on the estimated user's emotion. The visualization unit can estimate the user's emotion using, for example, an emotion analysis algorithm. For example, the visualization unit can analyze the user's input text and calculate an emotion score. The visualization unit can also estimate the emotion by analyzing the user's facial expression and voice. For example, the visualization unit can analyze the user's facial expression data captured with a camera and estimate the emotion. The visualization unit can also analyze the user's voice data recorded with a microphone and estimate the emotion. The visualization unit can also adjust the visualization operation procedure based on the estimated user's emotion. For example, if the user is nervous, simple and intuitive operation procedures can be provided. On the other hand, if the user is relaxed, detailed operation procedures can be provided. In this way, by adjusting the visualization operation procedure based on the user's emotion, intuitive operation procedures can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI.

[0121] The visualization unit can select the optimal display method by taking into account the user's device information. For example, if the user is using a smartphone, the visualization unit can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the visualization unit can also provide a display method optimized for a large screen. For example, the visualization unit can analyze the user's device information and select a display method that matches the type of device. Furthermore, if the user is using a smartwatch, the visualization unit can also provide a simple and highly visible display method. Furthermore, the visualization unit can evaluate the device information in real time and dynamically optimize the display method. In this way, the optimal display method can be selected by taking into account the user's device information, thereby providing the optimal display method. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without using AI.

[0122] The visualization unit can make the display content multilingual according to the user's language setting. The visualization unit can automatically set the display content based on, for example, the language setting of the user's device. The visualization unit can also provide a language switching function when the user uses multiple languages. For example, the visualization unit can analyze the user's language setting and provide display content according to the set language. Furthermore, when the user selects a specific language, the visualization unit can provide display content in that language. Furthermore, the visualization unit can evaluate the language setting in real time and dynamically make the display content multilingual. This makes it possible to provide appropriate information by making the display content multilingual according to the user's language setting. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without AI.

[0123] The visualization unit can customize the display content based on the user's occupation and lifestyle. For example, if the user is a businessman, the visualization unit can prioritize displaying business-related information. Furthermore, if the user is a student, the visualization unit can prioritize displaying education-related information. For example, the visualization unit can analyze the user's occupation information and provide display content according to the occupation. Furthermore, the visualization unit can analyze the user's lifestyle and provide display content according to the lifestyle. Furthermore, the visualization unit can evaluate the occupation and lifestyle information in real time and dynamically customize the display content. In this way, appropriate information can be provided by customizing the display content based on the user's occupation and lifestyle. Some or all of the above-described processing in the visualization unit may be performed, for example, using AI or without using AI. === Hard Collateral 1-1 === Each of the above-described elements, including the monitoring unit, detection unit, word cloud unit, visualization unit, and emotion estimation function, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the monitoring unit can monitor employee input text in real time using a keylogger in the smart device 14, and detect fraudulent words or actions using the specific processing unit 290 in the data processing device 12. The detection unit can be implemented, for example, by the specific processing unit 290 in the data processing device 12, and the notification unit can send an alert by email based on the detected fraudulent words or actions. The word cloud unit can be implemented, for example, by the control unit 46A of the smart device 14, and can convert non-problematic text into a word cloud, which the visualization unit can visually display. The emotion estimation function can be implemented, for example, by the specific processing unit 290 in the data processing device 12, and can adjust the monitoring frequency based on the user's emotions. === Hard Collateral 1-2 === Each of the multiple elements, including the monitoring unit, detection unit, word cloud unit, visualization unit, and emotion estimation function, described above, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the monitoring unit can monitor an employee's input text in real time using a keylogger in the smart glasses 214, and detect fraudulent words or actions using the specific processing unit 290 in the data processing device 12. The detection unit is implemented, for example, by the specific processing unit 290 in the data processing device 12, and the notification unit sends an alert by email based on the detected fraudulent words or actions. The word cloud unit is implemented, for example, by the control unit 46A of the smart glasses 214, and converts non-problematic text into a word cloud, which the visualization unit visually displays. The emotion estimation function is implemented, for example, by the specific processing unit 290 in the data processing device 12, and adjusts the monitoring frequency based on the user's emotion. === Hard Collateral 1-3 === Each of the multiple elements, including the monitoring unit, detection unit, word cloud unit, visualization unit, and emotion estimation function, is implemented, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the monitoring unit can monitor employee input text in real time using a keylogger in the headset-type terminal 314, and detect fraudulent words or actions using the specific processing unit 290 in the data processing device 12. The detection unit is implemented, for example, by the specific processing unit 290 in the data processing device 12, and the notification unit sends an alert by email based on the detected fraudulent words or actions. The word cloud unit is implemented, for example, by the control unit 46A of the headset-type terminal 314, and creates a word cloud of non-problematic text, which the visualization unit visually displays. The emotion estimation function is implemented, for example, by the specific processing unit 290 in the data processing device 12, and adjusts the monitoring frequency based on the user's emotion. === Hard Collateral 1-4 === Each of the above-described elements, including the monitoring unit, detection unit, word cloud unit, visualization unit, and emotion estimation function, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the monitoring unit can monitor employee input text in real time using the robot 414's keylogger and detect fraudulent words or actions using the specific processing unit 290 of the data processing device 12. The detection unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and the notification unit sends an alert by email based on the detected fraudulent words or actions. The word cloud unit is implemented, for example, by the control unit 46A of the robot 414, and converts non-problematic text into a word cloud, which the visualization unit visually displays. The emotion estimation function is implemented, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the monitoring frequency based on the user's emotions.

[0124] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0125] The monitoring unit can analyze the user's input speed and detect abnormal changes in speed. For example, if the input speed suddenly slows down from normal, the user may be experiencing difficulty, so an alert can be issued. Also, if the input speed suddenly increases, the user may be feeling impatient, so a notification can be sent to warn them. Furthermore, by learning the change patterns of input speed and detecting abnormal patterns, more accurate monitoring can be performed.

[0126] The detection unit can identify potential stressors based on the user's input. For example, if negative words are frequently entered, the user may be feeling stressed, and appropriate support can be provided. Furthermore, if a specific keyword is used repeatedly, there may be a problem related to that keyword, and a detailed investigation can be conducted. Furthermore, by analyzing the user's input emotional state in real time, appropriate responses can be taken.

[0127] The notification unit can send alerts at optimal timing, taking into account the user's schedule information. For example, if the user is in a meeting, the alert can be temporarily suspended and the notification can be sent after the meeting ends. Also, if the user is on a break, an alert can be sent immediately, encouraging a prompt response. Furthermore, by obtaining the user's schedule information in real time and sending notifications at optimal timing, the burden on the user can be reduced.

[0128] The word cloud unit can generate a customized word cloud based on a user's interests. For example, if a user is interested in a particular topic, it can prioritize displaying words related to that topic. It can also analyze the user's past search history and browsing history to generate a word cloud based on their interests. Furthermore, by reflecting user feedback and continuously improving the content of the word cloud display, it is possible to provide more personalized information.

[0129] The visualization unit can adjust the display method taking into account the remaining battery level of the user's device. For example, when the battery level is low, a simple, energy-saving display method can be provided. When the battery level is sufficient, a display method including detailed information can be provided. Furthermore, by monitoring the remaining battery level in real time and dynamically adjusting the display method, the battery life of the user's device can be extended.

[0130] The monitoring unit can identify potential health risks based on the user's input. For example, if words such as "tired" or "painful" are frequently input, the user may be experiencing health problems, and appropriate support can be provided. Furthermore, if keywords related to a specific symptom are repeatedly used, there may be a problem related to that symptom, and a more detailed investigation can be conducted. Furthermore, by analyzing the sentiment of the input and understanding the user's health condition in real time, appropriate measures can be taken.

[0131] The detection unit can identify potential learning needs based on the user's input. For example, if the user frequently inputs words such as "I don't understand" or "teach me," the unit may be in need of learning support, and appropriate resources can be provided. Furthermore, if keywords related to a specific topic are repeatedly used, learning resources related to that topic can be provided. Furthermore, by analyzing the input content and understanding the user's learning needs in real time, appropriate support can be provided.

[0132] The notification unit can analyze the user's past alert response history and select the optimal notification method. For example, it can identify patterns of alerts that were immediately responded to in the past and adjust the notification method based on those patterns. It can also analyze patterns of alerts that were ignored in the past and select a notification method that avoids those patterns. Furthermore, by referencing the past alert response history in real time and dynamically optimizing the notification method, the burden on the user can be reduced.

[0133] The word cloud unit can estimate the user's emotions and adjust the color of the word cloud based on the estimated user's emotions. For example, if the user has positive emotions, the word cloud can be displayed using bright colors. If the user has negative emotions, the word cloud can be displayed using subdued colors. Furthermore, by grasping the user's emotional state in real time and dynamically adjusting the colors, a visually pleasant display can be provided.

[0134] The visualization unit can select the optimal display layout by referring to the user's past operation history. For example, it can identify layouts that have been frequently used in the past and display those layouts preferentially. It can also analyze layouts that have been avoided in the past and select a display method that avoids those layouts. Furthermore, by referring to the past operation history in real time and dynamically optimizing the display layout, it is possible to improve the user's operation efficiency.

[0135] The processing flow of the second embodiment will be briefly explained below.

[0136] Step 1: The monitoring unit is installed on the employee's PC and monitors the text entered in real time. For example, the monitoring unit can use a keylogger to record all text entered by the employee and monitor it in real time. The monitoring unit can also analyze the text entered and detect specific keywords or patterns. Step 2: The detection unit detects fraudulent words and actions from the text monitored by the monitoring unit. For example, the detection unit can detect fraudulent words based on a list of prohibited words. The detection unit can also detect fraudulent behavior such as spam and harassment. Furthermore, the detection unit can use AI to learn patterns of fraudulent behavior and improve detection accuracy. Step 3: The notification unit sends an email alert based on the malicious words and actions detected by the detection unit. For example, the notification unit can automatically send an email containing details of the detected malicious words and actions. The notification unit can also adjust the notification method depending on the importance of the alert. Step 4: The word cloud unit creates a word cloud from the non-problematic text monitored by the monitoring unit. For example, the word cloud unit can use a text mining algorithm to extract frequently occurring words and display them visually. The word cloud unit can also use natural language processing technology to analyze the content of the text and display it as a word cloud. Step 5: The visualization unit visualizes the word cloud generated by the word cloud unit. For example, the visualization unit can display the generated word cloud as a graph or chart, providing it in a visually easy-to-understand format. The visualization unit can also customize the display method of the word cloud to display it according to the user's needs.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0142] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0165] 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.

[0166] 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.

[0167] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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).

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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).

[0194] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0195] 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."

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0207] 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.

[0208] [Explanation of symbols]

[0209] 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 monitoring unit that monitors the input text in real time; a detection unit that detects fraudulent words or fraudulent behavior from the text monitored by the monitoring unit; a notification unit that notifies an alert by email based on fraudulent words or fraudulent behavior detected by the detection unit; a word cloud unit that generates a word cloud of the non-problematic text monitored by the monitoring unit; a visualization unit that visualizes the word cloud generated by the word cloud unit. A system characterized by:

2. The monitoring unit It is installed on employees' PCs and monitors the text they type in real time.

2. The system of claim 1.

3. The detection unit Detecting fraudulent words and actions from the text monitored by the monitoring unit 2. The system of claim 1.

4. The notification unit An alert is sent by email based on the malicious words and actions detected by the detection unit.

2. The system of claim 1.

5. The word cloud portion includes: The non-problematic text monitored by the monitoring unit is converted into a word cloud.

2. The system of claim 1.

6. The visualization unit Visualizing the word cloud generated by the word cloud unit 2. The system of claim 1.

7. The word cloud portion includes: Uses text mining algorithms to extract and visually display frequently occurring words 2. The system of claim 1.

8. The visualization unit Uses natural language processing technology to analyze employee opinions and feedback and display them as a word cloud 2. The system of claim 1.

Images