system

Abstract

The system according to this embodiment aims to detect slang related to crime from posts on social media and identify accounts that are highly likely to be involved in criminal activity. [Solution] The system according to the embodiment comprises a slang detection unit, a context analysis unit, and an account identification unit. The slang detection unit detects slang related to crime from posts on social media. The context analysis unit analyzes the context before and after the slang detected by the slang detection unit. The account identification unit identifies accounts that are highly likely to be involved in criminal activity based on the context analyzed by the context analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to efficiently detect jargon related to crimes from posts on SNS and identify accounts involved in criminal activities.

[0005] The system according to the embodiment aims to detect jargon related to crimes from posts on SNS and identify accounts highly likely to be involved in criminal activities.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a slang detection unit, a context analysis unit, and an account identification unit. The slang detection unit detects slang related to crime from posts on social media. The context analysis unit analyzes the context before and after the slang detected by the slang detection unit. The account identification unit identifies accounts that are highly likely to be involved in criminal activity based on the context analyzed by the context analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect slang related to crime from posts on social media and identify accounts that are highly likely to be involved in criminal activity. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The SNS crime-related post detection system according to an embodiment of the present invention is a system that quickly and accurately detects crime-related posts on SNS and prevents involvement in crime. This system uses AI to analyze slang and context on SNS and quickly and accurately detects posts soliciting illegal part-time jobs. For example, crime solicitations on SNS are increasing, and solicitations for illegal part-time jobs, in particular, are a serious problem, especially among young people. Conventional methods have had difficulty understanding slang and context, and crime solicitation posts have often been overlooked. In addition, users are often misled by false information and misinformation, and discerning accurate information has been a challenge. The present invention provides a system that uses AI to analyze slang and context on SNS and quickly and accurately detects posts soliciting illegal part-time jobs. Specifically, a slang detection engine detects crime-related slang with high accuracy, and context analysis understands the context before and after the slang. Furthermore, a dangerous account determination function identifies accounts that are highly likely to be involved in criminal activity. For example, if a post says, "Please hand over a specific item at a specific location at 10 AM tomorrow," the generating AI will determine from the context that "specific item" is a code word and judge that it is highly likely to be related to a crime. The generating AI will also regularly update its code word list to be able to handle new code words. This system will allow law enforcement agencies to monitor illegal activities on social media and contribute to crime prevention and ensuring the accuracy and safety of information. For example, it is often difficult to notice criminal recruitment on social media, and posts soliciting illegal part-time jobs are frequently overlooked. However, by introducing this system, criminal recruitment posts can be detected quickly and accurately, protecting the safety of young people. In this way, the social media crime-related post detection system can quickly and accurately detect crime-related posts on social media and prevent involvement in crime before it happens.

[0029] The SNS crime-related post detection system according to this embodiment comprises a slang detection unit, a context analysis unit, and an account identification unit. The slang detection unit detects slang related to crime from posts on SNS. The slang detection unit detects slang with high accuracy, for example, using natural language processing technology. The slang detection unit can also learn patterns of slang using machine learning algorithms and respond to new slang. Furthermore, the slang detection unit can monitor posts on SNS in real time and quickly detect slang related to crime. For example, the slang detection unit analyzes posts on SNS and detects specific keywords or phrases. The slang detection unit can also periodically update its slang list and respond to new slang. The context analysis unit analyzes the context before and after the slang detected by the slang detection unit. The context analysis unit understands the context and determines its intent, for example, using natural language processing technology. The context analysis unit can also learn patterns of context using machine learning algorithms and accurately determine the intent of the slang. Furthermore, the context analysis unit can analyze posts on social media in real time and quickly determine the intent of coded language. For example, the context analysis unit analyzes the context before and after coded language to determine its intent. The context analysis unit can also accurately determine the intent of coded language based on context, reducing false positives. The account identification unit identifies accounts that are likely to be involved in criminal activity based on the context analyzed by the context analysis unit. For example, the account identification unit can learn account patterns using machine learning algorithms to identify accounts that are likely to be involved in criminal activity. The account identification unit can also monitor posts on social media in real time and quickly identify accounts that are likely to be involved in criminal activity. Furthermore, the account identification unit can implement a scoring system to prioritize monitoring of high-risk accounts. For example, the account identification unit identifies accounts that are likely to be involved in criminal activity based on the frequency and context of coded language use. The account identification unit can also prioritize monitoring of high-risk accounts using a scoring system.As a result, the SNS crime-related post detection system according to this embodiment can quickly and accurately detect crime-related posts on SNS and prevent involvement in crimes.

[0030] The slang detection unit detects crime-related slang from posts on social media. The slang detection unit uses, for example, natural language processing techniques to detect slang with high accuracy. Specifically, it employs techniques such as tokenization, morphological analysis, part-of-speech tagging, and dependency structure analysis. This allows it to accurately grasp the meaning of words and phrases within posts and detect slang. Furthermore, the slang detection unit can learn slang patterns using machine learning algorithms and adapt to new slang. For example, it uses supervised learning to learn past crime-related post data and extract slang features. In addition, the slang detection unit can monitor social media posts in real time and quickly detect crime-related slang. Specifically, it uses streaming data processing technology to analyze social media post data in real time and detect slang. For example, the slang detection unit analyzes social media posts and detects specific keywords and phrases. The slang detection unit also periodically updates its slang list to adapt to new slang. A cloud-based database is used to quickly reflect the latest slang information in the slang list. This allows the slang detection unit to always perform highly accurate detection based on the latest slang information.

[0031] The context analysis unit analyzes the context surrounding the slang detected by the slang detection unit. The context analysis unit understands the context and determines its intent, for example, using natural language processing techniques. Specifically, it generates context vectors to understand the meaning of sentences for context analysis and uses these to analyze the intent of the slang. Furthermore, the context analysis unit can learn contextual patterns using machine learning algorithms to accurately determine the intent of slang. For example, it utilizes recurrent neural networks (RNNs) and transformer models using deep learning to learn long-term contextual dependencies. In addition, the context analysis unit can analyze posts on social media in real time and quickly determine the intent of slang. Specifically, it streams post data in real time and analyzes the context surrounding the slang. For example, the context analysis unit analyzes the context surrounding the slang and determines its intent. The context analysis unit can also accurately determine the intent of slang based on context, reducing false positives. As a result, the context analysis unit can analyze the intent of slang with high accuracy and improve the detection accuracy of crime-related posts.

[0032] The account identification unit identifies accounts that are highly likely to be involved in criminal activity based on the context analyzed by the context analysis unit. For example, the account identification unit uses machine learning algorithms to learn account patterns and identify accounts likely to be involved in criminal activity. Specifically, it uses data from past crime-related accounts to learn account characteristics and identify new crime-related accounts. Furthermore, the account identification unit can monitor social media posts in real time and quickly identify accounts likely to be involved in criminal activity. Specifically, it analyzes post data in real time to identify accounts that post crime-related slang or context. In addition, the account identification unit can implement a scoring system to prioritize monitoring of high-risk accounts. For example, the account identification unit identifies accounts likely to be involved in criminal activity based on the frequency and context of slang use. The scoring system calculates a score based on each account's post content and activity history, prioritizing the monitoring of high-risk accounts. This allows the account identification unit to quickly and accurately identify accounts that are highly likely to be involved in criminal activity, thereby contributing to crime prevention.

[0033] The slang detection unit can detect crime-related slang from social media posts with high accuracy. The slang detection unit uses, for example, natural language processing technology to detect slang with high accuracy. Furthermore, the slang detection unit can learn slang patterns using machine learning algorithms and adapt to new slang. In addition, the slang detection unit can monitor social media posts in real time and quickly detect crime-related slang. This ensures that crime recruitment posts are not missed by detecting crime-related slang with high accuracy. Some or all of the above processing in the slang detection unit may be performed using, for example, AI, or without AI. For example, the slang detection unit can input social media posts into an AI and have the AI ​​perform slang detection.

[0034] The slang detection unit can continuously update its slang list in response to social trends and the emergence of new slang. For example, the slang detection unit can analyze news articles and social media trends to detect new slang. It can also learn new slang patterns using machine learning algorithms and update its slang list. Furthermore, the slang detection unit can monitor social media posts in real time to quickly detect new slang and update its slang list. This maintains detection accuracy by enabling it to respond to new slang. Some or all of the above processes in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input news articles and social media trends into an AI and have the AI ​​perform the detection of new slang and update the slang list.

[0035] The context analysis unit can understand the context surrounding slang and determine its intent. For example, the context analysis unit uses natural language processing technology to understand the context and determine its intent. Furthermore, the context analysis unit can learn contextual patterns using machine learning algorithms to accurately determine the intent of slang. In addition, the context analysis unit can analyze social media posts in real time and quickly determine the intent of slang. This allows for accurate determination of slang intent based on context and reduces false positives. Some or all of the above-described processes in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can input the context surrounding slang into an AI and have the AI ​​perform contextual understanding and intent determination.

[0036] The context analysis unit can accurately determine the intent of slang based on context, thereby reducing false positives. For example, the context analysis unit uses natural language processing techniques to understand the context and determine its intent. Furthermore, the context analysis unit can learn contextual patterns using machine learning algorithms to accurately determine the intent of slang. In addition, the context analysis unit can analyze social media posts in real time and quickly determine the intent of slang. This reduces false positives and provides accurate information. Some or all of the above-described processes in the context analysis unit may be performed using AI, or not. For example, the context analysis unit can input the context before and after the slang into the AI, allowing the AI ​​to understand the context and determine the intent.

[0037] The account identification unit can identify accounts that are highly likely to be involved in criminal activity based on the frequency and context of slang usage. For example, the account identification unit can use machine learning algorithms to learn account patterns and identify accounts likely to be involved in criminal activity. Furthermore, the account identification unit can monitor social media posts in real time and quickly identify accounts likely to be involved in criminal activity. In addition, the account identification unit can implement a scoring system to prioritize monitoring of high-risk accounts. This contributes to crime prevention by identifying accounts likely to be involved in criminal activity. Some or all of the above processes in the account identification unit may be performed using AI, or not. For example, the account identification unit can input the frequency and context of slang usage into an AI and have the AI ​​identify accounts likely to be involved in criminal activity.

[0038] The account identification unit can implement a scoring system and prioritize monitoring of high-risk accounts. For example, the account identification unit can use machine learning algorithms to learn account patterns and identify high-risk accounts. Furthermore, the account identification unit can monitor social media posts in real time and quickly identify high-risk accounts. In addition, the account identification unit can use the scoring system to prioritize monitoring of high-risk accounts. This contributes to crime prevention by prioritizing the monitoring of high-risk accounts. Some or all of the above processes in the account identification unit may be performed using AI, or not. For example, the account identification unit can input the scoring system into an AI and have the AI ​​perform the identification and monitoring of high-risk accounts.

[0039] The slang detection unit can improve the accuracy of slang detection by considering the time of day and frequency of posts when detecting slang. For example, the slang detection unit analyzes the time of day and frequency of posts and adjusts the accuracy of slang detection. The slang detection unit can also improve the accuracy of slang detection by learning patterns of time of day and frequency using machine learning algorithms. Furthermore, the slang detection unit can monitor posts on social media in real time and adjust the accuracy of slang detection based on the time of day and frequency. This improves the accuracy of slang detection by considering the time of day and frequency of posts. Some or all of the above processing in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input post time of day and frequency data into AI and have the AI ​​perform the adjustment of slang detection accuracy.

[0040] The slang detection unit can improve the accuracy of slang detection by referring to the poster's past posting history when detecting slang. For example, the slang detection unit analyzes the poster's past posting history and adjusts the accuracy of slang detection. The slang detection unit can also improve the accuracy of slang detection by learning patterns in past posting history using machine learning algorithms. Furthermore, the slang detection unit can monitor posts on social media in real time and adjust the accuracy of slang detection based on past posting history. This improves the accuracy of slang detection by referring to the poster's past posting history. Some or all of the above processing in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input the poster's past posting history data into AI and have the AI ​​perform the adjustment of the slang detection accuracy.

[0041] The slang detection unit can improve the accuracy of slang detection by considering the geographical information of the post when detecting slang. For example, the slang detection unit can analyze the geographical information of the post and adjust the accuracy of slang detection. The slang detection unit can also improve the accuracy of slang detection by learning patterns in geographical information using machine learning algorithms. Furthermore, the slang detection unit can monitor posts on social media in real time and adjust the accuracy of slang detection based on geographical information. This improves the accuracy of slang detection by considering the geographical information of the post. Some or all of the above processing in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input geographical information data of the post into AI and have the AI ​​perform the adjustment of the slang detection accuracy.

[0042] The slang detection unit can improve the accuracy of slang detection by analyzing the content of images and videos in posts when detecting slang. For example, the slang detection unit can improve the accuracy of slang detection by analyzing text in images using image recognition technology. Furthermore, the slang detection unit can improve the accuracy of slang detection by analyzing audio in videos using audio analysis technology. In addition, the slang detection unit can monitor posts on social media in real time and adjust the accuracy of slang detection based on the content of images and videos. This improves the accuracy of slang detection by analyzing the content of images and videos in posts. Some or all of the above-described processes in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input image and video data from posts into an AI and have the AI ​​adjust the accuracy of slang detection.

[0043] The context analysis unit can apply different analysis algorithms depending on the category and topic of the post during context analysis. For example, the context analysis unit can analyze the category and topic of the post and select an appropriate analysis algorithm. Furthermore, the context analysis unit can learn category and topic patterns using machine learning algorithms and apply the optimal analysis algorithm. In addition, the context analysis unit can monitor posts on social media in real time and apply analysis algorithms based on category and topic. This improves the accuracy of context analysis by applying analysis algorithms according to the category and topic of the post. Some or all of the above processes in the context analysis unit may be performed using AI, or not. For example, the context analysis unit can input post category and topic data into AI and have the AI ​​select and apply analysis algorithms.

[0044] The context analysis unit can improve the accuracy of its analysis by considering the language and dialect of the post during context analysis. For example, the context analysis unit can analyze the language and dialect of the post and select an appropriate analysis algorithm. Furthermore, the context analysis unit can learn language and dialect patterns using machine learning algorithms and apply the optimal analysis algorithm. In addition, the context analysis unit can monitor posts on social media in real time and adjust the analysis accuracy based on language and dialect. This improves the accuracy of context analysis by considering the language and dialect of the post. Some or all of the above processes in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can input language and dialect data of the post into AI and have the AI ​​perform the adjustment of the analysis accuracy.

[0045] The context analysis unit can deepen its understanding of the context by analyzing the content of images and videos in posts during context analysis. For example, the context analysis unit can use image recognition technology to analyze text within images to deepen its understanding of the context. Furthermore, the context analysis unit can use speech analysis technology to analyze audio within videos to improve its understanding of the context. In addition, the context analysis unit can monitor posts on social media in real time and deepen its understanding of the context based on the content of images and videos. This allows for a deeper understanding of the context by analyzing the content of images and videos in posts. Some or all of the above-described processes in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can input image and video data from posts into an AI and have the AI ​​perform analysis to deepen its understanding of the context.

[0046] The context analysis unit can improve the accuracy of its analysis by referring to related links and quotations in posts during context analysis. For example, the context analysis unit can analyze related links within posts to deepen its understanding of the context. It can also refer to quotations to improve its understanding of the context. Furthermore, the context analysis unit can monitor posts on social media in real time and improve the accuracy of its analysis based on related links and quotations. This improves the accuracy of context analysis by referring to related links and quotations in posts. Some or all of the above processes in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can input related link and quotation data from posts into AI and have the AI ​​perform the improvement of analysis accuracy.

[0047] The account identification unit can improve its identification accuracy by referring to the poster's past behavioral history when identifying an account. For example, the account identification unit can analyze the poster's past behavioral history and adjust the identification accuracy. The account identification unit can also improve its identification accuracy by learning patterns in past behavioral history using machine learning algorithms. Furthermore, the account identification unit can monitor posts on social media in real time and adjust the identification accuracy based on past behavioral history. This improves the accuracy of account identification by referring to the poster's past behavioral history. Some or all of the above processes in the account identification unit may be performed using AI, for example, or without AI. For example, the account identification unit can input the poster's past behavioral history data into AI and have the AI ​​perform the adjustment of the identification accuracy.

[0048] The account identification unit can improve its identification accuracy by considering the poster's followers and following relationships when identifying accounts. For example, the account identification unit analyzes followers and following relationships and adjusts the identification accuracy. The account identification unit can also improve its identification accuracy by learning patterns of followers and following relationships using machine learning algorithms. Furthermore, the account identification unit can monitor posts on social media in real time and adjust the identification accuracy based on followers and following relationships. This improves the accuracy of account identification by considering the poster's followers and following relationships. Some or all of the above processing in the account identification unit may be performed using AI, for example, or without AI. For example, the account identification unit can input follower and following relationship data into AI and have the AI ​​perform the adjustment of the identification accuracy.

[0049] The account identification unit can improve its identification accuracy by considering the poster's geographical information when identifying accounts. For example, the account identification unit can analyze geographical information and adjust the identification accuracy. The account identification unit can also improve its identification accuracy by learning geographical information patterns using machine learning algorithms. Furthermore, the account identification unit can monitor posts on social media in real time and adjust the identification accuracy based on geographical information. This improves the accuracy of account identification by considering the poster's geographical information. Some or all of the above processes in the account identification unit may be performed using AI, for example, or without AI. For example, the account identification unit can input geographical information data into AI and have the AI ​​perform the adjustment of the identification accuracy.

[0050] The account identification unit can improve its identification accuracy by analyzing the poster's social media activity during account identification. For example, the account identification unit analyzes social media activity and adjusts the identification accuracy. The account identification unit can also improve its identification accuracy by learning patterns of social media activity using machine learning algorithms. Furthermore, the account identification unit can monitor posts on social media in real time and adjust the identification accuracy based on social media activity. This improves the accuracy of account identification by analyzing the poster's social media activity. Some or all of the above processing in the account identification unit may be performed using AI, for example, or without AI. For example, the account identification unit can input social media activity data into AI and have the AI ​​perform the adjustment of the identification accuracy.

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

[0052] A social media crime-related post detection system can analyze the geographical information of posts and monitor the frequency of crime-related posts in specific areas. For example, it can analyze the location information of posts to detect an increase in crime-related posts in a particular area. Furthermore, it can identify areas with high crime rates based on geographical information and prioritize monitoring posts in those areas. In addition, it can use geographical information to learn patterns of crime-related posts and build predictive models. This allows for understanding trends in crime-related posts in each region and implementing effective countermeasures.

[0053] A social media crime-related post detection system can analyze the content of images and videos posted and have the capability to detect crime-related visual content. For example, it can use image recognition technology to analyze text and objects within posted images and detect elements related to crime. It can also use audio analysis technology to analyze audio within videos and detect statements related to crime. Furthermore, based on the analysis results of the visual content, it can evaluate the risk level of posts and notify law enforcement agencies of high-risk posts. This improves the accuracy of analysis of posts that include not only text but also images and videos.

[0054] A social media crime-related post detection system can incorporate features to improve the accuracy of crime-related post detection by referencing a user's past posting history. For example, it can analyze a user's past posts and learn patterns related to crime. It can also prioritize monitoring of posts from specific users based on their past posting history. Furthermore, it can build a predictive model for crime-related posts using past posting history to predict future crime-related posts. This allows for improved accuracy in detecting crime-related posts by considering the user's past behavior.

[0055] A social media crime-related post detection system can have the capability to apply different analysis algorithms depending on the post's category and topic. For example, it can analyze the post's category and topic and select the appropriate analysis algorithm. It can also learn category and topic patterns using machine learning algorithms and apply the optimal analysis algorithm. Furthermore, it can monitor social media posts in real time and apply analysis algorithms based on category and topic. This allows for improved accuracy of contextual analysis by applying analysis algorithms according to the post's category and topic.

[0056] A social media crime-related post detection system can incorporate features to improve the accuracy of slang detection by considering the time of day and frequency of posts. For example, it can analyze the time of day and frequency of posts and adjust the accuracy of slang detection accordingly. Furthermore, it can use machine learning algorithms to learn patterns in time of day and frequency to improve slang detection accuracy. Additionally, it can monitor social media posts in real time and adjust slang detection accuracy based on time of day and frequency. This allows for improved slang detection accuracy by considering the time of day and frequency of posts.

[0057] A social media crime-related post detection system can be equipped with a function to improve the accuracy of contextual analysis by referring to related links and quotations within posts. For example, it can analyze related links within posts to deepen the understanding of the context. It can also refer to quotations to improve the understanding of the context. Furthermore, it can monitor posts on social media in real time and improve the accuracy of analysis based on related links and quotations. In this way, the accuracy of contextual analysis can be improved by referring to related links and quotations within posts.

[0058] The following briefly describes the processing flow for example form 1.

[0059] Step 1: The slang detection unit detects slang related to crime from posts on social media. The slang detection unit uses natural language processing technology and machine learning algorithms to detect slang with high accuracy and can handle new slang. It also monitors social media posts in real time and detects specific keywords and phrases. Furthermore, it regularly updates the slang list to handle new slang. Step 2: The context analysis unit analyzes the context surrounding the slang detected by the slang detection unit. The context analysis unit uses natural language processing techniques and machine learning algorithms to understand the context and determine its intent. Furthermore, it analyzes social media posts in real time to quickly determine the intent of the slang. It accurately determines the intent of the slang based on the context and reduces false positives. Step 3: The account identification unit identifies accounts that are likely to be involved in criminal activity based on the context analyzed by the context analysis unit. The account identification unit uses machine learning algorithms to learn account patterns and identify accounts that are likely to be involved in criminal activity. It also monitors posts on social media in real time and implements a scoring system to prioritize monitoring of high-risk accounts.

[0060] (Example of form 2) The SNS crime-related post detection system according to an embodiment of the present invention is a system that quickly and accurately detects crime-related posts on SNS and prevents involvement in crime. This system uses AI to analyze slang and context on SNS and quickly and accurately detects posts soliciting illegal part-time jobs. For example, crime solicitations on SNS are increasing, and solicitations for illegal part-time jobs, in particular, are a serious problem, especially among young people. Conventional methods have had difficulty understanding slang and context, and crime solicitation posts have often been overlooked. In addition, users are often misled by false information and misinformation, and discerning accurate information has been a challenge. The present invention provides a system that uses AI to analyze slang and context on SNS and quickly and accurately detects posts soliciting illegal part-time jobs. Specifically, a slang detection engine detects crime-related slang with high accuracy, and context analysis understands the context before and after the slang. Furthermore, a dangerous account determination function identifies accounts that are highly likely to be involved in criminal activity. For example, if a post says, "Please hand over a specific item at a specific location at 10 AM tomorrow," the generating AI will determine from the context that "specific item" is a code word and judge that it is highly likely to be related to a crime. The generating AI will also regularly update its code word list to be able to handle new code words. This system will allow law enforcement agencies to monitor illegal activities on social media and contribute to crime prevention and ensuring the accuracy and safety of information. For example, it is often difficult to notice criminal recruitment on social media, and posts soliciting illegal part-time jobs are frequently overlooked. However, by introducing this system, criminal recruitment posts can be detected quickly and accurately, protecting the safety of young people. In this way, the social media crime-related post detection system can quickly and accurately detect crime-related posts on social media and prevent involvement in crime before it happens.

[0061] The SNS crime-related post detection system according to this embodiment comprises a slang detection unit, a context analysis unit, and an account identification unit. The slang detection unit detects slang related to crime from posts on SNS. The slang detection unit detects slang with high accuracy, for example, using natural language processing technology. The slang detection unit can also learn patterns of slang using machine learning algorithms and respond to new slang. Furthermore, the slang detection unit can monitor posts on SNS in real time and quickly detect slang related to crime. For example, the slang detection unit analyzes posts on SNS and detects specific keywords or phrases. The slang detection unit can also periodically update its slang list and respond to new slang. The context analysis unit analyzes the context before and after the slang detected by the slang detection unit. The context analysis unit understands the context and determines its intent, for example, using natural language processing technology. The context analysis unit can also learn patterns of context using machine learning algorithms and accurately determine the intent of the slang. Furthermore, the context analysis unit can analyze posts on social media in real time and quickly determine the intent of coded language. For example, the context analysis unit analyzes the context before and after coded language to determine its intent. The context analysis unit can also accurately determine the intent of coded language based on context, reducing false positives. The account identification unit identifies accounts that are likely to be involved in criminal activity based on the context analyzed by the context analysis unit. For example, the account identification unit can learn account patterns using machine learning algorithms to identify accounts that are likely to be involved in criminal activity. The account identification unit can also monitor posts on social media in real time and quickly identify accounts that are likely to be involved in criminal activity. Furthermore, the account identification unit can implement a scoring system to prioritize monitoring of high-risk accounts. For example, the account identification unit identifies accounts that are likely to be involved in criminal activity based on the frequency and context of coded language use. The account identification unit can also prioritize monitoring of high-risk accounts using a scoring system.As a result, the SNS crime-related post detection system according to this embodiment can quickly and accurately detect crime-related posts on SNS and prevent involvement in crimes.

[0062] The slang detection unit detects crime-related slang from posts on social media. The slang detection unit uses, for example, natural language processing techniques to detect slang with high accuracy. Specifically, it employs techniques such as tokenization, morphological analysis, part-of-speech tagging, and dependency structure analysis. This allows it to accurately grasp the meaning of words and phrases within posts and detect slang. Furthermore, the slang detection unit can learn slang patterns using machine learning algorithms and adapt to new slang. For example, it uses supervised learning to learn past crime-related post data and extract slang features. In addition, the slang detection unit can monitor social media posts in real time and quickly detect crime-related slang. Specifically, it uses streaming data processing technology to analyze social media post data in real time and detect slang. For example, the slang detection unit analyzes social media posts and detects specific keywords and phrases. The slang detection unit also periodically updates its slang list to adapt to new slang. A cloud-based database is used to quickly reflect the latest slang information in the slang list. This allows the slang detection unit to always perform highly accurate detection based on the latest slang information.

[0063] The context analysis unit analyzes the context surrounding the slang detected by the slang detection unit. The context analysis unit understands the context and determines its intent, for example, using natural language processing techniques. Specifically, it generates context vectors to understand the meaning of sentences for context analysis and uses these to analyze the intent of the slang. Furthermore, the context analysis unit can learn contextual patterns using machine learning algorithms to accurately determine the intent of slang. For example, it utilizes recurrent neural networks (RNNs) and transformer models using deep learning to learn long-term contextual dependencies. In addition, the context analysis unit can analyze posts on social media in real time and quickly determine the intent of slang. Specifically, it streams post data in real time and analyzes the context surrounding the slang. For example, the context analysis unit analyzes the context surrounding the slang and determines its intent. The context analysis unit can also accurately determine the intent of slang based on context, reducing false positives. As a result, the context analysis unit can analyze the intent of slang with high accuracy and improve the detection accuracy of crime-related posts.

[0064] The account identification unit identifies accounts that are highly likely to be involved in criminal activity based on the context analyzed by the context analysis unit. For example, the account identification unit uses machine learning algorithms to learn account patterns and identify accounts likely to be involved in criminal activity. Specifically, it uses data from past crime-related accounts to learn account characteristics and identify new crime-related accounts. Furthermore, the account identification unit can monitor social media posts in real time and quickly identify accounts likely to be involved in criminal activity. Specifically, it analyzes post data in real time to identify accounts that post crime-related slang or context. In addition, the account identification unit can implement a scoring system to prioritize monitoring of high-risk accounts. For example, the account identification unit identifies accounts likely to be involved in criminal activity based on the frequency and context of slang use. The scoring system calculates a score based on each account's post content and activity history, prioritizing the monitoring of high-risk accounts. This allows the account identification unit to quickly and accurately identify accounts that are highly likely to be involved in criminal activity, thereby contributing to crime prevention.

[0065] The slang detection unit can detect crime-related slang from social media posts with high accuracy. The slang detection unit uses, for example, natural language processing technology to detect slang with high accuracy. Furthermore, the slang detection unit can learn slang patterns using machine learning algorithms and adapt to new slang. In addition, the slang detection unit can monitor social media posts in real time and quickly detect crime-related slang. This ensures that crime recruitment posts are not missed by detecting crime-related slang with high accuracy. Some or all of the above processing in the slang detection unit may be performed using, for example, AI, or without AI. For example, the slang detection unit can input social media posts into an AI and have the AI ​​perform slang detection.

[0066] The slang detection unit can continuously update its slang list in response to social trends and the emergence of new slang. For example, the slang detection unit can analyze news articles and social media trends to detect new slang. It can also learn new slang patterns using machine learning algorithms and update its slang list. Furthermore, the slang detection unit can monitor social media posts in real time to quickly detect new slang and update its slang list. This maintains detection accuracy by enabling it to respond to new slang. Some or all of the above processes in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input news articles and social media trends into an AI and have the AI ​​perform the detection of new slang and update the slang list.

[0067] The context analysis unit can understand the context surrounding slang and determine its intent. For example, the context analysis unit uses natural language processing technology to understand the context and determine its intent. Furthermore, the context analysis unit can learn contextual patterns using machine learning algorithms to accurately determine the intent of slang. In addition, the context analysis unit can analyze social media posts in real time and quickly determine the intent of slang. This allows for accurate determination of slang intent based on context and reduces false positives. Some or all of the above-described processes in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can input the context surrounding slang into an AI and have the AI ​​perform contextual understanding and intent determination.

[0068] The context analysis unit can accurately determine the intent of slang based on context, thereby reducing false positives. For example, the context analysis unit uses natural language processing techniques to understand the context and determine its intent. Furthermore, the context analysis unit can learn contextual patterns using machine learning algorithms to accurately determine the intent of slang. In addition, the context analysis unit can analyze social media posts in real time and quickly determine the intent of slang. This reduces false positives and provides accurate information. Some or all of the above-described processes in the context analysis unit may be performed using AI, or not. For example, the context analysis unit can input the context before and after the slang into the AI, allowing the AI ​​to understand the context and determine the intent.

[0069] The account identification unit can identify accounts that are highly likely to be involved in criminal activity based on the frequency and context of slang usage. For example, the account identification unit can use machine learning algorithms to learn account patterns and identify accounts likely to be involved in criminal activity. Furthermore, the account identification unit can monitor social media posts in real time and quickly identify accounts likely to be involved in criminal activity. In addition, the account identification unit can implement a scoring system to prioritize monitoring of high-risk accounts. This contributes to crime prevention by identifying accounts likely to be involved in criminal activity. Some or all of the above processes in the account identification unit may be performed using AI, or not. For example, the account identification unit can input the frequency and context of slang usage into an AI and have the AI ​​identify accounts likely to be involved in criminal activity.

[0070] The account identification unit can implement a scoring system and prioritize monitoring of high-risk accounts. For example, the account identification unit can use machine learning algorithms to learn account patterns and identify high-risk accounts. Furthermore, the account identification unit can monitor social media posts in real time and quickly identify high-risk accounts. In addition, the account identification unit can use the scoring system to prioritize monitoring of high-risk accounts. This contributes to crime prevention by prioritizing the monitoring of high-risk accounts. Some or all of the above processes in the account identification unit may be performed using AI, or not. For example, the account identification unit can input the scoring system into an AI and have the AI ​​perform the identification and monitoring of high-risk accounts.

[0071] The slang detection unit can estimate the user's emotions and adjust the accuracy of slang detection based on the estimated emotions. For example, the slang detection unit estimates the user's emotions using an emotion estimation algorithm. The slang detection unit can also learn emotion patterns using a machine learning algorithm and adjust the accuracy of slang detection. Furthermore, the slang detection unit can monitor posts on social media in real time and adjust the accuracy of slang detection based on the user's emotions. This reduces false positives by adjusting the accuracy of slang detection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input user emotion data into an AI and have the AI ​​perform the adjustment of the slang detection accuracy.

[0072] The slang detection unit can improve the accuracy of slang detection by considering the time of day and frequency of posts when detecting slang. For example, the slang detection unit analyzes the time of day and frequency of posts and adjusts the accuracy of slang detection. The slang detection unit can also improve the accuracy of slang detection by learning patterns of time of day and frequency using machine learning algorithms. Furthermore, the slang detection unit can monitor posts on social media in real time and adjust the accuracy of slang detection based on the time of day and frequency. This improves the accuracy of slang detection by considering the time of day and frequency of posts. Some or all of the above processing in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input post time of day and frequency data into AI and have the AI ​​perform the adjustment of slang detection accuracy.

[0073] The slang detection unit can improve the accuracy of slang detection by referring to the poster's past posting history when detecting slang. For example, the slang detection unit analyzes the poster's past posting history and adjusts the accuracy of slang detection. The slang detection unit can also improve the accuracy of slang detection by learning patterns in past posting history using machine learning algorithms. Furthermore, the slang detection unit can monitor posts on social media in real time and adjust the accuracy of slang detection based on past posting history. This improves the accuracy of slang detection by referring to the poster's past posting history. Some or all of the above processing in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input the poster's past posting history data into AI and have the AI ​​perform the adjustment of the slang detection accuracy.

[0074] The slang detection unit can estimate the user's emotions and determine the detection priority of slang based on the estimated user emotions. For example, the slang detection unit estimates the user's emotions using an emotion estimation algorithm. The slang detection unit can also learn emotion patterns using a machine learning algorithm and determine the detection priority of slang. Furthermore, the slang detection unit can monitor posts on social media in real time and determine the detection priority of slang based on the user's emotions. This allows for a quick response by determining the detection priority of slang according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the slang detection unit may be performed using AI, or not using AI. For example, the slang detection unit can input user emotion data into an AI and have the AI ​​determine the detection priority of slang.

[0075] The slang detection unit can improve the accuracy of slang detection by considering the geographical information of the post when detecting slang. For example, the slang detection unit can analyze the geographical information of the post and adjust the accuracy of slang detection. The slang detection unit can also improve the accuracy of slang detection by learning patterns in geographical information using machine learning algorithms. Furthermore, the slang detection unit can monitor posts on social media in real time and adjust the accuracy of slang detection based on geographical information. This improves the accuracy of slang detection by considering the geographical information of the post. Some or all of the above processing in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input geographical information data of the post into AI and have the AI ​​perform the adjustment of the slang detection accuracy.

[0076] The slang detection unit can improve the accuracy of slang detection by analyzing the content of images and videos in posts when detecting slang. For example, the slang detection unit can improve the accuracy of slang detection by analyzing text in images using image recognition technology. Furthermore, the slang detection unit can improve the accuracy of slang detection by analyzing audio in videos using audio analysis technology. In addition, the slang detection unit can monitor posts on social media in real time and adjust the accuracy of slang detection based on the content of images and videos. This improves the accuracy of slang detection by analyzing the content of images and videos in posts. Some or all of the above-described processes in the slang detection unit may be performed using AI, for example, or without AI. For example, the slang detection unit can input image and video data from posts into an AI and have the AI ​​adjust the accuracy of slang detection.

[0077] The context analysis unit can estimate the user's emotions and adjust the accuracy of the context analysis based on the estimated user emotions. For example, the context analysis unit estimates the user's emotions using an emotion estimation algorithm. The context analysis unit can also learn emotion patterns using a machine learning algorithm and adjust the accuracy of the context analysis. Furthermore, the context analysis unit can monitor posts on social media in real time and adjust the accuracy of the context analysis based on the user's emotions. This reduces false positives by adjusting the accuracy of the context analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the context analysis unit may be performed using AI, or not using AI. For example, the context analysis unit can input user emotion data into an AI and have the AI ​​perform the adjustment of the accuracy of the context analysis.

[0078] The context analysis unit can apply different analysis algorithms depending on the category and topic of the post during context analysis. For example, the context analysis unit can analyze the category and topic of the post and select an appropriate analysis algorithm. Furthermore, the context analysis unit can learn category and topic patterns using machine learning algorithms and apply the optimal analysis algorithm. In addition, the context analysis unit can monitor posts on social media in real time and apply analysis algorithms based on category and topic. This improves the accuracy of context analysis by applying analysis algorithms according to the category and topic of the post. Some or all of the above processes in the context analysis unit may be performed using AI, or not. For example, the context analysis unit can input post category and topic data into AI and have the AI ​​select and apply analysis algorithms.

[0079] The context analysis unit can improve the accuracy of its analysis by considering the language and dialect of the post during context analysis. For example, the context analysis unit can analyze the language and dialect of the post and select an appropriate analysis algorithm. Furthermore, the context analysis unit can learn language and dialect patterns using machine learning algorithms and apply the optimal analysis algorithm. In addition, the context analysis unit can monitor posts on social media in real time and adjust the analysis accuracy based on language and dialect. This improves the accuracy of context analysis by considering the language and dialect of the post. Some or all of the above processes in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can input language and dialect data of the post into AI and have the AI ​​perform the adjustment of the analysis accuracy.

[0080] The context analysis unit can estimate the user's emotions and determine the priority of context analysis based on the estimated user emotions. For example, the context analysis unit can estimate the user's emotions using an emotion estimation algorithm. The context analysis unit can also learn emotion patterns using a machine learning algorithm and determine the priority of context analysis. Furthermore, the context analysis unit can monitor posts on social media in real time and determine the priority of context analysis based on the user's emotions. This allows for a rapid response by determining the priority of context analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the context analysis unit may be performed using AI, or not using AI. For example, the context analysis unit can input user emotion data into an AI and have the AI ​​perform the determination of the priority of context analysis.

[0081] The context analysis unit can deepen its understanding of the context by analyzing the content of images and videos in posts during context analysis. For example, the context analysis unit can use image recognition technology to analyze text within images to deepen its understanding of the context. Furthermore, the context analysis unit can use speech analysis technology to analyze audio within videos to improve its understanding of the context. In addition, the context analysis unit can monitor posts on social media in real time and deepen its understanding of the context based on the content of images and videos. This allows for a deeper understanding of the context by analyzing the content of images and videos in posts. Some or all of the above-described processes in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can input image and video data from posts into an AI and have the AI ​​perform analysis to deepen its understanding of the context.

[0082] The context analysis unit can improve the accuracy of its analysis by referring to related links and quotations in posts during context analysis. For example, the context analysis unit can analyze related links within posts to deepen its understanding of the context. It can also refer to quotations to improve its understanding of the context. Furthermore, the context analysis unit can monitor posts on social media in real time and improve the accuracy of its analysis based on related links and quotations. This improves the accuracy of context analysis by referring to related links and quotations in posts. Some or all of the above processes in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can input related link and quotation data from posts into AI and have the AI ​​perform the improvement of analysis accuracy.

[0083] The account identification unit can estimate the user's emotions and adjust the accuracy of account identification based on the estimated emotions. For example, the account identification unit estimates the user's emotions using an emotion estimation algorithm. The account identification unit can also learn emotion patterns using a machine learning algorithm and adjust the accuracy of account identification. Furthermore, the account identification unit can monitor posts on social media in real time and adjust the accuracy of account identification based on the user's emotions. This reduces false positives by adjusting the accuracy of account identification according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the account identification unit may be performed using AI or not using AI. For example, the account identification unit can input user emotion data into AI and have the AI ​​perform the adjustment of the accuracy of account identification.

[0084] The account identification unit can improve its identification accuracy by referring to the poster's past behavioral history when identifying an account. For example, the account identification unit can analyze the poster's past behavioral history and adjust the identification accuracy. The account identification unit can also improve its identification accuracy by learning patterns in past behavioral history using machine learning algorithms. Furthermore, the account identification unit can monitor posts on social media in real time and adjust the identification accuracy based on past behavioral history. This improves the accuracy of account identification by referring to the poster's past behavioral history. Some or all of the above processes in the account identification unit may be performed using AI, for example, or without AI. For example, the account identification unit can input the poster's past behavioral history data into AI and have the AI ​​perform the adjustment of the identification accuracy.

[0085] The account identification unit can improve its identification accuracy by considering the poster's followers and following relationships when identifying accounts. For example, the account identification unit analyzes followers and following relationships and adjusts the identification accuracy. The account identification unit can also improve its identification accuracy by learning patterns of followers and following relationships using machine learning algorithms. Furthermore, the account identification unit can monitor posts on social media in real time and adjust the identification accuracy based on followers and following relationships. This improves the accuracy of account identification by considering the poster's followers and following relationships. Some or all of the above processing in the account identification unit may be performed using AI, for example, or without AI. For example, the account identification unit can input follower and following relationship data into AI and have the AI ​​perform the adjustment of the identification accuracy.

[0086] The account identification unit can estimate a user's emotions and determine the priority of account identification based on the estimated emotions. For example, the account identification unit can estimate a user's emotions using an emotion estimation algorithm. Furthermore, the account identification unit can learn emotion patterns using a machine learning algorithm and determine the priority of account identification. In addition, the account identification unit can monitor posts on social media in real time and determine the priority of account identification based on user emotions. This allows for a rapid response by determining the priority of account identification according to user emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the account identification unit may be performed using AI, or not. For example, the account identification unit can input user emotion data into an AI and have the AI ​​determine the priority of account identification.

[0087] The account identification unit can improve its identification accuracy by considering the poster's geographical information when identifying accounts. For example, the account identification unit can analyze geographical information and adjust the identification accuracy. The account identification unit can also improve its identification accuracy by learning geographical information patterns using machine learning algorithms. Furthermore, the account identification unit can monitor posts on social media in real time and adjust the identification accuracy based on geographical information. This improves the accuracy of account identification by considering the poster's geographical information. Some or all of the above processes in the account identification unit may be performed using AI, for example, or without AI. For example, the account identification unit can input geographical information data into AI and have the AI ​​perform the adjustment of the identification accuracy.

[0088] The account identification unit can improve its identification accuracy by analyzing the poster's social media activity during account identification. For example, the account identification unit analyzes social media activity and adjusts the identification accuracy. The account identification unit can also improve its identification accuracy by learning patterns of social media activity using machine learning algorithms. Furthermore, the account identification unit can monitor posts on social media in real time and adjust the identification accuracy based on social media activity. This improves the accuracy of account identification by analyzing the poster's social media activity. Some or all of the above processing in the account identification unit may be performed using AI, for example, or without AI. For example, the account identification unit can input social media activity data into AI and have the AI ​​perform the adjustment of the identification accuracy.

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

[0090] The SNS crime-related post detection system can further incorporate features to estimate user emotions and evaluate the risk level of posts based on those estimated emotions. For example, it can analyze user emotions using an emotion estimation algorithm and prioritize the detection of posts with strong negative emotions such as anger or anxiety. Furthermore, it can score the risk level of posts based on the emotion estimation results and notify law enforcement agencies of high-scoring posts. Additionally, it can continuously monitor posts from users with specific emotions using the emotion estimation results, enabling early detection of signs of crime. This improves the accuracy of crime-related post detection by performing risk assessments based on emotions.

[0091] A social media crime-related post detection system can analyze the geographical information of posts and monitor the frequency of crime-related posts in specific areas. For example, it can analyze the location information of posts to detect an increase in crime-related posts in a particular area. Furthermore, it can identify areas with high crime rates based on geographical information and prioritize monitoring posts in those areas. In addition, it can use geographical information to learn patterns of crime-related posts and build predictive models. This allows for understanding trends in crime-related posts in each region and implementing effective countermeasures.

[0092] A social media crime-related post detection system can analyze the content of images and videos posted and have the capability to detect crime-related visual content. For example, it can use image recognition technology to analyze text and objects within posted images and detect elements related to crime. It can also use audio analysis technology to analyze audio within videos and detect statements related to crime. Furthermore, based on the analysis results of the visual content, it can evaluate the risk level of posts and notify law enforcement agencies of high-risk posts. This improves the accuracy of analysis of posts that include not only text but also images and videos.

[0093] A social media crime-related post detection system can incorporate features to improve the accuracy of crime-related post detection by referencing a user's past posting history. For example, it can analyze a user's past posts and learn patterns related to crime. It can also prioritize monitoring of posts from specific users based on their past posting history. Furthermore, it can build a predictive model for crime-related posts using past posting history to predict future crime-related posts. This allows for improved accuracy in detecting crime-related posts by considering the user's past behavior.

[0094] A social media crime-related post detection system can have the capability to apply different analysis algorithms depending on the post's category and topic. For example, it can analyze the post's category and topic and select the appropriate analysis algorithm. It can also learn category and topic patterns using machine learning algorithms and apply the optimal analysis algorithm. Furthermore, it can monitor social media posts in real time and apply analysis algorithms based on category and topic. This allows for improved accuracy of contextual analysis by applying analysis algorithms according to the post's category and topic.

[0095] A social media crime-related post detection system can be equipped with the ability to estimate users' emotions and prioritize posts based on those emotions. For example, it can use an emotion estimation algorithm to analyze users' emotions and prioritize the detection of posts with strong negative emotions such as anger or anxiety. Furthermore, it can score the priority of posts based on the emotion estimation results and notify law enforcement agencies of high-scoring posts. In addition, it can use the emotion estimation results to continuously monitor posts from users with specific emotions and detect signs of crime early. This allows for a rapid response by prioritizing based on emotions.

[0096] A social media crime-related post detection system can incorporate features to improve the accuracy of slang detection by considering the time of day and frequency of posts. For example, it can analyze the time of day and frequency of posts and adjust the accuracy of slang detection accordingly. Furthermore, it can use machine learning algorithms to learn patterns in time of day and frequency to improve slang detection accuracy. Additionally, it can monitor social media posts in real time and adjust slang detection accuracy based on time of day and frequency. This allows for improved slang detection accuracy by considering the time of day and frequency of posts.

[0097] A social media crime-related post detection system can be equipped with a function to estimate user emotions and adjust the accuracy of slang detection based on those emotions. For example, it can analyze user emotions using an emotion estimation algorithm and increase the accuracy of slang detection for posts with strong negative emotions. It can also dynamically adjust the accuracy of slang detection based on the emotion estimation results to reduce false positives. Furthermore, it can continuously monitor posts from users with specific emotions using the emotion estimation results to maintain the accuracy of slang detection. In this way, detection accuracy can be improved by adjusting the accuracy of slang detection based on emotions.

[0098] A social media crime-related post detection system can be equipped with a function to improve the accuracy of contextual analysis by referring to related links and quotations within posts. For example, it can analyze related links within posts to deepen the understanding of the context. It can also refer to quotations to improve the understanding of the context. Furthermore, it can monitor posts on social media in real time and improve the accuracy of analysis based on related links and quotations. In this way, the accuracy of contextual analysis can be improved by referring to related links and quotations within posts.

[0099] A social media crime-related post detection system can be equipped with a function to estimate user sentiment and adjust the accuracy of account identification based on the estimated sentiment. For example, it can analyze user sentiment using a sentiment estimation algorithm and prioritize the identification of accounts of users with strong negative sentiment. Furthermore, it can dynamically adjust the accuracy of account identification based on the sentiment estimation results to reduce false positives. In addition, it can continuously monitor accounts of users with specific sentiments using the sentiment estimation results to maintain the accuracy of account identification. In this way, the accuracy of identification can be improved by adjusting the accuracy of account identification based on sentiment.

[0100] The following briefly describes the processing flow for example form 2.

[0101] Step 1: The slang detection unit detects slang related to crime from posts on social media. The slang detection unit uses natural language processing technology and machine learning algorithms to detect slang with high accuracy and can handle new slang. It also monitors social media posts in real time and detects specific keywords and phrases. Furthermore, it regularly updates the slang list to handle new slang. Step 2: The context analysis unit analyzes the context surrounding the slang detected by the slang detection unit. The context analysis unit uses natural language processing techniques and machine learning algorithms to understand the context and determine its intent. Furthermore, it analyzes social media posts in real time to quickly determine the intent of the slang. It accurately determines the intent of the slang based on the context and reduces false positives. Step 3: The account identification unit identifies accounts that are likely to be involved in criminal activity based on the context analyzed by the context analysis unit. The account identification unit uses machine learning algorithms to learn account patterns and identify accounts that are likely to be involved in criminal activity. It also monitors posts on social media in real time and implements a scoring system to prioritize monitoring of high-risk accounts.

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

[0103] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

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

[0105] Each of the multiple elements described above, including the slang detection unit, context analysis unit, and account identification unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the slang detection unit is implemented by the processor 46 of the smart device 14 and analyzes posts on social media to detect slang related to crime. The context analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the context before and after the slang to determine its intent. The account identification unit is implemented by the control unit 46A of the smart device 14 and identifies accounts that are likely to be involved in criminal activity. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

[0107] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

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

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

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

[0112] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0113] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0114] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

[0117] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

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

[0119] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

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

[0121] Each of the multiple elements described above, including the slang detection unit, context analysis unit, and account identification unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the slang detection unit is implemented by the processor 46 of the smart glasses 214 and analyzes posts on social media to detect slang related to crime. The context analysis unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes the context before and after the slang to determine its intent. The account identification unit is implemented by the control unit 46A of the smart glasses 214 and identifies accounts that are likely to be involved in criminal activity. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

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

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

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

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

[0128] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0129] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0130] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

[0133] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

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

[0135] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

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

[0137] Each of the multiple elements described above, including the slang detection unit, context analysis unit, and account identification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the slang detection unit is implemented by the processor 46 of the headset terminal 314 and analyzes posts on social media to detect slang related to crime. The context analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the context before and after the slang to determine its intent. The account identification unit is implemented by the control unit 46A of the headset terminal 314 and identifies accounts that are likely to be involved in criminal activity. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

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

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

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

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

[0144] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0145] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0146] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0149] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

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

[0152] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

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

[0154] Each of the multiple elements described above, including the slang detection unit, context analysis unit, and account identification unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the slang detection unit is implemented by the processor 46 of the robot 414 and analyzes posts on social media to detect slang related to crime. The context analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the context before and after the slang to determine its intent. The account identification unit is implemented by the control unit 46A of the robot 414 and identifies accounts that are likely to be involved in criminal activity. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0155] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0157] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0158] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0159] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

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

[0162] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

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

[0164] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0165] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0166] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0167] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0168] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0170] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0171] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0172] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0173] (Note 1) A code word detection unit that detects crime-related code words from social media posts, A context analysis unit analyzes the context before and after the slang detected by the slang detection unit, The system includes an account identification unit that identifies accounts that are likely to be involved in criminal activity based on the context analyzed by the context analysis unit. A system characterized by the following features. (Note 2) The aforementioned slang detection unit, High-precision detection of crime-related slang from social media posts. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned slang detection unit, The slang list will be continuously updated in response to social trends and the emergence of new slang terms. The system described in Appendix 1, characterized by the features described herein. (Note 4) The context analysis unit, Understand the context surrounding the slang and determine its intent. The system described in Appendix 1, characterized by the features described herein. (Note 5) The context analysis unit, Accurately determine the intent of slang based on context and reduce false positives. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned account identification unit is Identifying accounts likely to be involved in criminal activity based on the frequency and context of their use of slang. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned account identification unit is We will implement a scoring system and prioritize monitoring of high-risk accounts. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned slang detection unit, It estimates the user's emotions and adjusts the accuracy of slang detection based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned slang detection unit, When detecting slang, we improve the accuracy of slang detection by considering the time of day and frequency of posts. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned slang detection unit, When detecting slang, the accuracy of slang detection is improved by referring to the poster's past posting history. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned slang detection unit, The system estimates the user's emotions and determines the priority for detecting slang based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned slang detection unit, When detecting slang, consider the geographical information of the post to improve the accuracy of slang detection. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned slang detection unit, When detecting slang, the content of images and videos in posts is analyzed to improve the accuracy of slang detection. The system described in Appendix 1, characterized by the features described herein. (Note 14) The context analysis unit, It estimates the user's emotions and adjusts the accuracy of contextual analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The context analysis unit, During contextual analysis, different analysis algorithms are applied depending on the post's category and topic. The system described in Appendix 1, characterized by the features described herein. (Note 16) The context analysis unit, When performing contextual analysis, consider the language and dialect of the post to improve analysis accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 17) The context analysis unit, It estimates the user's emotions and determines the priority of contextual analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The context analysis unit, During contextual analysis, the content of images and videos in a post is analyzed to deepen the understanding of the context. The system described in Appendix 1, characterized by the features described herein. (Note 19) The context analysis unit, During contextual analysis, we improve the accuracy of the analysis by referring to related links and citations in the post. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned account identification unit is It estimates user sentiment and adjusts the accuracy of account identification based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned account identification unit is When identifying an account, we improve the accuracy of the identification process by referring to the poster's past activity history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned account identification unit is When identifying an account, we consider the poster's followers and following relationships to improve the accuracy of the identification process. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned account identification unit is It estimates user sentiment and determines account identification priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned account identification unit is When identifying an account, we consider the poster's geographical information to improve identification accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned account identification unit is Analyzing the poster's social media activity improves the accuracy of account identification. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

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

Claims

1. A code word detection unit that detects crime-related code words from social media posts, A context analysis unit analyzes the context before and after the slang detected by the slang detection unit, The system includes an account identification unit that identifies accounts that are likely to be involved in criminal activity based on the context analyzed by the context analysis unit. A system characterized by the following features.

2. The aforementioned slang detection unit, High-precision detection of crime-related slang from social media posts. The system according to feature 1.

3. The aforementioned slang detection unit, The slang list will be continuously updated in response to social trends and the emergence of new slang terms. The system according to feature 1.

4. The context analysis unit, Understand the context surrounding the slang and determine its intent. The system according to feature 1.

5. The context analysis unit, Accurately determine the intent of slang based on context and reduce false positives. The system according to feature 1.

6. The aforementioned account identification unit is Identifying accounts likely to be involved in criminal activity based on the frequency and context of their use of slang. The system according to feature 1.

7. The aforementioned account identification unit is We will implement a scoring system and prioritize monitoring of high-risk accounts. The system according to feature 1.

8. The aforementioned slang detection unit, It estimates the user's emotions and adjusts the accuracy of slang detection based on the estimated user emotions. The system according to feature 1.

Images