system

Abstract

The system according to the embodiment aims to detect fraudulent methods in real time and warn users. [Solution] A system according to an embodiment includes a collection unit, a transcription unit, a detection unit, and a notification unit. The collection unit collects audio data. The transcription unit transcribes the audio data collected by the collection unit. The detection unit detects fraudulent methods based on the text data transcribed by the transcription unit. The notification unit sends a warning notification to a user based on the fraudulent method detected by the detection unit.

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies do not adequately detect fraudulent methods in real time and warn users, and there is room for improvement.

[0005] The system according to the embodiment aims to detect fraudulent methods in real time and warn users. [Means for solving the problem]

[0006] A system according to an embodiment includes a collection unit, a transcription unit, a detection unit, and a notification unit. The collection unit collects audio data. The transcription unit transcribes the audio data collected by the collection unit. The detection unit detects fraudulent methods based on the text data transcribed by the transcription unit. The notification unit sends a warning notification to a user based on the fraudulent method detected by the detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect fraudulent methods in real time and warn users. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

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

[0028] (Example 1) A fraud prevention system according to an embodiment of the present invention is a system that incorporates a smartphone or wearable device with a model trained to recognize fraudulent conversations and provides a notification service to prevent fraud. This fraud prevention system collects voice data when a user uses a smartphone or wearable device and transcribes it using an API such as OpenAI (registered trademark). The transcribed text data is then input into a pre-trained model for detecting fraudulent conversations. This model detects fraudulent conversations in real time. If a fraudulent conversation is detected, the system sends a warning to the user. For example, a notification such as "This conversation may be fraudulent. Please be careful" is displayed. This allows users to prevent themselves from becoming victims of fraud. This system is particularly effective for senior users. Given the high rate of smartphone ownership among seniors, a large market is expected. Furthermore, by using a wearable device, fraudulent conversations can be detected and notifications can be received in real time even while on the go. For example, if a senior user encounters a fraudulent conversation over the phone, the system analyzes the conversation in real time and immediately sends a warning if it determines that the conversation is likely fraudulent. This allows users to prevent themselves from becoming victims of fraud. Because this system is equipped with a model that has been trained to recognize fraudulent methods, it can also respond to new fraud methods. For example, if a new fraud method emerges, the system can respond quickly by training the model to learn that method. In this way, by equipping smartphones and wearable devices with a model that has been trained to recognize the conversational methods used in special frauds and providing a notification service that prevents fraud before it occurs, the safety of users, especially the senior generation, can be ensured. In this way, the fraud prevention system can ensure the safety of users and prevent fraud before it occurs.

[0029] A fraud prevention system according to an embodiment includes a collection unit, a transcription unit, a detection unit, and a notification unit. The collection unit collects voice data when a user uses a smartphone or a wearable device. The collection unit collects voice data, for example, using a microphone on the smartphone. The collection unit can also collect voice data using a microphone on a wearable device. The collection unit can also collect voice data in real time and transmit the voice data to the system. For example, the collection unit collects user conversations in real time using a microphone on the smartphone and transmits the collected voice data to the system. The transcription unit transcribes the voice data collected by the collection unit. The transcription unit transcribes the voice data using, for example, an OpenAI API. The transcription unit converts the voice data into text data and transmits it to the system. For example, the transcription unit transcribes the voice data with high accuracy using an OpenAI API. The detection unit detects fraudulent methods based on the text data transcribed by the transcription unit. The detection unit uses, for example, a pre-trained model for detecting fraudulent methods. The detection unit detects conversations that correspond to fraudulent methods in real time and notifies the system. For example, the detection unit uses a pre-trained model for detecting fraudulent methods to detect fraudulent methods with high accuracy. The notification unit sends a warning notification to the user based on the fraudulent method detected by the detection unit. The notification unit sends a warning notification to the user's smartphone, for example. The notification unit can also send a warning notification to the user's wearable device. For example, the notification unit sends a notification to the user's smartphone stating, "This conversation may be fraudulent. Please be careful." This allows the fraud prevention system according to the embodiment to ensure the safety of users and prevent fraudulent behavior.

[0030] The collection unit can collect voice data using a microphone of a smartphone or a wearable device. The collection unit collects voice data using, for example, a microphone of a smartphone. For example, the collection unit collects a user's conversation in real time using the microphone of the smartphone. The collection unit can also collect voice data using a microphone of a wearable device. For example, the collection unit collects a user's conversation in real time using the microphone of the wearable device. This allows the collection unit to efficiently collect voice data by using the microphone of the smartphone or the wearable device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data collected using the microphone of the smartphone to a generation AI and have the generation AI analyze the voice data.

[0031] The transcription unit can transcribe the voice data using a general voice recognition API. The transcription unit can transcribe the voice data using, for example, an OpenAI API. For example, the transcription unit can transcribe the voice data with high accuracy using the OpenAI API. The transcription unit can also transcribe the voice data using a general voice recognition API such as Google (registered trademark) Speech-to-Text or IBM Watson. For example, the transcription unit can transcribe the voice data using Google Speech-to-Text. The transcription unit can also transcribe the voice data using IBM Watson. As a result, the transcription unit can improve the transcription accuracy of the voice data by using a general voice recognition API. Some or all of the above-described processing in the transcription unit can be performed using, for example, AI or without AI. For example, the transcription unit can input text data transcribed using the OpenAI API to a generation AI and cause the generation AI to analyze the text data.

[0032] The detection unit can use a model that has been trained in advance to detect fraudulent methods. The detection unit, for example, uses a model that has been trained in advance to detect fraudulent methods. For example, the detection unit uses a model that has been trained in advance to detect fraudulent methods to detect fraudulent methods with high accuracy. The detection unit can also use a machine learning algorithm to detect fraudulent methods. For example, the detection unit uses a machine learning algorithm to detect fraudulent methods. The detection unit can also use a deep learning algorithm to detect fraudulent methods. For example, the detection unit uses a deep learning algorithm to detect fraudulent methods with high accuracy. In this way, the detection unit can detect fraudulent methods with high accuracy by using a model that has been trained in advance to detect fraudulent methods. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input a model that has been trained in advance to detect fraudulent methods into a generation AI and cause the generation AI to detect fraudulent methods.

[0033] The notification unit can send a warning notification to the user. The notification unit, for example, sends the warning notification to the user's smartphone. For example, the notification unit sends a notification to the user's smartphone with content such as, "This conversation may be fraudulent. Please be careful." The notification unit can also send a warning notification to the user's wearable device. For example, the notification unit sends a warning notification to the user's wearable device. In this way, the notification unit can prevent fraud by sending a warning notification to the user. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input a warning notification generated based on the fraudulent method detected by the detection unit to the generation AI and cause the generation AI to send the warning notification.

[0034] The fraud prevention system includes a consent acquisition unit and collects voice data after obtaining the user's consent. The consent acquisition unit collects voice data after obtaining the user's consent. The consent acquisition unit, for example, displays a message requesting consent from the user and obtains consent. For example, the consent acquisition unit may display a message requesting consent on the user's smartphone, such as "Do you agree to the collection of voice data?", and obtain consent. The consent acquisition unit may also display a message requesting consent on the user's wearable device and obtain consent. For example, the consent acquisition unit may display a message requesting consent on the user's wearable device and obtain consent. In this way, the consent acquisition unit collects voice data after obtaining the user's consent, thereby enabling the system to operate while protecting privacy. Some or all of the above-described processing in the consent acquisition unit may be performed using AI, or may be performed without using AI. For example, the consent acquisition unit may input a message for obtaining the user's consent into the generation AI and cause the generation AI to execute the consent acquisition process.

[0035] The fraud prevention system includes a model update unit that periodically retrains the model using a new dataset. The model update unit periodically retrains the model using a new dataset. For example, when a new fraud technique emerges, the model update unit causes the model to learn the technique. For example, the model update unit collects a dataset related to new fraud techniques and retrains the model. The model update unit also periodically updates the existing dataset to maintain the accuracy of the model. For example, the model update unit periodically collects a new dataset and retrains the model to respond to the latest fraud techniques. In this way, the model update unit can quickly respond to new fraud techniques by periodically retraining the model. Some or all of the above-mentioned processing in the model update unit may be performed using AI, for example, or may be performed without using AI. For example, the model update unit may input a new dataset to the generation AI and cause the generation AI to retrain the model.

[0036] The collection unit may have a function of automatically filtering background noise when collecting voice data. For example, the collection unit filters ambient noise in real time when collecting voice data. For example, the collection unit removes noise in a specific frequency band when collecting voice data. The collection unit may also emphasize and collect only the user's voice when collecting voice data. For example, the collection unit emphasizes and collects only the user's voice when collecting voice data. In this way, the collection unit automatically filters background noise, thereby improving the quality of the voice data. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may have a generation AI perform filtering of the voice data.

[0037] When collecting voice data, the collection unit can prioritize collecting important conversations by referring to the user's past conversation history. The collection unit, for example, prioritizes collecting conversations containing important keywords from the user's past conversation history. For example, the collection unit analyzes the user's past conversation history and prioritizes collecting conversations with specific people. The collection unit can also prioritize collecting conversations from specific time periods based on the user's past conversation history. For example, the collection unit prioritizes collecting conversations from specific time periods based on the user's past conversation history. In this way, the collection unit can prioritize collecting important conversations by referring to the user's past conversation history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past conversation history into a generation AI and have the generation AI determine the priority of important conversations.

[0038] When collecting voice data, the collection unit can prioritize collecting highly relevant voice data by taking into account the user's geographical location information. For example, when the user is in a specific location, the collection unit prioritizes collecting conversations related to that location. For example, when the user is traveling, the collection unit prioritizes collecting conversations related to the user's destination. Furthermore, when the user is in a specific area, the collection unit can also prioritize collecting conversations related to that area. For example, when the user is in a specific area, the collection unit prioritizes collecting conversations related to that area. In this way, the collection unit can prioritize collecting highly relevant voice data by taking into account the user's geographical location information. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to determine the priority of highly relevant voice data.

[0039] When collecting voice data, the collection unit can analyze the user's social media activities and collect related voice data. The collection unit, for example, analyzes the content of the user's social media posts and prioritizes the collection of related conversations. For example, the collection unit takes into account the user's friendships on social media and prioritizes the collection of conversations with specific friends. The collection unit can also collect related conversations based on the time period during which the user is active on social media. For example, the collection unit collects related conversations based on the time period during which the user is active on social media. In this way, the collection unit can efficiently collect related voice data by analyzing the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's social media activities into a generation AI and cause the generation AI to collect related voice data.

[0040] During transcription, the transcription unit can adjust the level of detail of the transcription based on the importance of the audio data. For example, the transcription unit transcribes conversations of high importance in detail. For example, the transcription unit transcribes conversations of low importance in a concise manner. The transcription unit can also gradually adjust the level of detail of the transcription depending on the importance. For example, the transcription unit gradually adjusts the level of detail of the transcription depending on the importance. This allows the transcription unit to adjust the level of detail of the transcription based on the importance of the audio data, thereby enabling efficient transcription. Some or all of the above-mentioned processing in the transcription unit may be performed using, or without, AI. For example, the transcription unit can input the importance of the audio data to a generation AI and have the generation AI adjust the level of detail of the transcription.

[0041] When transcribing, the transcription unit can apply different transcription algorithms depending on the category of the audio data. For example, the transcription unit applies an algorithm including technical terms to business conversations. For example, the transcription unit applies a concise algorithm to everyday conversations. The transcription unit can also apply an algorithm suitable for a specific industry to conversations specialized in that industry. For example, the transcription unit applies an algorithm suitable for a specific industry to conversations specialized in that industry. In this way, the transcription unit applies different algorithms depending on the category of audio data, thereby improving the accuracy of the transcription. Some or all of the above-mentioned processing in the transcription unit may be performed using, or without, AI, for example. For example, the transcription unit can input the category of audio data to the generation AI and cause the generation AI to apply an algorithm depending on the category.

[0042] During transcription, the transcription unit can determine the priority of transcription based on the time when the audio data was collected. The transcription unit, for example, prioritizes transcribing the most recent audio data. For example, the transcription unit prioritizes transcribing audio data collected during a specific time period. The transcription unit can also prioritize transcribing audio data from a time period specified by the user. For example, the transcription unit prioritizes transcribing audio data from a time period specified by the user. This enables efficient transcription by determining the priority of transcription based on the time when the audio data was collected. Some or all of the above-described processing in the transcription unit may be performed using, for example, AI, or may be performed without using AI. For example, the transcription unit can input the time when the audio data was collected into the generation AI and have the generation AI determine the priority of transcription.

[0043] During transcription, the transcription unit can adjust the order of transcription based on the relevance of the audio data. For example, the transcription unit prioritizes transcribing important conversations. For example, the transcription unit prioritizes transcribing highly relevant conversations. The transcription unit can also prioritize transcribing conversations specified by a user. For example, the transcription unit prioritizes transcribing conversations specified by a user. This allows the transcription unit to adjust the order of transcription based on the relevance of the audio data, thereby enabling efficient transcription. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or may be performed without using AI. For example, the transcription unit can input the relevance of the audio data to a generation AI and have the generation AI adjust the order of transcription.

[0044] When detecting fraudulent methods, the detection unit can improve the accuracy of detection by taking into account the interrelationships in the voice data. The detection unit detects fraudulent methods, for example, by taking into account the context of the conversation. For example, the detection unit detects fraudulent methods by integrating multiple conversations. The detection unit can also detect fraudulent methods by analyzing the flow of the conversation. For example, the detection unit detects fraudulent methods by analyzing the flow of the conversation. In this way, the detection unit improves the accuracy of detecting fraudulent methods by taking into account the interrelationships in the voice data. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the interrelationships in the voice data into a generation AI and cause the generation AI to detect fraudulent methods.

[0045] When detecting fraudulent methods, the detection unit can perform the detection by taking into account attribute information of the person who submitted the voice data. The detection unit detects fraudulent methods by taking into account, for example, the age of the person who submitted the voice data. For example, the detection unit detects fraudulent methods by taking into account the gender of the person who submitted the voice data. The detection unit can also detect fraudulent methods by taking into account the submitter's past behavioral history. For example, the detection unit detects fraudulent methods by taking into account the submitter's past behavioral history. In this way, the detection unit improves the accuracy of detecting fraudulent methods by taking into account the submitter's attribute information. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the submitter's attribute information into the generation AI and cause the generation AI to detect fraudulent methods.

[0046] When detecting fraudulent methods, the detection unit can perform the detection by taking into account the geographical distribution of voice data. For example, the detection unit prioritizes the detection of fraudulent methods that are prevalent in a specific region. For example, the detection unit detects fraudulent methods that are highly geographically related. The detection unit can also analyze and detect trends in fraudulent methods by region. For example, the detection unit analyzes and detects trends in fraudulent methods by region. In this way, the detection unit improves the accuracy of detecting fraudulent methods by taking the geographical distribution of voice data into consideration. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input the geographical distribution of voice data into a generation AI and have the generation AI detect fraudulent methods.

[0047] When detecting fraudulent methods, the detection unit can improve the accuracy of detection by referring to literature related to the audio data. The detection unit, for example, detects fraudulent methods based on related literature. For example, the detection unit detects fraudulent methods by referring to past cases. The detection unit can also detect fraudulent methods based on academic papers. For example, the detection unit detects fraudulent methods based on academic papers. In this way, the detection unit improves the accuracy of detecting fraudulent methods by referring to related literature. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input related literature into a generation AI and have the generation AI detect fraudulent methods.

[0048] When sending a warning notification, the notification unit can select the optimal notification method by referring to the user's past response history. The notification unit, for example, prioritizes the use of a notification method that the user has previously preferred. For example, the notification unit analyzes the user's past response history and selects the optimal notification method. The notification unit can also avoid notification methods that the user has previously ignored. For example, the notification unit avoids notification methods that the user has previously ignored. In this way, the notification unit can select the optimal notification method by referring to the user's past response history. Some or all of the above-described processing in the notification unit may be performed using, or without, AI. For example, the notification unit can input the user's past response history into a generation AI and have the generation AI select the optimal notification method.

[0049] When sending a warning notification, the notification unit can adjust the timing of the notification based on the user's current situation. For example, if the user is in a meeting, the notification unit sends the warning notification after the meeting ends. For example, if the user is driving, the notification unit sends the warning notification after the driving ends. The notification unit can also immediately send a warning notification when the user is taking a break. For example, if the user is taking a break, the notification unit immediately sends a warning notification. This allows the notification unit to adjust the timing of the notification based on the user's current situation, thereby enabling notification at a more appropriate time. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's current situation to the generation AI and have the generation AI adjust the timing of the notification.

[0050] When sending a warning notification, the notification unit can select the optimal notification method by taking into account the user's geographical location information. For example, when the user is at home, the notification unit sends the notification to a smartphone. For example, when the user is out, the notification unit sends the notification to a wearable device. Furthermore, when the user is in a specific location, the notification unit can also select a notification method appropriate for that location. For example, when the user is in a specific location, the notification unit selects a notification method appropriate for that location. In this way, the notification unit can select the optimal notification method by taking into account the user's geographical location information. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's geographical location information to a generation AI and have the generation AI select the optimal notification method.

[0051] When sending a warning notification, the notification unit can analyze the user's social media activity and suggest a notification method. For example, if the user frequently uses social media, the notification unit can send the notification through social media. For example, if the user prefers to use a specific social media platform, the notification unit can send the notification through that platform. The notification unit can also suggest the optimal notification timing based on the time period during which the user is active on social media. For example, the notification unit can suggest the optimal notification timing based on the time period during which the user is active on social media. In this way, the notification unit can suggest the optimal notification method by analyzing the user's social media activity. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's social media activity into a generation AI and have the generation AI suggest the optimal notification method.

[0052] When obtaining consent, the consent acquisition unit can select the optimal consent acquisition method by referring to the user's past consent history. For example, the consent acquisition unit prioritizes the use of methods to which the user has previously consented. For example, the consent acquisition unit analyzes the user's past consent history and selects the optimal consent acquisition method. The consent acquisition unit can also avoid methods that the user has previously rejected. For example, the consent acquisition unit avoids methods that the user has previously rejected. In this way, the consent acquisition unit can select the optimal consent acquisition method by referring to the user's past consent history. Some or all of the above-described processing in the consent acquisition unit may be performed using AI, for example, or may be performed without using AI. For example, the consent acquisition unit can input the user's past consent history into the generation AI and have the generation AI select the optimal consent acquisition method.

[0053] When obtaining consent, the consent acquisition unit can select the optimal consent acquisition method by taking into account the user's device information. For example, if the user is using a smartphone, the consent acquisition unit provides a consent acquisition method that matches the screen size. For example, if the user is using a tablet, the consent acquisition unit provides a consent acquisition method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the consent acquisition unit can also provide a concise and highly visible consent acquisition method. For example, if the user is using a smartwatch, the consent acquisition unit provides a concise and highly visible consent acquisition method. This allows the consent acquisition unit to select the optimal consent acquisition method by taking into account the user's device information. Some or all of the above-described processing in the consent acquisition unit may be performed using AI, for example, or may be performed without using AI. For example, the consent acquisition unit can input the user's device information into the generation AI and have the generation AI select the optimal consent acquisition method.

[0054] The model update unit can optimize the update algorithm by referring to past learning data when updating the model. The model update unit, for example, selects an optimal update algorithm based on past learning data. For example, the model update unit analyzes past learning data and adjusts the update algorithm. The model update unit can also improve the accuracy of the update algorithm by referring to past learning data. For example, the model update unit improves the accuracy of the update algorithm by referring to past learning data. In this way, the model update unit improves the accuracy of the update algorithm by referring to the past learning data. Some or all of the above-mentioned processing in the model update unit may be performed using, for example, AI, or may be performed without using AI. For example, the model update unit can input past learning data to a generation AI and cause the generation AI to optimize the update algorithm.

[0055] When updating the model, the model update unit can weight the training data based on the time when the voice data was collected. The model update unit, for example, performs model update by assigning a high weight to the most recent voice data. For example, the model update unit performs model update by assigning a weight to voice data collected in a specific time period. The model update unit can also perform model update by assigning a weight to voice data in a time period specified by the user. For example, the model update unit performs model update by assigning a weight to voice data in a time period specified by the user. In this way, the model update unit weights the training data based on the time when the voice data was collected, thereby improving the accuracy of the model update. Some or all of the above-mentioned processing in the model update unit may be performed using AI, for example, or may be performed without using AI. For example, the model update unit can input the time when the voice data was collected to the generation AI and cause the generation AI to weight the training data.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] The fraud prevention system may further include a behavior analysis unit that analyzes the user's behavioral patterns. The behavior analysis unit can learn the user's daily behavioral patterns and issue a warning if abnormal behavior is detected. For example, if a user who normally only makes calls during specific times of the day makes a long call during an abnormal time, the behavior analysis unit will determine that behavior as abnormal and issue a warning. In addition, if a user only performs a specific behavior when in a specific location, the behavior analysis unit can also issue a warning if the user performs similar behavior outside of that location. This allows the fraud prevention system to detect fraud with greater accuracy by taking the user's behavioral patterns into account.

[0058] When transcribing audio data, the transcription unit can automatically generate a summary based on the user's speech. For example, it can extract important points from a long conversation and generate a concise summary. The transcription unit can also adjust the content of the summary based on specific keywords. For example, if keywords such as "fraud" or "money" are included, those parts can be highlighted and included in the summary. This allows the transcription unit to help the user quickly grasp important information.

[0059] When detecting fraudulent methods, the detection unit can improve the accuracy of detection by referring to the user's past fraud victim history. For example, for a user who has fallen victim to a specific fraudulent method in the past, strict detection standards for that method can be set. The detection unit can also adjust the alert level for new fraudulent methods based on the user's past victim history. This allows the detection unit to take into account the user's past victim history and thereby prevent fraud more effectively.

[0060] When sending a warning notification to a user, the notification unit can adjust the content of the notification according to the user's level of understanding. For example, for senior users, the notification unit can send a notification using simple, easy-to-understand language. The notification unit can also customize the content of the notification according to the user's education level and expertise. For example, for users with technical knowledge, the notification unit can send a notification containing detailed technical information. In this way, the notification unit can prevent fraud by sending an appropriate notification according to the user's level of understanding.

[0061] When collecting voice data, the collection unit can prioritize collecting highly relevant voice data by taking into account the user's geographical location information. For example, if the user is in a specific location, conversations related to that location can be collected preferentially. Also, if the user is traveling, conversations related to the user's destination can be collected preferentially. Furthermore, if the user is in a specific area, conversations related to that area can be collected preferentially. In this way, the collection unit can prioritize collecting highly relevant voice data by taking into account the user's geographical location information.

[0062] When collecting voice data, the collection unit can analyze the user's social media activities and collect related voice data. For example, the collection unit can analyze the content of the user's social media posts and prioritize collection of related conversations. It can also prioritize collection of conversations with specific friends, taking into account the user's friendships on social media. It can also collect related conversations based on the time periods during which the user is active on social media. This allows the collection unit to efficiently collect related voice data by analyzing the user's social media activities.

[0063] The processing flow of the first embodiment will be briefly explained below.

[0064] Step 1: The collection unit collects voice data when a user uses a smartphone or a wearable device. For example, the collection unit collects voice data in real time using the microphone of the smartphone or the microphone of the wearable device and transmits it to the system. Step 2: The transcription unit transcribes the audio data collected by the collection unit. For example, it uses OpenAI's API to transcribe the audio data with high accuracy, converts it into text data, and sends it to the system. Step 3: The detection unit detects fraudulent methods based on the text data transcribed by the transcription unit. For example, it uses a pre-trained model to detect fraudulent methods, and detects conversations that correspond to fraudulent methods in real time and notifies the system. Step 4: The notification unit sends a warning notification to the user based on the fraudulent method detected by the detection unit. For example, the notification unit sends a message to the user's smartphone or wearable device stating, "This conversation may be fraudulent. Please be careful."

[0065] (Example 2) A fraud prevention system according to an embodiment of the present invention is a system that incorporates a smartphone or wearable device with a model trained to recognize fraudulent conversations and provides a notification service to prevent fraud. This fraud prevention system collects voice data from a user's smartphone or wearable device and transcribes it using an OpenAI API or similar. The transcribed text data is then input into a pre-trained model for detecting fraudulent conversations. This model detects fraudulent conversations in real time. If a fraudulent conversation is detected, the system sends a warning to the user. For example, a notification such as "This conversation may be fraudulent. Please be careful." This allows users to prevent themselves from becoming victims of fraud. This system is particularly effective for senior users. Given the high rate of smartphone ownership among seniors, a large market is expected. Furthermore, by using a wearable device, fraudulent conversations can be detected and notifications can be received in real time even while on the go. For example, if a senior user encounters a fraudulent conversation over the phone, the system analyzes the conversation in real time and immediately sends a warning if it determines that the conversation is likely fraudulent. This allows users to prevent themselves from becoming victims of fraud. Because this system is equipped with a model that has been trained to recognize fraudulent methods, it can also respond to new fraud methods. For example, if a new fraud method emerges, the system can respond quickly by training the model to learn that method. In this way, by equipping smartphones and wearable devices with a model that has been trained to recognize the conversational methods used in special frauds and providing a notification service that prevents fraud before it occurs, the safety of users, especially the senior generation, can be ensured. In this way, the fraud prevention system can ensure the safety of users and prevent fraud before it occurs.

[0066] A fraud prevention system according to an embodiment includes a collection unit, a transcription unit, a detection unit, and a notification unit. The collection unit collects voice data when a user uses a smartphone or a wearable device. The collection unit collects voice data, for example, using a microphone on the smartphone. The collection unit can also collect voice data using a microphone on a wearable device. The collection unit can also collect voice data in real time and transmit the voice data to the system. For example, the collection unit collects user conversations in real time using a microphone on the smartphone and transmits the collected voice data to the system. The transcription unit transcribes the voice data collected by the collection unit. The transcription unit transcribes the voice data using, for example, an OpenAI API. The transcription unit converts the voice data into text data and transmits it to the system. For example, the transcription unit transcribes the voice data with high accuracy using an OpenAI API. The detection unit detects fraudulent methods based on the text data transcribed by the transcription unit. The detection unit uses, for example, a pre-trained model for detecting fraudulent methods. The detection unit detects conversations that correspond to fraudulent methods in real time and notifies the system. For example, the detection unit uses a pre-trained model for detecting fraudulent methods to detect fraudulent methods with high accuracy. The notification unit sends a warning notification to the user based on the fraudulent method detected by the detection unit. The notification unit sends a warning notification to the user's smartphone, for example. The notification unit can also send a warning notification to the user's wearable device. For example, the notification unit sends a notification to the user's smartphone stating, "This conversation may be fraudulent. Please be careful." This allows the fraud prevention system according to the embodiment to ensure the safety of users and prevent fraudulent behavior.

[0067] The collection unit can collect voice data using a microphone of a smartphone or a wearable device. The collection unit collects voice data using, for example, a microphone of a smartphone. For example, the collection unit collects a user's conversation in real time using the microphone of the smartphone. The collection unit can also collect voice data using a microphone of a wearable device. For example, the collection unit collects a user's conversation in real time using the microphone of the wearable device. This allows the collection unit to efficiently collect voice data by using the microphone of the smartphone or the wearable device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input voice data collected using the microphone of the smartphone to a generation AI and have the generation AI analyze the voice data.

[0068] The transcription unit can transcribe the audio data using a general speech recognition API. The transcription unit can transcribe the audio data using, for example, an OpenAI API. For example, the transcription unit can transcribe the audio data with high accuracy using the OpenAI API. The transcription unit can also transcribe the audio data using a general speech recognition API such as Google Speech-to-Text or IBM Watson. For example, the transcription unit can transcribe the audio data using Google Speech-to-Text. The transcription unit can also transcribe the audio data using IBM Watson. As a result, the transcription unit can improve the transcription accuracy of the audio data by using a general speech recognition API. Some or all of the above-described processing in the transcription unit can be performed using, for example, AI or without AI. For example, the transcription unit can input text data transcribed using the OpenAI API to a generation AI and have the generation AI analyze the text data.

[0069] The detection unit can use a model that has been trained in advance to detect fraudulent methods. The detection unit, for example, uses a model that has been trained in advance to detect fraudulent methods. For example, the detection unit uses a model that has been trained in advance to detect fraudulent methods to detect fraudulent methods with high accuracy. The detection unit can also use a machine learning algorithm to detect fraudulent methods. For example, the detection unit uses a machine learning algorithm to detect fraudulent methods. The detection unit can also use a deep learning algorithm to detect fraudulent methods. For example, the detection unit uses a deep learning algorithm to detect fraudulent methods with high accuracy. In this way, the detection unit can detect fraudulent methods with high accuracy by using a model that has been trained in advance to detect fraudulent methods. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input a model that has been trained in advance to detect fraudulent methods into a generation AI and cause the generation AI to detect fraudulent methods.

[0070] The notification unit can send a warning notification to the user. The notification unit, for example, sends the warning notification to the user's smartphone. For example, the notification unit sends a notification to the user's smartphone with content such as, "This conversation may be fraudulent. Please be careful." The notification unit can also send a warning notification to the user's wearable device. For example, the notification unit sends a warning notification to the user's wearable device. In this way, the notification unit can prevent fraud by sending a warning notification to the user. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input a warning notification generated based on the fraudulent method detected by the detection unit to the generation AI and cause the generation AI to send the warning notification.

[0071] The fraud prevention system includes a consent acquisition unit and collects voice data after obtaining the user's consent. The consent acquisition unit collects voice data after obtaining the user's consent. The consent acquisition unit, for example, displays a message requesting consent from the user and obtains consent. For example, the consent acquisition unit may display a message requesting consent on the user's smartphone, such as "Do you agree to the collection of voice data?", and obtain consent. The consent acquisition unit may also display a message requesting consent on the user's wearable device and obtain consent. For example, the consent acquisition unit may display a message requesting consent on the user's wearable device and obtain consent. In this way, the consent acquisition unit collects voice data after obtaining the user's consent, thereby enabling the system to operate while protecting privacy. Some or all of the above-described processing in the consent acquisition unit may be performed using AI, or may be performed without using AI. For example, the consent acquisition unit may input a message for obtaining the user's consent into the generation AI and cause the generation AI to execute the consent acquisition process.

[0072] The fraud prevention system includes a model update unit that periodically retrains the model using a new dataset. The model update unit periodically retrains the model using a new dataset. For example, when a new fraud technique emerges, the model update unit causes the model to learn the technique. For example, the model update unit collects a dataset related to new fraud techniques and retrains the model. The model update unit also periodically updates the existing dataset to maintain the accuracy of the model. For example, the model update unit periodically collects a new dataset and retrains the model to respond to the latest fraud techniques. In this way, the model update unit can quickly respond to new fraud techniques by periodically retraining the model. Some or all of the above-mentioned processing in the model update unit may be performed using AI, for example, or may be performed without using AI. For example, the model update unit may input a new dataset to the generation AI and cause the generation AI to retrain the model.

[0073] The collection unit can estimate the user's emotions and adjust the timing of collecting voice data based on the estimated user's emotions. For example, if the user is nervous, the collection unit delays the collection timing and collects voice data in a relaxed state. For example, if the user is relaxed, the collection unit collects voice data immediately. The collection unit can also collect voice data in a short time if the user is in a hurry. For example, if the user is in a hurry, the collection unit collects voice data in a short time. In this way, the collection unit can collect more appropriate data by adjusting the timing of collecting voice data according to the user's emotions. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input data for estimating the user's emotions to a generation AI and cause the generation AI to estimate the emotions.

[0074] The collection unit may have a function of automatically filtering background noise when collecting voice data. For example, the collection unit filters ambient noise in real time when collecting voice data. For example, the collection unit removes noise in a specific frequency band when collecting voice data. The collection unit may also emphasize and collect only the user's voice when collecting voice data. For example, the collection unit emphasizes and collects only the user's voice when collecting voice data. In this way, the collection unit automatically filters background noise, thereby improving the quality of the voice data. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may have a generation AI perform filtering of the voice data.

[0075] When collecting voice data, the collection unit can prioritize collecting important conversations by referring to the user's past conversation history. The collection unit, for example, prioritizes collecting conversations containing important keywords from the user's past conversation history. For example, the collection unit analyzes the user's past conversation history and prioritizes collecting conversations with specific people. The collection unit can also prioritize collecting conversations from specific time periods based on the user's past conversation history. For example, the collection unit prioritizes collecting conversations from specific time periods based on the user's past conversation history. In this way, the collection unit can prioritize collecting important conversations by referring to the user's past conversation history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past conversation history into a generation AI and have the generation AI determine the priority of important conversations.

[0076] The collection unit can estimate the user's emotions and determine the priority of the voice data to be collected based on the estimated user's emotions. For example, when the user is nervous, the collection unit prioritizes collecting conversations of high importance. For example, when the user is relaxed, the collection unit collects all conversations equally. The collection unit can also prioritize collecting important conversations that can be completed in a short time when the user is in a hurry. For example, when the user is in a hurry, the collection unit prioritizes collecting important conversations that can be completed in a short time. In this way, the collection unit can prioritize collecting important data by determining the priority of the voice data based on the user's emotions. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input data for estimating the user's emotions to the generation AI and cause the generation AI to estimate the emotions.

[0077] When collecting voice data, the collection unit can prioritize collecting highly relevant voice data by taking into account the user's geographical location information. For example, when the user is in a specific location, the collection unit prioritizes collecting conversations related to that location. For example, when the user is traveling, the collection unit prioritizes collecting conversations related to the user's destination. Furthermore, when the user is in a specific area, the collection unit can also prioritize collecting conversations related to that area. For example, when the user is in a specific area, the collection unit prioritizes collecting conversations related to that area. In this way, the collection unit can prioritize collecting highly relevant voice data by taking into account the user's geographical location information. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to determine the priority of highly relevant voice data.

[0078] When collecting voice data, the collection unit can analyze the user's social media activities and collect related voice data. The collection unit, for example, analyzes the content of the user's social media posts and prioritizes the collection of related conversations. For example, the collection unit takes into account the user's friendships on social media and prioritizes the collection of conversations with specific friends. The collection unit can also collect related conversations based on the time period during which the user is active on social media. For example, the collection unit collects related conversations based on the time period during which the user is active on social media. In this way, the collection unit can efficiently collect related voice data by analyzing the user's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's social media activities into a generation AI and cause the generation AI to collect related voice data.

[0079] The transcription unit can estimate the user's emotions and adjust the transcription expression method based on the estimated user's emotions. For example, if the user is nervous, the transcription unit uses concise and easy-to-understand expressions. For example, if the user is relaxed, the transcription unit uses detailed expressions. Furthermore, if the user is in a hurry, the transcription unit can also use expressions that focus on the main points. For example, if the user is in a hurry, the transcription unit uses expressions that focus on the main points. This allows the transcription unit to adjust the transcription expression method based on the user's emotions, thereby enabling more appropriate transcription. Some or all of the above-mentioned processing in the transcription unit may be performed using AI, for example, or may be performed without using AI. For example, the transcription unit can input data for estimating the user's emotions into the generation AI and have the generation AI perform emotion estimation.

[0080] During transcription, the transcription unit can adjust the level of detail of the transcription based on the importance of the audio data. For example, the transcription unit transcribes conversations of high importance in detail. For example, the transcription unit transcribes conversations of low importance in a concise manner. The transcription unit can also gradually adjust the level of detail of the transcription depending on the importance. For example, the transcription unit gradually adjusts the level of detail of the transcription depending on the importance. This allows the transcription unit to adjust the level of detail of the transcription based on the importance of the audio data, thereby enabling efficient transcription. Some or all of the above-mentioned processing in the transcription unit may be performed using, or without, AI. For example, the transcription unit can input the importance of the audio data to a generation AI and have the generation AI adjust the level of detail of the transcription.

[0081] When transcribing, the transcription unit can apply different transcription algorithms depending on the category of the audio data. For example, the transcription unit applies an algorithm including technical terms to business conversations. For example, the transcription unit applies a concise algorithm to everyday conversations. The transcription unit can also apply an algorithm suitable for a specific industry to conversations specialized in that industry. For example, the transcription unit applies an algorithm suitable for a specific industry to conversations specialized in that industry. In this way, the transcription unit applies different algorithms depending on the category of audio data, thereby improving the accuracy of the transcription. Some or all of the above-mentioned processing in the transcription unit may be performed using, or without, AI, for example. For example, the transcription unit can input the category of audio data to the generation AI and cause the generation AI to apply an algorithm depending on the category.

[0082] The transcription unit can estimate the user's emotions and adjust the length of the transcription based on the estimated user emotions. For example, if the user is nervous, the transcription unit can provide a short, concise transcription. For example, if the user is relaxed, the transcription unit can provide a detailed transcription. The transcription unit can also provide a concise transcription if the user is in a hurry. For example, if the user is in a hurry, the transcription unit can provide a concise transcription. This allows the transcription unit to adjust the length of the transcription based on the user's emotions, thereby enabling more appropriate transcription. Some or all of the above-described processing in the transcription unit may be performed using AI, or may be performed without AI. For example, the transcription unit can input data for estimating the user's emotions into the generation AI and have the generation AI perform emotion estimation.

[0083] During transcription, the transcription unit can determine the priority of transcription based on the time when the audio data was collected. The transcription unit, for example, prioritizes transcribing the most recent audio data. For example, the transcription unit prioritizes transcribing audio data collected during a specific time period. The transcription unit can also prioritize transcribing audio data from a time period specified by the user. For example, the transcription unit prioritizes transcribing audio data from a time period specified by the user. This enables efficient transcription by determining the priority of transcription based on the time when the audio data was collected. Some or all of the above-described processing in the transcription unit may be performed using, for example, AI, or may be performed without using AI. For example, the transcription unit can input the time when the audio data was collected into the generation AI and have the generation AI determine the priority of transcription.

[0084] During transcription, the transcription unit can adjust the order of transcription based on the relevance of the audio data. For example, the transcription unit prioritizes transcribing important conversations. For example, the transcription unit prioritizes transcribing highly relevant conversations. The transcription unit can also prioritize transcribing conversations specified by a user. For example, the transcription unit prioritizes transcribing conversations specified by a user. This allows the transcription unit to adjust the order of transcription based on the relevance of the audio data, thereby enabling efficient transcription. Some or all of the above-described processing in the transcription unit may be performed using AI, for example, or may be performed without using AI. For example, the transcription unit can input the relevance of the audio data to a generation AI and have the generation AI adjust the order of transcription.

[0085] The detection unit can estimate the user's emotions and adjust the detection criteria for fraudulent schemes based on the estimated user's emotions. For example, the detection unit applies strict detection criteria when the user is nervous. For example, the detection unit applies normal detection criteria when the user is relaxed. The detection unit can also apply rapid detection criteria when the user is in a hurry. For example, the detection unit applies rapid detection criteria when the user is in a hurry. This allows the detection unit to adjust the detection criteria for fraudulent schemes based on the user's emotions, enabling more appropriate detection. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input data for estimating the user's emotions into the generation AI and have the generation AI perform emotion estimation.

[0086] When detecting fraudulent methods, the detection unit can improve the accuracy of detection by taking into account the interrelationships in the voice data. The detection unit detects fraudulent methods, for example, by taking into account the context of the conversation. For example, the detection unit detects fraudulent methods by integrating multiple conversations. The detection unit can also detect fraudulent methods by analyzing the flow of the conversation. For example, the detection unit detects fraudulent methods by analyzing the flow of the conversation. In this way, the detection unit improves the accuracy of detecting fraudulent methods by taking into account the interrelationships in the voice data. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the interrelationships in the voice data into a generation AI and cause the generation AI to detect fraudulent methods.

[0087] When detecting fraudulent methods, the detection unit can perform the detection by taking into account attribute information of the person who submitted the voice data. The detection unit detects fraudulent methods by taking into account, for example, the age of the person who submitted the voice data. For example, the detection unit detects fraudulent methods by taking into account the gender of the person who submitted the voice data. The detection unit can also detect fraudulent methods by taking into account the submitter's past behavioral history. For example, the detection unit detects fraudulent methods by taking into account the submitter's past behavioral history. In this way, the detection unit improves the accuracy of detecting fraudulent methods by taking into account the submitter's attribute information. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the submitter's attribute information into the generation AI and cause the generation AI to detect fraudulent methods.

[0088] The detection unit can estimate the user's emotions and adjust the display order of the detection results based on the estimated user's emotions. For example, if the user is nervous, the detection unit displays important detection results first. For example, if the user is relaxed, the detection unit displays all detection results evenly. The detection unit can also display detection results so that the user can check them quickly if the user is in a hurry. For example, if the user is in a hurry, the detection unit displays detection results so that the user can check them quickly. This allows the detection unit to adjust the display order of the detection results based on the user's emotions, enabling more appropriate display. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input data for estimating the user's emotions to the generation AI and cause the generation AI to estimate the emotions.

[0089] When detecting fraudulent methods, the detection unit can perform the detection by taking into account the geographical distribution of voice data. For example, the detection unit prioritizes the detection of fraudulent methods that are prevalent in a specific region. For example, the detection unit detects fraudulent methods that are highly geographically related. The detection unit can also analyze and detect trends in fraudulent methods by region. For example, the detection unit analyzes and detects trends in fraudulent methods by region. In this way, the detection unit improves the accuracy of detecting fraudulent methods by taking the geographical distribution of voice data into consideration. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input the geographical distribution of voice data into a generation AI and have the generation AI detect fraudulent methods.

[0090] When detecting fraudulent methods, the detection unit can improve the accuracy of detection by referring to literature related to the audio data. The detection unit, for example, detects fraudulent methods based on related literature. For example, the detection unit detects fraudulent methods by referring to past cases. The detection unit can also detect fraudulent methods based on academic papers. For example, the detection unit detects fraudulent methods based on academic papers. In this way, the detection unit improves the accuracy of detecting fraudulent methods by referring to related literature. Some or all of the above-mentioned processing in the detection unit may be performed using AI, for example, or may be performed without using AI. For example, the detection unit can input related literature into a generation AI and have the generation AI detect fraudulent methods.

[0091] The notification unit can estimate the user's emotions and adjust the way the warning notification is expressed based on the estimated user's emotions. For example, if the user is nervous, the notification unit transmits the warning notification using calm expression. For example, if the user is relaxed, the notification unit transmits the warning notification including detailed information. The notification unit can also transmit a concise and quick warning notification if the user is in a hurry. For example, if the user is in a hurry, the notification unit transmits a concise and quick warning notification. This allows the notification unit to adjust the way the warning notification is expressed based on the user's emotions, thereby enabling more appropriate notification. Some or all of the above-mentioned processing in the notification unit may be performed using AI, for example, or may be performed without using AI. For example, the notification unit can input data for estimating the user's emotions into the generation AI and cause the generation AI to estimate the emotions.

[0092] When sending a warning notification, the notification unit can select the optimal notification method by referring to the user's past response history. The notification unit, for example, prioritizes the use of a notification method that the user has previously preferred. For example, the notification unit analyzes the user's past response history and selects the optimal notification method. The notification unit can also avoid notification methods that the user has previously ignored. For example, the notification unit avoids notification methods that the user has previously ignored. In this way, the notification unit can select the optimal notification method by referring to the user's past response history. Some or all of the above-described processing in the notification unit may be performed using, or without, AI. For example, the notification unit can input the user's past response history into a generation AI and have the generation AI select the optimal notification method.

[0093] When sending a warning notification, the notification unit can adjust the timing of the notification based on the user's current situation. For example, if the user is in a meeting, the notification unit sends the warning notification after the meeting ends. For example, if the user is driving, the notification unit sends the warning notification after the driving ends. The notification unit can also immediately send a warning notification when the user is taking a break. For example, if the user is taking a break, the notification unit immediately sends a warning notification. This allows the notification unit to adjust the timing of the notification based on the user's current situation, thereby enabling notification at a more appropriate time. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's current situation to the generation AI and have the generation AI adjust the timing of the notification.

[0094] The notification unit can estimate the user's emotions and determine the priority of notifications based on the estimated user emotions. For example, if the user is nervous, the notification unit prioritizes sending important notifications. For example, if the user is relaxed, the notification unit sends all notifications equally. The notification unit can also prioritize sending important notifications so that the user can check them quickly if the user is in a hurry. For example, if the user is in a hurry, the notification unit prioritizes sending important notifications so that the user can check them quickly. In this way, the notification unit can prioritize sending important notifications based on the user's emotions. Some or all of the above-mentioned processing in the notification unit may be performed using AI, for example, or may be performed without using AI. For example, the notification unit can input data for estimating the user's emotions to a generation AI and have the generation AI perform emotion estimation.

[0095] When sending a warning notification, the notification unit can select the optimal notification method by taking into account the user's geographical location information. For example, when the user is at home, the notification unit sends the notification to a smartphone. For example, when the user is out, the notification unit sends the notification to a wearable device. Furthermore, when the user is in a specific location, the notification unit can also select a notification method appropriate for that location. For example, when the user is in a specific location, the notification unit selects a notification method appropriate for that location. In this way, the notification unit can select the optimal notification method by taking into account the user's geographical location information. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's geographical location information to a generation AI and have the generation AI select the optimal notification method.

[0096] When sending a warning notification, the notification unit can analyze the user's social media activity and suggest a notification method. For example, if the user frequently uses social media, the notification unit can send the notification through social media. For example, if the user prefers to use a specific social media platform, the notification unit can send the notification through that platform. The notification unit can also suggest the optimal notification timing based on the time period during which the user is active on social media. For example, the notification unit can suggest the optimal notification timing based on the time period during which the user is active on social media. In this way, the notification unit can suggest the optimal notification method by analyzing the user's social media activity. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's social media activity into a generation AI and have the generation AI suggest the optimal notification method.

[0097] The consent acquisition unit can estimate the user's emotions and adjust the consent acquisition method based on the estimated user's emotions. For example, if the user is nervous, the consent acquisition unit provides a concise and easy-to-understand consent acquisition method. For example, if the user is relaxed, the consent acquisition unit provides a consent acquisition method including detailed information. The consent acquisition unit can also provide a method that allows consent to be acquired quickly if the user is in a hurry. For example, if the user is in a hurry, the consent acquisition unit provides a method that allows consent to be acquired quickly. This allows the consent acquisition unit to adjust the consent acquisition method based on the user's emotions, thereby enabling more appropriate consent acquisition. Some or all of the above-mentioned processing in the consent acquisition unit may be performed using AI, for example, or may be performed without using AI. For example, the consent acquisition unit can input data for estimating the user's emotions into the generation AI and cause the generation AI to estimate the emotions.

[0098] When obtaining consent, the consent acquisition unit can select the optimal consent acquisition method by referring to the user's past consent history. For example, the consent acquisition unit prioritizes the use of methods to which the user has previously consented. For example, the consent acquisition unit analyzes the user's past consent history and selects the optimal consent acquisition method. The consent acquisition unit can also avoid methods that the user has previously rejected. For example, the consent acquisition unit avoids methods that the user has previously rejected. In this way, the consent acquisition unit can select the optimal consent acquisition method by referring to the user's past consent history. Some or all of the above-described processing in the consent acquisition unit may be performed using AI, for example, or may be performed without using AI. For example, the consent acquisition unit can input the user's past consent history into the generation AI and have the generation AI select the optimal consent acquisition method.

[0099] The consent acquisition unit can estimate the user's emotions and determine the priority of consent acquisition based on the estimated user's emotions. For example, when the user is nervous, the consent acquisition unit prioritizes acquiring important consents. For example, when the user is relaxed, the consent acquisition unit acquires all consents equally. Furthermore, when the user is in a hurry, the consent acquisition unit can prioritize acquiring important consents so that they can be confirmed quickly. For example, when the user is in a hurry, the consent acquisition unit prioritizes acquiring important consents so that they can be confirmed quickly. In this way, the consent acquisition unit can prioritize acquiring important consents by determining the priority of consent acquisition based on the user's emotions. Some or all of the above-described processing in the consent acquisition unit may be performed using AI, for example, or may be performed without using AI. For example, the consent acquisition unit can input data for estimating the user's emotions into the generation AI and cause the generation AI to estimate the emotions.

[0100] When obtaining consent, the consent acquisition unit can select the optimal consent acquisition method by taking into account the user's device information. For example, if the user is using a smartphone, the consent acquisition unit provides a consent acquisition method that matches the screen size. For example, if the user is using a tablet, the consent acquisition unit provides a consent acquisition method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the consent acquisition unit can also provide a concise and highly visible consent acquisition method. For example, if the user is using a smartwatch, the consent acquisition unit provides a concise and highly visible consent acquisition method. This allows the consent acquisition unit to select the optimal consent acquisition method by taking into account the user's device information. Some or all of the above-described processing in the consent acquisition unit may be performed using AI, for example, or may be performed without using AI. For example, the consent acquisition unit can input the user's device information into the generation AI and have the generation AI select the optimal consent acquisition method.

[0101] The model update unit can estimate the user's emotion and adjust the timing of the model update based on the estimated user's emotion. For example, if the user is relaxed, the model update unit performs the model update immediately. For example, if the user is busy, the model update unit postpones the model update. The model update unit can also perform the model update in a short time if the user is in a hurry. For example, if the user is in a hurry, the model update unit performs the model update in a short time. In this way, the model update unit adjusts the timing of the model update based on the user's emotion, thereby enabling the model update at a more appropriate time. Some or all of the above-described processing in the model update unit may be performed using AI, for example, or may be performed without using AI. For example, the model update unit can input data for estimating the user's emotion to the generation AI and cause the generation AI to estimate the emotion.

[0102] The model update unit can optimize the update algorithm by referring to past learning data when updating the model. The model update unit, for example, selects an optimal update algorithm based on past learning data. For example, the model update unit analyzes past learning data and adjusts the update algorithm. The model update unit can also improve the accuracy of the update algorithm by referring to past learning data. For example, the model update unit improves the accuracy of the update algorithm by referring to past learning data. In this way, the model update unit improves the accuracy of the update algorithm by referring to the past learning data. Some or all of the above-mentioned processing in the model update unit may be performed using, for example, AI, or may be performed without using AI. For example, the model update unit can input past learning data to a generation AI and cause the generation AI to optimize the update algorithm.

[0103] The model update unit can estimate the user's emotions and adjust the frequency of model updates based on the estimated user's emotions. For example, the model update unit performs model updates frequently when the user is relaxed. For example, the model update unit reduces the frequency of model updates when the user is busy. The model update unit can also adjust the frequency of model updates when the user is in a hurry. For example, the model update unit adjusts the frequency of model updates when the user is in a hurry. In this way, the model update unit can adjust the frequency of model updates based on the user's emotions, thereby enabling model updates at a more appropriate frequency. Some or all of the above-mentioned processing in the model update unit may be performed using AI, for example, or may be performed without using AI. For example, the model update unit can input data for estimating the user's emotions to the generation AI and cause the generation AI to estimate the emotions.

[0104] When updating the model, the model update unit can weight the training data based on the time when the voice data was collected. The model update unit, for example, performs model update by assigning a high weight to the most recent voice data. For example, the model update unit performs model update by assigning a weight to voice data collected in a specific time period. The model update unit can also perform model update by assigning a weight to voice data in a time period specified by the user. For example, the model update unit performs model update by assigning a weight to voice data in a time period specified by the user. In this way, the model update unit weights the training data based on the time when the voice data was collected, thereby improving the accuracy of the model update. Some or all of the above-mentioned processing in the model update unit may be performed using AI, for example, or may be performed without using AI. For example, the model update unit can input the time when the voice data was collected to the generation AI and cause the generation AI to weight the training data. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, transcription unit, detection unit, notification unit, consent acquisition unit, and model update unit, described above, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects audio data using a microphone of the smart device 14 and transmits the collected audio data to the data processing device 12. The transcription unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and transcribes the audio data using an OpenAI API. The detection unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and detects fraudulent methods using a pre-trained model for detecting fraudulent methods. The notification unit is implemented, for example, by the control unit 46A of the smart device 14 and sends a warning notification to the user. The consent acquisition unit is implemented, for example, by the control unit 46A of the smart device 14 and displays a message to obtain user consent. The model update unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and retrains the model using a new dataset. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, transcription unit, detection unit, notification unit, consent acquisition unit, and model update unit, described above, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects audio data using a microphone in the smart glasses 214 and transmits the collected audio data to the data processing device 12. The transcription unit is implemented, for example, by the specific processing unit 290 in the data processing device 12 and transcribes the audio data using an OpenAI API. The detection unit is implemented, for example, by the specific processing unit 290 in the data processing device 12 and detects fraudulent methods using a pre-trained model for detecting fraudulent methods. The notification unit is implemented, for example, by the control unit 46A in the smart glasses 214 and sends a warning notification to the user. The consent acquisition unit is implemented, for example, by the control unit 46A in the smart glasses 214 and displays a message to obtain user consent. The model update unit is implemented, for example, by the specific processing unit 290 in the data processing device 12 and retrains the model using a new dataset. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, transcription unit, detection unit, notification unit, consent acquisition unit, and model update unit, described above, is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects voice data using a microphone of the headset type terminal 314 and transmits the voice data to the data processing device 12. The transcription unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and transcribes the voice data using an OpenAI API. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects fraudulent methods using a pre-trained model for detecting fraudulent methods. The notification unit is realized, for example, by the control unit 46A of the headset type terminal 314 and sends a warning notification to the user. The consent acquisition unit is realized, for example, by the control unit 46A of the headset type terminal 314 and displays a message to obtain user consent. The model update unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and retrains the model using a new dataset. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, transcription unit, detection unit, notification unit, consent acquisition unit, and model update unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects audio data using a microphone of the robot 414 and transmits the collected audio data to the data processing device 12. The transcription unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and transcribes the audio data using an OpenAI API. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects fraudulent methods using a pre-trained model for detecting fraudulent methods. The notification unit is realized, for example, by the control unit 46A of the robot 414 and sends a warning notification to the user. The consent acquisition unit is realized, for example, by the control unit 46A of the robot 414 and displays a message to obtain user consent. The model update unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and retrains the model using a new dataset.

[0105] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0106] The fraud prevention system may further include a behavior analysis unit that analyzes the user's behavioral patterns. The behavior analysis unit can learn the user's daily behavioral patterns and issue a warning if abnormal behavior is detected. For example, if a user who normally only makes calls during specific times of the day makes a long call during an abnormal time, the behavior analysis unit will determine that behavior as abnormal and issue a warning. In addition, if a user only performs a specific behavior when in a specific location, the behavior analysis unit can also issue a warning if the user performs similar behavior outside of that location. This allows the fraud prevention system to detect fraud with greater accuracy by taking the user's behavioral patterns into account.

[0107] When collecting the user's voice data, the collection unit can analyze the user's tone and speed of voice to detect changes in emotion. For example, if the user suddenly raises the tone of their voice, the collection unit can detect this change and infer a change in emotion. Also, if the user speaks at a faster speed than usual, the collection unit can detect this change in speed and infer tension or impatience. This allows the collection unit to detect changes in the user's emotions in real time and issue a warning if the possibility of fraud increases.

[0108] When transcribing audio data, the transcription unit can automatically generate a summary based on the user's speech. For example, it can extract important points from a long conversation and generate a concise summary. The transcription unit can also adjust the content of the summary based on specific keywords. For example, if keywords such as "fraud" or "money" are included, those parts can be highlighted and included in the summary. This allows the transcription unit to help the user quickly grasp important information.

[0109] When detecting fraudulent methods, the detection unit can improve the accuracy of detection by referring to the user's past fraud victim history. For example, for a user who has fallen victim to a specific fraudulent method in the past, strict detection standards for that method can be set. The detection unit can also adjust the alert level for new fraudulent methods based on the user's past victim history. This allows the detection unit to take into account the user's past victim history and thereby prevent fraud more effectively.

[0110] When sending a warning notification to a user, the notification unit can adjust the content of the notification according to the user's level of understanding. For example, for senior users, the notification unit can send a notification using simple, easy-to-understand language. The notification unit can also customize the content of the notification according to the user's education level and expertise. For example, for users with technical knowledge, the notification unit can send a notification containing detailed technical information. In this way, the notification unit can prevent fraud by sending an appropriate notification according to the user's level of understanding.

[0111] The fraud prevention system may further include a notification adjustment unit that estimates the user's emotions and adjusts the content of the notification based on the estimated emotions. For example, if the user is nervous, the notification adjustment unit may send a warning notification in a calm manner. If the user is relaxed, the notification adjustment unit may send a warning notification containing detailed information. Furthermore, if the user is in a hurry, the notification adjustment unit may send a concise and quick warning notification. This allows the notification adjustment unit to adjust the content of the notification based on the user's emotions, thereby enabling more effective fraud prevention.

[0112] The fraud prevention system may further include a model update adjustment unit that estimates the user's emotions and adjusts the model update frequency based on the estimated emotions. For example, the model update adjustment unit may perform model updates more frequently when the user is relaxed. Also, the model update adjustment unit may reduce the frequency of model updates when the user is busy. Furthermore, the model update adjustment unit may adjust the frequency of model updates when the user is in a hurry. In this way, the model update adjustment unit can adjust the frequency of model updates based on the user's emotions, thereby enabling model updates at a more appropriate frequency.

[0113] When collecting voice data, the collection unit can prioritize collecting highly relevant voice data by taking into account the user's geographical location information. For example, if the user is in a specific location, conversations related to that location can be collected preferentially. Also, if the user is traveling, conversations related to the user's destination can be collected preferentially. Furthermore, if the user is in a specific area, conversations related to that area can be collected preferentially. In this way, the collection unit can prioritize collecting highly relevant voice data by taking into account the user's geographical location information.

[0114] When collecting voice data, the collection unit can analyze the user's social media activities and collect related voice data. For example, the collection unit can analyze the content of the user's social media posts and prioritize collection of related conversations. It can also prioritize collection of conversations with specific friends, taking into account the user's friendships on social media. It can also collect related conversations based on the time periods during which the user is active on social media. This allows the collection unit to efficiently collect related voice data by analyzing the user's social media activities.

[0115] The transcription unit can estimate the user's emotions and adjust the transcription expression style based on the estimated user emotions. For example, if the user is nervous, concise and easy-to-understand expressions can be used. If the user is relaxed, detailed expressions can be used. Furthermore, if the user is in a hurry, expressions that focus on the main points can be used. In this way, the transcription unit can adjust the transcription expression style based on the user's emotions, thereby enabling more appropriate transcription.

[0116] The processing flow of the second embodiment will be briefly explained below.

[0117] Step 1: The collection unit collects voice data when a user uses a smartphone or a wearable device. For example, the collection unit collects voice data in real time using the microphone of the smartphone or the microphone of the wearable device and transmits it to the system. Step 2: The transcription unit transcribes the audio data collected by the collection unit. For example, it uses OpenAI's API to transcribe the audio data with high accuracy, converts it into text data, and sends it to the system. Step 3: The detection unit detects fraudulent methods based on the text data transcribed by the transcription unit. For example, it uses a pre-trained model to detect fraudulent methods, and detects conversations that correspond to fraudulent methods in real time and notifies the system. Step 4: The notification unit sends a warning notification to the user based on the fraudulent method detected by the detection unit. For example, the notification unit sends a message to the user's smartphone or wearable device stating, "This conversation may be fraudulent. Please be careful."

[0118] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0119] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0120] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0123] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0124] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

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

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

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0139] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0140] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

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

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0152] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0155] 7, a 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.

[0156] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0157] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0158] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0160] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0161] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0162] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0163] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0164] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0166] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0167] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0168] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0169] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0170] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0172] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0173] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0174] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0175] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0176] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0177] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0178] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0179] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0180] 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.

[0181] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0182] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0183] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0184] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0185] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0186] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0187] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0188] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0189] [Explanation of symbols]

[0190] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects voice data; a transcription unit that transcribes the voice data collected by the collection unit; a detection unit that detects fraudulent methods based on the text data transcribed by the transcription unit; a notification unit that sends a warning notification to a user based on the fraudulent method detected by the detection unit; Equipped with A system characterized by:

2. The collecting unit Collecting audio data using the microphone on your smartphone or wearable device 2. The system of claim 1.

3. The transcription unit Transcribe audio data using popular speech recognition APIs 2. The system of claim 1.

4. The detection unit Use pre-trained models to detect fraudulent methods 2. The system of claim 1.

5. The notification unit Send a warning notification to the user 2. The system of claim 1.

6. Equipped with a model update section, Periodically retrain the model with a new dataset 2. The system of claim 1.

7. The collecting unit The user's emotions are estimated, and the timing of collecting voice data is adjusted based on the estimated user's emotions.

2. The system of claim 1.

8. The collecting unit Equipped with a function to automatically filter background noise when collecting voice data 2. The system of claim 1.

Images