system

Abstract

To provide a system capable of efficiently detecting slander messages on SNS and taking appropriate measures.SOLUTION: A system in an embodiment includes a filtering unit, a collection unit, a generation unit, and a distribution unit. The filtering unit analyzes messages on SNS and determines the degree of slander. The collection unit collects slander messages detected by the filtering unit. The generation unit creates documents of damage reports and evidence based on the messages collected by the collection unit. The distribution unit distributes a mental care message based on the documents created by the generation unit.SELECTED DRAWING: Figure 1

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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to efficiently detect defamatory messages on SNS and take appropriate measures.

[0005] The system according to the embodiment aims to efficiently detect defamatory messages on SNS and take appropriate measures.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a filtering unit, a collection unit, a generation unit, and a distribution unit. The filtering unit analyzes messages on social media and determines the degree of defamation. The collection unit collects the defamatory messages detected by the filtering unit. The generation unit creates victim reports and evidence documents based on the messages collected by the collection unit. The distribution unit distributes mental health care messages based on the documents created by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently detect defamatory messages on social media and take appropriate countermeasures. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The defamation prevention system according to an embodiment of the present invention is a system that prevents defamation on social media and supports victims. This defamation prevention system uses a generation AI to analyze messages on social media and determine the degree of defamation. Next, it collects excessive defamatory messages and automatically creates documents such as police reports. Furthermore, it provides a function to deliver mental health support messages. For example, the defamation prevention system filters out excessive defamation directed at a designated person. The generation AI analyzes messages on social media and determines the degree of defamation. Next, the defamation prevention system collects excessive defamatory messages and automatically creates documents such as police reports. Based on the defamatory messages collected by the generation AI, it automatically creates police reports and evidence documents. Furthermore, the defamation prevention system delivers mental health support messages. The AI ​​analyzes the victim's mental state and automatically creates and delivers appropriate mental care messages. This service is expected to reduce the number of suicides caused by online defamation and harassment. In this way, the defamation prevention system can prevent online defamation and harassment and support victims.

[0029] The defamation prevention system according to this embodiment comprises a filtering unit, a collection unit, a generation unit, and a distribution unit. The filtering unit analyzes messages on social media and determines the degree of defamation. The filtering unit, for example, detects specific keywords or phrases and determines the degree of defamation. The filtering unit uses a generation AI to analyze messages on social media and determines the degree of defamation. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze messages and determines the degree of defamation. The collection unit collects defamatory messages detected by the filtering unit. The collection unit, for example, stores the detected defamatory messages in a database. The collection unit uses a generation AI to collect detected defamatory messages. For example, the generation AI automatically classifies the detected messages and stores them in a database. The generation unit creates victim reports and evidence documents based on the messages collected by the collection unit. The generation unit automatically creates legally valid victim reports and evidence documents based on collected messages. The generation unit uses a generation AI to create victim reports and evidence documents based on collected messages. For example, the generation AI analyzes the collected messages, extracts necessary information, and creates victim reports and evidence documents. The distribution unit distributes mental care messages based on the documents created by the generation unit. The distribution unit analyzes the victim's mental state and automatically creates and distributes appropriate mental care messages. The distribution unit uses a generation AI to analyze the victim's mental state and automatically creates and distributes mental care messages. For example, the generation AI analyzes the victim's mental state and creates mental care messages that include words of encouragement and methods for providing psychological support. As a result, the defamation prevention system according to this embodiment can prevent defamation on social media and support victims.

[0030] The filtering unit analyzes messages on social media and determines the degree of defamation. For example, the filtering unit detects specific keywords or phrases and determines the degree of defamation. Specifically, the filtering unit uses natural language processing techniques to analyze the content of messages and detect keywords or phrases that may be defamatory. This includes word frequency analysis and contextual analysis. Furthermore, it uses generative AI to analyze messages on social media and determine the degree of defamation. The generative AI uses text generation AI (e.g., LLM) to analyze messages and determine the degree of defamation. The generative AI learns from past data and has the ability to identify patterns of defamation. For example, the generative AI performs sentiment analysis on messages and determines messages with strong negative emotions as having a high degree of defamation. The generative AI also understands context and evaluates the degree of defamation considering the meaning of the entire sentence, not just keyword matching. This allows the filtering unit to perform more advanced analysis without relying on simple keyword matching. Furthermore, the filtering unit can continuously learn and adapt to new patterns and trends in defamation. For example, even if new slang or jargon emerges, the generating AI can quickly learn it and respond appropriately. As a result, the filtering unit can always perform highly accurate defamation detection based on the latest information, effectively preventing defamation on social media.

[0031] The collection unit collects defamatory messages detected by the filtering unit. For example, the collection unit stores the detected defamatory messages in a database. Specifically, the collection unit receives defamatory messages sent from the filtering unit and stores them in the database in an appropriate format. The collection unit uses a generation AI to collect detected defamatory messages. The generation AI automatically classifies the detected messages and stores them in the database. For example, the generation AI analyzes metadata such as message content, sender, and date and time of transmission, and classifies the messages based on this information. Furthermore, the collection unit can evaluate the importance and urgency of messages, prioritize them, and store them accordingly. This allows the collection unit to efficiently manage a vast amount of defamatory messages and quickly search and extract necessary information. The collection unit also ensures database security and takes measures to prevent unauthorized access to stored messages. For example, it strictly manages access permissions to the database and protects data using encryption technology. This enables the collection unit to securely collect and store defamatory messages, thereby improving the overall reliability of the system.

[0032] The generation unit creates victim reports and evidence documents based on messages collected by the collection unit. For example, the generation unit automatically creates legally valid victim reports and evidence documents based on collected messages. Specifically, the generation unit analyzes the content of collected messages, extracts necessary information, and creates victim reports and evidence documents. The generation unit uses generation AI to create victim reports and evidence documents based on collected messages. The generation AI analyzes collected messages, extracts necessary information, and creates victim reports and evidence documents. For example, the generation AI automatically extracts information such as the message sender, date and time of transmission, and content, and uses this information to create victim reports and evidence documents. Furthermore, the generation unit can automatically apply formats and wording to meet legal requirements, creating legally valid documents. This allows the generation unit to support victims in quickly taking legal action. The generation unit also authenticates the created documents with digital signatures and timestamps to ensure the reliability and evidentiary value of the documents. This allows the generation unit to reliably provide victims with the necessary evidence when taking legal action and to support their legal response to defamation.

[0033] The distribution unit delivers mental health care messages based on documents created by the generation unit. For example, the distribution unit analyzes the victim's mental state and automatically creates and delivers appropriate mental health care messages. Specifically, the distribution unit monitors the victim's social media activity and message content to analyze their mental state. The generation AI analyzes the victim's mental state and creates mental health care messages that include words of encouragement and methods for providing psychological support. For example, the generation AI performs an emotional analysis of the victim's messages, and if negative emotions are strong, it creates a mental health care message that includes words of encouragement and methods for providing psychological support. Furthermore, the distribution unit can adjust the content and timing of the mental health care messages according to the victim's mental state. This allows the distribution unit to provide victims with appropriate mental health care messages at the right time, supporting their mental health. The distribution unit can also collect feedback from victims and continuously improve the content and delivery methods of mental health care messages. This allows the distribution unit to provide effective mental health care to victims and mitigate the psychological damage caused by defamation.

[0034] The filtering unit can detect specific keywords or phrases and determine the degree of defamation. For example, the filtering unit can detect specific keywords or phrases and determine the degree of defamation. For example, the filtering unit can detect insulting words or aggressive expressions and determine the degree of defamation. The filtering unit can also determine the degree of defamation using contextual analysis. For example, the filtering unit can analyze the context before and after a message and determine the degree of defamation. This allows for accurate determination of the degree of defamation by detecting specific keywords or phrases. Some or all of the above-described processes in the filtering unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the filtering unit can input specific keywords or phrases into a generation AI and have the generation AI perform the determination of the degree of defamation.

[0035] The collection unit can save detected defamatory messages. For example, the collection unit can save detected defamatory messages to a database. For example, the collection unit can automatically classify detected messages and save them to a database. The collection unit can also save messages in file format. For example, the collection unit can save detected messages as text files or CSV files. By saving defamatory messages, they can be used as evidence later. Some or all of the above processing in the collection unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the collection unit can input detected defamatory messages into a generation AI and have the generation AI classify and save the messages.

[0036] The generation unit can create victim reports and evidence documents based on collected messages. For example, the generation unit can automatically create legally valid victim reports and evidence documents based on collected messages. For example, the generation unit can analyze collected messages, extract necessary information, and create victim reports and evidence documents. The generation unit can also create documents in a format that can be submitted as evidence based on collected messages. For example, the generation unit can create documents in PDF format or printable format from collected messages. This reduces the burden on victims by automatically creating victim reports and evidence documents. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input collected messages into a generation AI and have the generation AI create victim reports and evidence documents.

[0037] The distribution unit can analyze the victim's mental state and automatically create and distribute mental care messages. For example, the distribution unit can analyze the victim's mental state and automatically create and distribute appropriate mental care messages. For example, the distribution unit can analyze the victim's mental state and create mental care messages that include words of encouragement and methods for providing psychological support. The distribution unit can also adjust the content of the mental care messages according to the victim's mental state. For example, if the victim is feeling stressed, the distribution unit can distribute a mental care message with a relaxing effect. This allows for the provision of emotional support by providing mental care to the victim. Some or all of the above processing in the distribution unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the distribution unit can input the victim's mental state into a generation AI and have the generation AI create and distribute mental care messages.

[0038] The filtering unit can optimize its filtering algorithm by referring to past defamation data. For example, the filtering unit can analyze past defamation data to identify frequently occurring keywords and phrases and reflect them in the filtering algorithm. The filtering unit can also learn offensive expressions used in specific contexts from past defamation data and incorporate them into the filtering algorithm. Furthermore, the filtering unit can quantify the degree of defamation based on past defamation data and adjust the threshold of the filtering algorithm. This improves the accuracy of the filtering algorithm by referring to past data. Some or all of the above processing in the filtering unit may be performed using generative AI, or it may be performed without generative AI. For example, the filtering unit can input past defamation data into generative AI and have the generative AI perform the optimization of the filtering algorithm.

[0039] The filtering unit can perform filtering by considering the attribute information of the message sender. For example, if the message sender has a history of defamation, the filtering unit will tighten the filtering criteria. Furthermore, if the message sender is anonymous, the filtering unit can strengthen the filtering criteria and increase the sensitivity to detecting defamation. In addition, if the message sender has specific attributes (e.g., age, gender), the filtering unit can adjust the filtering criteria based on those attributes. This improves the accuracy of filtering by considering the sender's attribute information. Some or all of the above processing in the filtering unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the filtering unit can input the message sender's attribute information into a generative AI and have the generative AI adjust the filtering criteria.

[0040] The filtering unit can perform filtering while considering the geographical distribution of messages. For example, if the message sender is from a specific region, the filtering unit will perform filtering while considering expressions specific to that region. Furthermore, if the message senders are from different regions, the filtering unit can analyze regional trends in defamation and adjust the filtering criteria accordingly. Additionally, if the message senders are concentrated in a specific region, the filtering unit can perform filtering based on the culture and language of that region. This allows for accurate detection of region-specific defamation by considering geographical distribution. Some or all of the above processing in the filtering unit may be performed using or without a generative AI. For example, the filtering unit can input geographical distribution data of messages into a generative AI and have the generative AI adjust the filtering criteria.

[0041] The filtering unit can improve the accuracy of filtering by referring to relevant literature for the message. For example, if the content of a message is related to a specific document, the filtering unit will filter by referring to the content of that document. Furthermore, if the content of a message is related to a specific topic, the filtering unit can filter by referring to literature on that topic. In addition, if the content of a message is related to a specific incident or event, the filtering unit can filter by referring to literature on that incident or event. This improves the accuracy of filtering by referring to relevant literature. Some or all of the above processing in the filtering unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the filtering unit can input relevant literature for a message into a generative AI and have the generative AI perform the filtering accuracy improvement.

[0042] The collection unit can improve the accuracy of collection by considering the interrelationships between messages. For example, if the message sender is the same person, the collection unit will also collect other messages from that person. Furthermore, if a message relates to a specific topic, the collection unit can also collect other messages related to that topic. In addition, if a message relates to a specific incident or event, the collection unit can also collect other messages related to that incident or event. This improves the accuracy of collection by considering the interrelationships between messages. Some or all of the above processing in the collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the collection unit can input message interrelationship data into a generative AI and have the generative AI perform the task of improving the accuracy of collection.

[0043] The collection unit can perform data collection while considering the attribute information of the message sender. For example, if a message sender has a history of defamation, the collection unit will prioritize collecting messages from that person. The collection unit can also prioritize collecting messages from anonymous message senders. Furthermore, if a message sender has specific attributes (e.g., age, gender), the collection unit can collect messages based on those attributes. This improves the accuracy of data collection by considering the sender's attribute information. Some or all of the above processing in the collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the collection unit can input the attribute information of the message sender into a generative AI and have the generative AI perform the data collection.

[0044] The collection unit can perform collection while considering the geographical distribution of messages. For example, if the message sender originates from a specific region, the collection unit will consider the region's unique expressions during collection. Furthermore, if the message senders originate from different regions, the collection unit can analyze regional trends in defamation and adjust the collection criteria accordingly. Additionally, if the message senders are concentrated in a particular region, the collection unit can perform collection based on the culture and language of that region. This allows for the accurate collection of region-specific defamation by considering geographical distribution. Some or all of the above processing in the collection unit may be performed using or without a generative AI. For example, the collection unit can input geographical distribution data of messages into a generative AI and have the generative AI adjust the collection criteria.

[0045] The collection unit can improve the accuracy of its collection by referring to relevant literature related to the message. For example, if the content of the message is related to a specific document, the collection unit will refer to the content of that document to perform the collection. Furthermore, if the content of the message is related to a specific topic, the collection unit can also refer to literature related to that topic to perform the collection. In addition, if the content of the message is related to a specific incident or event, the collection unit can also refer to literature related to that incident or event to perform the collection. This improves the accuracy of the collection by referring to relevant literature. Some or all of the above processing in the collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the collection unit can input relevant literature related to the message into a generative AI and have the generative AI perform the task of improving the accuracy of the collection.

[0046] The generation unit can improve the accuracy of generation by considering the interrelationships between messages. For example, if the message sender is the same person, the generation unit will generate documents while also considering other messages from that person. Furthermore, if the messages relate to a specific topic, the generation unit can also generate documents while considering other messages related to that topic. In addition, if the messages relate to a specific incident or event, the generation unit can also generate documents while considering other messages related to that incident or event. This improves the accuracy of generation by considering the interrelationships between messages. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input message interrelationship data into a generation AI and have the generation AI perform the generation accuracy improvement.

[0047] The generation unit can perform generation while considering the attribute information of the message sender. For example, if the message sender has a history of defamation, the generation unit will generate a document based on that person's messages. The generation unit can also generate a document based on the messages of an anonymous message sender. Furthermore, if the message sender has specific attributes (e.g., age, gender), the generation unit can generate a document based on those attributes. This improves the accuracy of generation by considering the sender's attribute information. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the message sender's attribute information into the generation AI and have the generation AI perform the generation.

[0048] The generation unit can perform generation while considering the geographical distribution of messages. For example, if the message sender originates from a specific region, the generation unit will generate documents while considering the unique expressions of that region. Furthermore, if the message senders originate from different regions, the generation unit can analyze regional trends in defamation and adjust the content of the documents accordingly. Additionally, if the message senders are concentrated in a specific region, the generation unit can generate documents based on the culture and language of that region. This allows for the generation of documents that accurately reflect region-specific defamation by considering geographical distribution. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input geographical distribution data of messages into a generation AI and have the generation AI perform the generation.

[0049] The generation unit can improve the accuracy of its generation by referring to relevant literature related to the message. For example, if the content of the message is related to a specific document, the generation unit can generate a document by referring to the content of that document. Furthermore, if the content of the message is related to a specific topic, the generation unit can generate a document by referring to literature on that topic. In addition, if the content of the message is related to a specific incident or event, the generation unit can generate a document by referring to literature on that incident or event. This improves the accuracy of the generation by referring to relevant literature. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input relevant literature related to the message into a generation AI and have the generation AI perform the task of improving the accuracy of the generation.

[0050] The distribution unit can create optimal mental care messages by referring to the victim's past mental state. For example, the distribution unit can refer to mental care messages from periods when the victim was stressed in the past and distribute similar messages. It can also refer to mental care messages from periods when the victim was relaxed in the past and distribute similar messages. Furthermore, it can refer to mental care messages from periods when the victim was angry in the past and distribute similar messages. This allows for the creation of more appropriate mental care messages by referring to past mental states. Some or all of the above processing in the distribution unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the distribution unit can input the victim's past mental state data into a generative AI and have the generative AI create the optimal mental care message.

[0051] The distribution unit can customize mental care messages based on the victim's current living situation. For example, if the victim is currently experiencing stress at work, the distribution unit can deliver a mental care message to alleviate work-related stress. It can also deliver a mental care message to promote relaxation at home if the victim is currently relaxing at home. Furthermore, if the victim is currently experiencing anger at school, the distribution unit can deliver a mental care message to alleviate anger at school. This allows for more appropriate mental care by customizing messages based on the victim's current living situation. Some or all of the above processing in the distribution unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the distribution unit can input data on the victim's current living situation into a generative AI and have the generative AI customize the mental care messages.

[0052] The distribution unit can create optimal mental care messages by considering the victim's geographical location. For example, if the victim lives in a specific region, the distribution unit can create a mental care message based on the culture and language of that region. Furthermore, if the victim lives in a different region, the distribution unit can create a mental care message considering the culture and language of that region. In addition, if the victim moves to a specific region, the distribution unit can create a mental care message based on the culture and language of that region. This allows for the creation of region-specific mental care messages by considering geographical location. Some or all of the above processing in the distribution unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the distribution unit can input the victim's geographical location information into a generative AI and have the generative AI create the optimal mental care message.

[0053] The distribution unit can analyze the victim's social media activity and create mental care messages. For example, if the victim is experiencing stress on social media, the distribution unit can create a mental care message to alleviate that stress. It can also create a mental care message to promote relaxation if the victim is feeling relaxed on social media. Furthermore, if the victim is feeling angry on social media, the distribution unit can create a mental care message to soothe that anger. This allows for the creation of more appropriate mental care messages by analyzing social media activity. Some or all of the above processing in the distribution unit may be performed using or without a generative AI. For example, the distribution unit can input the victim's social media activity data into a generative AI and have the generative AI create the mental care messages.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The filtering unit can perform filtering by considering the sender's past behavior history. For example, if a sender has a history of defamation, their messages will be strictly filtered. Conversely, if a sender has sent many positive messages in the past, their messages can be filtered more loosely. Furthermore, if a sender has caused problems in the past regarding a specific topic, messages related to that topic can be filtered with greater emphasis. In this way, considering the sender's past behavior history improves the accuracy of filtering.

[0056] The collection unit can evaluate the trustworthiness of message senders and collect messages based on that trustworthiness. For example, if a sender's trustworthiness is low, their messages can be prioritized for collection. Conversely, if a sender's trustworthiness is high, their messages can be delayed. Furthermore, if a sender's trustworthiness is moderate, their messages can be collected with the usual priority. This improves the accuracy of collection by considering the trustworthiness of the senders.

[0057] The generation unit can analyze the intent of the message sender and generate documents based on that intent. For example, if the sender's intent is aggressive, it will prioritize generating documents based on that message. If the sender's intent is neutral, it can generate documents based on that message with the usual priority. Furthermore, if the sender's intent is positive, it can postpone the generation of documents based on that message. This improves the accuracy of generation by considering the sender's intent.

[0058] The distribution department can evaluate the effectiveness of past mental health care messages to victims and create new messages based on that evaluation. For example, it can redistribute mental health care messages that were previously effective. It can also improve and redistribute mental health care messages that were previously ineffective. Furthermore, it can re-evaluate mental health care messages whose effectiveness was unclear in the past and distribute them as needed. This allows for more appropriate mental health care by considering the effectiveness of past messages.

[0059] The filtering unit can perform filtering while considering the social influence of the message sender. For example, if a sender has high social influence, their messages will be filtered strictly. If a sender has low social influence, their messages will be filtered more loosely. Furthermore, if a sender has moderate social influence, their messages will be filtered according to normal standards. In this way, considering the sender's social influence improves the accuracy of filtering.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The filtering unit analyzes messages on social media and determines the degree of defamation. For example, it detects specific keywords or phrases and analyzes the message using a generation AI to determine the degree of defamation. Step 2: The collection unit collects the defamatory messages detected by the filtering unit. For example, the detected defamatory messages are stored in a database and automatically classified using a generation AI. Step 3: The generation unit creates victim reports and evidence documents based on the messages collected by the collection unit. For example, it automatically creates legally valid victim reports and evidence documents based on the collected messages and extracts the necessary information using generation AI. Step 4: The distribution unit distributes mental health care messages based on the documents created by the generation unit. For example, it analyzes the victim's mental state and uses generation AI to automatically create and distribute appropriate mental health care messages.

[0062] (Example of form 2) The defamation prevention system according to an embodiment of the present invention is a system that prevents defamation on social media and supports victims. This defamation prevention system uses a generation AI to analyze messages on social media and determine the degree of defamation. Next, it collects excessive defamatory messages and automatically creates documents such as police reports. Furthermore, it provides a function to deliver mental health support messages. For example, the defamation prevention system filters out excessive defamation directed at a designated person. The generation AI analyzes messages on social media and determines the degree of defamation. Next, the defamation prevention system collects excessive defamatory messages and automatically creates documents such as police reports. Based on the defamatory messages collected by the generation AI, it automatically creates police reports and evidence documents. Furthermore, the defamation prevention system delivers mental health support messages. The AI ​​analyzes the victim's mental state and automatically creates and delivers appropriate mental care messages. This service is expected to reduce the number of suicides caused by online defamation and harassment. In this way, the defamation prevention system can prevent online defamation and harassment and support victims.

[0063] The defamation prevention system according to this embodiment comprises a filtering unit, a collection unit, a generation unit, and a distribution unit. The filtering unit analyzes messages on social media and determines the degree of defamation. The filtering unit, for example, detects specific keywords or phrases and determines the degree of defamation. The filtering unit uses a generation AI to analyze messages on social media and determines the degree of defamation. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze messages and determines the degree of defamation. The collection unit collects defamatory messages detected by the filtering unit. The collection unit, for example, stores the detected defamatory messages in a database. The collection unit uses a generation AI to collect detected defamatory messages. For example, the generation AI automatically classifies the detected messages and stores them in a database. The generation unit creates victim reports and evidence documents based on the messages collected by the collection unit. The generation unit automatically creates legally valid victim reports and evidence documents based on collected messages. The generation unit uses a generation AI to create victim reports and evidence documents based on collected messages. For example, the generation AI analyzes the collected messages, extracts necessary information, and creates victim reports and evidence documents. The distribution unit distributes mental care messages based on the documents created by the generation unit. The distribution unit analyzes the victim's mental state and automatically creates and distributes appropriate mental care messages. The distribution unit uses a generation AI to analyze the victim's mental state and automatically creates and distributes mental care messages. For example, the generation AI analyzes the victim's mental state and creates mental care messages that include words of encouragement and methods for providing psychological support. As a result, the defamation prevention system according to this embodiment can prevent defamation on social media and support victims.

[0064] The filtering unit analyzes messages on social media and determines the degree of defamation. For example, the filtering unit detects specific keywords or phrases and determines the degree of defamation. Specifically, the filtering unit uses natural language processing techniques to analyze the content of messages and detect keywords or phrases that may be defamatory. This includes word frequency analysis and contextual analysis. Furthermore, it uses generative AI to analyze messages on social media and determine the degree of defamation. The generative AI uses text generation AI (e.g., LLM) to analyze messages and determine the degree of defamation. The generative AI learns from past data and has the ability to identify patterns of defamation. For example, the generative AI performs sentiment analysis on messages and determines messages with strong negative emotions as having a high degree of defamation. The generative AI also understands context and evaluates the degree of defamation considering the meaning of the entire sentence, not just keyword matching. This allows the filtering unit to perform more advanced analysis without relying on simple keyword matching. Furthermore, the filtering unit can continuously learn and adapt to new patterns and trends in defamation. For example, even if new slang or jargon emerges, the generating AI can quickly learn it and respond appropriately. As a result, the filtering unit can always perform highly accurate defamation detection based on the latest information, effectively preventing defamation on social media.

[0065] The collection unit collects defamatory messages detected by the filtering unit. For example, the collection unit stores the detected defamatory messages in a database. Specifically, the collection unit receives defamatory messages sent from the filtering unit and stores them in the database in an appropriate format. The collection unit uses a generation AI to collect detected defamatory messages. The generation AI automatically classifies the detected messages and stores them in the database. For example, the generation AI analyzes metadata such as message content, sender, and date and time of transmission, and classifies the messages based on this information. Furthermore, the collection unit can evaluate the importance and urgency of messages, prioritize them, and store them accordingly. This allows the collection unit to efficiently manage a vast amount of defamatory messages and quickly search and extract necessary information. The collection unit also ensures database security and takes measures to prevent unauthorized access to stored messages. For example, it strictly manages access permissions to the database and protects data using encryption technology. This enables the collection unit to securely collect and store defamatory messages, thereby improving the overall reliability of the system.

[0066] The generation unit creates victim reports and evidence documents based on messages collected by the collection unit. For example, the generation unit automatically creates legally valid victim reports and evidence documents based on collected messages. Specifically, the generation unit analyzes the content of collected messages, extracts necessary information, and creates victim reports and evidence documents. The generation unit uses generation AI to create victim reports and evidence documents based on collected messages. The generation AI analyzes collected messages, extracts necessary information, and creates victim reports and evidence documents. For example, the generation AI automatically extracts information such as the message sender, date and time of transmission, and content, and uses this information to create victim reports and evidence documents. Furthermore, the generation unit can automatically apply formats and wording to meet legal requirements, creating legally valid documents. This allows the generation unit to support victims in quickly taking legal action. The generation unit also authenticates the created documents with digital signatures and timestamps to ensure the reliability and evidentiary value of the documents. This allows the generation unit to reliably provide victims with the necessary evidence when taking legal action and to support their legal response to defamation.

[0067] The distribution unit delivers mental health care messages based on documents created by the generation unit. For example, the distribution unit analyzes the victim's mental state and automatically creates and delivers appropriate mental health care messages. Specifically, the distribution unit monitors the victim's social media activity and message content to analyze their mental state. The generation AI analyzes the victim's mental state and creates mental health care messages that include words of encouragement and methods for providing psychological support. For example, the generation AI performs an emotional analysis of the victim's messages, and if negative emotions are strong, it creates a mental health care message that includes words of encouragement and methods for providing psychological support. Furthermore, the distribution unit can adjust the content and timing of the mental health care messages according to the victim's mental state. This allows the distribution unit to provide victims with appropriate mental health care messages at the right time, supporting their mental health. The distribution unit can also collect feedback from victims and continuously improve the content and delivery methods of mental health care messages. This allows the distribution unit to provide effective mental health care to victims and mitigate the psychological damage caused by defamation.

[0068] The filtering unit can detect specific keywords or phrases and determine the degree of defamation. For example, the filtering unit can detect specific keywords or phrases and determine the degree of defamation. For example, the filtering unit can detect insulting words or aggressive expressions and determine the degree of defamation. The filtering unit can also determine the degree of defamation using contextual analysis. For example, the filtering unit can analyze the context before and after a message and determine the degree of defamation. This allows for accurate determination of the degree of defamation by detecting specific keywords or phrases. Some or all of the above-described processes in the filtering unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the filtering unit can input specific keywords or phrases into a generation AI and have the generation AI perform the determination of the degree of defamation.

[0069] The collection unit can save detected defamatory messages. For example, the collection unit can save detected defamatory messages to a database. For example, the collection unit can automatically classify detected messages and save them to a database. The collection unit can also save messages in file format. For example, the collection unit can save detected messages as text files or CSV files. By saving defamatory messages, they can be used as evidence later. Some or all of the above processing in the collection unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the collection unit can input detected defamatory messages into a generation AI and have the generation AI classify and save the messages.

[0070] The generation unit can create victim reports and evidence documents based on collected messages. For example, the generation unit can automatically create legally valid victim reports and evidence documents based on collected messages. For example, the generation unit can analyze collected messages, extract necessary information, and create victim reports and evidence documents. The generation unit can also create documents in a format that can be submitted as evidence based on collected messages. For example, the generation unit can create documents in PDF format or printable format from collected messages. This reduces the burden on victims by automatically creating victim reports and evidence documents. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input collected messages into a generation AI and have the generation AI create victim reports and evidence documents.

[0071] The distribution unit can analyze the victim's mental state and automatically create and distribute mental care messages. For example, the distribution unit can analyze the victim's mental state and automatically create and distribute appropriate mental care messages. For example, the distribution unit can analyze the victim's mental state and create mental care messages that include words of encouragement and methods for providing psychological support. The distribution unit can also adjust the content of the mental care messages according to the victim's mental state. For example, if the victim is feeling stressed, the distribution unit can distribute a mental care message with a relaxing effect. This allows for the provision of emotional support by providing mental care to the victim. Some or all of the above processing in the distribution unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the distribution unit can input the victim's mental state into a generation AI and have the generation AI create and distribute mental care messages.

[0072] The filtering unit can estimate the user's emotions and adjust the filtering criteria based on the estimated emotions. For example, if the user is stressed, the filtering unit can tighten the filtering criteria and increase the sensitivity to detecting slander. Conversely, if the user is relaxed, the filtering unit can loosen the filtering criteria and decrease the sensitivity to detecting slander. Furthermore, if the user is angry, the filtering unit can strengthen the filtering criteria for specific aggressive keywords. This allows for more appropriate filtering by adjusting the filtering criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filtering unit may be performed using or without a generative AI. For example, the filtering unit can input user emotion data into a generative AI and have the generative AI adjust the filtering criteria.

[0073] The filtering unit can optimize its filtering algorithm by referring to past defamation data. For example, the filtering unit can analyze past defamation data to identify frequently occurring keywords and phrases and reflect them in the filtering algorithm. The filtering unit can also learn offensive expressions used in specific contexts from past defamation data and incorporate them into the filtering algorithm. Furthermore, the filtering unit can quantify the degree of defamation based on past defamation data and adjust the threshold of the filtering algorithm. This improves the accuracy of the filtering algorithm by referring to past data. Some or all of the above processing in the filtering unit may be performed using generative AI, or it may be performed without generative AI. For example, the filtering unit can input past defamation data into generative AI and have the generative AI perform the optimization of the filtering algorithm.

[0074] The filtering unit can perform filtering by considering the attribute information of the message sender. For example, if the message sender has a history of defamation, the filtering unit will tighten the filtering criteria. Furthermore, if the message sender is anonymous, the filtering unit can strengthen the filtering criteria and increase the sensitivity to detecting defamation. In addition, if the message sender has specific attributes (e.g., age, gender), the filtering unit can adjust the filtering criteria based on those attributes. This improves the accuracy of filtering by considering the sender's attribute information. Some or all of the above processing in the filtering unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the filtering unit can input the message sender's attribute information into a generative AI and have the generative AI adjust the filtering criteria.

[0075] The filtering unit can estimate the user's emotions and adjust the order in which the filtering results are displayed based on the estimated emotions. For example, if the user is stressed, the filtering unit may prioritize displaying messages with a high degree of slander. Conversely, if the user is relaxed, the filtering unit may prioritize displaying messages with a low degree of slander. Furthermore, if the user is angry, the filtering unit may prioritize displaying messages containing specific aggressive keywords. This allows for the provision of more appropriate information by adjusting the display order according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the filtering unit may be performed using or without a generative AI. For example, the filtering unit can input user emotion data into a generative AI and have the generative AI adjust the display order.

[0076] The filtering unit can perform filtering while considering the geographical distribution of messages. For example, if the message sender is from a specific region, the filtering unit will perform filtering while considering expressions specific to that region. Furthermore, if the message senders are from different regions, the filtering unit can analyze regional trends in defamation and adjust the filtering criteria accordingly. Additionally, if the message senders are concentrated in a specific region, the filtering unit can perform filtering based on the culture and language of that region. This allows for accurate detection of region-specific defamation by considering geographical distribution. Some or all of the above processing in the filtering unit may be performed using or without a generative AI. For example, the filtering unit can input geographical distribution data of messages into a generative AI and have the generative AI adjust the filtering criteria.

[0077] The filtering unit can improve the accuracy of filtering by referring to relevant literature for the message. For example, if the content of a message is related to a specific document, the filtering unit will filter by referring to the content of that document. Furthermore, if the content of a message is related to a specific topic, the filtering unit can filter by referring to literature on that topic. In addition, if the content of a message is related to a specific incident or event, the filtering unit can filter by referring to literature on that incident or event. This improves the accuracy of filtering by referring to relevant literature. Some or all of the above processing in the filtering unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the filtering unit can input relevant literature for a message into a generative AI and have the generative AI perform the filtering accuracy improvement.

[0078] The collection unit can estimate the user's emotions and determine the priority of messages to collect based on the estimated emotions. For example, if the user is stressed, the collection unit will prioritize collecting messages with a high degree of slander. Conversely, if the user is relaxed, the collection unit can also prioritize collecting messages with a low degree of slander. Furthermore, if the user is angry, the collection unit can prioritize collecting messages containing specific aggressive keywords. This allows for the priority collection of important messages by determining the priority of messages to collect according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collection unit may be performed using or without a generative AI. For example, the collection unit can input user emotion data into a generative AI and have the generative AI determine the priority of messages to collect.

[0079] The collection unit can improve the accuracy of collection by considering the interrelationships between messages. For example, if the message sender is the same person, the collection unit will also collect other messages from that person. Furthermore, if a message relates to a specific topic, the collection unit can also collect other messages related to that topic. In addition, if a message relates to a specific incident or event, the collection unit can also collect other messages related to that incident or event. This improves the accuracy of collection by considering the interrelationships between messages. Some or all of the above processing in the collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the collection unit can input message interrelationship data into a generative AI and have the generative AI perform the task of improving the accuracy of collection.

[0080] The collection unit can perform data collection while considering the attribute information of the message sender. For example, if a message sender has a history of defamation, the collection unit will prioritize collecting messages from that person. The collection unit can also prioritize collecting messages from anonymous message senders. Furthermore, if a message sender has specific attributes (e.g., age, gender), the collection unit can collect messages based on those attributes. This improves the accuracy of data collection by considering the sender's attribute information. Some or all of the above processing in the collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the collection unit can input the attribute information of the message sender into a generative AI and have the generative AI perform the data collection.

[0081] The data collection unit can estimate the user's emotions and adjust how collected messages are displayed based on the estimated emotions. For example, if the user is stressed, the data collection unit can highlight messages with a high degree of slander. Conversely, if the user is relaxed, the data collection unit can highlight messages with a low degree of slander. Furthermore, if the user is angry, the data collection unit can highlight messages containing specific aggressive keywords. This allows for more appropriate information to be provided by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the data collection unit may be performed using or without a generative AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI adjust the display method.

[0082] The collection unit can perform collection while considering the geographical distribution of messages. For example, if the message sender originates from a specific region, the collection unit will consider the region's unique expressions during collection. Furthermore, if the message senders originate from different regions, the collection unit can analyze regional trends in defamation and adjust the collection criteria accordingly. Additionally, if the message senders are concentrated in a particular region, the collection unit can perform collection based on the culture and language of that region. This allows for the accurate collection of region-specific defamation by considering geographical distribution. Some or all of the above processing in the collection unit may be performed using or without a generative AI. For example, the collection unit can input geographical distribution data of messages into a generative AI and have the generative AI adjust the collection criteria.

[0083] The collection unit can improve the accuracy of its collection by referring to relevant literature related to the message. For example, if the content of the message is related to a specific document, the collection unit will refer to the content of that document to perform the collection. Furthermore, if the content of the message is related to a specific topic, the collection unit can also refer to literature related to that topic to perform the collection. In addition, if the content of the message is related to a specific incident or event, the collection unit can also refer to literature related to that incident or event to perform the collection. This improves the accuracy of the collection by referring to relevant literature. Some or all of the above processing in the collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the collection unit can input relevant literature related to the message into a generative AI and have the generative AI perform the task of improving the accuracy of the collection.

[0084] The generation unit can estimate the user's emotions and determine the priority of documents to generate based on the estimated emotions. For example, if the user is stressed, the generation unit will prioritize generating documents based on messages with a high degree of defamation. Conversely, if the user is relaxed, the generation unit can prioritize generating documents based on messages with a low degree of defamation. Furthermore, if the user is angry, the generation unit can prioritize generating documents based on messages containing specific aggressive keywords. This allows for the priority generation of important documents by determining the priority of documents according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation 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 generation unit may be performed using or without a generation AI. For example, the generation unit can input user emotion data into a generation AI and have the generation AI determine the priority of documents.

[0085] The generation unit can improve the accuracy of generation by considering the interrelationships between messages. For example, if the message sender is the same person, the generation unit will generate documents while also considering other messages from that person. Furthermore, if the messages relate to a specific topic, the generation unit can also generate documents while considering other messages related to that topic. In addition, if the messages relate to a specific incident or event, the generation unit can also generate documents while considering other messages related to that incident or event. This improves the accuracy of generation by considering the interrelationships between messages. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input message interrelationship data into a generation AI and have the generation AI perform the generation accuracy improvement.

[0086] The generation unit can perform generation while considering the attribute information of the message sender. For example, if the message sender has a history of defamation, the generation unit will generate a document based on that person's messages. The generation unit can also generate a document based on the messages of an anonymous message sender. Furthermore, if the message sender has specific attributes (e.g., age, gender), the generation unit can generate a document based on those attributes. This improves the accuracy of generation by considering the sender's attribute information. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the message sender's attribute information into the generation AI and have the generation AI perform the generation.

[0087] The generation unit can estimate the user's emotions and adjust how the generated documents are displayed based on the estimated emotions. For example, if the user is stressed, the generation unit can prominently display documents based on messages with a high degree of slander. Conversely, if the user is relaxed, the generation unit can also prominently display documents based on messages with a low degree of slander. Furthermore, if the user is angry, the generation unit can prominently display documents based on messages containing specific aggressive keywords. This allows for more appropriate information to be provided by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using or without a generation AI. For example, the generation unit can input user emotion data into a generation AI and have the generation AI adjust the display method.

[0088] The generation unit can perform generation while considering the geographical distribution of messages. For example, if the message sender originates from a specific region, the generation unit will generate documents while considering the unique expressions of that region. Furthermore, if the message senders originate from different regions, the generation unit can analyze regional trends in defamation and adjust the content of the documents accordingly. Additionally, if the message senders are concentrated in a specific region, the generation unit can generate documents based on the culture and language of that region. This allows for the generation of documents that accurately reflect region-specific defamation by considering geographical distribution. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input geographical distribution data of messages into a generation AI and have the generation AI perform the generation.

[0089] The generation unit can improve the accuracy of its generation by referring to relevant literature related to the message. For example, if the content of the message is related to a specific document, the generation unit can generate a document by referring to the content of that document. Furthermore, if the content of the message is related to a specific topic, the generation unit can generate a document by referring to literature on that topic. In addition, if the content of the message is related to a specific incident or event, the generation unit can generate a document by referring to literature on that incident or event. This improves the accuracy of the generation by referring to relevant literature. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input relevant literature related to the message into a generation AI and have the generation AI perform the task of improving the accuracy of the generation.

[0090] The delivery unit can estimate the user's emotions and adjust the content of the mental care messages it delivers based on the estimated emotions. For example, if the user is feeling stressed, the delivery unit can deliver a relaxing mental care message. It can also deliver a positive mental care message if the user is relaxed. Furthermore, if the user is feeling angry, the delivery unit can deliver a message to help them calm down. This allows for more appropriate mental care by adjusting the content of the mental care messages according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the delivery unit may be performed using or without a generative AI. For example, the delivery unit can input user emotion data into a generative AI and have the generative AI adjust the content of the mental care messages.

[0091] The distribution unit can create optimal mental care messages by referring to the victim's past mental state. For example, the distribution unit can refer to mental care messages from periods when the victim was stressed in the past and distribute similar messages. It can also refer to mental care messages from periods when the victim was relaxed in the past and distribute similar messages. Furthermore, it can refer to mental care messages from periods when the victim was angry in the past and distribute similar messages. This allows for the creation of more appropriate mental care messages by referring to past mental states. Some or all of the above processing in the distribution unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the distribution unit can input the victim's past mental state data into a generative AI and have the generative AI create the optimal mental care message.

[0092] The distribution unit can customize mental care messages based on the victim's current living situation. For example, if the victim is currently experiencing stress at work, the distribution unit can deliver a mental care message to alleviate work-related stress. It can also deliver a mental care message to promote relaxation at home if the victim is currently relaxing at home. Furthermore, if the victim is currently experiencing anger at school, the distribution unit can deliver a mental care message to alleviate anger at school. This allows for more appropriate mental care by customizing messages based on the victim's current living situation. Some or all of the above processing in the distribution unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the distribution unit can input data on the victim's current living situation into a generative AI and have the generative AI customize the mental care messages.

[0093] The delivery unit can estimate the user's emotions and determine the priority of mental care messages to deliver based on the estimated emotions. For example, if the user is stressed, the delivery unit will prioritize delivering relaxing mental care messages. It can also prioritize delivering positive mental care messages if the user is relaxed. Furthermore, if the user is angry, the delivery unit can prioritize delivering calming mental care messages. This allows for more appropriate mental care by prioritizing mental care messages according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using or without a generative AI. For example, the delivery unit can input user emotion data into a generative AI and have the generative AI determine the priority of mental care messages.

[0094] The distribution unit can create optimal mental care messages by considering the victim's geographical location. For example, if the victim lives in a specific region, the distribution unit can create a mental care message based on the culture and language of that region. Furthermore, if the victim lives in a different region, the distribution unit can create a mental care message considering the culture and language of that region. In addition, if the victim moves to a specific region, the distribution unit can create a mental care message based on the culture and language of that region. This allows for the creation of region-specific mental care messages by considering geographical location. Some or all of the above processing in the distribution unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the distribution unit can input the victim's geographical location information into a generative AI and have the generative AI create the optimal mental care message.

[0095] The distribution unit can analyze the victim's social media activity and create mental care messages. For example, if the victim is experiencing stress on social media, the distribution unit can create a mental care message to alleviate that stress. It can also create a mental care message to promote relaxation if the victim is feeling relaxed on social media. Furthermore, if the victim is feeling angry on social media, the distribution unit can create a mental care message to soothe that anger. This allows for the creation of more appropriate mental care messages by analyzing social media activity. Some or all of the above processing in the distribution unit may be performed using or without a generative AI. For example, the distribution unit can input the victim's social media activity data into a generative AI and have the generative AI create the mental care messages.

[0096] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0097] The filtering unit can perform filtering by considering the sender's past behavior history. For example, if a sender has a history of defamation, their messages will be strictly filtered. Conversely, if a sender has sent many positive messages in the past, their messages can be filtered more loosely. Furthermore, if a sender has caused problems in the past regarding a specific topic, messages related to that topic can be filtered with greater emphasis. In this way, considering the sender's past behavior history improves the accuracy of filtering.

[0098] The collection unit can evaluate the trustworthiness of message senders and collect messages based on that trustworthiness. For example, if a sender's trustworthiness is low, their messages can be prioritized for collection. Conversely, if a sender's trustworthiness is high, their messages can be delayed. Furthermore, if a sender's trustworthiness is moderate, their messages can be collected with the usual priority. This improves the accuracy of collection by considering the trustworthiness of the senders.

[0099] The generation unit can analyze the intent of the message sender and generate documents based on that intent. For example, if the sender's intent is aggressive, it will prioritize generating documents based on that message. If the sender's intent is neutral, it can generate documents based on that message with the usual priority. Furthermore, if the sender's intent is positive, it can postpone the generation of documents based on that message. This improves the accuracy of generation by considering the sender's intent.

[0100] The distribution department can evaluate the effectiveness of past mental health care messages to victims and create new messages based on that evaluation. For example, it can redistribute mental health care messages that were previously effective. It can also improve and redistribute mental health care messages that were previously ineffective. Furthermore, it can re-evaluate mental health care messages whose effectiveness was unclear in the past and distribute them as needed. This allows for more appropriate mental health care by considering the effectiveness of past messages.

[0101] The filtering unit can perform filtering while considering the social influence of the message sender. For example, if a sender has high social influence, their messages will be filtered strictly. If a sender has low social influence, their messages will be filtered more loosely. Furthermore, if a sender has moderate social influence, their messages will be filtered according to normal standards. In this way, considering the sender's social influence improves the accuracy of filtering.

[0102] The filtering unit can estimate the user's emotions and adjust the filtering criteria based on those emotions. For example, if the user is stressed, the filtering criteria can be tightened to increase the sensitivity to detecting slander and defamation. Conversely, if the user is relaxed, the filtering criteria can be loosened to decrease the sensitivity to detecting slander and defamation. Furthermore, if the user is angry, the filtering criteria for specific aggressive keywords can be strengthened. This allows for more appropriate filtering by adjusting the filtering criteria according to the user's emotions.

[0103] The data collection unit can estimate the user's emotions and determine the priority of messages to collect based on those emotions. For example, if the user is stressed, it can prioritize collecting messages with a high degree of slander. Conversely, if the user is relaxed, it can prioritize collecting messages with a low degree of slander. Furthermore, if the user is angry, it can prioritize collecting messages containing specific aggressive keywords. By prioritizing messages according to the user's emotions, it is possible to prioritize the collection of important messages.

[0104] The generation unit can estimate the user's emotions and determine the priority of documents to generate based on those estimated emotions. For example, if the user is stressed, it can prioritize generating documents based on messages with a high degree of defamation. Conversely, if the user is relaxed, it can prioritize generating documents based on messages with a low degree of defamation. Furthermore, if the user is angry, it can prioritize generating documents based on messages containing specific aggressive keywords. By prioritizing documents according to the user's emotions, it is possible to prioritize the generation of important documents.

[0105] The delivery unit can estimate the user's emotions and adjust the content of the mental care messages delivered based on those estimates. For example, if the user is feeling stressed, it can deliver a relaxing mental care message. If the user is relaxed, it can deliver a positive mental care message. Furthermore, if the user is angry, it can deliver a message to help them calm down. By adjusting the content of mental care messages according to the user's emotions, more appropriate mental care becomes possible.

[0106] The delivery unit can estimate the user's emotions and determine the priority of mental care messages to deliver based on those estimated emotions. For example, if the user is feeling stressed, it can prioritize delivering mental care messages with a relaxing effect. Similarly, if the user is relaxed, it can prioritize delivering positive mental care messages. Furthermore, if the user is feeling angry, it can prioritize delivering mental care messages to help them calm down. This allows for more appropriate mental care by prioritizing messages according to the user's emotions.

[0107] The following briefly describes the processing flow for example form 2.

[0108] Step 1: The filtering unit analyzes messages on social media and determines the degree of defamation. For example, it detects specific keywords or phrases and analyzes the message using a generation AI to determine the degree of defamation. Step 2: The collection unit collects the defamatory messages detected by the filtering unit. For example, the detected defamatory messages are stored in a database and automatically classified using a generation AI. Step 3: The generation unit creates victim reports and evidence documents based on the messages collected by the collection unit. For example, it automatically creates legally valid victim reports and evidence documents based on the collected messages and extracts the necessary information using generation AI. Step 4: The distribution unit distributes mental health care messages based on the documents created by the generation unit. For example, it analyzes the victim's mental state and uses generation AI to automatically create and distribute appropriate mental health care messages.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] Each of the multiple elements described above, including the filtering unit, collection unit, generation unit, and distribution unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the filtering unit is implemented by the control unit 46A of the smart device 14, which analyzes messages on social media and determines the degree of defamation. The collection unit is implemented by the identification processing unit 290 of the data processing device 12, which collects the detected defamatory messages. The generation unit is implemented by the identification processing unit 290 of the data processing device 12, which creates a victim report and evidence documents based on the collected messages. The distribution unit is implemented by the control unit 46A of the smart device 14, which analyzes the victim's mental state and automatically creates and distributes a mental care message. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0113] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the filtering unit, collection unit, generation unit, and distribution unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the filtering unit is implemented by the control unit 46A of the smart glasses 214, which analyzes messages on social media and determines the degree of defamation. The collection unit is implemented by the identification processing unit 290 of the data processing device 12, which collects the detected defamatory messages. The generation unit is implemented by the identification processing unit 290 of the data processing device 12, which creates a victim report and evidence documents based on the collected messages. The distribution unit is implemented by the control unit 46A of the smart glasses 214, which analyzes the victim's mental state and automatically creates and distributes a mental care message. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0129] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Each of the multiple elements described above, including the filtering unit, collection unit, generation unit, and distribution unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the filtering unit is implemented by the control unit 46A of the headset terminal 314, which analyzes messages on social networking services and determines the degree of defamation. The collection unit is implemented by the identification processing unit 290 of the data processing device 12, which collects detected defamatory messages. The generation unit is implemented by the identification processing unit 290 of the data processing device 12, which creates victim reports and evidence documents based on the collected messages. The distribution unit is implemented by the control unit 46A of the headset terminal 314, which analyzes the victim's mental state and automatically creates and distributes mental care messages. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0145] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the filtering unit, collection unit, generation unit, and distribution unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the filtering unit is implemented by the control unit 46A of the robot 414, which analyzes messages on social media and determines the degree of defamation. The collection unit is implemented by the identification processing unit 290 of the data processing unit 12, which collects the detected defamatory messages. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, which creates a victim report and evidence documents based on the collected messages. The distribution unit is implemented by the control unit 46A of the robot 414, which analyzes the victim's mental state and automatically creates and distributes a mental care message. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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."

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] (Note 1) A filtering unit that analyzes messages on social media and determines the degree of defamation, A collection unit that collects defamatory messages detected by the filtering unit, Based on the messages collected by the aforementioned collection unit, a generation unit creates victim reports and evidence documents, The system includes a distribution unit that delivers mental care messages based on documents created by the generation unit. system. (Note 2) The filtering unit is It detects specific keywords or phrases and determines the degree of defamation. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Save detected defamatory messages. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Based on the collected messages, we will create a police report and supporting documents. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned distribution unit, Analyze the victim's mental state and automatically create and deliver mental health care messages. The system described in Appendix 1, characterized by the features described herein. (Note 6) The filtering unit is It estimates the user's sentiment and adjusts the filtering criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The filtering unit is Optimize the filtering algorithm by referring to past defamation data. The system described in Appendix 1, characterized by the features described herein. (Note 8) The filtering unit is Filter messages by considering the sender's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 9) The filtering unit is It estimates the user's sentiment and adjusts the order in which filtering results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The filtering unit is Filter messages considering their geographical distribution. The system described in Appendix 1, characterized by the features described herein. (Note 11) The filtering unit is Improve filtering accuracy by referring to related literature for messages. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is It estimates the user's emotions and determines the priority of messages to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is Improve the accuracy of data collection by considering the interrelationships between messages. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is The data is collected while taking into account the sender's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is We estimate the user's emotions and adjust how collected messages are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned collection unit is The collection process takes into account the geographical distribution of the messages. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned collection unit is Referencing related literature for messages improves the accuracy of data collection. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is It estimates the user's emotions and determines the priority of documents to generate based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is Improve generation accuracy by considering the interrelationships between messages. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is The message is generated while taking into account the sender's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is It estimates the user's emotions and adjusts how the generated documents are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is The generation process takes into account the geographical distribution of the messages. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is Referencing related literature for messages improves generation accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned distribution unit, It estimates the user's emotions and adjusts the content of mental health messages delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned distribution unit, Create the most appropriate message by referring to the victim's past mental state. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned distribution unit, Customize mental health messages based on the victim's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned distribution unit, It estimates the user's emotions and determines the priority of mental health messages to deliver based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned distribution unit, Create the most appropriate mental health care message, taking into account the victim's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned distribution unit, Analyze the victim's social media activity to create mental health support messages. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A filtering unit that analyzes messages on social media and determines the degree of defamation, A collection unit that collects defamatory messages detected by the filtering unit, Based on the messages collected by the aforementioned collection unit, a generation unit creates victim reports and evidence documents, The system includes a distribution unit that delivers mental care messages based on documents created by the generation unit, The filtering unit estimates the user's emotions and, if the estimated emotions indicate that the user is experiencing stress, adjusts the filtering criteria to increase the sensitivity of detecting defamation. system.

2. The filtering unit is It detects specific keywords or phrases and determines the degree of defamation. The system according to feature 1.

3. The aforementioned collection unit is Save detected defamatory messages. The system according to feature 1.

4. The generating unit is Based on the collected messages, we will create a police report and supporting documents. The system according to feature 1.

5. The aforementioned distribution unit, The system analyzes the victim's mental state and automatically creates and delivers mental health care messages. The system according to feature 1.

6. The filtering unit is When the estimated user's emotional state is relaxed, the filtering criteria are adjusted to lower the sensitivity of detecting defamation. The system according to feature 1.

7. The filtering unit is Optimize the filtering algorithm by referring to past defamation data. The system according to feature 1.

8. The filtering unit is Filter messages by considering the sender's attribute information. The system according to feature 1.

Images