system

Abstract

The system according to this embodiment aims to prevent ordinary users from applying to job postings for illegal part-time work made on social media. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a fake reply unit, and a notification unit. The collection unit collects posts on social media. The analysis unit analyzes the posts collected by the collection unit and identifies posts recruiting for illegal part-time jobs. The fake reply unit sends a fake reply to the illegal part-time job recruitment posts identified by the analysis unit. The notification unit notifies public authorities of the information obtained by the fake reply unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of 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 risk that ordinary users may apply for recruitment posts of part-time jobs conducted on SNS.

[0005] The system according to the embodiment aims to prevent ordinary users from applying for recruitment posts of part-time jobs conducted on SNS.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a fake reply unit, and a notification unit. The collection unit collects posts on social media. The analysis unit analyzes the posts collected by the collection unit and identifies posts recruiting for illegal part-time jobs. The fake reply unit sends a fake reply to the illegal part-time job recruitment posts identified by the analysis unit. The notification unit notifies public authorities of the information obtained by the fake reply unit. [Effects of the Invention]

[0007] The system according to this embodiment can prevent ordinary users from applying to job postings for illegal part-time work made on social media. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. 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 reception 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 reception 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 system according to an embodiment of the present invention is a system that prevents contact between ordinary users and illegal job recruiters by using a generation AI and a real smartphone to apply to illegal job postings made on social media, thereby burying ordinary users' applications among a large number of other applications. This system is a mechanism that prevents contact between ordinary users and illegal job recruiters by using a generation AI and a real smartphone to apply to illegal job postings made on social media, thereby burying ordinary users' applications among a large number of other applications. For example, an AI agent monitors various social media platforms 24 hours a day to check in real time whether a post is an illegal job posting. The timing and wording are made using a generation AI to make it difficult to distinguish between a human and an AI. Next, if an illegal job posting is detected, a public institution is immediately contacted. If the confidence level does not meet the standard value, the system waits for a response from the public institution before proceeding to the next step. After that, the relevant post is shared with the social media platform operator, and contact is made, including the possibility of mass posting. In some cases, permission is obtained before proceeding to the next step. Since there may be users who reacted to the post in question, we will request the SNS operator to investigate and temporarily suspend the accounts of any general users who reacted. Next, the AI ​​agent will instruct the AI ​​installed in each physical device to begin sending fake replies. The AI ​​agent will prompt each physical device to specify what kind of person profile it should be communicating as. For example, it will specify age, gender, occupation, active hours, writing style, personality, etc. Based on the specified profile, the AI ​​in each physical device will begin communicating with the recruiter. Any information obtained as a result of the communication (such as the date and time of the meeting and the location) will be shared with the police as it becomes available. The reason for using physical devices is that each device is assigned a phone number, making it impossible to determine whether it is an AI or a real person on SNS. Also, since users are often directed to highly anonymous apps after making contact on SNS, it is necessary for the AI ​​to be able to communicate while disguised even after being directed there. Furthermore, by making recruiters aware that "applications from certain phone numbers are not accepted," we can make general users aware that "using a specific phone number will make them less likely to get involved in an incident."This allows the system to use a generating AI and a real smartphone to apply to job postings for illegal part-time jobs on social media, thereby burying applications from ordinary users among a large volume of other applications and preventing contact between ordinary users and those offering illegal part-time jobs.

[0029] The system according to this embodiment comprises a collection unit, an analysis unit, a fake reply unit, and a notification unit. The collection unit collects posts on social networking services (SNS). The collection unit can, for example, monitor various SNS 24 hours a day and collect posts. The collection unit can also use AI to set the types of SNS to collect and the collection frequency. The analysis unit analyzes the posts collected by the collection unit and identifies posts recruiting for illegal part-time jobs. The analysis unit can, for example, use a generation AI to analyze the content of posts and identify posts that have the characteristics of illegal part-time jobs. The generation AI can, for example, use a text generation AI (e.g., LLM) to analyze the content of posts. The fake reply unit makes fake replies to the illegal part-time job recruitment posts identified by the analysis unit. The fake reply unit can, for example, have an AI agent generate a prompt, and a real AI can make a reply based on that prompt. The AI ​​agent can, for example, use prompt generation technology to generate appropriate reply content. The notification unit notifies public authorities of the information obtained by the fake reply unit. The notification unit can, for example, immediately contact public authorities if it detects a job posting for illegal work. The notification unit can also use AI to set the type of information to be notified and the timing of notifications. This allows the system to send fake replies to job postings for illegal work on social media, preventing contact between ordinary users and those recruiting for illegal work.

[0030] The data collection unit collects posts from social media. For example, the collection unit can monitor various social media platforms 24 hours a day and collect posts. Specifically, the collection unit accesses multiple social media platforms using APIs and obtains post data in real time. This allows the collection unit to collect posts from multiple social media platforms. The collection unit can also use AI to set the types of social media platforms to collect and the collection frequency. For example, the AI ​​can be set to monitor specific keywords or hashtags and prioritize the collection of related posts. The collection frequency can be set to high when real-time monitoring is necessary and low when periodic monitoring is sufficient. This allows the collection unit to efficiently and effectively collect posts from social media, improving the overall system performance. Furthermore, the collection unit centrally manages the collected data and makes it accessible to the analysis unit and the fake reply unit. The collected data is stored on a cloud server and made accessible in real time by the analysis unit and the fake reply unit as needed. This allows the collection unit to quickly and accurately collect posts from social media, improving the overall system efficiency.

[0031] The analysis unit analyzes posts collected by the collection unit to identify illegal job postings. The analysis unit can, for example, use a generative AI to analyze the content of posts and identify posts that have the characteristics of illegal jobs. Specifically, the generative AI can analyze the content of posts using a text generation AI (e.g., LLM). The generative AI utilizes natural language processing technology to analyze the context and keywords of the post content and identify posts that have the characteristics of illegal jobs. For example, it prioritizes analyzing posts containing keywords such as "high income," "short term," and "easy work" to identify posts that are likely to be illegal jobs. In addition, the generative AI can learn from past data and identify patterns in posts that have the characteristics of illegal jobs. As a result, the analysis unit can quickly and accurately analyze the collected posts and identify illegal job postings. Furthermore, the analysis unit classifies the identified illegal job postings so that the fake reply unit and notification unit can respond efficiently. For example, it can classify posts according to the type of illegal job and risk level and take appropriate action. As a result, the analysis unit can effectively analyze the collected posts and improve the reliability and security of the entire system.

[0032] The fake reply unit sends fake replies to illegal job postings identified by the analysis unit. For example, the fake reply unit can use an AI agent to generate prompts, which are then used by a real AI to send replies. Specifically, the AI ​​agent can use prompt generation technology to generate appropriate replies. For instance, the AI ​​agent might generate an interesting reply to an illegal job posting, initiating communication with the recruiter. The real AI then uses natural language to respond based on the generated prompt, continuing the interaction with the recruiter. This allows the fake reply unit to extract detailed information from the illegal job recruiters. Furthermore, the fake reply unit can modify the prompts generated by the AI ​​agent as needed to provide more effective replies. For example, it can flexibly change its replies in response to the recruiter's reactions to extract more detailed information. This allows the fake reply unit to communicate effectively with illegal job recruiters and improve the overall system performance.

[0033] The notification unit notifies public authorities of information obtained by the fake reply unit. For example, the notification unit can immediately contact public authorities if it detects an advertisement for illegal part-time work. Specifically, the notification unit can use AI to set the type of information to be notified and the timing of notifications. For example, if an advertisement for illegal part-time work is identified, it can be set to immediately notify public authorities of the detailed information. The notification unit organizes the collected information, extracts the necessary information, and provides it to public authorities. This allows public authorities to respond quickly. Furthermore, the notification unit can flexibly set the timing of notifications. For example, it can notify immediately in cases of high urgency and periodically in cases of low urgency. This allows the notification unit to notify public authorities efficiently and effectively, improving the reliability and security of the entire system. In addition, the notification unit manages the history of notification content and can refer to past notification content. This allows the notification unit to make more effective notifications based on past notification content.

[0034] The data collection unit can monitor various social media platforms 24 hours a day. For example, it can use AI to monitor various social media platforms 24 hours a day and collect posts. The data collection unit can also configure the monitoring frequency and the technologies used. For example, it can prioritize monitoring specific social media platforms. Furthermore, the data collection unit can filter posts based on specific keywords or hashtags. This allows the data collection unit to quickly detect job postings for illegal part-time work by monitoring various social media platforms 24 hours a day.

[0035] The analysis unit can analyze the content of posts using a generative AI and identify posts that have the characteristics of illegal part-time jobs. For example, the analysis unit can use a generative AI to analyze the content of posts and identify posts that have the characteristics of illegal part-time jobs. The generative AI can analyze the content of posts using a text generation AI (for example, LLM). The generative AI can also configure the model and training data to be used. For example, the generative AI has learned from a large amount of text data and has advanced natural language processing capabilities. As a result, the analysis unit can identify posts that have the characteristics of illegal part-time jobs with high accuracy by using the generative AI.

[0036] The spoofed reply unit allows an AI agent to generate a prompt, which the actual device's AI then uses to generate a reply. For example, the AI ​​agent can generate a prompt, which the actual device's AI then uses to generate a reply. The AI ​​agent can also configure the technologies used and the prompt generation methods. For instance, the AI ​​agent can use prompt generation technology to generate an appropriate reply. This allows the spoofed reply unit to generate a prompt, which in turn enables the actual device's AI to provide an appropriate reply.

[0037] The notification unit can immediately contact public authorities upon detecting an advertisement for illegal part-time work. For example, the notification unit can immediately contact public authorities upon detecting an advertisement for illegal part-time work. The notification unit can also configure the type of information to be notified and the timing of notifications. For instance, the notification unit can set a time range and criteria for immediate notification. This allows the notification unit to respond quickly by immediately contacting public authorities upon detecting an advertisement for illegal part-time work.

[0038] The fake reply unit allows each AI in the actual machine to initiate communication with the recruiter based on a specified profile. The fake reply unit can also configure the characteristics and settings of the profile. For example, the fake reply unit can specify age, gender, occupation, active time slots, writing style, personality, etc. This allows the fake reply unit to deceive the recruiter by communicating based on the specified profile.

[0039] The collection unit can filter the types of posts to be collected based on specific keywords or hashtags. For example, the collection unit can prioritize collecting posts containing keywords such as "illegal part-time jobs" or "high income." The collection unit can filter and collect posts containing specific hashtags (e.g., #illegalparttimejobrecruitment). The collection unit can filter and collect posts containing specific phrases (e.g., "easy money"). This allows the collection unit to efficiently collect posts by filtering them based on specific keywords or hashtags.

[0040] The collection unit can adjust the frequency of collected posts based on specific times of day or days of the week. For example, the collection unit can prioritize collecting job postings for illegal part-time work that are posted at night. The collection unit can prioritize collecting job postings for illegal part-time work that are posted on weekends. The collection unit can prioritize collecting job postings for illegal part-time work that are posted during specific event periods. This allows the collection unit to perform effective collection by adjusting the collection frequency based on specific times of day or days of the week.

[0041] The data collection unit can select the target social media platforms for collecting posts based on specific regions or languages. For example, the unit can prioritize collecting posts in Japanese. It can prioritize collecting posts from specific regions (e.g., urban areas). It can prioritize collecting posts in specific languages ​​(e.g., English). This allows the data collection unit to perform more effective data collection by selecting target social media platforms based on specific regions or languages.

[0042] The data collection unit can filter the content of the posts it collects based on specific user groups. For example, it can prioritize collecting content posted by young users. It can prioritize collecting content posted by users in a specific occupation (e.g., students). It can prioritize collecting content posted by users with specific interests (e.g., high-paying part-time jobs). This allows the data collection unit to effectively collect data by filtering posts based on specific user groups.

[0043] The analysis unit can classify the content of posts to be analyzed based on specific contexts and topics. For example, the analysis unit can classify posts containing keywords such as "illegal part-time jobs" or "high income." The analysis unit can classify posts containing specific hashtags (e.g., #illegalparttimejobrecruitment). The analysis unit can classify posts containing specific phrases (e.g., "easy money"). This allows the analysis unit to perform effective analysis by classifying posts based on specific contexts and topics.

[0044] The analysis unit can evaluate the reliability of posts being analyzed based on the poster's past posting history. For example, the analysis unit can analyze the poster's past posting history and prioritize the analysis of highly reliable posts. The analysis unit can filter out posts with low reliability from the poster's past posting history. The analysis unit can evaluate reliability based on the poster's past posting history. As a result, the analysis unit can perform effective analysis by evaluating reliability based on the poster's past posting history.

[0045] The analysis unit can classify the content of posts to be analyzed based on specific regions or languages. For example, the analysis unit can prioritize the analysis of posts written in Japanese. The analysis unit can prioritize the analysis of posts from specific regions (e.g., urban areas). The analysis unit can prioritize the analysis of posts in specific languages ​​(e.g., English). This allows the analysis unit to perform more effective analysis by classifying posts based on specific regions or languages.

[0046] The analysis unit can classify the content of posts to be analyzed based on specific time periods or days of the week. For example, the analysis unit can prioritize the analysis of job postings for illegal part-time work posted at night. The analysis unit can prioritize the analysis of job postings for illegal part-time work posted on weekends. The analysis unit can prioritize the analysis of job postings for illegal part-time work posted during specific event periods. This allows the analysis unit to perform effective analysis by classifying posts based on specific time periods or days of the week.

[0047] The fake reply function can customize the content of its replies based on specific contexts and topics. For example, it can customize replies to include keywords such as "illegal part-time jobs" or "high income." It can also customize replies to include specific hashtags (e.g., #illegalparttimejobswanted). Furthermore, it can customize replies to include specific phrases (e.g., "easy money"). This allows the fake reply function to provide more effective replies by customizing its responses based on specific contexts and topics.

[0048] The fake reply function can evaluate the reliability of the reply content based on past reply history. For example, the fake reply function can analyze past reply history and prioritize the use of highly reliable reply content. The fake reply function can filter out unreliable reply content from past reply history. The fake reply function can evaluate reliability based on past reply history. As a result, the fake reply function can provide effective replies by evaluating reliability based on past reply history.

[0049] The fake reply function can customize the content of its replies based on specific regions or languages. For example, it can prioritize replies in Japanese. It can prioritize replies from specific regions (e.g., urban areas). It can prioritize replies in specific languages ​​(e.g., English). This allows the fake reply function to provide more effective replies by customizing its content based on specific regions and languages.

[0050] The fake reply function can customize the content of its replies based on specific times of day or days of the week. For example, it can prioritize replies sent at night, on weekends, or during specific events. This allows the fake reply function to provide more effective replies by customizing its content based on specific times of day or days of the week.

[0051] The notification unit can customize the content of its notifications based on specific contexts and topics. For example, it can customize notifications to include keywords such as "illegal part-time jobs" or "high-paying jobs." It can also customize notifications to include specific hashtags (e.g., #illegalpartnerrecruitment). Furthermore, it can customize notifications to include specific phrases (e.g., "easy money"). This allows the notification unit to provide more effective notifications by customizing content based on specific contexts and topics.

[0052] The notification unit can customize the content of its notifications based on specific regions or languages. For example, it can prioritize notifications in Japanese. It can prioritize notifications for specific regions (e.g., urban areas). It can prioritize notifications in specific languages ​​(e.g., English). This allows the notification unit to provide more effective notifications by customizing the content based on specific regions and languages.

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

[0054] In addition to analyzing the content of posts, the analytics department can also analyze the poster's past behavior history. For example, it can analyze what kind of posts the poster has made in the past to evaluate the reliability of a job posting for illegal part-time work. Furthermore, the analytics department can evaluate the influence of a post by considering metrics such as the number of followers and engagement rate of the poster. This allows the analytics department to conduct more accurate analyses by comprehensively evaluating not only the content of the post but also the poster's behavior history and influence.

[0055] The data collection unit can filter posts on social media based on specific regions or languages. For example, it can prioritize collecting posts written in Japanese. It can also prioritize collecting posts from specific regions (e.g., urban areas). Furthermore, it can prioritize collecting posts in specific languages ​​(e.g., English). This allows the data collection unit to effectively collect data by filtering posts based on specific regions and languages.

[0056] In addition to analyzing the content of posts, the analysis unit can analyze the poster's past posting history to evaluate the reliability of the posts. For example, the analysis unit can analyze what kind of posts the poster has made in the past and prioritize the analysis of highly reliable posts. The analysis unit can also filter out posts with low reliability from the poster's past posting history. This allows the analysis unit to perform effective analysis by evaluating reliability based on the poster's past posting history.

[0057] The fake reply function can be customized based on specific contexts and topics when generating replies. For example, it can customize replies to include keywords such as "illegal part-time jobs" or "high income." It can also customize replies to include specific hashtags (e.g., #illegalpartnerrecruitment). Furthermore, it can customize replies to include specific phrases (e.g., "easy money"). This allows the fake reply function to provide effective replies by customizing them based on specific contexts and topics.

[0058] The notification unit can customize notification content based on specific regions and languages. For example, it can prioritize Japanese notification content. It can also prioritize notification content for specific regions (e.g., urban areas). Furthermore, it can prioritize notification content in specific languages ​​(e.g., English). This allows the notification unit to provide more effective notifications by customizing content based on specific regions and languages.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The collection unit collects posts from social media. The collection unit can, for example, monitor various social media platforms 24 hours a day and collect posts. The collection unit can also use AI to set the types of social media platforms to collect and the collection frequency. Step 2: The analysis unit analyzes the posts collected by the collection unit and identifies posts recruiting for illegal part-time jobs. The analysis unit can, for example, use a generation AI to analyze the content of posts and identify posts that have the characteristics of illegal part-time jobs. The generation AI can, for example, use a text generation AI (e.g., LLM) to analyze the content of posts. Step 3: The fake reply unit sends fake replies to the illegal job postings identified by the analysis unit. The fake reply unit can, for example, have an AI agent generate a prompt, and a real AI can then send a reply based on that prompt. The AI ​​agent can, for example, use prompt generation technology to generate appropriate reply content. Step 4: The notification unit notifies public authorities of the information obtained by the fake reply unit. For example, the notification unit can immediately contact public authorities if it detects a recruitment ad for illegal part-time work. The notification unit can also use AI to set the type of information to be notified and the timing of the notification.

[0061] (Example of form 2) The system according to an embodiment of the present invention is a system that prevents contact between ordinary users and illegal job recruiters by using a generation AI and a real smartphone to apply to illegal job postings made on social media, thereby burying ordinary users' applications among a large number of other applications. This system is a mechanism that prevents contact between ordinary users and illegal job recruiters by using a generation AI and a real smartphone to apply to illegal job postings made on social media, thereby burying ordinary users' applications among a large number of other applications. For example, an AI agent monitors various social media platforms 24 hours a day to check in real time whether a post is an illegal job posting. The timing and wording are made using a generation AI to make it difficult to distinguish between a human and an AI. Next, if an illegal job posting is detected, a public institution is immediately contacted. If the confidence level does not meet the standard value, the system waits for a response from the public institution before proceeding to the next step. After that, the relevant post is shared with the social media platform operator, and contact is made, including the possibility of mass posting. In some cases, permission is obtained before proceeding to the next step. Since there may be users who reacted to the post in question, we will request the SNS operator to investigate and temporarily suspend the accounts of any general users who reacted. Next, the AI ​​agent will instruct the AI ​​installed in each physical device to begin sending fake replies. The AI ​​agent will prompt each physical device to specify what kind of person profile it should be communicating as. For example, it will specify age, gender, occupation, active hours, writing style, personality, etc. Based on the specified profile, the AI ​​in each physical device will begin communicating with the recruiter. Any information obtained as a result of the communication (such as the date and time of the meeting and the location) will be shared with the police as it becomes available. The reason for using physical devices is that each device is assigned a phone number, making it impossible to determine whether it is an AI or a real person on SNS. Also, since users are often directed to highly anonymous apps after making contact on SNS, it is necessary for the AI ​​to be able to communicate while disguised even after being directed there. Furthermore, by making recruiters aware that "applications from certain phone numbers are not accepted," we can make general users aware that "using a specific phone number will make them less likely to get involved in an incident."This allows the system to use a generating AI and a real smartphone to apply to job postings for illegal part-time jobs on social media, thereby burying applications from ordinary users among a large volume of other applications and preventing contact between ordinary users and those offering illegal part-time jobs.

[0062] The system according to this embodiment comprises a collection unit, an analysis unit, a fake reply unit, and a notification unit. The collection unit collects posts on social networking services (SNS). The collection unit can, for example, monitor various SNS 24 hours a day and collect posts. The collection unit can also use AI to set the types of SNS to collect and the collection frequency. The analysis unit analyzes the posts collected by the collection unit and identifies posts recruiting for illegal part-time jobs. The analysis unit can, for example, use a generation AI to analyze the content of posts and identify posts that have the characteristics of illegal part-time jobs. The generation AI can, for example, use a text generation AI (e.g., LLM) to analyze the content of posts. The fake reply unit makes fake replies to the illegal part-time job recruitment posts identified by the analysis unit. The fake reply unit can, for example, have an AI agent generate a prompt, and a real AI can make a reply based on that prompt. The AI ​​agent can, for example, use prompt generation technology to generate appropriate reply content. The notification unit notifies public authorities of the information obtained by the fake reply unit. The notification unit can, for example, immediately contact public authorities if it detects a job posting for illegal work. The notification unit can also use AI to set the type of information to be notified and the timing of notifications. This allows the system to send fake replies to job postings for illegal work on social media, preventing contact between ordinary users and those recruiting for illegal work.

[0063] The data collection unit collects posts from social media. For example, the collection unit can monitor various social media platforms 24 hours a day and collect posts. Specifically, the collection unit accesses multiple social media platforms using APIs and obtains post data in real time. This allows the collection unit to collect posts from multiple social media platforms. The collection unit can also use AI to set the types of social media platforms to collect and the collection frequency. For example, the AI ​​can be set to monitor specific keywords or hashtags and prioritize the collection of related posts. The collection frequency can be set to high when real-time monitoring is necessary and low when periodic monitoring is sufficient. This allows the collection unit to efficiently and effectively collect posts from social media, improving the overall system performance. Furthermore, the collection unit centrally manages the collected data and makes it accessible to the analysis unit and the fake reply unit. The collected data is stored on a cloud server and made accessible in real time by the analysis unit and the fake reply unit as needed. This allows the collection unit to quickly and accurately collect posts from social media, improving the overall system efficiency.

[0064] The analysis unit analyzes posts collected by the collection unit to identify illegal job postings. The analysis unit can, for example, use a generative AI to analyze the content of posts and identify posts that have the characteristics of illegal jobs. Specifically, the generative AI can analyze the content of posts using a text generation AI (e.g., LLM). The generative AI utilizes natural language processing technology to analyze the context and keywords of the post content and identify posts that have the characteristics of illegal jobs. For example, it prioritizes analyzing posts containing keywords such as "high income," "short term," and "easy work" to identify posts that are likely to be illegal jobs. In addition, the generative AI can learn from past data and identify patterns in posts that have the characteristics of illegal jobs. As a result, the analysis unit can quickly and accurately analyze the collected posts and identify illegal job postings. Furthermore, the analysis unit classifies the identified illegal job postings so that the fake reply unit and notification unit can respond efficiently. For example, it can classify posts according to the type of illegal job and risk level and take appropriate action. As a result, the analysis unit can effectively analyze the collected posts and improve the reliability and security of the entire system.

[0065] The fake reply unit sends fake replies to illegal job postings identified by the analysis unit. For example, the fake reply unit can use an AI agent to generate prompts, which are then used by a real AI to send replies. Specifically, the AI ​​agent can use prompt generation technology to generate appropriate replies. For instance, the AI ​​agent might generate an interesting reply to an illegal job posting, initiating communication with the recruiter. The real AI then uses natural language to respond based on the generated prompt, continuing the interaction with the recruiter. This allows the fake reply unit to extract detailed information from the illegal job recruiters. Furthermore, the fake reply unit can modify the prompts generated by the AI ​​agent as needed to provide more effective replies. For example, it can flexibly change its replies in response to the recruiter's reactions to extract more detailed information. This allows the fake reply unit to communicate effectively with illegal job recruiters and improve the overall system performance.

[0066] The notification unit notifies public authorities of information obtained by the fake reply unit. For example, the notification unit can immediately contact public authorities if it detects an advertisement for illegal part-time work. Specifically, the notification unit can use AI to set the type of information to be notified and the timing of notifications. For example, if an advertisement for illegal part-time work is identified, it can be set to immediately notify public authorities of the detailed information. The notification unit organizes the collected information, extracts the necessary information, and provides it to public authorities. This allows public authorities to respond quickly. Furthermore, the notification unit can flexibly set the timing of notifications. For example, it can notify immediately in cases of high urgency and periodically in cases of low urgency. This allows the notification unit to notify public authorities efficiently and effectively, improving the reliability and security of the entire system. In addition, the notification unit manages the history of notification content and can refer to past notification content. This allows the notification unit to make more effective notifications based on past notification content.

[0067] The data collection unit can monitor various social media platforms 24 hours a day. For example, it can use AI to monitor various social media platforms 24 hours a day and collect posts. The data collection unit can also configure the monitoring frequency and the technologies used. For example, it can prioritize monitoring specific social media platforms. Furthermore, the data collection unit can filter posts based on specific keywords or hashtags. This allows the data collection unit to quickly detect job postings for illegal part-time work by monitoring various social media platforms 24 hours a day.

[0068] The analysis unit can analyze the content of posts using a generative AI and identify posts that have the characteristics of illegal part-time jobs. For example, the analysis unit can use a generative AI to analyze the content of posts and identify posts that have the characteristics of illegal part-time jobs. The generative AI can analyze the content of posts using a text generation AI (for example, LLM). The generative AI can also configure the model and training data to be used. For example, the generative AI has learned from a large amount of text data and has advanced natural language processing capabilities. As a result, the analysis unit can identify posts that have the characteristics of illegal part-time jobs with high accuracy by using the generative AI.

[0069] The spoofed reply unit allows an AI agent to generate a prompt, which the actual device's AI then uses to generate a reply. For example, the AI ​​agent can generate a prompt, which the actual device's AI then uses to generate a reply. The AI ​​agent can also configure the technologies used and the prompt generation methods. For instance, the AI ​​agent can use prompt generation technology to generate an appropriate reply. This allows the spoofed reply unit to generate a prompt, which in turn enables the actual device's AI to provide an appropriate reply.

[0070] The notification unit can immediately contact public authorities upon detecting an advertisement for illegal part-time work. For example, the notification unit can immediately contact public authorities upon detecting an advertisement for illegal part-time work. The notification unit can also configure the type of information to be notified and the timing of notifications. For instance, the notification unit can set a time range and criteria for immediate notification. This allows the notification unit to respond quickly by immediately contacting public authorities upon detecting an advertisement for illegal part-time work.

[0071] The fake reply unit allows each AI in the actual machine to initiate communication with the recruiter based on a specified profile. The fake reply unit can also configure the characteristics and settings of the profile. For example, the fake reply unit can specify age, gender, occupation, active time slots, writing style, personality, etc. This allows the fake reply unit to deceive the recruiter by communicating based on the specified profile.

[0072] The data collection unit can estimate the user's emotions and determine the priority of posts to collect based on the estimated emotions. For example, if the user is feeling anxious, the data collection unit can prioritize collecting posts related to illegal part-time jobs based on that emotion. If the user is excited, the data collection unit can prioritize collecting posts containing specific keywords based on that emotion. If the user is relaxed, the data collection unit can prioritize collecting general posts based on that emotion. This allows the data collection unit to collect more effectively by prioritizing posts based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0073] The collection unit can filter the types of posts to be collected based on specific keywords or hashtags. For example, the collection unit can prioritize collecting posts containing keywords such as "illegal part-time jobs" or "high income." The collection unit can filter and collect posts containing specific hashtags (e.g., #illegalparttimejobrecruitment). The collection unit can filter and collect posts containing specific phrases (e.g., "easy money"). This allows the collection unit to efficiently collect posts by filtering them based on specific keywords or hashtags.

[0074] The collection unit can adjust the frequency of collected posts based on specific times of day or days of the week. For example, the collection unit can prioritize collecting job postings for illegal part-time work that are posted at night. The collection unit can prioritize collecting job postings for illegal part-time work that are posted on weekends. The collection unit can prioritize collecting job postings for illegal part-time work that are posted during specific event periods. This allows the collection unit to perform effective collection by adjusting the collection frequency based on specific times of day or days of the week.

[0075] The data collection unit can estimate the user's emotions and classify the content of the posts it collects based on those estimated emotions. For example, if a user is feeling anxious, the data collection unit can classify high-risk posts based on that emotion. If a user is excited, the data collection unit can classify interesting posts based on that emotion. If a user is relaxed, the data collection unit can classify general posts based on that emotion. This allows the data collection unit to collect more effectively by classifying the content of posts based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0076] The data collection unit can select the target social media platforms for collecting posts based on specific regions or languages. For example, the unit can prioritize collecting posts in Japanese. It can prioritize collecting posts from specific regions (e.g., urban areas). It can prioritize collecting posts in specific languages ​​(e.g., English). This allows the data collection unit to perform more effective data collection by selecting target social media platforms based on specific regions or languages.

[0077] The data collection unit can filter the content of the posts it collects based on specific user groups. For example, it can prioritize collecting content posted by young users. It can prioritize collecting content posted by users in a specific occupation (e.g., students). It can prioritize collecting content posted by users with specific interests (e.g., high-paying part-time jobs). This allows the data collection unit to effectively collect data by filtering posts based on specific user groups.

[0078] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is feeling anxious, the analysis unit can provide a concise and easy-to-understand display method based on that emotion. If the user is excited, the analysis unit can provide a display method that includes detailed information based on that emotion. If the user is relaxed, the analysis unit can provide a general display method based on that emotion. In this way, the analysis unit can provide a more effective display by adjusting the display method of the analysis results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0079] The analysis unit can classify the content of posts to be analyzed based on specific contexts and topics. For example, the analysis unit can classify posts containing keywords such as "illegal part-time jobs" or "high income." The analysis unit can classify posts containing specific hashtags (e.g., #illegalparttimejobrecruitment). The analysis unit can classify posts containing specific phrases (e.g., "easy money"). This allows the analysis unit to perform effective analysis by classifying posts based on specific contexts and topics.

[0080] The analysis unit can evaluate the reliability of posts being analyzed based on the poster's past posting history. For example, the analysis unit can analyze the poster's past posting history and prioritize the analysis of highly reliable posts. The analysis unit can filter out posts with low reliability from the poster's past posting history. The analysis unit can evaluate reliability based on the poster's past posting history. As a result, the analysis unit can perform effective analysis by evaluating reliability based on the poster's past posting history.

[0081] The analysis unit can estimate the user's emotions and adjust the importance of the analysis results based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can prioritize displaying information of high importance based on that emotion. If the user is excited, the analysis unit can prioritize displaying detailed information based on that emotion. If the user is relaxed, the analysis unit can prioritize displaying general information based on that emotion. This allows the analysis unit to display information more effectively by adjusting the importance of the analysis results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0082] The analysis unit can classify the content of posts to be analyzed based on specific regions or languages. For example, the analysis unit can prioritize the analysis of posts written in Japanese. The analysis unit can prioritize the analysis of posts from specific regions (e.g., urban areas). The analysis unit can prioritize the analysis of posts in specific languages ​​(e.g., English). This allows the analysis unit to perform more effective analysis by classifying posts based on specific regions or languages.

[0083] The analysis unit can classify the content of posts to be analyzed based on specific time periods or days of the week. For example, the analysis unit can prioritize the analysis of job postings for illegal part-time work posted at night. The analysis unit can prioritize the analysis of job postings for illegal part-time work posted on weekends. The analysis unit can prioritize the analysis of job postings for illegal part-time work posted during specific event periods. This allows the analysis unit to perform effective analysis by classifying posts based on specific time periods or days of the week.

[0084] The fake reply unit can estimate the user's emotions and adjust the expression of its reply based on those emotions. For example, if the user is feeling anxious, the fake reply unit can use reassuring expressions based on that emotion. If the user is excited, the fake reply unit can use engaging expressions based on that emotion. If the user is relaxed, the fake reply unit can use general expressions based on that emotion. This allows the fake reply unit to provide more effective replies by adjusting the expression of its reply based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] The fake reply function can customize the content of its replies based on specific contexts and topics. For example, it can customize replies to include keywords such as "illegal part-time jobs" or "high income." It can also customize replies to include specific hashtags (e.g., #illegalparttimejobswanted). Furthermore, it can customize replies to include specific phrases (e.g., "easy money"). This allows the fake reply function to provide more effective replies by customizing its responses based on specific contexts and topics.

[0086] The fake reply function can evaluate the reliability of the reply content based on past reply history. For example, the fake reply function can analyze past reply history and prioritize the use of highly reliable reply content. The fake reply function can filter out unreliable reply content from past reply history. The fake reply function can evaluate reliability based on past reply history. As a result, the fake reply function can provide effective replies by evaluating reliability based on past reply history.

[0087] The fake reply function can estimate the user's emotions and prioritize reply content based on those emotions. For example, if the user is feeling anxious, the fake reply function can prioritize using high-priority reply content based on that emotion. If the user is excited, the fake reply function can prioritize using detailed reply content based on that emotion. If the user is relaxed, the fake reply function can prioritize using general reply content based on that emotion. This allows the fake reply function to provide more effective replies by prioritizing reply content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0088] The fake reply function can customize the content of its replies based on specific regions or languages. For example, it can prioritize replies in Japanese. It can prioritize replies from specific regions (e.g., urban areas). It can prioritize replies in specific languages ​​(e.g., English). This allows the fake reply function to provide more effective replies by customizing its content based on specific regions and languages.

[0089] The fake reply function can customize the content of its replies based on specific times of day or days of the week. For example, it can prioritize replies sent at night, on weekends, or during specific events. This allows the fake reply function to provide more effective replies by customizing its content based on specific times of day or days of the week.

[0090] The notification unit can estimate the user's emotions and adjust the way the notification content is expressed based on the estimated emotions. For example, if the user is feeling anxious, the notification unit can use a reassuring expression based on that emotion. If the user is excited, the notification unit can use an engaging expression based on that emotion. If the user is relaxed, the notification unit can use a general expression based on that emotion. This allows the notification unit to provide more effective notifications by adjusting the way the notification content is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The notification unit can customize the content of its notifications based on specific contexts and topics. For example, it can customize notifications to include keywords such as "illegal part-time jobs" or "high-paying jobs." It can also customize notifications to include specific hashtags (e.g., #illegalpartnerrecruitment). Furthermore, it can customize notifications to include specific phrases (e.g., "easy money"). This allows the notification unit to provide more effective notifications by customizing content based on specific contexts and topics.

[0092] The notification unit can estimate the user's emotions and prioritize notification content based on those emotions. For example, if the user is feeling anxious, the notification unit can prioritize high-priority notifications based on that emotion. If the user is excited, the notification unit can prioritize detailed notifications based on that emotion. If the user is relaxed, the notification unit can prioritize general notifications based on that emotion. This allows the notification unit to provide more effective notifications by prioritizing notification content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The notification unit can customize the content of its notifications based on specific regions or languages. For example, it can prioritize notifications in Japanese. It can prioritize notifications for specific regions (e.g., urban areas). It can prioritize notifications in specific languages ​​(e.g., English). This allows the notification unit to provide more effective notifications by customizing the content based on specific regions and languages.

[0094] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0095] In addition to analyzing the content of posts, the analytics department can also analyze the poster's past behavior history. For example, it can analyze what kind of posts the poster has made in the past to evaluate the reliability of a job posting for illegal part-time work. Furthermore, the analytics department can evaluate the influence of a post by considering metrics such as the number of followers and engagement rate of the poster. This allows the analytics department to conduct more accurate analyses by comprehensively evaluating not only the content of the post but also the poster's behavior history and influence.

[0096] The data collection unit can filter posts on social media based on specific regions or languages. For example, it can prioritize collecting posts written in Japanese. It can also prioritize collecting posts from specific regions (e.g., urban areas). Furthermore, it can prioritize collecting posts in specific languages ​​(e.g., English). This allows the data collection unit to effectively collect data by filtering posts based on specific regions and languages.

[0097] In addition to analyzing the content of posts, the analysis unit can analyze the poster's past posting history to evaluate the reliability of the posts. For example, the analysis unit can analyze what kind of posts the poster has made in the past and prioritize the analysis of highly reliable posts. The analysis unit can also filter out posts with low reliability from the poster's past posting history. This allows the analysis unit to perform effective analysis by evaluating reliability based on the poster's past posting history.

[0098] The fake reply function can be customized based on specific contexts and topics when generating replies. For example, it can customize replies to include keywords such as "illegal part-time jobs" or "high income." It can also customize replies to include specific hashtags (e.g., #illegalpartnerrecruitment). Furthermore, it can customize replies to include specific phrases (e.g., "easy money"). This allows the fake reply function to provide effective replies by customizing them based on specific contexts and topics.

[0099] The notification unit can customize notification content based on specific regions and languages. For example, it can prioritize Japanese notification content. It can also prioritize notification content for specific regions (e.g., urban areas). Furthermore, it can prioritize notification content in specific languages ​​(e.g., English). This allows the notification unit to provide more effective notifications by customizing content based on specific regions and languages.

[0100] The data collection unit can estimate the user's emotions and determine the priority of posts to collect based on those estimated emotions. For example, if the user is feeling anxious, the unit can prioritize collecting posts related to illegal part-time jobs based on that emotion. Similarly, if the user is excited, the unit can prioritize collecting posts containing specific keywords based on that emotion. Furthermore, if the user is relaxed, the unit can prioritize collecting general posts based on that emotion. This allows the data collection unit to perform more effective data collection by prioritizing posts based on the user's emotions.

[0101] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can provide a concise and easy-to-understand display method based on that emotion. If the user is excited, the analysis unit can provide a display method that includes detailed information based on that emotion. Furthermore, if the user is relaxed, the analysis unit can provide a general display method based on that emotion. In this way, the analysis unit can provide a more effective display by adjusting the display method of the analysis results based on the user's emotions.

[0102] The fake reply function can estimate the user's emotions and adjust the expression of the reply based on those emotions. For example, if the user is feeling anxious, the fake reply function can use reassuring expressions based on that emotion. Similarly, if the user is excited, the fake reply function can use interesting expressions based on that emotion. Furthermore, if the user is relaxed, the fake reply function can use general expressions based on that emotion. As a result, the fake reply function can provide more effective replies by adjusting the expression of the reply based on the user's emotions.

[0103] The notification unit can estimate the user's emotions and adjust the way the notification content is presented based on those emotions. For example, if the user is feeling anxious, the notification unit can use reassuring language based on that emotion. Similarly, if the user is excited, the notification unit can use attention-grabbing language based on that emotion. Furthermore, if the user is relaxed, the notification unit can use general language based on that emotion. This allows the notification unit to provide more effective notifications by adjusting the way the notification content is presented based on the user's emotions.

[0104] The notification unit can estimate the user's emotions and prioritize notification content based on those emotions. For example, if the user is feeling anxious, the notification unit can prioritize high-priority notifications based on that emotion. Similarly, if the user is excited, the notification unit can prioritize detailed notifications based on that emotion. Furthermore, if the user is relaxed, the notification unit can prioritize general notifications based on that emotion. This allows the notification unit to prioritize notifications based on the user's emotions, enabling more effective notifications.

[0105] The following briefly describes the processing flow for example form 2.

[0106] Step 1: The collection unit collects posts from social media. The collection unit can, for example, monitor various social media platforms 24 hours a day and collect posts. The collection unit can also use AI to set the types of social media platforms to collect and the collection frequency. Step 2: The analysis unit analyzes the posts collected by the collection unit and identifies posts recruiting for illegal part-time jobs. The analysis unit can, for example, use a generation AI to analyze the content of posts and identify posts that have the characteristics of illegal part-time jobs. The generation AI can, for example, use a text generation AI (e.g., LLM) to analyze the content of posts. Step 3: The fake reply unit sends fake replies to the illegal job postings identified by the analysis unit. The fake reply unit can, for example, have an AI agent generate a prompt, and a real AI can then send a reply based on that prompt. The AI ​​agent can, for example, use prompt generation technology to generate appropriate reply content. Step 4: The notification unit notifies public authorities of the information obtained by the fake reply unit. For example, the notification unit can immediately contact public authorities if it detects a recruitment ad for illegal part-time work. The notification unit can also use AI to set the type of information to be notified and the timing of the notification.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] Each of the multiple elements described above, including the collection unit, analysis unit, fake reply unit, and notification unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14, which monitors various SNS 24 hours a day and collects posts. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the collected posts and identifies posts soliciting illegal part-time jobs. The fake reply unit is implemented by the control unit 46A of the smart device 14, which sends a fake reply to the identified illegal part-time job solicitation post. The notification unit is implemented by the identification processing unit 290 of the data processing unit 12, which notifies public authorities of the information obtained by the fake reply unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0111] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements described above, including the collection unit, analysis unit, fake reply unit, and notification unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214, which monitors various social networking services (SNS) 24 hours a day and collects posts. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the collected posts and identifies posts soliciting illegal part-time jobs. The fake reply unit is implemented by the control unit 46A of the smart glasses 214, which sends a fake reply to the identified illegal part-time job postings. The notification unit is implemented by the identification processing unit 290 of the data processing unit 12, which notifies public authorities of the information obtained by the fake reply unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0127] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the collection unit, analysis unit, fake reply unit, and notification unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314, which monitors various SNS 24 hours a day and collects posts. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, which analyzes the collected posts and identifies posts soliciting illegal part-time jobs. The fake reply unit is implemented by the control unit 46A of the headset terminal 314, which sends a fake reply to the identified illegal part-time job solicitation posts. The notification unit is implemented by the identification processing unit 290 of the data processing unit 12, which notifies public authorities of the information obtained by the fake reply unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0143] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] Each of the multiple elements described above, including the collection unit, analysis unit, fake reply unit, and notification unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414, which monitors various SNS 24 hours a day and collects posts. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which analyzes the collected posts and identifies posts soliciting illegal part-time jobs. The fake reply unit is implemented by, for example, the control unit 46A of the robot 414, which sends a fake reply to the identified illegal part-time job solicitation posts. The notification unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which notifies public authorities of the information obtained by the fake reply unit. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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."

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] (Note 1) The collection department collects posts from social media, The analysis unit analyzes the posts collected by the aforementioned collection unit and identifies posts recruiting for illegal part-time jobs, The aforementioned analysis unit performs a fake reply to the job posting for illegal part-time work that was identified by the analysis unit, The system includes a notification unit that notifies a public institution of the information obtained by the aforementioned forged reply unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is We monitor various social media platforms 24 hours a day. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, We use generation AI to analyze post content and identify posts that have characteristics of illegal part-time jobs. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned fake reply section is, The AI ​​agent generates a prompt, and the AI ​​on the actual device responds based on that prompt. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned notification unit, If we detect any advertisements for illegal part-time jobs, we will immediately contact the relevant authorities. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned fake reply section is, Based on the specified profile, each AI unit begins communicating with the recruiter. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is It estimates user sentiment and determines the priority of posts to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Filter the types of posts to collect based on specific keywords or hashtags. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is Adjust the frequency of posts collected based on specific times of day or days of the week. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates user sentiment and categorizes the content of collected posts based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is The social media platforms from which posts are collected are selected based on specific regions and languages. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is Filter the content of the posts you collect based on specific user groups. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, The content of the posts to be analyzed is categorized based on specific contexts and topics. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, The reliability of the posts being analyzed is evaluated based on the poster's past posting history. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts the importance of the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, The content of the posts to be analyzed is categorized based on specific regions or languages. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, The content of the posts to be analyzed is categorized based on specific time periods and days of the week. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned fake reply section is, It estimates the user's emotions and adjusts the way the response is phrased based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned fake reply section is, Customize your replies based on specific contexts or topics. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned fake reply section is, The reliability of the reply is evaluated based on past reply history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned fake reply section is, It estimates the user's emotions and prioritizes replies based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned fake reply section is, Customize the reply based on specific regions or languages. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned fake reply section is, Customize the content of your replies based on specific times of day or days of the week. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned notification unit, It estimates the user's emotions and adjusts the way notifications are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned notification unit, Customize the content of notifications based on specific contexts or topics. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned notification unit, It estimates the user's emotions and prioritizes notification content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned notification unit, Customize the content of notifications based on specific regions or languages. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection department collects posts from social media, The analysis unit analyzes the posts collected by the aforementioned collection unit and identifies posts recruiting for illegal part-time jobs, The aforementioned analysis unit performs a fake reply to the job posting for illegal part-time work that was identified by the analysis unit, The system includes a notification unit that notifies a public institution of the information obtained by the aforementioned forged reply unit. A system characterized by the following features.

2. The aforementioned collection unit is We monitor various social media platforms 24 hours a day. The system according to feature 1.

3. The aforementioned analysis unit, We use generation AI to analyze the content of posts and identify posts that have characteristics of illegal part-time jobs. The system according to feature 1.

4. The aforementioned fake reply section is, The AI ​​agent generates a prompt, and the AI ​​on the actual device responds based on that prompt. The system according to feature 1.

5. The aforementioned notification unit, If we detect any advertisements for illegal part-time jobs, we will immediately contact the relevant authorities. The system according to feature 1.

6. The aforementioned fake reply section is, Based on the specified profile, each AI in the machine begins communicating with the recruiter. The system according to feature 1.

7. The aforementioned collection unit is It estimates user sentiment and determines the priority of posts to collect based on the estimated user sentiment. The system according to feature 1.

8. The aforementioned collection unit is Filter the types of posts to collect based on specific keywords or hashtags. The system according to feature 1.

Images