system

Abstract

The system according to this embodiment aims to detect communications using coded language and enable the early detection of criminal activity. [Solution] The system according to the embodiment comprises a collection unit, a learning unit, a monitoring unit, a warning unit, and a processing unit. The collection unit collects data held by the police and chat service providers. The learning unit learns from the data collected by the collection unit and builds a model for detecting coded language exchanges. The monitoring unit monitors the chat content using the model built by the learning unit. The warning unit issues a warning when the monitoring unit detects coded language exchanges. The processing unit bans accounts based on the warnings issued by the warning 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, it is difficult to detect conversations using jargon, and there is a problem that it is difficult to detect criminal acts at an early stage.

[0005] The system according to the embodiment aims to detect conversations using jargon and enable early detection of criminal acts.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a learning unit, a monitoring unit, a warning unit, and a processing unit. The collection unit collects data held by the police and chat service providers. The learning unit learns from the data collected by the collection unit and builds a model for detecting coded language exchanges. The monitoring unit monitors the chat content using the model built by the learning unit. The warning unit issues a warning when the monitoring unit detects coded language exchanges. The processing unit bans accounts based on the warnings issued by the warning unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect communications using coded language, enabling the early detection of 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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. As an example of the communication standard applied to the communication I / F, wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark) can be mentioned.

[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 linked 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 slang detection system according to an embodiment of the present invention is a system that uses generative AI to detect and predict the use of slang in open chats and private chats. This slang detection system collects data held by the police and chat service providers, and the generative AI learns from this data to build a model for detecting the use of slang. Furthermore, the generative AI monitors the content of the chat and issues a warning when it detects the use of slang. This system can accelerate the detection of illegal job exchanges and contribute to the provision of safe and secure services. For example, it collects data held by the police and chat service providers. This data includes slang and account information used in illegal jobs. For example, it includes slang such as "beating" and "rice cooker". This data is input into the generative AI. Next, the generative AI learns from the collected data. The generative AI builds a model for detecting the use of slang. This model can determine slang by considering the surrounding sentences and context. For example, from the context of "using a rice cooker", it determines that "rice cooker" is slang. Furthermore, the generative AI monitors the content of the chat. The generating AI analyzes chat content in real time and detects the use of coded language. For example, if the word "taki" (to beat / criticize) is used in an open chat or private chat, the AI ​​analyzes the surrounding context to determine if it is coded language. If coded language is detected, the generating AI issues a warning. This warning is sent to the chat service provider and the police. This allows for the early detection of illegal job-related communications and enables countermeasures to be taken. For example, early banning of accounts that have been detected using coded language can help prevent crime. This system can detect sophisticated coded language communications that cannot be covered by monitoring alone. By using the generating AI, it is possible to analyze talk text that cannot be covered by AI filtering and determine coded language from the surrounding text and context. This is expected to improve the crime detection rate. In this way, the coded language detection system can detect illegal job-related communications early and contribute to the provision of safe and secure services.

[0029] The coded language detection system according to this embodiment comprises a collection unit, a learning unit, a monitoring unit, a warning unit, and a processing unit. The collection unit collects data held by the police and chat service providers. For example, the collection unit can collect past crime data held by the police and chat logs held by chat service providers. The collection unit inputs this data into a generating AI. The learning unit learns from the data collected by the collection unit and builds a model for detecting coded language exchanges. For example, the learning unit uses the generating AI to build a model for detecting coded language exchanges based on the collected data. The generating AI can determine coded language by considering the surrounding sentences and context in order to detect coded language exchanges. For example, the generating AI determines that "rice cooker" is coded language from the context of "using a rice cooker". The monitoring unit monitors the chat content using the model built by the learning unit. For example, the monitoring unit analyzes the chat content in real time and detects coded language exchanges. The monitoring unit can use the generating AI to analyze the chat content and detect coded language exchanges. For example, the monitoring unit analyzes the context before and after the use of the word "tachi" in open chats or private chats to determine if it is slang. The warning unit issues a warning when the monitoring unit detects the use of slang. The warning unit notifies chat service providers and the police, for example, when it detects the use of slang. The warning unit can issue warnings using generative AI when it detects the use of slang. For example, the warning unit notifies that accounts where slang is detected should be banned early. The processing unit bans accounts based on the warnings issued by the warning unit. The processing unit bans accounts where slang is detected based on the warnings issued by the warning unit. The processing unit can ban accounts based on the warnings issued by the warning unit using generative AI. For example, by banning accounts where slang is detected early, the processing unit can help prevent crime.As a result, the coded language detection system according to this embodiment can detect illegal part-time job transactions at an early stage, leading to the provision of safe and secure services.

[0030] The data collection unit collects data held by the police and chat service providers. Specifically, it can collect past crime data held by the police and chat logs held by chat service providers. The police's past crime data includes the type of crime, date and time of occurrence, location, information on those involved, and the slang used. This data is important for understanding crime trends and slang usage patterns. Chat logs held by chat service providers include message exchanges between users, date and time of sending, sender and recipient information, and the words and phrases used. This data is necessary to understand the usage of slang and its context. The data collection unit inputs this data into a generating AI. The generating AI analyzes the collected data and uses it as foundational data to build a model for detecting slang exchanges. When collecting data, the data collection unit takes full consideration of privacy protection and data security, and collects data through appropriate procedures. For example, data collection includes obtaining permission from relevant agencies and anonymizing the data. This allows the data collection unit to collect data efficiently and securely, improving the overall system performance.

[0031] The learning unit learns from the data collected by the collection unit and builds a model for detecting slang. Specifically, it uses a generative AI to build a model for detecting slang based on the collected data. The generative AI can determine slang by considering the surrounding sentences and context in order to detect slang. For example, the generative AI determines that "rice cooker" is slang from the context of "using a rice cooker." By learning from a large amount of data, the generative AI understands the usage patterns and contexts of slang and improves the accuracy of slang detection. The learning unit monitors the learning process of the generative AI and adjusts parameters or adds data as needed. For example, if the generative AI cannot accurately detect a particular slang term, the learning unit adds data related to that slang term and retrains it. The learning unit also evaluates the learning results of the generative AI and verifies the accuracy and reliability of the model. This allows the learning unit to build a model for detecting slang with high accuracy and improve the overall system performance.

[0032] The monitoring unit monitors chat content using a model built by the learning unit. Specifically, it analyzes chat content in real time and detects the use of coded language. The monitoring unit can analyze chat content and detect coded language using generative AI. For example, if the word "tackling" is used in an open chat or private chat, the monitoring unit analyzes the surrounding context to determine whether it is coded language. The generative AI utilizes natural language processing technology to analyze chat content in real time and detect the use of coded language. The generative AI can understand the chat content contextually and detect the use of coded language with high accuracy. Based on the analysis results of the generative AI, the monitoring unit issues a warning when it detects the use of coded language. This allows the monitoring unit to monitor chat content in real time and detect coded language early. Furthermore, the monitoring unit can periodically analyze chat content to understand the trends and patterns of coded language use. This allows the monitoring unit to continuously monitor coded language and improve the reliability and security of the entire system.

[0033] The warning unit issues a warning when the monitoring unit detects coded language exchanges. Specifically, it notifies chat service providers and the police when coded language exchanges are detected. The warning unit can issue warnings when coded language exchanges are detected using a generation AI. For example, the warning unit may notify that accounts that have been detected using coded language should be banned as soon as possible. Based on the analysis results of the generation AI, the warning unit issues an appropriate warning when coded language exchanges are detected. The warning unit can flexibly set the content and target of the warnings. For example, when coded language exchanges are detected, the warning unit can not only issue a warning to the chat service provider but also notify the police. Furthermore, the warning unit can describe the content of the warning in detail, providing the specific content and context of the coded language exchanges. This allows the warning unit to provide information for early detection of coded language exchanges and for appropriate action. In addition, the warning unit records the history of warnings issued so that they can be referenced later. This allows the warning unit to manage the history of responses to coded language exchanges, improving the overall reliability and transparency of the system.

[0034] The processing unit bans accounts based on warnings issued by the warning unit. Specifically, it bans accounts that are detected to be using coded language based on warnings issued by the warning unit. The processing unit can use generated AI to ban accounts based on warnings issued by the warning unit. For example, by banning accounts that are detected to be using coded language early on, the processing unit can help prevent crime. The processing unit receives notifications from the warning unit and checks the details of the target account. It refers to the target account's past chat history and warning history to determine the necessity of banning. When the processing unit executes an account ban, it notifies the user and clearly states the reason and duration of the ban. This allows the user to understand why their account was banned and to take steps to prevent recurrence. Furthermore, the processing unit records information on banned accounts and builds a database to prevent further fraudulent activity. This allows the processing unit to effectively eliminate accounts that use coded language and improve the overall security of the system. In addition, the processing unit continuously monitors accounts even after the ban is executed and strives to prevent recurrence. This allows the processing unit to detect accounts using coded language early on and respond quickly.

[0035] The data collection unit can dynamically change the types of data it collects based on past crime data and the frequency of slang usage. For example, the data collection unit can analyze past crime data and prioritize the collection of slang that occurred frequently during specific periods. The data collection unit can focus on collecting specific data during times when slang is frequently used. If a newly discovered slang term is found, the data collection unit can prioritize the collection of data related to that term. This allows for more effective detection of slang interactions by dynamically changing the types of data collected based on past crime data and the frequency of slang usage. Some or all of the above-described processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input past crime data and slang usage frequency data into a generating AI and have the generating AI change the types of data to collect.

[0036] The data collection unit can monitor the frequency of occurrence of specific keywords and phrases in real time during data collection and automatically update the data to be collected. For example, if a particular keyword is used frequently, the data collection unit will prioritize the collection of data related to that keyword. The data collection unit can monitor the frequency of keyword occurrences in real time and dynamically change the data to be collected. When a new keyword appears, the data collection unit can aggregate the data related to that keyword. This allows for more effective detection of coded language exchanges by monitoring the frequency of occurrence of specific keywords and phrases in real time and automatically updating the data to be collected. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input frequency data of specific keywords and phrases into a generating AI and have the generating AI update the data to be collected.

[0037] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, if the user is in a specific area, the data collection unit can prioritize the collection of data related to that area. Based on the user's location information, the data collection unit can collect crime data in the vicinity. If the user is on the move, the data collection unit can collect data related to the area the user is moving to. This allows for more effective data collection by prioritizing the collection of highly relevant data by considering the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant data.

[0038] The data collection unit can analyze a user's social media activity and collect relevant data during data collection. For example, if a user is active on a particular social media platform, the data collection unit can collect data related to that activity. The data collection unit can analyze the content of a user's social media posts and collect relevant data. The data collection unit can analyze the activities of a user's social media followers and friends and collect relevant data. This allows for more effective data collection by analyzing a user's social media activity and collecting relevant data. Some or all of the above-described processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's social media activity data into a generating AI and have the generating AI perform the collection of relevant data.

[0039] The learning unit can dynamically adjust the model parameters during training based on the frequency and context of slang usage. For example, if slang is frequently used, the learning unit adjusts the model parameters to improve the accuracy of slang detection. The learning unit can determine the meaning of slang based on context and adjust the model parameters accordingly. If a new slang term is discovered, the learning unit can dynamically adjust the model parameters to accommodate it. This allows for improved slang detection accuracy by dynamically adjusting the model parameters based on the frequency and context of slang usage. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input slang frequency data and context data into a generating AI and have the generating AI adjust the model parameters.

[0040] The learning unit can build multilingual models to handle different languages ​​and dialects during training. For example, the learning unit can learn slang used in different languages ​​and build a multilingual model. The learning unit can learn slang specific to a dialect and build a model that corresponds to that dialect. The learning unit can use the multilingual models to detect slang exchanges in different languages ​​and dialects. By building multilingual models to handle different languages ​​and dialects, a wider range of slang exchanges can be detected. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input data in different languages ​​and dialects into a generative AI and have the generative AI perform the construction of a multilingual model.

[0041] The learning unit can weight the training data based on specific time periods or events during training. For example, the learning unit can prioritize learning slang that frequently occurs during specific time periods. The learning unit can learn slang related to events and weight them accordingly. The learning unit can dynamically adjust the weighting of the training data based on time periods or events. This allows for more effective training by weighting the training data based on specific time periods or events. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data for specific time periods or events into a generating AI and have the generating AI perform the weighting of the training data.

[0042] The learning unit can integrate data from different platforms during training. For example, the learning unit can integrate data collected from social networking services (SNS) and forums. The learning unit can learn slang used on different platforms and build an integrated model. The learning unit can integrate and learn data while considering the characteristics of each platform. This allows for the detection of a wider range of slang interactions by integrating and learning data from different platforms. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data from different platforms into a generative AI and have the generative AI perform the data integration.

[0043] The monitoring unit can perform analysis considering not only the chat content but also the sender's attribute information during monitoring. For example, the monitoring unit can prioritize the analysis of slang common in a specific age group based on the sender's age information. The monitoring unit can analyze gender-related slang considering the sender's gender information. The monitoring unit can perform slang analysis by comprehensively considering the sender's attribute information. As a result, by performing analysis considering not only the chat content but also the sender's attribute information, the exchange of slang can be detected more effectively. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the sender's attribute information into a generating AI and have the generating AI perform slang analysis.

[0044] The monitoring unit can translate chat content in real time and perform multilingual analysis during monitoring. For example, the monitoring unit can translate chat content in real time and analyze slang exchanges in different languages. The monitoring unit can perform multilingual analysis and improve the accuracy of detecting slang in different languages. The monitoring unit can analyze slang exchanges based on the content translated in real time. As a result, by translating chat content in real time and performing multilingual analysis, a wider range of slang exchanges can be detected. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input chat content into a generating AI and have the generating AI perform real-time translation and analysis.

[0045] The warning unit can determine the priority of warnings by referring to past warning history when an warning is issued. For example, if a similar warning has been issued in the past, the warning unit will give that warning a higher priority. The warning unit can analyze past warning history and prioritize issuing warnings of high importance. The warning unit can dynamically adjust the priority of warnings based on the warning history. This allows for more effective warnings by determining the priority of warnings by referring to past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input past warning history data into a generating AI and have the generating AI perform the determination of warning priorities.

[0046] The warning unit can display warnings in multiple languages ​​when an alert is issued, accommodating users of different languages. For example, the warning unit can automatically translate warnings based on the user's language settings. The warning unit can display warnings in multiple languages, accommodating users of different languages. If the user selects a specific language, the warning unit can display the warning in that language. This allows the warning unit to accommodate users of different languages ​​by displaying warnings in multiple languages. Some or all of the above-described processes in the warning unit may be performed using AI, or not. For example, the warning unit can input warning content into a generating AI and have the generating AI perform the multilingual display.

[0047] The warning unit can optimize the content of a warning based on the user's device information when a warning is issued. For example, if the user is using a smartphone, the warning unit can display a warning that is adapted to the screen size. If the user is using a tablet, the warning unit can display a warning optimized for a larger screen. If the user is using a smartwatch, the warning unit can display a concise and highly visible warning. This allows for more effective warnings by optimizing the content of the warning based on the user's device information. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's device information into a generating AI and have the generating AI perform the optimization of the warning content.

[0048] The warning unit can customize the content of a warning based on the user's past behavior history. For example, the warning unit can customize the content of a warning based on the user's past behavior history. The warning unit can adjust the content of a warning by referring to warnings the user has received in the past. The warning unit can analyze the user's behavior patterns and provide the most appropriate warning content. This allows for more effective warnings by customizing the content of warnings based on the user's past behavior history. Some or all of the above-described processes in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's past behavior history data into a generating AI and have the generating AI perform the customization of the warning content.

[0049] The processing unit can determine the priority of an account ban by referring to past ban history. For example, the processing unit will prioritize banning an account if it has committed similar violations in the past. The processing unit can analyze past ban history and prioritize banning accounts of high importance. The processing unit can dynamically adjust the priority of processing based on the ban history. This allows for more effective account banning by determining the priority of processing by referring to past ban history. Some or all of the above processing in the processing unit may be performed using AI, for example, or without AI. For example, the processing unit can input past ban history data into a generating AI and have the generating AI determine the priority of processing.

[0050] The processing unit can coordinate across different platforms and implement bans on multiple platforms when banning accounts. For example, if the same account is being used on different platforms, the processing unit will coordinate to implement the ban. The processing unit can share information between platforms and implement account bans efficiently. The processing unit can coordinate bans on multiple platforms and take effective countermeasures. As a result, by coordinating across different platforms and implementing bans on multiple platforms, account bans can be carried out more effectively. Some or all of the above-described processes in the processing unit may be performed using AI, for example, or without AI. For example, the processing unit can input data from different platforms into a generating AI and have the generating AI execute the process of implementing a coordinated ban.

[0051] The processing unit can select the optimal processing method when an account is banned, taking into account the user's geographical location information. For example, if the user is in a specific region, the processing unit can select a processing method related to that region. Based on the user's location information, the processing unit can select the optimal method for notifying the user of the ban. If the user is on the move, the processing unit can select a processing method related to the destination region. By selecting the optimal processing method while considering the user's geographical location information, account bans can be carried out more effectively. Some or all of the above processing in the processing unit may be performed using AI, for example, or without AI. For example, the processing unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal processing method.

[0052] The processing unit can analyze a user's social media activity and ban related accounts when banning an account. For example, the processing unit can analyze a user's social media activity, identify related accounts, and ban them. The processing unit can analyze the accounts of a user's followers and friends and ban related accounts. The processing unit can ban related accounts based on the user's social media activity history. This allows for more effective account banning by analyzing a user's social media activity and banning related accounts as well. Some or all of the above processing in the processing unit may be performed using AI, for example, or without AI. For example, the processing unit can input the user's social media activity data into a generating AI and have the generating AI perform the banning of related accounts.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The data collection unit can dynamically change the types of data it collects based on past crime data and the frequency of slang usage. For example, it can analyze past crime data and prioritize the collection of slang that was frequently used during specific periods. It can also focus on collecting specific data during times when slang is frequently used. Furthermore, if a new slang term is discovered, it can prioritize the collection of data related to that term. By dynamically changing the types of data collected based on past crime data and the frequency of slang usage, it becomes possible to more effectively detect the use of slang.

[0055] The data collection unit can monitor the frequency of specific keywords and phrases in real time during data collection and automatically update the collection target. For example, if a particular keyword is used frequently, data related to that keyword can be prioritized for collection. It can also dynamically change the collection target by monitoring keyword frequency in real time. Furthermore, if a new keyword appears, data related to that keyword can be aggregated. This allows for more effective detection of coded language exchanges by monitoring the frequency of specific keywords and phrases in real time and automatically updating the collection target.

[0056] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location. For example, if a user is in a specific area, it can prioritize the collection of data related to that area. It can also collect crime data in the vicinity based on the user's location. Furthermore, if a user is on the move, it can collect data related to the area they are moving to. This allows for more effective data collection by prioritizing the collection of highly relevant data while considering the user's geographical location.

[0057] The data collection unit can analyze a user's social media activity and collect relevant data. For example, if a user is active on a specific social media platform, it can collect data related to that activity. It can also analyze the content of a user's social media posts and collect relevant data. Furthermore, it can analyze the activities of a user's social media followers and friends and collect relevant data. This allows for more effective data collection by analyzing a user's social media activity and collecting relevant data.

[0058] The learning unit can dynamically adjust the model parameters during training based on the frequency and context of slang usage. For example, if slang is frequently used, the model parameters can be adjusted to improve the accuracy of slang detection. It can also determine the meaning of slang based on context and adjust the model parameters accordingly. Furthermore, if new slang is discovered, the model parameters can be dynamically adjusted to accommodate it. This allows for improved slang detection accuracy by dynamically adjusting the model parameters based on the frequency and context of slang usage.

[0059] The learning unit can build multilingual models to handle different languages ​​and dialects during training. For example, it can learn slang used in different languages ​​and build multilingual models. It can also learn slang specific to a dialect and build models that handle dialects. Furthermore, it can use the multilingual models to detect slang exchanges in different languages ​​and dialects. By building multilingual models that can handle different languages ​​and dialects, it becomes possible to detect a wider range of slang exchanges.

[0060] The monitoring unit can analyze not only the chat content but also the sender's attribute information during monitoring. For example, it can prioritize the analysis of slang common in a specific age group based on the sender's age information. It can also analyze gender-related slang by considering the sender's gender information. Furthermore, it can analyze slang by comprehensively considering the sender's attribute information. As a result, by analyzing not only the chat content but also the sender's attribute information, it can more effectively detect the exchange of slang.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The data collection unit collects data held by the police and chat service providers. For example, it collects past crime data held by the police and chat logs held by chat service providers, and inputs this data into the generating AI. Step 2: The learning unit learns from the data collected by the collection unit and builds a model to detect slang. Using generative AI, it builds a model to detect slang based on the collected data and determines the slang by considering the surrounding sentences and context. Step 3: The monitoring unit monitors the chat content using the model built by the learning unit. It analyzes the chat content in real time and detects the use of coded language. Generative AI can be used to analyze the chat content and detect the use of coded language. Step 4: The warning unit issues a warning when the monitoring unit detects the use of coded language. When coded language is detected, it notifies the chat service provider and the police, and requests that the account in question be banned as soon as possible. Step 5: The processing unit bans accounts based on warnings issued by the warning unit. Based on warnings issued by the warning unit, accounts that have been detected to be using coded language are banned to help prevent crime.

[0063] (Example of form 2) The slang detection system according to an embodiment of the present invention is a system that uses generative AI to detect and predict the use of slang in open chats and private chats. This slang detection system collects data held by the police and chat service providers, and the generative AI learns from this data to build a model for detecting the use of slang. Furthermore, the generative AI monitors the content of the chat and issues a warning when it detects the use of slang. This system can accelerate the detection of illegal job exchanges and contribute to the provision of safe and secure services. For example, it collects data held by the police and chat service providers. This data includes slang and account information used in illegal jobs. For example, it includes slang such as "beating" and "rice cooker". This data is input into the generative AI. Next, the generative AI learns from the collected data. The generative AI builds a model for detecting the use of slang. This model can determine slang by considering the surrounding sentences and context. For example, from the context of "using a rice cooker", it determines that "rice cooker" is slang. Furthermore, the generative AI monitors the content of the chat. The generating AI analyzes chat content in real time and detects the use of coded language. For example, if the word "taki" (to beat / criticize) is used in an open chat or private chat, the AI ​​analyzes the surrounding context to determine if it is coded language. If coded language is detected, the generating AI issues a warning. This warning is sent to the chat service provider and the police. This allows for the early detection of illegal job-related communications and enables countermeasures to be taken. For example, early banning of accounts that have been detected using coded language can help prevent crime. This system can detect sophisticated coded language communications that cannot be covered by monitoring alone. By using the generating AI, it is possible to analyze talk text that cannot be covered by AI filtering and determine coded language from the surrounding text and context. This is expected to improve the crime detection rate. In this way, the coded language detection system can detect illegal job-related communications early and contribute to the provision of safe and secure services.

[0064] The coded language detection system according to this embodiment comprises a collection unit, a learning unit, a monitoring unit, a warning unit, and a processing unit. The collection unit collects data held by the police and chat service providers. For example, the collection unit can collect past crime data held by the police and chat logs held by chat service providers. The collection unit inputs this data into a generating AI. The learning unit learns from the data collected by the collection unit and builds a model for detecting coded language exchanges. For example, the learning unit uses the generating AI to build a model for detecting coded language exchanges based on the collected data. The generating AI can determine coded language by considering the surrounding sentences and context in order to detect coded language exchanges. For example, the generating AI determines that "rice cooker" is coded language from the context of "using a rice cooker". The monitoring unit monitors the chat content using the model built by the learning unit. For example, the monitoring unit analyzes the chat content in real time and detects coded language exchanges. The monitoring unit can use the generating AI to analyze the chat content and detect coded language exchanges. For example, the monitoring unit analyzes the context before and after the use of the word "tachi" in open chats or private chats to determine if it is slang. The warning unit issues a warning when the monitoring unit detects the use of slang. The warning unit notifies chat service providers and the police, for example, when it detects the use of slang. The warning unit can issue warnings using generative AI when it detects the use of slang. For example, the warning unit notifies that accounts where slang is detected should be banned early. The processing unit bans accounts based on the warnings issued by the warning unit. The processing unit bans accounts where slang is detected based on the warnings issued by the warning unit. The processing unit can ban accounts based on the warnings issued by the warning unit using generative AI. For example, by banning accounts where slang is detected early, the processing unit can help prevent crime.As a result, the coded language detection system according to this embodiment can detect illegal part-time job transactions at an early stage, leading to the provision of safe and secure services.

[0065] The data collection unit collects data held by the police and chat service providers. Specifically, it can collect past crime data held by the police and chat logs held by chat service providers. The police's past crime data includes the type of crime, date and time of occurrence, location, information on those involved, and the slang used. This data is important for understanding crime trends and slang usage patterns. Chat logs held by chat service providers include message exchanges between users, date and time of sending, sender and recipient information, and the words and phrases used. This data is necessary to understand the usage of slang and its context. The data collection unit inputs this data into a generating AI. The generating AI analyzes the collected data and uses it as foundational data to build a model for detecting slang exchanges. When collecting data, the data collection unit takes full consideration of privacy protection and data security, and collects data through appropriate procedures. For example, data collection includes obtaining permission from relevant agencies and anonymizing the data. This allows the data collection unit to collect data efficiently and securely, improving the overall system performance.

[0066] The learning unit learns from the data collected by the collection unit and builds a model for detecting slang. Specifically, it uses a generative AI to build a model for detecting slang based on the collected data. The generative AI can determine slang by considering the surrounding sentences and context in order to detect slang. For example, the generative AI determines that "rice cooker" is slang from the context of "using a rice cooker." By learning from a large amount of data, the generative AI understands the usage patterns and contexts of slang and improves the accuracy of slang detection. The learning unit monitors the learning process of the generative AI and adjusts parameters or adds data as needed. For example, if the generative AI cannot accurately detect a particular slang term, the learning unit adds data related to that slang term and retrains it. The learning unit also evaluates the learning results of the generative AI and verifies the accuracy and reliability of the model. This allows the learning unit to build a model for detecting slang with high accuracy and improve the overall system performance.

[0067] The monitoring unit monitors chat content using a model built by the learning unit. Specifically, it analyzes chat content in real time and detects the use of coded language. The monitoring unit can analyze chat content and detect coded language using generative AI. For example, if the word "tackling" is used in an open chat or private chat, the monitoring unit analyzes the surrounding context to determine whether it is coded language. The generative AI utilizes natural language processing technology to analyze chat content in real time and detect the use of coded language. The generative AI can understand the chat content contextually and detect the use of coded language with high accuracy. Based on the analysis results of the generative AI, the monitoring unit issues a warning when it detects the use of coded language. This allows the monitoring unit to monitor chat content in real time and detect coded language early. Furthermore, the monitoring unit can periodically analyze chat content to understand the trends and patterns of coded language use. This allows the monitoring unit to continuously monitor coded language and improve the reliability and security of the entire system.

[0068] The warning unit issues a warning when the monitoring unit detects coded language exchanges. Specifically, it notifies chat service providers and the police when coded language exchanges are detected. The warning unit can issue warnings when coded language exchanges are detected using a generation AI. For example, the warning unit may notify that accounts that have been detected using coded language should be banned as soon as possible. Based on the analysis results of the generation AI, the warning unit issues an appropriate warning when coded language exchanges are detected. The warning unit can flexibly set the content and target of the warnings. For example, when coded language exchanges are detected, the warning unit can not only issue a warning to the chat service provider but also notify the police. Furthermore, the warning unit can describe the content of the warning in detail, providing the specific content and context of the coded language exchanges. This allows the warning unit to provide information for early detection of coded language exchanges and for appropriate action. In addition, the warning unit records the history of warnings issued so that they can be referenced later. This allows the warning unit to manage the history of responses to coded language exchanges, improving the overall reliability and transparency of the system.

[0069] The processing unit bans accounts based on warnings issued by the warning unit. Specifically, it bans accounts that are detected to be using coded language based on warnings issued by the warning unit. The processing unit can use generated AI to ban accounts based on warnings issued by the warning unit. For example, by banning accounts that are detected to be using coded language early on, the processing unit can help prevent crime. The processing unit receives notifications from the warning unit and checks the details of the target account. It refers to the target account's past chat history and warning history to determine the necessity of banning. When the processing unit executes an account ban, it notifies the user and clearly states the reason and duration of the ban. This allows the user to understand why their account was banned and to take steps to prevent recurrence. Furthermore, the processing unit records information on banned accounts and builds a database to prevent further fraudulent activity. This allows the processing unit to effectively eliminate accounts that use coded language and improve the overall security of the system. In addition, the processing unit continuously monitors accounts even after the ban is executed and strives to prevent recurrence. This allows the processing unit to detect accounts using coded language early on and respond quickly.

[0070] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can reduce the frequency of data collection to lessen the user's burden. If the user is relaxed, the data collection unit can increase the frequency of data collection to collect more data. If the user is in a hurry, the data collection unit can adjust the timing of data collection to avoid interrupting the user's activities. In this way, by adjusting the timing of data collection based on the user's emotions, the user's burden can be reduced and more data can be collected. 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 data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0071] The data collection unit can dynamically change the types of data it collects based on past crime data and the frequency of slang usage. For example, the data collection unit can analyze past crime data and prioritize the collection of slang that occurred frequently during specific periods. The data collection unit can focus on collecting specific data during times when slang is frequently used. If a newly discovered slang term is found, the data collection unit can prioritize the collection of data related to that term. This allows for more effective detection of slang interactions by dynamically changing the types of data collected based on past crime data and the frequency of slang usage. Some or all of the above-described processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input past crime data and slang usage frequency data into a generating AI and have the generating AI change the types of data to collect.

[0072] The data collection unit can monitor the frequency of occurrence of specific keywords and phrases in real time during data collection and automatically update the data to be collected. For example, if a particular keyword is used frequently, the data collection unit will prioritize the collection of data related to that keyword. The data collection unit can monitor the frequency of keyword occurrences in real time and dynamically change the data to be collected. When a new keyword appears, the data collection unit can aggregate the data related to that keyword. This allows for more effective detection of coded language exchanges by monitoring the frequency of occurrence of specific keywords and phrases in real time and automatically updating the data to be collected. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input frequency data of specific keywords and phrases into a generating AI and have the generating AI update the data to be collected.

[0073] The data collection unit can estimate the user's emotions and prioritize the data to be collected based on the estimated emotions. For example, if the user is stressed, the data collection unit will postpone the collection of less important data. If the user is relaxed, the data collection unit can prioritize the collection of more important data. If the user is in a hurry, the data collection unit can prioritize data that can be collected quickly. This reduces the burden on the user and allows for more effective data collection by prioritizing the data to be collected based on 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 data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI determine the priority of the data to be collected.

[0074] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, if the user is in a specific area, the data collection unit can prioritize the collection of data related to that area. Based on the user's location information, the data collection unit can collect crime data in the vicinity. If the user is on the move, the data collection unit can collect data related to the area the user is moving to. This allows for more effective data collection by prioritizing the collection of highly relevant data by considering the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI perform the collection of highly relevant data.

[0075] The data collection unit can analyze a user's social media activity and collect relevant data during data collection. For example, if a user is active on a particular social media platform, the data collection unit can collect data related to that activity. The data collection unit can analyze the content of a user's social media posts and collect relevant data. The data collection unit can analyze the activities of a user's social media followers and friends and collect relevant data. This allows for more effective data collection by analyzing a user's social media activity and collecting relevant data. Some or all of the above-described processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's social media activity data into a generating AI and have the generating AI perform the collection of relevant data.

[0076] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit can prioritize learning data to reduce stress. If the user is relaxed, the learning unit can learn data to maintain that relaxed state. If the user is in a hurry, the learning unit can prioritize data that can be learned quickly. This allows for more effective learning by selecting training data based on 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 learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI perform the selection of training data.

[0077] The learning unit can dynamically adjust the model parameters during training based on the frequency and context of slang usage. For example, if slang is frequently used, the learning unit adjusts the model parameters to improve the accuracy of slang detection. The learning unit can determine the meaning of slang based on context and adjust the model parameters accordingly. If a new slang term is discovered, the learning unit can dynamically adjust the model parameters to accommodate it. This allows for improved slang detection accuracy by dynamically adjusting the model parameters based on the frequency and context of slang usage. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input slang frequency data and context data into a generating AI and have the generating AI adjust the model parameters.

[0078] The learning unit can build multilingual models to handle different languages ​​and dialects during training. For example, the learning unit can learn slang used in different languages ​​and build a multilingual model. The learning unit can learn slang specific to a dialect and build a model that corresponds to that dialect. The learning unit can use the multilingual models to detect slang exchanges in different languages ​​and dialects. By building multilingual models to handle different languages ​​and dialects, a wider range of slang exchanges can be detected. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input data in different languages ​​and dialects into a generative AI and have the generative AI perform the construction of a multilingual model.

[0079] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency to alleviate the user's burden. If the user is relaxed, the learning unit can increase the learning frequency to learn more data. If the user is in a hurry, the learning unit can adjust the learning frequency to avoid interfering with the user's activities. By adjusting the learning frequency based on the user's emotions, the user's burden is reduced and learning can be performed more effectively. 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 learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user emotion data into the generative AI and have the generative AI adjust the learning frequency.

[0080] The learning unit can weight the training data based on specific time periods or events during training. For example, the learning unit can prioritize learning slang that frequently occurs during specific time periods. The learning unit can learn slang related to events and weight them accordingly. The learning unit can dynamically adjust the weighting of the training data based on time periods or events. This allows for more effective training by weighting the training data based on specific time periods or events. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data for specific time periods or events into a generating AI and have the generating AI perform the weighting of the training data.

[0081] The learning unit can integrate data from different platforms during training. For example, the learning unit can integrate data collected from social networking services (SNS) and forums. The learning unit can learn slang used on different platforms and build an integrated model. The learning unit can integrate and learn data while considering the characteristics of each platform. This allows for the detection of a wider range of slang interactions by integrating and learning data from different platforms. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data from different platforms into a generative AI and have the generative AI perform the data integration.

[0082] The monitoring unit can estimate the user's emotions and adjust the monitoring criteria based on the estimated emotions. For example, if the user is stressed, the monitoring unit can reduce the frequency of monitoring to alleviate the user's burden. If the user is relaxed, the monitoring unit can increase the frequency of monitoring to monitor more data. If the user is in a hurry, the monitoring unit can adjust the timing of monitoring to avoid interfering with the user's activities. In this way, by adjusting the monitoring criteria based on the user's emotions, the burden on the user can be reduced and monitoring can be performed more effectively. 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 monitoring unit may be performed using AI, for example, or not using AI. For example, the monitoring unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the monitoring criteria.

[0083] The monitoring unit can perform analysis considering not only the chat content but also the sender's attribute information during monitoring. For example, the monitoring unit can prioritize the analysis of slang common in a specific age group based on the sender's age information. The monitoring unit can analyze gender-related slang considering the sender's gender information. The monitoring unit can perform slang analysis by comprehensively considering the sender's attribute information. As a result, by performing analysis considering not only the chat content but also the sender's attribute information, the exchange of slang can be detected more effectively. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the sender's attribute information into a generating AI and have the generating AI perform slang analysis.

[0084] The monitoring unit can translate chat content in real time and perform multilingual analysis during monitoring. For example, the monitoring unit can translate chat content in real time and analyze slang exchanges in different languages. The monitoring unit can perform multilingual analysis and improve the accuracy of detecting slang in different languages. The monitoring unit can analyze slang exchanges based on the content translated in real time. As a result, by translating chat content in real time and performing multilingual analysis, a wider range of slang exchanges can be detected. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input chat content into a generating AI and have the generating AI perform real-time translation and analysis.

[0085] The warning unit can estimate the user's emotions and adjust the content and expression of the warning based on the estimated emotions. For example, if the user is stressed, the warning unit can issue a warning in a gentle tone. If the user is relaxed, the warning unit can issue a warning with detailed information. If the user is in a hurry, the warning unit can issue a concise and quick warning. By adjusting the content and expression of the warning based on the user's emotions, the user's burden can be reduced and warnings can be issued more effectively. 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 warning unit may be performed using AI, for example, or not using AI. For example, the warning unit can input user emotion data into the generative AI and have the generative AI adjust the content and expression of the warning.

[0086] The warning unit can determine the priority of warnings by referring to past warning history when an warning is issued. For example, if a similar warning has been issued in the past, the warning unit will give that warning a higher priority. The warning unit can analyze past warning history and prioritize issuing warnings of high importance. The warning unit can dynamically adjust the priority of warnings based on the warning history. This allows for more effective warnings by determining the priority of warnings by referring to past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input past warning history data into a generating AI and have the generating AI perform the determination of warning priorities.

[0087] The warning unit can display warnings in multiple languages ​​when an alert is issued, accommodating users of different languages. For example, the warning unit can automatically translate warnings based on the user's language settings. The warning unit can display warnings in multiple languages, accommodating users of different languages. If the user selects a specific language, the warning unit can display the warning in that language. This allows the warning unit to accommodate users of different languages ​​by displaying warnings in multiple languages. Some or all of the above-described processes in the warning unit may be performed using AI, or not. For example, the warning unit can input warning content into a generating AI and have the generating AI perform the multilingual display.

[0088] The warning unit can estimate the user's emotions and adjust the timing of warnings based on the estimated emotions. For example, if the user is stressed, the warning unit can delay the warning. If the user is relaxed, the warning unit can advance the warning. If the user is in a hurry, the warning unit can issue a warning quickly. By adjusting the timing of warnings based on the user's emotions, the user's burden can be reduced and warnings can be issued more effectively. 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 warning unit may be performed using AI, for example, or not using AI. For example, the warning unit can input user emotion data into a generative AI and have the generative AI adjust the timing of warnings.

[0089] The warning unit can optimize the content of a warning based on the user's device information when a warning is issued. For example, if the user is using a smartphone, the warning unit can display a warning that is adapted to the screen size. If the user is using a tablet, the warning unit can display a warning optimized for a larger screen. If the user is using a smartwatch, the warning unit can display a concise and highly visible warning. This allows for more effective warnings by optimizing the content of the warning based on the user's device information. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's device information into a generating AI and have the generating AI perform the optimization of the warning content.

[0090] The warning unit can customize the content of a warning based on the user's past behavior history. For example, the warning unit can customize the content of a warning based on the user's past behavior history. The warning unit can adjust the content of a warning by referring to warnings the user has received in the past. The warning unit can analyze the user's behavior patterns and provide the most appropriate warning content. This allows for more effective warnings by customizing the content of warnings based on the user's past behavior history. Some or all of the above-described processes in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's past behavior history data into a generating AI and have the generating AI perform the customization of the warning content.

[0091] The processing unit can estimate the user's emotions and adjust the account ban criteria based on the estimated emotions. For example, if the user is stressed, the processing unit can relax the account ban criteria. If the user is relaxed, the processing unit can tighten the account ban criteria. If the user is in a hurry, the processing unit can quickly ban the account. By adjusting the account ban criteria based on the user's emotions, the burden on the user can be reduced and account bans can be carried out more effectively. 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 processing unit may be performed using AI or not using AI. For example, the processing unit can input user emotion data into a generative AI and have the generative AI adjust the account ban criteria.

[0092] The processing unit can determine the priority of an account ban by referring to past ban history. For example, the processing unit will prioritize banning an account if it has committed similar violations in the past. The processing unit can analyze past ban history and prioritize banning accounts of high importance. The processing unit can dynamically adjust the priority of processing based on the ban history. This allows for more effective account banning by determining the priority of processing by referring to past ban history. Some or all of the above processing in the processing unit may be performed using AI, for example, or without AI. For example, the processing unit can input past ban history data into a generating AI and have the generating AI determine the priority of processing.

[0093] The processing unit can coordinate across different platforms and implement bans on multiple platforms when banning accounts. For example, if the same account is being used on different platforms, the processing unit will coordinate to implement the ban. The processing unit can share information between platforms and implement account bans efficiently. The processing unit can coordinate bans on multiple platforms and take effective countermeasures. As a result, by coordinating across different platforms and implementing bans on multiple platforms, account bans can be carried out more effectively. Some or all of the above-described processes in the processing unit may be performed using AI, for example, or without AI. For example, the processing unit can input data from different platforms into a generating AI and have the generating AI execute the process of implementing a coordinated ban.

[0094] The processing unit can estimate the user's emotions and adjust the method of notifying the user of an account ban based on the estimated emotions. For example, if the user is stressed, the processing unit can send a ban notification in a calm tone. If the user is relaxed, the processing unit can send a ban notification with detailed information. If the user is in a hurry, the processing unit can send a concise and quick ban notification. By adjusting the method of notifying the user of an account ban based on their emotions, the burden on the user can be reduced and account bans can be carried out more effectively. 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 processing unit may be performed using AI or not using AI. For example, the processing unit can input user emotion data into a generative AI and have the generative AI adjust the notification method.

[0095] The processing unit can select the optimal processing method when an account is banned, taking into account the user's geographical location information. For example, if the user is in a specific region, the processing unit can select a processing method related to that region. Based on the user's location information, the processing unit can select the optimal method for notifying the user of the ban. If the user is on the move, the processing unit can select a processing method related to the destination region. By selecting the optimal processing method while considering the user's geographical location information, account bans can be carried out more effectively. Some or all of the above processing in the processing unit may be performed using AI, for example, or without AI. For example, the processing unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal processing method.

[0096] The processing unit can analyze a user's social media activity and ban related accounts when banning an account. For example, the processing unit can analyze a user's social media activity, identify related accounts, and ban them. The processing unit can analyze the accounts of a user's followers and friends and ban related accounts. The processing unit can ban related accounts based on the user's social media activity history. This allows for more effective account banning by analyzing a user's social media activity and banning related accounts as well. Some or all of the above processing in the processing unit may be performed using AI, for example, or without AI. For example, the processing unit can input the user's social media activity data into a generating AI and have the generating AI perform the banning of related accounts.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on those emotions. For example, if the user is stressed, the unit can reduce the frequency of data collection to lessen the user's burden. Conversely, if the user is relaxed, the unit can increase the frequency of data collection to collect more data. Furthermore, if the user is in a hurry, the unit can adjust the timing of data collection to avoid interrupting the user's activities. In this way, by adjusting the timing of data collection based on the user's emotions, the user's burden can be reduced and more data can be collected.

[0099] The data collection unit can dynamically change the types of data it collects based on past crime data and the frequency of slang usage. For example, it can analyze past crime data and prioritize the collection of slang that was frequently used during specific periods. It can also focus on collecting specific data during times when slang is frequently used. Furthermore, if a new slang term is discovered, it can prioritize the collection of data related to that term. By dynamically changing the types of data collected based on past crime data and the frequency of slang usage, it becomes possible to more effectively detect the use of slang.

[0100] The data collection unit can monitor the frequency of specific keywords and phrases in real time during data collection and automatically update the collection target. For example, if a particular keyword is used frequently, data related to that keyword can be prioritized for collection. It can also dynamically change the collection target by monitoring keyword frequency in real time. Furthermore, if a new keyword appears, data related to that keyword can be aggregated. This allows for more effective detection of coded language exchanges by monitoring the frequency of specific keywords and phrases in real time and automatically updating the collection target.

[0101] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location. For example, if a user is in a specific area, it can prioritize the collection of data related to that area. It can also collect crime data in the vicinity based on the user's location. Furthermore, if a user is on the move, it can collect data related to the area they are moving to. This allows for more effective data collection by prioritizing the collection of highly relevant data while considering the user's geographical location.

[0102] The data collection unit can analyze a user's social media activity and collect relevant data. For example, if a user is active on a specific social media platform, it can collect data related to that activity. It can also analyze the content of a user's social media posts and collect relevant data. Furthermore, it can analyze the activities of a user's social media followers and friends and collect relevant data. This allows for more effective data collection by analyzing a user's social media activity and collecting relevant data.

[0103] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is stressed, it can prioritize learning data that helps reduce stress. If the user is relaxed, it can prioritize learning data that helps maintain that relaxed state. Furthermore, if the user is in a hurry, it can prioritize data that allows for quick learning. By selecting training data based on the user's emotions, learning can be performed more effectively.

[0104] The learning unit can dynamically adjust the model parameters during training based on the frequency and context of slang usage. For example, if slang is frequently used, the model parameters can be adjusted to improve the accuracy of slang detection. It can also determine the meaning of slang based on context and adjust the model parameters accordingly. Furthermore, if new slang is discovered, the model parameters can be dynamically adjusted to accommodate it. This allows for improved slang detection accuracy by dynamically adjusting the model parameters based on the frequency and context of slang usage.

[0105] The learning unit can build multilingual models to handle different languages ​​and dialects during training. For example, it can learn slang used in different languages ​​and build multilingual models. It can also learn slang specific to a dialect and build models that handle dialects. Furthermore, it can use the multilingual models to detect slang exchanges in different languages ​​and dialects. By building multilingual models that can handle different languages ​​and dialects, it becomes possible to detect a wider range of slang exchanges.

[0106] The monitoring unit can estimate the user's emotions and adjust the monitoring criteria based on those emotions. For example, if the user is stressed, the monitoring frequency can be reduced to lessen the user's burden. Conversely, if the user is relaxed, the monitoring frequency can be increased to collect more data. Furthermore, if the user is in a hurry, the timing of monitoring can be adjusted to avoid interrupting the user's activities. In this way, by adjusting the monitoring criteria based on the user's emotions, the user's burden can be reduced and monitoring can be performed more effectively.

[0107] The monitoring unit can analyze not only the chat content but also the sender's attribute information during monitoring. For example, it can prioritize the analysis of slang common in a specific age group based on the sender's age information. It can also analyze gender-related slang by considering the sender's gender information. Furthermore, it can analyze slang by comprehensively considering the sender's attribute information. As a result, by analyzing not only the chat content but also the sender's attribute information, it can more effectively detect the exchange of slang.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The data collection unit collects data held by the police and chat service providers. For example, it collects past crime data held by the police and chat logs held by chat service providers, and inputs this data into the generating AI. Step 2: The learning unit learns from the data collected by the collection unit and builds a model to detect slang. Using generative AI, it builds a model to detect slang based on the collected data and determines the slang by considering the surrounding sentences and context. Step 3: The monitoring unit monitors the chat content using the model built by the learning unit. It analyzes the chat content in real time and detects the use of coded language. Generative AI can be used to analyze the chat content and detect the use of coded language. Step 4: The warning unit issues a warning when the monitoring unit detects the use of coded language. When coded language is detected, it notifies the chat service provider and the police, and requests that the account in question be banned as soon as possible. Step 5: The processing unit bans accounts based on warnings issued by the warning unit. Based on warnings issued by the warning unit, accounts that have been detected to be using coded language are banned to help prevent crime.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] Each of the multiple elements described above, including the collection unit, learning unit, monitoring unit, warning unit, and processing unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects data held by the police and chat service providers. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns from the collected data to build a model for detecting coded language exchanges. The monitoring unit is implemented by the control unit 46A of the smart device 14 and analyzes the chat content in real time to detect coded language exchanges. The warning unit is implemented by the specific processing unit 290 of the data processing unit 12 and issues a warning when coded language exchanges are detected. The processing unit is implemented by the control unit 46A of the smart device 14 and bans accounts based on the warnings. 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.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the collection unit, learning unit, monitoring unit, warning unit, and processing unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects data held by the police and chat service providers. The learning unit is implemented by the identification processing unit 290 of the data processing unit 12 and learns from the collected data to build a model for detecting coded language exchanges. The monitoring unit is implemented by the control unit 46A of the smart glasses 214 and analyzes the chat content in real time to detect coded language exchanges. The warning unit is implemented by the identification processing unit 290 of the data processing unit 12 and issues a warning when coded language exchanges are detected. The processing unit is implemented by the control unit 46A of the smart glasses 214 and bans accounts based on the warnings. 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.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the collection unit, learning unit, monitoring unit, warning unit, and processing unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects data held by the police and chat service providers. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the collected data to build a model for detecting coded language exchanges. The monitoring unit is implemented by the control unit 46A of the headset terminal 314 and analyzes the chat content in real time to detect coded language exchanges. The warning unit is implemented by the specific processing unit 290 of the data processing unit 12 and issues a warning when coded language exchanges are detected. The processing unit is implemented by the control unit 46A of the headset terminal 314 and bans accounts based on the warnings. 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.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] Each of the multiple elements described above, including the collection unit, learning unit, monitoring unit, warning unit, and processing unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects data held by the police and chat service providers. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns from the collected data to build a model for detecting coded language exchanges. The monitoring unit is implemented by the control unit 46A of the robot 414 and analyzes the chat content in real time to detect coded language exchanges. The warning unit is implemented by the specific processing unit 290 of the data processing unit 12 and issues a warning when coded language exchanges are detected. The processing unit is implemented by the control unit 46A of the robot 414 and bans accounts based on the warnings. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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."

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] (Note 1) The collection unit collects data held by the police and chat service providers, A learning unit learns from the data collected by the aforementioned collection unit and constructs a model for detecting the exchange of coded language, A monitoring unit that monitors the chat content using the model constructed by the learning unit, A warning unit that issues a warning when the monitoring unit detects the exchange of coded language, The system includes a processing unit that bans an account based on a warning issued by the aforementioned warning unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is The types of data collected are dynamically changed based on past crime data and the frequency of slang usage. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is During data collection, the frequency of specific keywords and phrases is monitored in real time, and the data collection targets are automatically updated. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting data, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is During data collection, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, During training, the model parameters are dynamically adjusted based on the frequency and context of slang usage. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, During training, we build multilingual models to handle different languages ​​and dialects. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, During training, the training data is weighted based on specific time periods or events. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned learning unit, During training, data from different platforms is integrated for learning. The system described in Appendix 1, characterized by the features described herein. (Note 14) The monitoring unit, The system estimates user sentiment and adjusts monitoring criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The monitoring unit, During monitoring, the analysis will consider not only the chat content but also the sender's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The monitoring unit, During monitoring, the chat content is translated in real time, and multilingual analysis is performed. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned warning unit is The system estimates the user's emotions and adjusts the content and expression of warnings based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned warning unit is When a warning is issued, the system prioritizes the warning by referring to past warning history. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned warning unit is When a warning is issued, the warning content will be displayed in multiple languages ​​to accommodate users with different language skills. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned warning unit is It estimates the user's emotions and adjusts the timing of warnings based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned warning unit is When a warning is issued, the content of the warning is optimized based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned warning unit is When a warning is issued, the content of the warning is customized based on the user's past behavior history. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned processing unit, We estimate user sentiment and adjust account ban criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned processing unit, When banning an account, the priority of the process is determined by referring to the past ban history. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned processing unit, When an account is banned, coordination between different platforms is performed to implement a ban across multiple platforms. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned processing unit, We estimate the user's sentiment and adjust the account ban notification method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned processing unit, When an account is banned, the system will select the most appropriate action based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned processing unit, When an account is banned, the system analyzes the user's social media activity and bans related accounts as well. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0182] 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. The collection unit collects data held by the police and chat service providers, A learning unit learns from the data collected by the aforementioned collection unit and constructs a model for detecting the exchange of coded language, A monitoring unit that monitors the chat content using the model constructed by the learning unit, A warning unit that issues a warning when the monitoring unit detects the exchange of coded language, The system includes a processing unit that bans an account based on a warning issued by the aforementioned warning unit. A system characterized by the following features.

2. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system according to feature 1.

3. The aforementioned collection unit is The types of data collected are dynamically changed based on past crime data and the frequency of slang usage. The system according to feature 1.

4. The aforementioned collection unit is During data collection, the frequency of specific keywords and phrases is monitored in real time, and the data collection targets are automatically updated. The system according to feature 1.

5. The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system according to feature 1.

6. The aforementioned collection unit is When collecting data, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system according to feature 1.

7. The aforementioned collection unit is During data collection, the system analyzes users' social media activity and collects relevant data. The system according to feature 1.

8. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system according to feature 1.

Images