system

Abstract

The system according to this embodiment aims to detect the possibility of fraud during a telephone conversation in real time and to respond quickly. [Solution] The system according to the embodiment comprises a recording unit, a conversion unit, an analysis unit, an alert unit, and a communication unit. The recording unit records the user's telephone conversation in real time. The conversion unit converts the audio data recorded by the recording unit into text. The analysis unit analyzes the text data converted by the conversion unit. The alert unit issues an alert based on the results of the analysis by the analysis unit. The communication unit contacts the police based on the alert issued by the alert unit.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , ,

[0003] , , , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0007] The system according to this embodiment can detect the possibility of fraud during a telephone conversation in real time and respond quickly. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) A fraud detection system according to an embodiment of the present invention is a system that records a user's telephone conversation in real time, converts it into text using a generative AI, and detects potentially fraudulent phrases, patterns, and keywords. This fraud detection system records the user's telephone conversation in real time and converts the audio data into text using natural language processing technology. Next, the generative AI analyzes the text data and detects potentially fraudulent phrases, patterns, and keywords. If detected, the information is automatically analyzed and an alert is sent to the user. Furthermore, the police are contacted if necessary. For example, the user's telephone conversation is recorded in real time. At this time, noise cancellation technology is used so that the content of the conversation is recorded clearly. The recorded audio data is converted into text using natural language processing technology. For example, a conversation such as "Hello, your bank account is at risk" is recorded and its content is converted into text data. Next, the generative AI analyzes the text data. The generative AI has learned potentially fraudulent phrases, patterns, and keywords in advance and performs analysis based on these. For example, if keywords such as "bank account," "risk," and "transfer" are included, it is determined that there is a high possibility of fraud. If detected, the information is automatically analyzed and an alert is sent to the user. The alert is sent as a notification to the user's smartphone. For example, a message such as "This may be a scam. Please be careful" may be displayed. Furthermore, the police will be contacted if necessary. If the generating AI determines that there is a very high probability of fraud, it will automatically contact the police. For example, a message such as "A conversation with a very high probability of fraud has been detected. Please check the details" will be sent to the police. This protects the user from the risk of fraud and allows them to have phone conversations with peace of mind. It also enables prompt contact with the police, contributing to the prevention of fraud. In this way, the fraud detection system can analyze the user's phone conversations in real time, send an alert if there is a possibility of fraud, and contact the police if necessary.

[0029] The fraud detection system according to this embodiment comprises a recording unit, a conversion unit, an analysis unit, an alert unit, and a communication unit. The recording unit records the user's telephone conversation in real time. The recording unit can record the content of the conversation clearly, for example, by using noise cancellation technology. The conversion unit converts the audio data recorded by the recording unit into text. The conversion unit converts the audio data into text data, for example, by using natural language processing technology. The analysis unit analyzes the text data converted by the conversion unit. The analysis unit analyzes the text data using generative AI to detect potentially fraudulent phrases, patterns, and keywords. The generative AI is implemented, for example, using a deep learning model or a natural language processing model. The alert unit issues an alert based on the results analyzed by the analysis unit. The alert unit can, for example, send a notification to the user's smartphone. The communication unit contacts the police based on the alert issued by the alert unit. The communication unit can, for example, contact the police if it is determined that there is a very high probability of fraud. As a result, the fraud detection system according to the embodiment can analyze the user's phone conversation in real time, issue an alert if there is a possibility of fraud, and contact the police if necessary.

[0030] The recording unit can record conversations clearly using noise-canceling technology. Noise-canceling technologies include, for example, active noise cancellation and passive noise cancellation. For instance, the recording unit can use active noise cancellation technology to reduce ambient noise and record conversations clearly. Alternatively, the recording unit can use passive noise cancellation technology to block noise by creating a physical barrier, resulting in clear recordings of conversations. For example, active noise cancellation technology uses a microphone to detect ambient noise and generates sound waves with the opposite phase to cancel it out. Passive noise cancellation technology physically blocks noise using earplugs or soundproofing materials. As a result, using noise-canceling technology allows for clear recording of conversations.

[0031] The analysis unit can analyze text data using generative AI to detect potentially fraudulent phrases, patterns, and keywords. The generative AI is implemented using, for example, deep learning models or natural language processing models. For instance, the generative AI learns from past fraud cases to pre-train phrases, patterns, and keywords that may be associated with fraud. For example, the generative AI might determine that a text is highly likely to be fraudulent if it contains keywords such as "bank account," "danger," or "transfer." Furthermore, the generative AI can calculate the degree of matching between phrases and patterns to assess the likelihood of fraud. For example, it calculates the degree of matching between phrases and patterns in the text data, and determines that a high degree of matching indicates a high likelihood of fraud. This allows for highly accurate detection of potentially fraudulent phrases, patterns, and keywords using the generative AI.

[0032] The alert unit can send notifications to the user's smartphone. The alert unit can send notifications to the user's smartphone in various formats, such as push notifications, SMS, and email. Push notifications are a method of sending notifications in real time through a smartphone application, allowing the user to receive the alert immediately. SMS is a method of sending text messages using the Short Message Service, allowing the user to receive the alert in their smartphone's messaging app. Email is a method of sending alerts using email, allowing the user to receive the alert in their email app. For example, the alert unit can send a push notification saying, "This may be a scam. Please be careful," if there is a possibility of fraud. The alert unit can also send an SMS message saying, "A conversation with a very high probability of being a scam has been detected. Please check the details," if there is a very high probability of fraud. This allows the system to quickly inform the user of potential scams by sending notifications to their smartphone.

[0033] The liaison department can contact the police if it determines that there is a high probability of fraud. The liaison department can contact the police via methods such as phone, email, or a dedicated app. The liaison department automatically contacts the police if its generating AI determines that there is a very high probability of fraud. For example, the liaison department sends a message to the police saying, "A conversation that is highly likely to be fraudulent has been detected. Please check the details." The liaison department also provides means for users to contact the police manually. For example, the liaison department provides a button for users to contact the police through the app. This allows for a quick response by contacting the police when there is a high probability of fraud.

[0034] The analysis unit can perform analysis based on data that the generation AI has previously learned. For example, the generation AI may have previously learned data on past fraud cases or user conversation data. The analysis unit analyzes text data based on the data that the generation AI has previously learned and detects potentially fraudulent phrases, patterns, and keywords. For example, the generation AI learns from past fraud cases to pre-learn potentially fraudulent phrases, patterns, and keywords. For example, the generation AI may determine that there is a high probability of fraud if keywords such as "bank account," "danger," and "transfer" are included. The generation AI can also calculate the degree of matching between phrases and patterns to evaluate the likelihood of fraud. For example, the generation AI calculates the degree of matching between phrases and patterns in the text data and determines that there is a high probability of fraud if the degree of matching is high. As a result, the accuracy of the analysis is improved by performing analysis based on data that the generation AI has previously learned.

[0035] The recording unit can automatically adjust the optimal recording settings by referring to the user's past conversation history during recording. For example, the recording unit can store the user's past conversation history in a database and refer to that data during recording. The recording unit automatically adjusts the optimal recording settings by referring to the user's past conversation history. For example, if the user has previously recorded an important conversation, the recording will start based on those settings. Also, if the user has previously recorded in a noisy environment, noise cancellation can be enhanced. Furthermore, if the user has previously recorded a short conversation, the recording time can be shortened. For example, the recording unit analyzes the past conversation history and automatically applies the optimal recording settings. This allows for automatic adjustment of the optimal recording settings by referring to the user's past conversation history.

[0036] The recording unit can dynamically adjust the recording quality according to the content of the conversation during recording. For example, the recording unit analyzes the content of the conversation in real time and dynamically adjusts the recording quality accordingly. The recording unit dynamically adjusts the recording quality according to the content of the conversation. For example, if an important conversation begins, it will record at high quality. Conversely, if casual conversation continues, it can record at low quality. Furthermore, if the content of the conversation changes, it can readjust the recording quality. For example, the recording unit analyzes the content of the conversation and, if it determines that an important conversation has begun, it will record at high quality. Conversely, if it determines that casual conversation continues, it can record at low quality. In this way, by dynamically adjusting the recording quality according to the content of the conversation, important conversations can be recorded at high quality.

[0037] The recording unit can optimize recording settings by considering the user's geographical location during recording. The recording unit acquires the user's geographical location using, for example, GPS data or Wi-Fi location information. During recording, the recording unit optimizes recording settings by considering the user's geographical location. For example, if the user is in a noisy environment, noise cancellation is enhanced. Conversely, if the user is in a quiet environment, the recording sensitivity can be set higher. Furthermore, if the user is moving, recording stability can be prioritized. For example, the recording unit acquires the user's geographical location and enhances noise cancellation if it determines the user is in a noisy environment. It can also set higher recording sensitivity if it determines the user is in a quiet environment. This allows for optimal recording settings by considering the user's geographical location.

[0038] The recording unit can analyze the user's social media activity during recording and prioritize recording relevant conversations. For example, the recording unit can store the user's social media activity in a database and refer to that data during recording. The recording unit analyzes the user's social media activity and prioritizes recording relevant conversations. For example, if the user is having an important conversation on social media, that conversation will be prioritized for recording. It can also prioritize recording conversations that may be fraudulent if the user is having one. Furthermore, if the user is using specific keywords on social media, those conversations will be prioritized for recording. For example, the recording unit analyzes the user's social media activity and prioritizes recording important conversations. It can also prioritize recording conversations that may be fraudulent. This allows the system to prioritize recording relevant conversations by analyzing the user's social media activity.

[0039] The conversion unit can dynamically change the text conversion algorithm during conversion, taking into account the context of the conversation. For example, the conversion unit can analyze the context of the conversation in real time and dynamically change the text conversion algorithm according to that context. The conversion unit can dynamically change the text conversion algorithm during conversion, taking into account the context of the conversation. For example, if the conversation is business-related, it can use an algorithm that takes technical terms into account. If the conversation is everyday conversation, it can also use an algorithm that prioritizes common words. Furthermore, if the conversation is technical, it can also use an algorithm that takes technical terms into account. For example, the conversion unit analyzes the context of the conversation and, if it determines that it is a business-related conversation, it uses an algorithm that takes technical terms into account. If it determines that it is everyday conversation, it can also use an algorithm that prioritizes common words. This makes it possible to perform more appropriate text conversion by taking the context of the conversation into account.

[0040] The conversion unit can apply different conversion algorithms depending on the category of the conversation during conversion. For example, the conversion unit analyzes the category of the conversation in real time and applies a different conversion algorithm depending on that category. The conversion unit applies different conversion algorithms depending on the category of the conversation during conversion. For example, if the conversation is medical, it uses an algorithm that takes medical terminology into account. If the conversation is legal, it can also use an algorithm that takes legal terminology into account. Furthermore, if the conversation is educational, it can also use an algorithm that takes educational terminology into account. For example, the conversion unit analyzes the category of the conversation and, if it determines that it is a medical conversation, uses an algorithm that takes medical terminology into account. If it determines that it is a legal conversation, it can also use an algorithm that takes legal terminology into account. This improves the accuracy of text conversion by using the appropriate conversion algorithm according to the category of the conversation.

[0041] The conversion unit can determine conversion priorities based on the time of day of the conversation. For example, the conversion unit analyzes the time of day of the conversation in real time and determines conversion priorities accordingly. The conversion unit determines conversion priorities based on the time of day of the conversation. For example, nighttime conversations will be converted by the next morning. Daytime conversations can also be converted in real time. Furthermore, weekend conversations can be converted by the beginning of the following week. For example, the conversion unit analyzes the time of day of the conversation and, if it determines it is a nighttime conversation, will complete the conversion by the next morning. The conversion unit can also perform the conversion in real time if it determines it is a daytime conversation. This enables efficient text conversion by determining conversion priorities based on the time of day of the conversation.

[0042] The conversion unit can adjust the order of conversion based on the relevance of the conversations during the conversion process. For example, the conversion unit analyzes the relevance of conversations in real time and adjusts the order of conversion according to that relevance. The conversion unit adjusts the order of conversion based on the relevance of conversations during the conversion process. For example, important conversations are converted with the highest priority. General conversations can be converted later. Furthermore, conversations with low relevance can be converted last. For example, the conversion unit analyzes the relevance of conversations and converts conversations with the highest priority if it determines they are important. The conversion unit can also convert conversations at a later date if it determines them to be general. In this way, by adjusting the order of conversion based on the relevance of conversations, important conversations can be converted preferentially.

[0043] The analysis unit can improve the accuracy of its analysis by considering the interrelationships of the conversation during analysis. For example, the analysis unit can analyze the context of the conversation and the relationships between participants in real time and improve the accuracy of the analysis based on these interrelationships. The analysis unit improves the accuracy of its analysis by considering the interrelationships of the conversation during analysis. For example, it can perform analysis considering the context of the conversation. It can also perform analysis considering the relationships between the participants in the conversation. Furthermore, it can also perform analysis considering the context of the conversation. For example, the analysis unit can analyze the context of the conversation and perform analysis considering the relationship between preceding and succeeding statements. It can also analyze the relationships between the participants in the conversation and perform analysis considering the relationships between the speakers. In this way, the accuracy of the analysis is improved by considering the interrelationships of the conversation.

[0044] The analysis unit can perform analysis while considering the attribute information of the conversation participants. For example, the analysis unit can analyze attribute information such as the age, gender, and occupation of the conversation participants in real time and perform analysis based on that attribute information. The analysis unit can perform analysis while considering the attribute information of the conversation participants. For example, it can perform analysis while considering the age of the conversation participants. It can also perform analysis while considering the occupation of the conversation participants. Furthermore, it can also perform analysis while considering the relationships between the conversation participants. For example, the analysis unit can analyze the age of the conversation participants and perform analysis according to their age. It can also analyze the occupation of the conversation participants and perform analysis according to their occupation. This makes it possible to perform more accurate analysis by considering the attribute information of the conversation participants.

[0045] The analysis unit can perform analysis while considering the geographical distribution of conversations. For example, the analysis unit can analyze the geographical distribution of conversations in real time and perform analysis based on that geographical distribution. The analysis unit considers the geographical distribution of conversations when performing analysis. For example, it can consider the location where the conversation took place. It can also consider the locations of the conversation participants. Furthermore, if the content of the conversation is related to a specific region, it can also consider information about that region when performing analysis. For example, the analysis unit can analyze the location where the conversation took place and consider information related to that location when performing analysis. It can also analyze the locations of the conversation participants and consider information related to those locations when performing analysis. In this way, by considering the geographical distribution of conversations, it becomes possible to perform analysis that reflects region-specific information.

[0046] The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the conversation during the analysis process. For example, the analysis unit can search a database for literature related to the content of the conversation and perform the analysis by referring to that literature. The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the conversation during the analysis process. For example, it can perform the analysis by referring to literature related to the content of the conversation. It can also perform the analysis by referring to literature related to keywords in the conversation. Furthermore, it can also perform the analysis by referring to literature related to patterns in the conversation. For example, the analysis unit can search a database for literature related to the content of the conversation and perform the analysis by referring to that literature. It can also perform the analysis by referring to literature related to keywords in the conversation. In this way, the accuracy of the analysis is improved by referring to relevant literature.

[0047] The alert unit can adjust the level of detail of an alert based on the importance of the conversation when an alert is issued. For example, the alert unit analyzes the importance of the conversation in real time and adjusts the level of detail of the alert accordingly. The alert unit adjusts the level of detail of an alert based on the importance of the conversation when an alert is issued. For example, in the case of an important conversation, a detailed alert is issued. In the case of a general conversation, a concise alert can be issued. Furthermore, in the case of a less relevant conversation, a minimal alert can be issued. For example, the alert unit analyzes the importance of the conversation and issues a detailed alert if it determines that the conversation is important. In addition, the alert unit can issue a concise alert if it determines that the conversation is general. By adjusting the level of detail of the alert based on the importance of the conversation, it is possible to issue alerts with an appropriate amount of information.

[0048] The alert unit can apply different alert algorithms depending on the conversation category when an alert is issued. For example, the alert unit analyzes the conversation category in real time and applies a different alert algorithm depending on that category. The alert unit applies different alert algorithms depending on the conversation category when an alert is issued. For example, in the case of a fraud-related conversation, an emergency alert is issued. In the case of a business-related conversation, a detailed alert can also be issued. Furthermore, in the case of an everyday conversation, a concise alert can also be issued. For example, the alert unit analyzes the conversation category and issues an emergency alert if it determines that the conversation is fraud-related. In addition, the alert unit can issue a detailed alert if it determines that the conversation is business-related. This allows for the effective issuance of alerts by using the appropriate alert algorithm according to the conversation category.

[0049] The alert unit can determine the priority of alerts based on when a conversation occurs. For example, the alert unit analyzes the timing of conversations in real time and determines the priority of alerts according to that timing. The alert unit determines the priority of alerts based on when a conversation occurs. For example, the most recent conversation will receive the highest priority alert. Past conversations can also be delayed in receiving alerts. Furthermore, future conversations can be predicted and alerts can be issued. For example, the alert unit analyzes the timing of a conversation and, if it determines it is a recent conversation, will receive the highest priority alert. The alert unit can also delay issuing alerts if it determines it is a past conversation. In this way, by determining the priority of alerts based on when a conversation occurs, alerts can be issued at the appropriate time.

[0050] The alert unit can adjust the order of alerts based on the relevance of the conversations when an alert is issued. For example, the alert unit analyzes the relevance of conversations in real time and adjusts the order of alerts according to that relevance. The alert unit adjusts the order of alerts based on the relevance of conversations when an alert is issued. For example, important conversations will receive the highest priority alert. General conversations can also be delayed in receiving alerts. Furthermore, conversations with low relevance can be delayed in receiving alerts. For example, the alert unit analyzes the relevance of conversations and, if it determines that a conversation is important, will receive the highest priority alert. The alert unit can also delay in receiving alerts if it determines that a conversation is general. In this way, by adjusting the order of alerts based on the relevance of conversations, important alerts can be issued preferentially.

[0051] The liaison department can select the most suitable method of communication by referring to past conversation data when making a call. For example, the liaison department can store past conversation data in a database and refer to that data when making a call. The liaison department selects the most suitable method of communication by referring to past conversation data when making a call. For example, it can select the most suitable method of communication based on how the police were contacted in the past. It can also select the most suitable method of communication by analyzing past conversation data. Furthermore, it can select the most suitable method of communication by referring to past contact history. For example, the liaison department can select the most suitable method of communication by referring to past data. It can also select the most suitable method of communication by analyzing past conversation data. In this way, the liaison department can select the most suitable method of communication by referring to past data.

[0052] The liaison department can customize the means of communication based on the content of the conversation. For example, the liaison department can analyze the content of the conversation in real time and customize the means of communication accordingly. The liaison department can customize the means of communication based on the content of the conversation. For example, if there is a high possibility of fraud, it will use an emergency contact method. If there is a low possibility of fraud, it can also use a normal contact method. Furthermore, it can select the most appropriate means of communication depending on the content of the conversation. For example, the liaison department will analyze the content of the conversation and use an emergency contact method if it determines there is a high possibility of fraud. If there is a low possibility of fraud, it can also use a normal contact method. This allows for communication in an appropriate manner by customizing the means of communication based on the content of the conversation.

[0053] The liaison unit can select the most appropriate method of contact by considering the geographical location information of the conversation. The liaison unit obtains the geographical location information of the conversation using, for example, GPS data or Wi-Fi location information. The liaison unit selects the most appropriate method of contact by considering the geographical location information of the conversation. For example, if the user is in a specific area, it will contact the police in that area. It can also contact the nearest police station if the user is on the move. Furthermore, if the user is overseas, it can contact the local police station. For example, the liaison unit obtains the geographical location information of the conversation and, if it determines that the user is in a specific area, it will contact the police in that area. It can also contact the nearest police station if it determines that the user is on the move. In this way, the liaison unit can select the most appropriate method of contact by considering the geographical location information.

[0054] The liaison department can improve the accuracy of communication by referring to relevant literature during communication. For example, the liaison department can search a database for literature related to the content of the conversation and use that literature to make communication. The liaison department can improve the accuracy of communication by referring to relevant literature during communication. For example, it can use literature related to the content of the conversation to make communication. It can also use literature related to keywords in the conversation to make communication. Furthermore, it can use literature related to patterns in the conversation to make communication. For example, the liaison department can search a database for literature related to the content of the conversation and use that literature to make communication. It can also use literature related to keywords in the conversation to make communication. In this way, the accuracy of communication is improved by referring to relevant literature.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The recording unit can learn specific patterns by referring to the user's past conversation history and optimize recording. For example, if a user has frequently used a particular phrase in the past, the recording sensitivity can be increased when that phrase appears. Similarly, if a user tends to have important conversations during certain time periods, the recording sensitivity can be increased during those times. Furthermore, if a user frequently has important conversations in certain locations, the recording settings for those locations can be optimized. This allows for the optimization of recording settings based on the user's past behavioral patterns.

[0057] The recording unit can adjust the recording start time based on the user's geographical location. For example, if the user is in a noisy environment, recording can start earlier to avoid missing important information. Conversely, if the user is in a quiet environment, recording can be delayed to avoid unwanted noise. Furthermore, if the user is on the move, the recording start time can be dynamically adjusted. This allows for the optimization of the recording start time based on the user's geographical location.

[0058] The conversion unit can analyze the context of a conversation in real time and dynamically change the text conversion algorithm according to that context. For example, if the conversation is business-related, it can use an algorithm that takes technical terms into account. If the conversation is everyday conversation, it can also use an algorithm that prioritizes common language. Furthermore, if the conversation is technical, it can use an algorithm that takes technical terms into account. This allows for more appropriate text conversion by considering the context of the conversation.

[0059] The analysis unit can perform analysis while considering the attribute information of the conversation participants. For example, it can analyze attribute information such as the age, gender, and occupation of the conversation participants in real time and perform analysis based on that attribute information. For example, it can perform analysis while considering the age of the conversation participants. It can also perform analysis while considering the occupation of the conversation participants. Furthermore, it can perform analysis while considering the relationships between the conversation participants. As a result, more accurate analysis becomes possible by considering the attribute information of the conversation participants.

[0060] The alerting unit can prioritize alerts based on when a conversation occurred. For example, recent conversations will receive the highest priority alert. Past conversations can be prioritized and alerts sent later. Furthermore, future conversations can be predicted and alerts sent accordingly. By prioritizing alerts based on when a conversation occurred, alerts can be sent at the appropriate time.

[0061] The liaison department can customize the means of communication based on the content of the conversation. For example, if there is a high probability of fraud, emergency contact methods will be used. Conversely, if the likelihood of fraud is low, regular contact methods can be used. Furthermore, the most appropriate means of communication can be selected depending on the content of the conversation. This allows for communication to be conducted in an appropriate manner by customizing the means of communication based on the content of the conversation.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The recording unit records the user's phone conversation in real time. The recording unit can record the conversation clearly, for example, by using noise cancellation technology. Step 2: The conversion unit converts the audio data recorded by the recording unit into text. The conversion unit converts the audio data into text data using, for example, natural language processing techniques. Step 3: The analysis unit analyzes the text data converted by the conversion unit. The analysis unit uses a generative AI to analyze the text data and detect potentially fraudulent phrases, patterns, and keywords. The generative AI is implemented using, for example, a deep learning model or a natural language processing model. Step 4: The alert unit issues an alert based on the results analyzed by the analysis unit. The alert unit can, for example, send a notification to the user's smartphone. Step 5: The liaison unit contacts the police based on the alerts issued by the alert unit. For example, the liaison unit may contact the police if it is determined that there is a very high probability of fraud.

[0064] (Example of form 2) A fraud detection system according to an embodiment of the present invention is a system that records a user's telephone conversation in real time, converts it into text using a generative AI, and detects potentially fraudulent phrases, patterns, and keywords. This fraud detection system records the user's telephone conversation in real time and converts the audio data into text using natural language processing technology. Next, the generative AI analyzes the text data and detects potentially fraudulent phrases, patterns, and keywords. If detected, the information is automatically analyzed and an alert is sent to the user. Furthermore, the police are contacted if necessary. For example, the user's telephone conversation is recorded in real time. At this time, noise cancellation technology is used so that the content of the conversation is recorded clearly. The recorded audio data is converted into text using natural language processing technology. For example, a conversation such as "Hello, your bank account is at risk" is recorded and its content is converted into text data. Next, the generative AI analyzes the text data. The generative AI has learned potentially fraudulent phrases, patterns, and keywords in advance and performs analysis based on these. For example, if keywords such as "bank account," "risk," and "transfer" are included, it is determined that there is a high possibility of fraud. If detected, the information is automatically analyzed and an alert is sent to the user. The alert is sent as a notification to the user's smartphone. For example, a message such as "This may be a scam. Please be careful" may be displayed. Furthermore, the police will be contacted if necessary. If the generating AI determines that there is a very high probability of fraud, it will automatically contact the police. For example, a message such as "A conversation with a very high probability of fraud has been detected. Please check the details" will be sent to the police. This protects the user from the risk of fraud and allows them to have phone conversations with peace of mind. It also enables prompt contact with the police, contributing to the prevention of fraud. In this way, the fraud detection system can analyze the user's phone conversations in real time, send an alert if there is a possibility of fraud, and contact the police if necessary.

[0065] The fraud detection system according to this embodiment comprises a recording unit, a conversion unit, an analysis unit, an alert unit, and a communication unit. The recording unit records the user's telephone conversation in real time. The recording unit can record the content of the conversation clearly, for example, by using noise cancellation technology. The conversion unit converts the audio data recorded by the recording unit into text. The conversion unit converts the audio data into text data, for example, by using natural language processing technology. The analysis unit analyzes the text data converted by the conversion unit. The analysis unit analyzes the text data using generative AI to detect potentially fraudulent phrases, patterns, and keywords. The generative AI is implemented, for example, using a deep learning model or a natural language processing model. The alert unit issues an alert based on the results analyzed by the analysis unit. The alert unit can, for example, send a notification to the user's smartphone. The communication unit contacts the police based on the alert issued by the alert unit. The communication unit can, for example, contact the police if it is determined that there is a very high probability of fraud. As a result, the fraud detection system according to the embodiment can analyze the user's phone conversation in real time, issue an alert if there is a possibility of fraud, and contact the police if necessary.

[0066] The recording unit can record conversations clearly using noise-canceling technology. Noise-canceling technologies include, for example, active noise cancellation and passive noise cancellation. For instance, the recording unit can use active noise cancellation technology to reduce ambient noise and record conversations clearly. Alternatively, the recording unit can use passive noise cancellation technology to block noise by creating a physical barrier, resulting in clear recordings of conversations. For example, active noise cancellation technology uses a microphone to detect ambient noise and generates sound waves with the opposite phase to cancel it out. Passive noise cancellation technology physically blocks noise using earplugs or soundproofing materials. As a result, using noise-canceling technology allows for clear recording of conversations.

[0067] The analysis unit can analyze text data using generative AI to detect potentially fraudulent phrases, patterns, and keywords. The generative AI is implemented using, for example, deep learning models or natural language processing models. For instance, the generative AI learns from past fraud cases to pre-train phrases, patterns, and keywords that may be associated with fraud. For example, the generative AI might determine that a text is highly likely to be fraudulent if it contains keywords such as "bank account," "danger," or "transfer." Furthermore, the generative AI can calculate the degree of matching between phrases and patterns to assess the likelihood of fraud. For example, it calculates the degree of matching between phrases and patterns in the text data, and determines that a high degree of matching indicates a high likelihood of fraud. This allows for highly accurate detection of potentially fraudulent phrases, patterns, and keywords using the generative AI.

[0068] The alert unit can send notifications to the user's smartphone. The alert unit can send notifications to the user's smartphone in various formats, such as push notifications, SMS, and email. Push notifications are a method of sending notifications in real time through a smartphone application, allowing the user to receive the alert immediately. SMS is a method of sending text messages using the Short Message Service, allowing the user to receive the alert in their smartphone's messaging app. Email is a method of sending alerts using email, allowing the user to receive the alert in their email app. For example, the alert unit can send a push notification saying, "This may be a scam. Please be careful," if there is a possibility of fraud. The alert unit can also send an SMS message saying, "A conversation with a very high probability of being a scam has been detected. Please check the details," if there is a very high probability of fraud. This allows the system to quickly inform the user of potential scams by sending notifications to their smartphone.

[0069] The liaison department can contact the police if it determines that there is a high probability of fraud. The liaison department can contact the police via methods such as phone, email, or a dedicated app. The liaison department automatically contacts the police if its generating AI determines that there is a very high probability of fraud. For example, the liaison department sends a message to the police saying, "A conversation that is highly likely to be fraudulent has been detected. Please check the details." The liaison department also provides means for users to contact the police manually. For example, the liaison department provides a button for users to contact the police through the app. This allows for a quick response by contacting the police when there is a high probability of fraud.

[0070] The analysis unit can perform analysis based on data that the generation AI has previously learned. For example, the generation AI may have previously learned data on past fraud cases or user conversation data. The analysis unit analyzes text data based on the data that the generation AI has previously learned and detects potentially fraudulent phrases, patterns, and keywords. For example, the generation AI learns from past fraud cases to pre-learn potentially fraudulent phrases, patterns, and keywords. For example, the generation AI may determine that there is a high probability of fraud if keywords such as "bank account," "danger," and "transfer" are included. The generation AI can also calculate the degree of matching between phrases and patterns to evaluate the likelihood of fraud. For example, the generation AI calculates the degree of matching between phrases and patterns in the text data and determines that there is a high probability of fraud if the degree of matching is high. As a result, the accuracy of the analysis is improved by performing analysis based on data that the generation AI has previously learned.

[0071] The recording unit can estimate the user's emotions and adjust the recording start time based on the estimated emotions. For example, the recording unit estimates the user's emotions using technologies such as voice tone analysis and facial recognition. For instance, if the user is nervous, recording can start immediately after the conversation begins. If the user is relaxed, recording can start from the most important part of the conversation. Furthermore, if the user is in a hurry, the entire conversation can be recorded. For example, the recording unit analyzes the user's voice tone and, if it determines the user is nervous, starts recording immediately after the conversation begins. It also recognizes the user's facial expressions and, if it determines the user is relaxed, can start recording from the most important part of the conversation. This allows for recording important conversations without missing anything by adjusting the recording start time based on the user's emotions.

[0072] The recording unit can automatically adjust the optimal recording settings by referring to the user's past conversation history during recording. For example, the recording unit can store the user's past conversation history in a database and refer to that data during recording. The recording unit automatically adjusts the optimal recording settings by referring to the user's past conversation history. For example, if the user has previously recorded an important conversation, the recording will start based on those settings. Also, if the user has previously recorded in a noisy environment, noise cancellation can be enhanced. Furthermore, if the user has previously recorded a short conversation, the recording time can be shortened. For example, the recording unit analyzes the past conversation history and automatically applies the optimal recording settings. This allows for automatic adjustment of the optimal recording settings by referring to the user's past conversation history.

[0073] The recording unit can dynamically adjust the recording quality according to the content of the conversation during recording. For example, the recording unit analyzes the content of the conversation in real time and dynamically adjusts the recording quality accordingly. The recording unit dynamically adjusts the recording quality according to the content of the conversation. For example, if an important conversation begins, it will record at high quality. Conversely, if casual conversation continues, it can record at low quality. Furthermore, if the content of the conversation changes, it can readjust the recording quality. For example, the recording unit analyzes the content of the conversation and, if it determines that an important conversation has begun, it will record at high quality. Conversely, if it determines that casual conversation continues, it can record at low quality. In this way, by dynamically adjusting the recording quality according to the content of the conversation, important conversations can be recorded at high quality.

[0074] The recording unit can estimate the user's emotions and determine recording priorities based on those estimated emotions. The recording unit estimates the user's emotions using technologies such as voice tone analysis and facial recognition. For example, if the user is nervous, the recording priority can be set higher. Conversely, if the user is relaxed, the recording priority can be set lower. Furthermore, if the user is in a hurry, the recording priority can be set to the highest priority. For instance, the recording unit analyzes the user's voice tone and, if it determines the user is nervous, sets the recording priority higher. It can also recognize the user's facial expressions and, if it determines the user is relaxed, sets the recording priority lower. This allows important conversations to be recorded preferentially by determining recording priorities based on the user's emotions.

[0075] The recording unit can optimize recording settings by considering the user's geographical location during recording. The recording unit acquires the user's geographical location using, for example, GPS data or Wi-Fi location information. During recording, the recording unit optimizes recording settings by considering the user's geographical location. For example, if the user is in a noisy environment, noise cancellation is enhanced. Conversely, if the user is in a quiet environment, the recording sensitivity can be set higher. Furthermore, if the user is moving, recording stability can be prioritized. For example, the recording unit acquires the user's geographical location and enhances noise cancellation if it determines the user is in a noisy environment. It can also set higher recording sensitivity if it determines the user is in a quiet environment. This allows for optimal recording settings by considering the user's geographical location.

[0076] The recording unit can analyze the user's social media activity during recording and prioritize recording relevant conversations. For example, the recording unit can store the user's social media activity in a database and refer to that data during recording. The recording unit analyzes the user's social media activity and prioritizes recording relevant conversations. For example, if the user is having an important conversation on social media, that conversation will be prioritized for recording. It can also prioritize recording conversations that may be fraudulent if the user is having one. Furthermore, if the user is using specific keywords on social media, those conversations will be prioritized for recording. For example, the recording unit analyzes the user's social media activity and prioritizes recording important conversations. It can also prioritize recording conversations that may be fraudulent. This allows the system to prioritize recording relevant conversations by analyzing the user's social media activity.

[0077] The conversion unit can estimate the user's emotions and adjust the accuracy of text conversion based on the estimated emotions. The conversion unit estimates the user's emotions using technologies such as voice tone analysis and facial expression recognition. For example, if the user is nervous, the text conversion accuracy can be set higher. Conversely, if the user is relaxed, the text conversion accuracy can be set lower. Furthermore, if the user is in a hurry, the speed of text conversion can be prioritized. For example, the conversion unit analyzes the user's voice tone and, if it determines the user is nervous, sets the text conversion accuracy higher. It can also recognize the user's facial expressions and, if it determines the user is relaxed, sets the text conversion accuracy lower. By adjusting the accuracy of text conversion based on the user's emotions, more accurate text conversion becomes possible.

[0078] The conversion unit can dynamically change the text conversion algorithm during conversion, taking into account the context of the conversation. For example, the conversion unit can analyze the context of the conversation in real time and dynamically change the text conversion algorithm according to that context. The conversion unit can dynamically change the text conversion algorithm during conversion, taking into account the context of the conversation. For example, if the conversation is business-related, it can use an algorithm that takes technical terms into account. If the conversation is everyday conversation, it can also use an algorithm that prioritizes common words. Furthermore, if the conversation is technical, it can also use an algorithm that takes technical terms into account. For example, the conversion unit analyzes the context of the conversation and, if it determines that it is a business-related conversation, it uses an algorithm that takes technical terms into account. If it determines that it is everyday conversation, it can also use an algorithm that prioritizes common words. This makes it possible to perform more appropriate text conversion by taking the context of the conversation into account.

[0079] The conversion unit can apply different conversion algorithms depending on the category of the conversation during conversion. For example, the conversion unit analyzes the category of the conversation in real time and applies a different conversion algorithm depending on that category. The conversion unit applies different conversion algorithms depending on the category of the conversation during conversion. For example, if the conversation is medical, it uses an algorithm that takes medical terminology into account. If the conversation is legal, it can also use an algorithm that takes legal terminology into account. Furthermore, if the conversation is educational, it can also use an algorithm that takes educational terminology into account. For example, the conversion unit analyzes the category of the conversation and, if it determines that it is a medical conversation, uses an algorithm that takes medical terminology into account. If it determines that it is a legal conversation, it can also use an algorithm that takes legal terminology into account. This improves the accuracy of text conversion by using the appropriate conversion algorithm according to the category of the conversation.

[0080] The conversion unit can estimate the user's emotions and adjust the text conversion speed based on the estimated emotions. The conversion unit estimates the user's emotions using technologies such as voice tone analysis and facial expression recognition. For example, if the user is nervous, the text conversion speed can be set slower. Conversely, if the user is relaxed, the text conversion speed can be set faster. Furthermore, if the user is in a hurry, the text conversion speed can be set to the fastest possible. For example, the conversion unit analyzes the user's voice tone and, if it determines the user is nervous, sets the text conversion speed slower. It can also recognize the user's facial expressions and, if it determines the user is relaxed, sets the text conversion speed faster. This allows for conversion tailored to the user's needs by adjusting the text conversion speed based on their emotions.

[0081] The conversion unit can determine conversion priorities based on the time of day of the conversation. For example, the conversion unit analyzes the time of day of the conversation in real time and determines conversion priorities accordingly. The conversion unit determines conversion priorities based on the time of day of the conversation. For example, nighttime conversations will be converted by the next morning. Daytime conversations can also be converted in real time. Furthermore, weekend conversations can be converted by the beginning of the following week. For example, the conversion unit analyzes the time of day of the conversation and, if it determines it is a nighttime conversation, will complete the conversion by the next morning. The conversion unit can also perform the conversion in real time if it determines it is a daytime conversation. This enables efficient text conversion by determining conversion priorities based on the time of day of the conversation.

[0082] The conversion unit can adjust the order of conversion based on the relevance of the conversations during the conversion process. For example, the conversion unit analyzes the relevance of conversations in real time and adjusts the order of conversion according to that relevance. The conversion unit adjusts the order of conversion based on the relevance of conversations during the conversion process. For example, important conversations are converted with the highest priority. General conversations can be converted later. Furthermore, conversations with low relevance can be converted last. For example, the conversion unit analyzes the relevance of conversations and converts conversations with the highest priority if it determines they are important. The conversion unit can also convert conversations at a later date if it determines them to be general. In this way, by adjusting the order of conversion based on the relevance of conversations, important conversations can be converted preferentially.

[0083] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated emotions. For example, the analysis unit estimates the user's emotions using technologies such as voice tone analysis and facial recognition. The analysis unit estimates the user's emotions and adjusts the analysis criteria based on the estimated emotions. For example, if the user is nervous, the analysis criteria can be set strictly. Conversely, if the user is relaxed, the analysis criteria can be set loosely. Furthermore, if the user is in a hurry, the speed of the analysis can be prioritized. For example, the analysis unit analyzes the user's voice tone and sets stricter analysis criteria if it determines the user is nervous. The analysis unit also recognizes the user's facial expressions and can set looser analysis criteria if it determines the user is relaxed. This allows for more appropriate analysis by adjusting the analysis criteria based on the user's emotions.

[0084] The analysis unit can improve the accuracy of its analysis by considering the interrelationships of the conversation during analysis. For example, the analysis unit can analyze the context of the conversation and the relationships between participants in real time and improve the accuracy of the analysis based on these interrelationships. The analysis unit improves the accuracy of its analysis by considering the interrelationships of the conversation during analysis. For example, it can perform analysis considering the context of the conversation. It can also perform analysis considering the relationships between the participants in the conversation. Furthermore, it can also perform analysis considering the context of the conversation. For example, the analysis unit can analyze the context of the conversation and perform analysis considering the relationship between preceding and succeeding statements. It can also analyze the relationships between the participants in the conversation and perform analysis considering the relationships between the speakers. In this way, the accuracy of the analysis is improved by considering the interrelationships of the conversation.

[0085] The analysis unit can perform analysis while considering the attribute information of the conversation participants. For example, the analysis unit can analyze attribute information such as the age, gender, and occupation of the conversation participants in real time and perform analysis based on that attribute information. The analysis unit can perform analysis while considering the attribute information of the conversation participants. For example, it can perform analysis while considering the age of the conversation participants. It can also perform analysis while considering the occupation of the conversation participants. Furthermore, it can also perform analysis while considering the relationships between the conversation participants. For example, the analysis unit can analyze the age of the conversation participants and perform analysis according to their age. It can also analyze the occupation of the conversation participants and perform analysis according to their occupation. This makes it possible to perform more accurate analysis by considering the attribute information of the conversation participants.

[0086] The analysis unit can estimate the user's emotions and adjust the display order of the analysis results based on the estimated emotions. The analysis unit estimates the user's emotions using technologies such as voice tone analysis and facial expression recognition. For example, if the user is nervous, important analysis results are displayed first. If the user is relaxed, detailed analysis results can be displayed first. Furthermore, if the user is in a hurry, concise analysis results can be displayed first. For example, the analysis unit analyzes the user's voice tone and, if it determines the user is nervous, displays important analysis results first. It can also recognize the user's facial expressions and, if it determines the user is relaxed, displays detailed analysis results first. This allows the results to be displayed in the optimal order for the user by adjusting the display order of the analysis results based on the user's emotions.

[0087] The analysis unit can perform analysis while considering the geographical distribution of conversations. For example, the analysis unit can analyze the geographical distribution of conversations in real time and perform analysis based on that geographical distribution. The analysis unit considers the geographical distribution of conversations when performing analysis. For example, it can consider the location where the conversation took place. It can also consider the locations of the conversation participants. Furthermore, if the content of the conversation is related to a specific region, it can also consider information about that region when performing analysis. For example, the analysis unit can analyze the location where the conversation took place and consider information related to that location when performing analysis. It can also analyze the locations of the conversation participants and consider information related to those locations when performing analysis. In this way, by considering the geographical distribution of conversations, it becomes possible to perform analysis that reflects region-specific information.

[0088] The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the conversation during the analysis process. For example, the analysis unit can search a database for literature related to the content of the conversation and perform the analysis by referring to that literature. The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the conversation during the analysis process. For example, it can perform the analysis by referring to literature related to the content of the conversation. It can also perform the analysis by referring to literature related to keywords in the conversation. Furthermore, it can also perform the analysis by referring to literature related to patterns in the conversation. For example, the analysis unit can search a database for literature related to the content of the conversation and perform the analysis by referring to that literature. It can also perform the analysis by referring to literature related to keywords in the conversation. In this way, the accuracy of the analysis is improved by referring to relevant literature.

[0089] The alert unit can estimate the user's emotions and adjust the way the alert is expressed based on those emotions. For example, the alert unit estimates the user's emotions using technologies such as voice tone analysis and facial recognition. It can then adjust the way the alert is expressed based on those emotions. For instance, if the user is nervous, it can issue an alert in a calm tone. Conversely, if the user is relaxed, it can issue an alert in a cheerful tone. Furthermore, if the user is in a hurry, it can issue an alert in a concise tone. For example, the alert unit analyzes the user's voice tone and, if it determines the user is nervous, issues an alert in a calm tone. It can also recognize the user's facial expressions and, if it determines the user is relaxed, issues an alert in a cheerful tone. This allows the alert to be delivered in the most optimal way for the user by adjusting its expression based on their emotions.

[0090] The alert unit can adjust the level of detail of an alert based on the importance of the conversation when an alert is issued. For example, the alert unit analyzes the importance of the conversation in real time and adjusts the level of detail of the alert accordingly. The alert unit adjusts the level of detail of an alert based on the importance of the conversation when an alert is issued. For example, in the case of an important conversation, a detailed alert is issued. In the case of a general conversation, a concise alert can be issued. Furthermore, in the case of a less relevant conversation, a minimal alert can be issued. For example, the alert unit analyzes the importance of the conversation and issues a detailed alert if it determines that the conversation is important. In addition, the alert unit can issue a concise alert if it determines that the conversation is general. By adjusting the level of detail of the alert based on the importance of the conversation, it is possible to issue alerts with an appropriate amount of information.

[0091] The alert unit can apply different alert algorithms depending on the conversation category when an alert is issued. For example, the alert unit analyzes the conversation category in real time and applies a different alert algorithm depending on that category. The alert unit applies different alert algorithms depending on the conversation category when an alert is issued. For example, in the case of a fraud-related conversation, an emergency alert is issued. In the case of a business-related conversation, a detailed alert can also be issued. Furthermore, in the case of an everyday conversation, a concise alert can also be issued. For example, the alert unit analyzes the conversation category and issues an emergency alert if it determines that the conversation is fraud-related. In addition, the alert unit can issue a detailed alert if it determines that the conversation is business-related. This allows for the effective issuance of alerts by using the appropriate alert algorithm according to the conversation category.

[0092] The alert unit can estimate the user's emotions and adjust the length of the alert based on those emotions. The alert unit estimates the user's emotions using technologies such as voice tone analysis and facial recognition. For example, if the user is nervous, a short alert is issued. Conversely, if the user is relaxed, a longer alert can be issued. Furthermore, if the user is in a hurry, the shortest possible alert can be issued. For instance, the alert unit analyzes the user's voice tone and issues a short alert if it determines the user is nervous. It can also recognize the user's facial expressions and issue a longer alert if it determines the user is relaxed. This allows the system to adjust the alert length based on the user's emotions, thereby delivering an alert of the optimal length for the user.

[0093] The alert unit can determine the priority of alerts based on when a conversation occurs. For example, the alert unit analyzes the timing of conversations in real time and determines the priority of alerts according to that timing. The alert unit determines the priority of alerts based on when a conversation occurs. For example, the most recent conversation will receive the highest priority alert. Past conversations can also be delayed in receiving alerts. Furthermore, future conversations can be predicted and alerts can be issued. For example, the alert unit analyzes the timing of a conversation and, if it determines it is a recent conversation, will receive the highest priority alert. The alert unit can also delay issuing alerts if it determines it is a past conversation. In this way, by determining the priority of alerts based on when a conversation occurs, alerts can be issued at the appropriate time.

[0094] The alert unit can adjust the order of alerts based on the relevance of the conversations when an alert is issued. For example, the alert unit analyzes the relevance of conversations in real time and adjusts the order of alerts according to that relevance. The alert unit adjusts the order of alerts based on the relevance of conversations when an alert is issued. For example, important conversations will receive the highest priority alert. General conversations can also be delayed in receiving alerts. Furthermore, conversations with low relevance can be delayed in receiving alerts. For example, the alert unit analyzes the relevance of conversations and, if it determines that a conversation is important, will receive the highest priority alert. The alert unit can also delay in receiving alerts if it determines that a conversation is general. In this way, by adjusting the order of alerts based on the relevance of conversations, important alerts can be issued preferentially.

[0095] The liaison unit can estimate the user's emotions and adjust the method of contacting the police based on those estimated emotions. The liaison unit estimates the user's emotions using technologies such as voice tone analysis and facial recognition. For example, if the user is nervous, it will contact the police quickly. If the user is relaxed, it can contact the police with more detailed information. Furthermore, if the user is in a hurry, it can contact the police with concise information. For example, the liaison unit analyzes the user's voice tone and, if it determines the user is nervous, will contact the police quickly. It can also recognize the user's facial expressions and, if it determines the user is relaxed, can contact the police with more detailed information. This allows for appropriate contact with the police by adjusting the method of contact based on the user's emotions.

[0096] The liaison department can select the most suitable method of communication by referring to past conversation data when making a call. For example, the liaison department can store past conversation data in a database and refer to that data when making a call. The liaison department selects the most suitable method of communication by referring to past conversation data when making a call. For example, it can select the most suitable method of communication based on how the police were contacted in the past. It can also select the most suitable method of communication by analyzing past conversation data. Furthermore, it can select the most suitable method of communication by referring to past contact history. For example, the liaison department can select the most suitable method of communication by referring to past data. It can also select the most suitable method of communication by analyzing past conversation data. In this way, the liaison department can select the most suitable method of communication by referring to past data.

[0097] The liaison department can customize the means of communication based on the content of the conversation. For example, the liaison department can analyze the content of the conversation in real time and customize the means of communication accordingly. The liaison department can customize the means of communication based on the content of the conversation. For example, if there is a high possibility of fraud, it will use an emergency contact method. If there is a low possibility of fraud, it can also use a normal contact method. Furthermore, it can select the most appropriate means of communication depending on the content of the conversation. For example, the liaison department will analyze the content of the conversation and use an emergency contact method if it determines there is a high possibility of fraud. If there is a low possibility of fraud, it can also use a normal contact method. This allows for communication in an appropriate manner by customizing the means of communication based on the content of the conversation.

[0098] The communication unit can estimate the user's emotions and determine the priority of communications based on those emotions. The communication unit estimates the user's emotions using technologies such as voice tone analysis and facial recognition. For example, if the user is nervous, the communication priority will be set higher. Conversely, if the user is relaxed, the communication priority may be set lower. Furthermore, if the user is in a hurry, the communication priority may be set to the highest priority. For example, the communication unit analyzes the user's voice tone and sets a higher priority if it determines the user is nervous. It can also recognize the user's facial expressions and set a lower priority if it determines the user is relaxed. This allows important communications to be prioritized by determining the priority of communications based on the user's emotions.

[0099] The liaison unit can select the most appropriate method of contact by considering the geographical location information of the conversation. The liaison unit obtains the geographical location information of the conversation using, for example, GPS data or Wi-Fi location information. The liaison unit selects the most appropriate method of contact by considering the geographical location information of the conversation. For example, if the user is in a specific area, it will contact the police in that area. It can also contact the nearest police station if the user is on the move. Furthermore, if the user is overseas, it can contact the local police station. For example, the liaison unit obtains the geographical location information of the conversation and, if it determines that the user is in a specific area, it will contact the police in that area. It can also contact the nearest police station if it determines that the user is on the move. In this way, the liaison unit can select the most appropriate method of contact by considering the geographical location information.

[0100] The liaison department can improve the accuracy of communication by referring to relevant literature during communication. For example, the liaison department can search a database for literature related to the content of the conversation and use that literature to make communication. The liaison department can improve the accuracy of communication by referring to relevant literature during communication. For example, it can use literature related to the content of the conversation to make communication. It can also use literature related to keywords in the conversation to make communication. Furthermore, it can use literature related to patterns in the conversation to make communication. For example, the liaison department can search a database for literature related to the content of the conversation and use that literature to make communication. It can also use literature related to keywords in the conversation to make communication. In this way, the accuracy of communication is improved by referring to relevant literature.

[0101] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0102] The recording unit can analyze the user's voice tone and speed in real time and detect changes in emotion. For example, if a user suddenly raises their voice or speaks quickly, it may indicate tension or anxiety. In this case, the recording unit can increase the recording sensitivity to ensure that important information is not missed. Conversely, if the user is speaking in a calm tone, the recording sensitivity can be returned to normal. Furthermore, if the user is emotional, the recording unit can increase its sensitivity to specific keywords. This allows for dynamic adjustment of recording settings in response to changes in the user's emotions.

[0103] The recording unit can learn specific patterns by referring to the user's past conversation history and optimize recording. For example, if a user has frequently used a particular phrase in the past, the recording sensitivity can be increased when that phrase appears. Similarly, if a user tends to have important conversations during certain time periods, the recording sensitivity can be increased during those times. Furthermore, if a user frequently has important conversations in certain locations, the recording settings for those locations can be optimized. This allows for the optimization of recording settings based on the user's past behavioral patterns.

[0104] The analysis unit can estimate the user's emotions and determine the priority of the analysis based on those emotions. For example, if the user is stressed, the analysis unit can prioritize analyses that are of high urgency. If the user is relaxed, it can perform a detailed analysis. Furthermore, if the user is in a hurry, the analysis unit can prioritize a concise analysis that gets straight to the point. By adjusting the priority of the analysis based on the user's emotions, the system can provide the user with the most optimal analysis results.

[0105] The alert system can estimate the user's emotions and adjust the timing of alerts based on those emotions. For example, if the user is stressed, an alert can be issued immediately to encourage a quick response. Conversely, if the user is relaxed, the alert can be delayed slightly to give the user time to think. Furthermore, if the user is in a hurry, a concise alert can be issued to enable a quick response. In this way, by adjusting the timing of alerts based on the user's emotions, alerts can be issued at the optimal time.

[0106] The liaison unit can estimate the user's emotions and adjust the content of the call to the police based on those emotions. For example, if the user is stressed, the liaison unit can provide detailed information to the police. If the user is relaxed, it can provide concise information. Furthermore, if the user is in a hurry, it can prioritize providing the most important information to the police. In this way, by adjusting the content of the call to the police based on the user's emotions, appropriate information can be provided.

[0107] The recording unit can adjust the recording start time based on the user's geographical location. For example, if the user is in a noisy environment, recording can start earlier to avoid missing important information. Conversely, if the user is in a quiet environment, recording can be delayed to avoid unwanted noise. Furthermore, if the user is on the move, the recording start time can be dynamically adjusted. This allows for the optimization of the recording start time based on the user's geographical location.

[0108] The conversion unit can analyze the context of a conversation in real time and dynamically change the text conversion algorithm according to that context. For example, if the conversation is business-related, it can use an algorithm that takes technical terms into account. If the conversation is everyday conversation, it can also use an algorithm that prioritizes common language. Furthermore, if the conversation is technical, it can use an algorithm that takes technical terms into account. This allows for more appropriate text conversion by considering the context of the conversation.

[0109] The analysis unit can perform analysis while considering the attribute information of the conversation participants. For example, it can analyze attribute information such as the age, gender, and occupation of the conversation participants in real time and perform analysis based on that attribute information. For example, it can perform analysis while considering the age of the conversation participants. It can also perform analysis while considering the occupation of the conversation participants. Furthermore, it can perform analysis while considering the relationships between the conversation participants. As a result, more accurate analysis becomes possible by considering the attribute information of the conversation participants.

[0110] The alerting unit can prioritize alerts based on when a conversation occurred. For example, recent conversations will receive the highest priority alert. Past conversations can be prioritized and alerts sent later. Furthermore, future conversations can be predicted and alerts sent accordingly. By prioritizing alerts based on when a conversation occurred, alerts can be sent at the appropriate time.

[0111] The liaison department can customize the means of communication based on the content of the conversation. For example, if there is a high probability of fraud, emergency contact methods will be used. Conversely, if the likelihood of fraud is low, regular contact methods can be used. Furthermore, the most appropriate means of communication can be selected depending on the content of the conversation. This allows for communication to be conducted in an appropriate manner by customizing the means of communication based on the content of the conversation.

[0112] The following briefly describes the processing flow for example form 2.

[0113] Step 1: The recording unit records the user's phone conversation in real time. The recording unit can record the conversation clearly, for example, by using noise cancellation technology. Step 2: The conversion unit converts the audio data recorded by the recording unit into text. The conversion unit converts the audio data into text data using, for example, natural language processing techniques. Step 3: The analysis unit analyzes the text data converted by the conversion unit. The analysis unit uses a generative AI to analyze the text data and detect potentially fraudulent phrases, patterns, and keywords. The generative AI is implemented using, for example, a deep learning model or a natural language processing model. Step 4: The alert unit issues an alert based on the results analyzed by the analysis unit. The alert unit can, for example, send a notification to the user's smartphone. Step 5: The liaison unit contacts the police based on the alerts issued by the alert unit. For example, the liaison unit may contact the police if it is determined that there is a very high probability of fraud.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] Each of the multiple elements described above, including the recording unit, conversion unit, analysis unit, alert unit, and communication unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the recording unit records the user's phone conversation in real time using the microphone 38B of the smart device 14. The conversion unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts the recorded voice data into text using natural language processing technology. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the text data using generation AI to detect potentially fraudulent phrases, patterns, and keywords. The alert unit is implemented by the control unit 46A of the smart device 14 and sends a notification to the user's smartphone. The communication unit is implemented by the specific processing unit 290 of the data processing unit 12 and contacts the police if it is determined that there is a very high probability of fraud. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0118] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] Each of the multiple elements described above, including the recording unit, conversion unit, analysis unit, alert unit, and communication unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the recording unit records the user's phone conversation in real time using the microphone 238 of the smart glasses 214. The conversion unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts the recorded audio data into text using natural language processing technology. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the text data using generation AI to detect potentially fraudulent phrases, patterns, and keywords. The alert unit is implemented by the control unit 46A of the smart glasses 214 and sends a notification to the user's smartphone. The communication unit is implemented by the specific processing unit 290 of the data processing unit 12 and contacts the police if it is determined that there is a very high probability of fraud. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0134] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] Each of the multiple elements described above, including the recording unit, conversion unit, analysis unit, alert unit, and communication unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the recording unit records the user's phone conversation in real time using the microphone 238 of the headset terminal 314. The conversion unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts the recorded audio data into text using natural language processing technology. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the text data using generation AI to detect potentially fraudulent phrases, patterns, and keywords. The alert unit is implemented by the control unit 46A of the headset terminal 314 and sends a notification to the user's smartphone. The communication unit is implemented by the specific processing unit 290 of the data processing unit 12 and contacts the police if it is determined that there is a very high probability of fraud. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0150] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Each of the multiple elements described above, including the recording unit, conversion unit, analysis unit, alert unit, and communication unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the recording unit records the user's phone conversation in real time using the microphone 238 of the robot 414. The conversion unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts the recorded audio data into text using natural language processing technology. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the text data using generation AI to detect potentially fraudulent phrases, patterns, and keywords. The alert unit is implemented by the control unit 46A of the robot 414 and sends a notification to the user's smartphone. The communication unit is implemented by the specific processing unit 290 of the data processing unit 12 and contacts the police if it is determined that there is a very high probability of fraud. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] (Note 1) A recording unit that records the user's phone conversation in real time, A conversion unit that converts the audio data recorded by the recording unit into text, An analysis unit analyzes the text data converted by the conversion unit, An alert unit that issues an alert based on the results analyzed by the aforementioned analysis unit, The system includes a liaison unit that contacts the police based on an alert issued by the aforementioned alert unit. A system characterized by the following features. (Note 2) The aforementioned recording unit is Use noise-canceling technology to record conversations clearly. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, This system uses generative AI to analyze text data and detect potentially fraudulent phrases, patterns, and keywords. The system described in Appendix 1, characterized by the features described herein. (Note 4) The alert unit is, Send a notification to the user's smartphone. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned liaison department, If it is determined that there is a high probability of fraud, the police will be contacted. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, The generating AI performs analysis based on data it has learned from beforehand. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned recording unit is It estimates the user's emotions and adjusts the recording start time based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned recording unit is During recording, the system automatically adjusts the optimal recording settings by referencing the user's past conversation history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned recording unit is During recording, the recording quality is dynamically adjusted according to the content of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned recording unit is It estimates the user's emotions and determines the priority of recordings based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned recording unit is During recording, the system optimizes recording settings by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned recording unit is During recording, the system analyzes the user's social media activity and prioritizes recording relevant conversations. The system described in Appendix 1, characterized by the features described herein. (Note 13) The conversion unit is It estimates the user's emotions and adjusts the accuracy of text conversion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The conversion unit is During conversion, the text conversion algorithm is dynamically changed to take into account the context of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 15) The conversion unit is During conversion, different conversion algorithms are applied depending on the category of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 16) The conversion unit is It estimates the user's emotions and adjusts the text conversion speed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The conversion unit is During conversion, the conversion priority is determined based on the time of day of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 18) The conversion unit is During conversion, the order of conversions is adjusted based on the relevance of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, We estimate the user's emotions and adjust the analysis criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During analysis, the accuracy of the analysis is improved by considering the interrelationships between conversations. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, During the analysis, the attribute information of the conversation participants is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, It estimates the user's emotions and adjusts the display order of the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, During the analysis, the geographical distribution of the conversations will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit, During analysis, we refer to relevant literature related to the conversation to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 25) The alert unit is, It estimates the user's emotions and adjusts how alerts are presented based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The alert unit is, When an alert is issued, adjust the level of detail of the alert based on the importance of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The alert unit is, When an alert is issued, different alert algorithms are applied depending on the category of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The alert unit is, It estimates the user's sentiment and adjusts the length of the alert based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The alert unit is, When an alert is issued, the priority of the alert is determined based on when the conversation occurred. The system described in Appendix 1, characterized by the features described herein. (Note 30) The alert unit is, When an alert is issued, the order of the alerts will be adjusted based on the relevance of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned liaison department, The system estimates the user's emotions and adjusts how to contact the police based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned liaison department, When contacting someone, the system will refer to past conversation data to select the most appropriate method of communication. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned liaison department, When contacting someone, customize the method of contact based on the content of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned liaison department, It estimates the user's emotions and determines the priority of communication based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned liaison department, When making contact, the system will select the most appropriate method of communication, taking into account the geographical location of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned liaison department, When making contact, refer to relevant literature to improve the accuracy of the conversation. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A recording unit that records the user's phone conversation in real time, A conversion unit that converts the audio data recorded by the recording unit into text, An analysis unit analyzes the text data converted by the conversion unit, An alert unit that issues an alert based on the results analyzed by the aforementioned analysis unit, The system includes a liaison unit that contacts the police based on an alert issued by the aforementioned alert unit. A system characterized by the following features.

2. The aforementioned recording unit is Use noise-canceling technology to record conversations clearly. The system according to feature 1.

3. The aforementioned analysis unit, Using generative AI, text data is analyzed to detect potentially fraudulent phrases, patterns, and keywords. The system according to feature 1.

4. The alert unit is, Send a notification to the user's smartphone. The system according to feature 1.

5. The aforementioned liaison department, If it is determined that there is a high probability of fraud, the police will be contacted. The system according to feature 1.

6. The aforementioned analysis unit, The generative AI performs analysis based on data it has previously learned. The system according to feature 1.

7. The aforementioned recording unit is It estimates the user's emotions and adjusts the recording start time based on the estimated emotions. The system according to feature 1.

8. The aforementioned recording unit is During recording, the system automatically adjusts the optimal recording settings by referencing the user's past conversation history. The system according to feature 1.

Images