system

Abstract

The system according to this embodiment aims to improve security by identifying AI-generated voice in voice calls. [Solution] The system according to the embodiment comprises an acquisition unit, an analysis unit, a determination unit, a warning unit, and an termination unit. The acquisition unit acquires voice data. The analysis unit analyzes the voice data acquired by the acquisition unit. The determination unit determines whether or not the voice was generated based on the data analyzed by the analysis unit. The warning unit issues a warning to the user based on the result determined by the determination unit. The termination unit terminates the call as necessary.

Description

Technical Field

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

Background Art

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

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to distinguish the voice generated by AI in a voice call, and there is a security risk.

[0005] The system according to the embodiment aims to distinguish the voice generated by AI in a voice call and improve security.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, an analysis unit, a determination unit, a warning unit, and an termination unit. The acquisition unit acquires voice data. The analysis unit analyzes the voice data acquired by the acquisition unit. The determination unit determines whether or not the voice was generated based on the data analyzed by the analysis unit. The warning unit issues a warning to the user based on the result determined by the determination unit. The termination unit terminates the call as necessary. [Effects of the Invention]

[0007] The system according to this embodiment can identify AI-generated voice in voice calls and improve security. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The voice call security system according to an embodiment of the present invention is a system that optionally provides a security function to determine whether a voice call made by a telecommunications carrier is AI-generated. When a voice call is initiated, the system uses AI to analyze the call content in real time and, based on the analyzed voice data, determines whether the voice was generated by the AI. Based on this determination, the system decides whether to issue a warning to the user or continue the call. For example, when a voice call is initiated, the AI ​​analyzes the call content in real time. For example, it acquires the voice data of the call and analyzes its voice waveform and features. This analysis includes the frequency components and temporal fluctuations of the voice. Next, based on the analyzed voice data, the AI ​​determines whether the voice was generated by the AI. For example, the AI ​​compares the features of the voice and determines whether it matches voice generated by a generation AI. This determination uses the training data of the generation AI and the features of known generated voices. Based on this determination, the system decides whether to issue a warning to the user or continue the call. For example, if it determines that the voice was AI-generated, it displays a warning message to the user. It is also possible to automatically terminate the call if necessary. This mechanism protects users from fraud and illegal activities using AI-generated voices. For example, even if a scammer uses AI to create fake voices to deceive a user, the AI ​​can detect these voices and warn the user, preventing them from becoming a victim. In this way, voice call security systems can protect users from fraud and misconduct using AI-generated voices.

[0029] The voice call security system according to the embodiment comprises an acquisition unit, an analysis unit, a determination unit, a warning unit, and a termination unit. The acquisition unit acquires voice data. The acquisition unit can, for example, acquire voice data of a call in real time. The acquisition unit acquires voice data of a call in real time and transmits the data to the analysis unit. The acquisition unit can also use noise cancellation technology to acquire voice data with high accuracy. For example, the acquisition unit uses noise cancellation technology to remove background noise during a call and acquire clear voice data. The analysis unit analyzes the voice data acquired by the acquisition unit. The analysis unit can, for example, analyze the frequency components and temporal variations of the voice. The analysis unit analyzes the frequency components of the voice using, for example, a Fourier transform. The analysis unit can also analyze the temporal variations of the voice using time-domain analysis. For example, the analysis unit analyzes the variations in the voice waveform and extracts the characteristics of the voice. The determination unit determines whether or not the voice was generated based on the data analyzed by the analysis unit. The determination unit can determine, for example, whether the voice was generated using the training data of the generation AI or the characteristics of known generated voices. The determination unit can, for example, compare the characteristics of the voice based on the training data of the generation AI and determine whether they match the generated voice. The determination unit can also determine whether the voice was generated using the characteristics of known generated voices. For example, the determination unit can obtain the characteristics of known generated voices from a database and compare them with the analyzed voice data. The warning unit issues a warning to the user based on the result determined by the determination unit. For example, if the warning unit determines that the voice is generated, it can display a warning message to the user. For example, the warning unit can display a warning message on the screen. The warning unit can also notify the user of the warning message by voice. For example, the warning unit can notify the user of the warning message by voice using speech synthesis technology. The termination unit terminates the call as necessary. For example, if the termination unit determines that the voice is generated, it can automatically terminate the call. For example, the termination unit can forcibly terminate the call. The termination unit can also terminate the call based on user instructions.For example, the termination unit ends the call when the user presses the button to end the call. This allows the voice call security system according to the embodiment to provide a security function that can determine whether the voice in a voice call is AI-generated.

[0030] The acquisition unit acquires audio data. For example, the acquisition unit can acquire audio data of a call in real time. Specifically, the acquisition unit starts collecting audio data at the same time as the start of a call and continues to acquire data until the call ends. For example, the acquisition unit acquires audio data of a call in real time and transmits that data to the analysis unit. This allows the acquisition unit to collect audio data during a call without interruption and provide it to the analysis unit. In addition, the acquisition unit can use noise cancellation technology to acquire audio data with high accuracy. For example, the acquisition unit can use noise cancellation technology to remove background noise during a call and acquire clear audio data. Noise cancellation technology detects ambient sounds and noise in real time and generates out-of-phase sound to cancel them out, making the audio during the call clearer. This allows the acquisition unit to acquire audio data during a call with high accuracy and provide it to the analysis unit. Furthermore, the acquisition unit can also collect audio data using multiple microphones. This allows the acquisition unit to identify the direction and distance of the sound and acquire more detailed audio data. For example, the acquisition unit identifies the location of the speaker during a call and collects audio data corresponding to that location. This allows the acquisition unit to acquire audio data during a call more accurately and provide it to the analysis unit.

[0031] The analysis unit analyzes the audio data acquired by the acquisition unit. For example, the analysis unit can analyze the frequency components and temporal variations of the audio. Specifically, the analysis unit uses the Fourier transform to analyze the frequency components of the audio. The Fourier transform is a method that decomposes an audio signal into frequency components and analyzes the intensity of each frequency component. This allows the analysis unit to understand the frequency characteristics of the audio data in detail. Furthermore, the analysis unit can also analyze the temporal variations of the audio using time-domain analysis. For example, the analysis unit analyzes the variations in the audio waveform and extracts the characteristics of the audio. Time-domain analysis is a method that analyzes the temporal variations of an audio signal to understand the start and end points of the audio, the intensity of the sound, etc. This allows the analysis unit to understand the temporal characteristics of the audio data in detail. In addition, the analysis unit can also analyze audio data using AI. For example, the analysis unit uses deep learning to analyze audio data and extract the characteristics of the audio. Deep learning is a method that uses a multi-layered neural network to analyze data and extract complex patterns and features. This allows the analysis unit to grasp the detailed characteristics of the audio data and provide them to the judgment unit. Furthermore, the analysis unit can also compare the characteristics of the audio data with past audio data or known audio data. This allows the analysis unit to grasp the characteristics of the audio data in detail and provide them to the judgment unit.

[0032] The determination unit determines whether or not the audio was generated based on the data analyzed by the analysis unit. The determination unit can determine, for example, whether or not the audio was generated using the training data of the generation AI or the characteristics of known generated audio. Specifically, the determination unit compares the features of the audio with those of the generation AI based on the training data of the generation AI and determines whether or not they match the generated audio. The training data of the generation AI is learned based on previously generated audio data and has a detailed understanding of the characteristics of generated audio. As a result, the determination unit can compare the features of the analyzed audio data with the training data of the generation AI and determine whether or not they match the generated audio. The determination unit can also determine whether or not the audio was generated using the characteristics of known generated audio. For example, the determination unit can obtain the characteristics of known generated audio from a database and compare them with the analyzed audio data. The characteristics of known generated audio have a detailed understanding of the characteristics of previously generated audio data and serve as a criterion for determining whether or not they match the generated audio. As a result, the determination unit can compare the characteristics of the analyzed audio data with the characteristics of known generated audio and determine whether or not they match the generated audio. Furthermore, the determination unit can also analyze the characteristics of the audio data using AI and determine whether or not they match the generated audio. This allows the judgment unit to grasp the characteristics of the analyzed audio data in detail and determine with high accuracy whether it matches the generated audio.

[0033] The warning unit issues a warning to the user based on the result determined by the judgment unit. For example, if the warning unit determines that the sound is generated audio, it can display a warning message to the user. Specifically, the warning unit displays the warning message on the screen. For example, it can display a warning message on the screen of a smartphone or computer to alert the user. The warning unit can also notify the user of the warning message by voice. For example, the warning unit can notify the user of the warning message by voice using speech synthesis technology. Speech synthesis technology is a technology that converts text data into speech, and can notify the user of the warning message in real time. This allows the warning unit to quickly and reliably convey the warning message to the user. Furthermore, the warning unit can also use warning means that utilize visual or tactile senses, such as vibration or flashing lights. For example, it can use the vibration function of a smartphone to issue a warning to the user. In addition, the warning unit can combine multiple warning means to reliably convey the warning to the user. This allows the warning unit to quickly and reliably convey the warning message to the user and minimize the risks associated with generated audio.

[0034] The termination unit will end the call as needed. For example, if it determines that the call is generated audio, the termination unit can automatically terminate the call. Specifically, the termination unit forcibly terminates the call based on the determination result of the determination unit. This quickly protects the user from the risks associated with generated audio. The termination unit can also terminate the call based on the user's instructions. For example, the termination unit will terminate the call if the user presses the end call button. This allows the user to end the call at their own discretion. Furthermore, the termination unit can notify the user of the call content and determination result after the call has ended. For example, the termination unit will notify the user of the call content and determination result via email or message after the call has ended. This allows the user to review the call content and determination result and take appropriate measures. Furthermore, the termination unit can record the call content after the call has ended so that it can be reviewed later. This allows the user to review the call content later and take appropriate measures. In this way, the termination unit can quickly and reliably terminate the call for the user, minimizing the risks associated with generated audio.

[0035] The acquisition unit can acquire call audio data in real time. For example, the acquisition unit can acquire call audio data in real time and transmit that data to the analysis unit. The acquisition unit can also use noise cancellation technology to acquire audio data with high accuracy. For example, the acquisition unit can use noise cancellation technology to remove background noise during a call and acquire clear audio data. This allows for immediate analysis by acquiring call audio data in real time. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can acquire call audio data in real time, input that data into a generating AI, and have the generating AI analyze the audio data.

[0036] The analysis unit can analyze the frequency components and temporal variations of speech. For example, the analysis unit can analyze the frequency components of speech using the Fourier transform. The analysis unit can also analyze the temporal variations of speech using time-domain analysis. For example, the analysis unit analyzes the variations in the speech waveform and extracts the characteristics of the speech. This allows for a detailed understanding of the characteristics of speech by analyzing its frequency components and temporal variations. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input speech data into a generating AI, and the generating AI can perform the analysis of the speech data.

[0037] The determination unit can determine whether or not the audio was generated using the training data of the generation AI or the characteristics of known generated audio. For example, the determination unit can compare the features of the audio based on the training data of the generation AI and determine whether or not they match the generated audio. The determination unit can also determine whether or not the audio was generated using the characteristics of known generated audio. For example, the determination unit can obtain the characteristics of known generated audio from a database and compare them with the analyzed audio data. This allows for highly accurate determination of whether or not the audio was generated using the training data of the generation AI or the characteristics of known generated audio. Some or all of the above processing in the determination unit may be performed using AI, for example, or without AI. For example, the determination unit can input audio data into the generation AI, and the generation AI can perform the determination of the audio data.

[0038] The warning unit can display a warning message to the user if it determines that the voice is generated. The warning unit can, for example, display the warning message on the screen. The warning unit can also notify the user of the warning message by voice. For example, the warning unit can notify the user of the warning message by voice using speech synthesis technology. This allows the user to be alerted by displaying a warning message to the user if it determines that the voice is generated. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input a warning message into a generation AI, and the generation AI can generate the warning message.

[0039] The termination unit can automatically terminate a call as needed. For example, the termination unit can automatically terminate a call if it determines that the call is a generated voice. The termination unit can also forcibly terminate a call. Furthermore, the termination unit can terminate a call based on user instructions. For example, the termination unit terminates a call when the user presses the end call button. This protects the user from fraudulent calls by automatically terminating calls as needed. Some or all of the above-described processes in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input a call termination instruction to a generating AI, which can then perform the call termination process.

[0040] The acquisition unit can analyze the user's past call history before a call begins and select the optimal acquisition method. For example, if the user has made long calls in the past, the acquisition unit will select a method that allows the AI ​​to efficiently acquire the voice data. For example, if the user has made short calls in the past, the acquisition unit will select a method that allows the AI ​​to quickly acquire the voice data. For example, if the user has made calls in the past during a specific time period, the acquisition unit will select the optimal acquisition method for that time period. In this way, the optimal acquisition method can be selected by analyzing the user's past call history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's past call history data into a generating AI, and the generating AI can select the optimal acquisition method.

[0041] The acquisition unit can filter audio data based on the content and context of the call. For example, if the content of the call is business-related, the AI ​​will prioritize the acquisition of important keywords. If the content of the call is private, the AI ​​will filter out specific privacy-related information. For example, based on the context of the call, the AI ​​will remove noise and acquire clear audio data. This allows for the priority acquisition of important audio data by filtering based on the content and context of the call. Some or all of the above processing in the acquisition unit may be performed using AI, or not. For example, the acquisition unit can input the content and context data of the call into a generating AI, which can then perform the filtering.

[0042] The acquisition unit can prioritize the acquisition of highly relevant data based on the user's geographical location information when acquiring audio data. For example, if the user is in a specific region, the acquisition unit will prioritize the acquisition of audio data related to that region. For example, if the user is on the move, the acquisition unit will prioritize the acquisition of highly relevant audio data based on the user's current location. For example, if the user is in a specific location, the acquisition unit will prioritize the acquisition of audio data related to that location. By prioritizing the acquisition of highly relevant data based on the user's geographical location information, more useful audio data can be acquired. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's geographical location information data into a generating AI, and the generating AI can select highly relevant data.

[0043] The acquisition unit can analyze the user's social media activity and acquire relevant data when acquiring audio data. For example, if the user is talking about a specific topic on social media, the acquisition unit can acquire audio data related to that topic. For example, if the user is participating in a specific event on social media, the acquisition unit can acquire audio data related to that event. For example, if the user is checking in to a specific location on social media, the acquisition unit can acquire audio data related to that location. In this way, relevant audio data can be acquired by analyzing the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's social media activity data into a generating AI, and the generating AI can select relevant data.

[0044] The analysis unit can adjust the level of detail of the analysis based on the importance of the audio data. For example, the analysis unit performs a detailed analysis for important audio data. For example, the analysis unit performs a standard analysis for general audio data. For example, the analysis unit performs a simplified analysis for unnecessary audio data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the audio. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI, and the generating AI can adjust the level of detail of the analysis.

[0045] The analysis unit can apply different analysis algorithms depending on the category of the audio data during analysis. For example, the analysis unit applies a business-oriented analysis algorithm to business-related audio data. For example, the analysis unit applies a private-use analysis algorithm to private audio data. For example, the analysis unit applies a field-specific analysis algorithm to audio data related to a particular field of expertise. By applying different analysis algorithms depending on the category of the audio, more accurate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI, and the generating AI can apply the analysis algorithm.

[0046] The analysis unit can determine the priority of analysis based on the start time of the call when analyzing audio data. For example, the analysis unit may prioritize the analysis of audio data immediately after the start of the call. For example, the analysis unit may analyze audio data in the middle of the call in a standard manner. For example, the analysis unit may simplify the analysis of audio data near the end of the call. By determining the priority of analysis based on the start time of the call, important audio data can be analyzed preferentially. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input call start time data into a generating AI, and the generating AI can determine the priority of analysis.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the audio data. For example, the analysis unit may prioritize the analysis of important audio data. For example, the analysis unit may analyze general audio data in a standard manner. For example, the analysis unit may postpone the analysis of unnecessary audio data. By adjusting the order of analysis based on the relevance of the audio data, efficient analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input relevance data of the audio data into a generating AI, and the generating AI can adjust the order of analysis.

[0048] The judgment unit can improve the accuracy of its judgment based on the interrelationships between audio data. For example, the judgment unit compares audio data before and after a call to confirm consistency. For example, the judgment unit compares audio data from different parts of a call to confirm interrelationships. For example, the judgment unit confirms the consistency between the content of the call and the audio data. By improving the accuracy of the judgment based on the interrelationships between audio data, more accurate judgments become possible. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input data on the interrelationships of audio data into a generating AI, and the generating AI can improve the accuracy of the judgment.

[0049] The judgment unit can make judgments based on the content and context of a call when judging voice data. For example, if the content of the call is business-related, the judgment unit will make a judgment based on that context. For example, if the content of the call is private, the judgment unit will make a judgment based on that context. For example, if the content of the call is related to a specific field of expertise, the judgment unit will make a judgment based on that context. This makes it possible to make more appropriate judgments by making judgments based on the content and context of the call. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without using AI. For example, the judgment unit can input the content and context data of the call into a generating AI, and the generating AI can make the judgment.

[0050] The judgment unit can perform judgments on audio data based on the geographical distribution of the audio. For example, the judgment unit may prioritize the judgment of audio data related to a specific region. For example, the judgment unit may compare geographically dispersed audio data to confirm consistency. For example, the judgment unit may evaluate the reliability of the audio data based on geographical information. This makes it possible to perform more accurate judgments by performing judgments based on the geographical distribution of the audio. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit may input geographical distribution data of the audio data into a generating AI, and the generating AI may perform the judgment.

[0051] The judgment unit can improve the accuracy of its judgment based on relevant literature for the audio data. For example, the judgment unit can improve the accuracy of its judgment by referring to an existing audio database. For example, the judgment unit can strengthen the criteria for judgment by referring to relevant research papers. For example, the judgment unit can improve the accuracy of its judgment by referring to the characteristics of known generated audio. By improving the accuracy of judgment based on relevant literature for the audio, more accurate judgment becomes possible. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input relevant literature data for the audio data into a generating AI, and the generating AI can improve the accuracy of the judgment.

[0052] The warning unit can select the optimal display method by referring to the user's past warning history when displaying a warning. For example, the warning unit can analyze the content of warnings the user has received in the past and select the optimal method when displaying similar warnings. For example, the warning unit can select a more prominent method when displaying warnings that the user has ignored in the past. For example, the warning unit can select a similar display method when displaying warnings that the user has responded to promptly in the past. In this way, the optimal warning display method can be selected by referring to the user's past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's past warning history data into a generating AI, and the generating AI can select the optimal display method.

[0053] The warning unit can adjust the content of the warning based on the user's current situation when displaying a warning. For example, if the user is driving, the warning unit will issue an audible warning. For example, if the user is in a meeting, the warning unit will issue a vibration warning. For example, if the user is relaxed, the warning unit will display detailed warning information. This allows for more appropriate warnings by adjusting the content of the warning based on the user's current situation. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's current situation data into a generating AI, and the generating AI can adjust the content of the warning.

[0054] The warning unit can select the optimal display method based on the user's device information when displaying a warning. For example, if the user is using a smartphone, the warning unit will display a warning that is appropriate for the screen size. If the user is using a tablet, the warning unit will display a warning optimized for a larger screen. If the user is using a smartwatch, the warning unit will display a concise and highly visible warning. By selecting the optimal display method based on the user's device information, it becomes possible to display warnings that are easy for the user to see. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input user device information data into a generating AI, and the generating AI can select the optimal display method.

[0055] The warning unit can provide multilingual warnings according to the user's language settings when displaying a warning. For example, the warning unit can automatically set the warning language based on the language settings of the user's device. For example, the warning unit can provide a language switching function if the user uses multiple languages. For example, if the user selects a specific language, the warning unit can provide a warning in that language. This makes it possible to provide warnings that are easy for the user to understand by providing multilingual warnings according to the user's language settings. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's language setting data into a generating AI, and the generating AI can provide multilingual warnings.

[0056] The termination unit can select the optimal termination method by referring to the user's past call history when a call ends. For example, if the user has ended a call quickly in the past, the termination unit will terminate the call in a similar manner. For example, if the user has continued a call for a long time in the past, the termination unit will terminate the call at an appropriate time. For example, if the user has ended a call during a specific time period in the past, the termination unit will terminate the call in a manner that is optimal for that time period. In this way, the optimal termination method can be selected by referring to the user's past call history. Some or all of the above processing in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input the user's past call history data into a generating AI, and the generating AI can select the optimal termination method.

[0057] The termination unit can adjust the termination method based on the user's current situation when a call ends. For example, if the user is driving, the termination unit will notify the user of the call ending by voice. For example, if the user is in a meeting, the termination unit will notify the user of the call ending by vibration. For example, if the user is relaxing, the termination unit will display detailed termination information. This allows for a more appropriate termination by adjusting the termination method based on the user's current situation. Some or all of the above processing in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input the user's current situation data into a generating AI, which can then adjust the termination method.

[0058] The termination unit can select the optimal termination method based on the user's device information when a call ends. For example, if the user is using a smartphone, the termination unit provides an termination method that is appropriate for the screen size. For example, if the user is using a tablet, the termination unit provides an termination method optimized for a large screen. For example, if the user is using a smartwatch, the termination unit provides a concise and highly visible termination method. By selecting the optimal termination method based on the user's device information, it becomes possible to provide an appropriate termination method for the user. Some or all of the above processing in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input the user's device information data into a generating AI, and the generating AI can select the optimal termination method.

[0059] The termination unit can provide a scheduled termination method based on the user's calendar information when a call ends. For example, the termination unit refers to appointments registered in the user's calendar and terminates the call at an appropriate time. For example, the termination unit prioritizes terminating calls related to specific events based on the user's calendar information. For example, the termination unit provides an optimal termination method tailored to the appointment based on the user's calendar information. This enables an appropriate termination for the user by providing an appointment-based termination method based on the user's calendar information. Some or all of the above processing in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input the user's calendar information data into a generating AI, and the generating AI can provide an appointment-based termination method.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The voice call security system may further include a suggestion unit that analyzes the user's past call history and proposes the optimal timing for starting a call. For example, if the user has made long calls in the past, the suggestion unit may suggest the optimal time to start a call. For example, if the user has made short calls in the past, the suggestion unit may suggest a time to start a call quickly. For example, if the user has made calls in the past during a specific time period, the suggestion unit may suggest the optimal timing for starting a call during that time period. In this way, the optimal timing for starting a call can be suggested by analyzing the user's past call history. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's past call history data into a generating AI, and the generating AI can then suggest the optimal timing for starting a call.

[0062] The voice call security system may further include a summarization unit that automatically summarizes the content of a call. The summarization unit may, for example, concisely summarize the important points of the call. The summarization unit may, for example, summarize the overall content of the call in a balanced manner. The summarization unit may, for example, provide a summary that quickly summarizes the main points of the call. This makes it possible to provide information that is easy for the user to understand by automatically summarizing the content of the call. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can input the content data of the call into a generating AI, and the generating AI can perform the summarization.

[0063] The voice call security system may further include a translation unit that automatically translates the content of the call. The translation unit may, for example, provide a concise translation of the call content. The translation unit may, for example, provide a balanced translation of the overall content of the call. The translation unit may, for example, quickly translate the main points of the call. This makes it possible to provide information that is easy for the user to understand by automatically translating the content of the call. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input the call content data into a generating AI, and the generating AI can perform the translation.

[0064] The voice call security system may further include a filtering unit that automatically filters the content of calls. The filtering unit may, for example, prioritize filtering important information from the call. The filtering unit may, for example, filter the overall information of the call in a balanced manner. The filtering unit may, for example, quickly filter the key points of the call. This ensures that important information is not missed by automatically filtering the content of the call. Some or all of the above processing in the filtering unit may be performed using AI, for example, or without AI. For example, the filtering unit can input the call content data into a generating AI, and the generating AI can perform the filtering.

[0065] The voice call security system may further include a classification unit that automatically categorizes the content of calls. The classification unit may, for example, classify the content of calls into business-related, private-related, or other categories. The classification unit may, for example, classify the content of calls based on specific topics. The classification unit may, for example, classify the content of calls based on importance. This enables the provision of information that is easy for users to organize by automatically classifying the content of calls. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit may input the content of calls into a generating AI, and the generating AI may perform the classification.

[0066] The voice call security system may further include an analysis unit that automatically analyzes the content of calls. The analysis unit may, for example, analyze the content of calls in detail and extract important points. The analysis unit may, for example, analyze the overall content of calls in a balanced manner. The analysis unit may, for example, quickly analyze the key points of calls. This enables the provision of information that is easy for users to understand by automatically analyzing the content of calls. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the call content data into a generating AI, and the generating AI can perform the analysis.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The acquisition unit acquires audio data. For example, the acquisition unit acquires audio data from a call in real time and transmits that data to the analysis unit. The acquisition unit also uses noise cancellation technology to remove background noise during the call and acquires clear audio data. Step 2: The analysis unit analyzes the audio data acquired by the acquisition unit. The analysis unit can, for example, analyze the frequency components and temporal variations of the audio. It extracts audio features using Fourier transforms and time-domain analysis. Step 3: The determination unit determines whether or not the speech was generated based on the data analyzed by the analysis unit. The determination unit determines whether or not the speech was generated using the training data of the generation AI or known characteristics of generated speech. Step 4: The warning unit issues a warning to the user based on the result determined by the judgment unit. For example, if the warning unit determines that the sound is generated audio, it displays a warning message to the user or notifies them by voice. Step 5: The termination unit terminates the call as necessary. For example, if it is determined that the call is generated voice, the termination unit will automatically terminate the call, or terminate the call based on user instructions.

[0069] (Example of form 2) The voice call security system according to an embodiment of the present invention is a system that optionally provides a security function to determine whether a voice call made by a telecommunications carrier is AI-generated. When a voice call is initiated, the system uses AI to analyze the call content in real time and, based on the analyzed voice data, determines whether the voice was generated by the AI. Based on this determination, the system decides whether to issue a warning to the user or continue the call. For example, when a voice call is initiated, the AI ​​analyzes the call content in real time. For example, it acquires the voice data of the call and analyzes its voice waveform and features. This analysis includes the frequency components and temporal fluctuations of the voice. Next, based on the analyzed voice data, the AI ​​determines whether the voice was generated by the AI. For example, the AI ​​compares the features of the voice and determines whether it matches voice generated by a generation AI. This determination uses the training data of the generation AI and the features of known generated voices. Based on this determination, the system decides whether to issue a warning to the user or continue the call. For example, if it determines that the voice was AI-generated, it displays a warning message to the user. It is also possible to automatically terminate the call if necessary. This mechanism protects users from fraud and illegal activities using AI-generated voices. For example, even if a scammer uses AI to create fake voices to deceive a user, the AI ​​can detect these voices and warn the user, preventing them from becoming a victim. In this way, voice call security systems can protect users from fraud and misconduct using AI-generated voices.

[0070] The voice call security system according to the embodiment comprises an acquisition unit, an analysis unit, a determination unit, a warning unit, and a termination unit. The acquisition unit acquires voice data. The acquisition unit can, for example, acquire voice data of a call in real time. The acquisition unit acquires voice data of a call in real time and transmits the data to the analysis unit. The acquisition unit can also use noise cancellation technology to acquire voice data with high accuracy. For example, the acquisition unit uses noise cancellation technology to remove background noise during a call and acquire clear voice data. The analysis unit analyzes the voice data acquired by the acquisition unit. The analysis unit can, for example, analyze the frequency components and temporal variations of the voice. The analysis unit analyzes the frequency components of the voice using, for example, a Fourier transform. The analysis unit can also analyze the temporal variations of the voice using time-domain analysis. For example, the analysis unit analyzes the variations in the voice waveform and extracts the characteristics of the voice. The determination unit determines whether or not the voice was generated based on the data analyzed by the analysis unit. The determination unit can determine, for example, whether the voice was generated using the training data of the generation AI or the characteristics of known generated voices. The determination unit can, for example, compare the characteristics of the voice based on the training data of the generation AI and determine whether they match the generated voice. The determination unit can also determine whether the voice was generated using the characteristics of known generated voices. For example, the determination unit can obtain the characteristics of known generated voices from a database and compare them with the analyzed voice data. The warning unit issues a warning to the user based on the result determined by the determination unit. For example, if the warning unit determines that the voice is generated, it can display a warning message to the user. For example, the warning unit can display a warning message on the screen. The warning unit can also notify the user of the warning message by voice. For example, the warning unit can notify the user of the warning message by voice using speech synthesis technology. The termination unit terminates the call as necessary. For example, if the termination unit determines that the voice is generated, it can automatically terminate the call. For example, the termination unit can forcibly terminate the call. The termination unit can also terminate the call based on user instructions.For example, the termination unit ends the call when the user presses the button to end the call. This allows the voice call security system according to the embodiment to provide a security function that can determine whether the voice in a voice call is AI-generated.

[0071] The acquisition unit acquires audio data. For example, the acquisition unit can acquire audio data of a call in real time. Specifically, the acquisition unit starts collecting audio data at the same time as the start of a call and continues to acquire data until the call ends. For example, the acquisition unit acquires audio data of a call in real time and transmits that data to the analysis unit. This allows the acquisition unit to collect audio data during a call without interruption and provide it to the analysis unit. In addition, the acquisition unit can use noise cancellation technology to acquire audio data with high accuracy. For example, the acquisition unit can use noise cancellation technology to remove background noise during a call and acquire clear audio data. Noise cancellation technology detects ambient sounds and noise in real time and generates out-of-phase sound to cancel them out, making the audio during the call clearer. This allows the acquisition unit to acquire audio data during a call with high accuracy and provide it to the analysis unit. Furthermore, the acquisition unit can also collect audio data using multiple microphones. This allows the acquisition unit to identify the direction and distance of the sound and acquire more detailed audio data. For example, the acquisition unit identifies the location of the speaker during a call and collects audio data corresponding to that location. This allows the acquisition unit to acquire audio data during a call more accurately and provide it to the analysis unit.

[0072] The analysis unit analyzes the audio data acquired by the acquisition unit. For example, the analysis unit can analyze the frequency components and temporal variations of the audio. Specifically, the analysis unit uses the Fourier transform to analyze the frequency components of the audio. The Fourier transform is a method that decomposes an audio signal into frequency components and analyzes the intensity of each frequency component. This allows the analysis unit to understand the frequency characteristics of the audio data in detail. Furthermore, the analysis unit can also analyze the temporal variations of the audio using time-domain analysis. For example, the analysis unit analyzes the variations in the audio waveform and extracts the characteristics of the audio. Time-domain analysis is a method that analyzes the temporal variations of an audio signal to understand the start and end points of the audio, the intensity of the sound, etc. This allows the analysis unit to understand the temporal characteristics of the audio data in detail. In addition, the analysis unit can also analyze audio data using AI. For example, the analysis unit uses deep learning to analyze audio data and extract the characteristics of the audio. Deep learning is a method that uses a multi-layered neural network to analyze data and extract complex patterns and features. This allows the analysis unit to grasp the detailed characteristics of the audio data and provide them to the judgment unit. Furthermore, the analysis unit can also compare the characteristics of the audio data with past audio data or known audio data. This allows the analysis unit to grasp the characteristics of the audio data in detail and provide them to the judgment unit.

[0073] The determination unit determines whether or not the audio was generated based on the data analyzed by the analysis unit. The determination unit can determine, for example, whether or not the audio was generated using the training data of the generation AI or the characteristics of known generated audio. Specifically, the determination unit compares the features of the audio with those of the generation AI based on the training data of the generation AI and determines whether or not they match the generated audio. The training data of the generation AI is learned based on previously generated audio data and has a detailed understanding of the characteristics of generated audio. As a result, the determination unit can compare the features of the analyzed audio data with the training data of the generation AI and determine whether or not they match the generated audio. The determination unit can also determine whether or not the audio was generated using the characteristics of known generated audio. For example, the determination unit can obtain the characteristics of known generated audio from a database and compare them with the analyzed audio data. The characteristics of known generated audio have a detailed understanding of the characteristics of previously generated audio data and serve as a criterion for determining whether or not they match the generated audio. As a result, the determination unit can compare the characteristics of the analyzed audio data with the characteristics of known generated audio and determine whether or not they match the generated audio. Furthermore, the determination unit can also analyze the characteristics of the audio data using AI and determine whether or not they match the generated audio. This allows the judgment unit to grasp the characteristics of the analyzed audio data in detail and determine with high accuracy whether it matches the generated audio.

[0074] The warning unit issues a warning to the user based on the result determined by the judgment unit. For example, if the warning unit determines that the sound is generated audio, it can display a warning message to the user. Specifically, the warning unit displays the warning message on the screen. For example, it can display a warning message on the screen of a smartphone or computer to alert the user. The warning unit can also notify the user of the warning message by voice. For example, the warning unit can notify the user of the warning message by voice using speech synthesis technology. Speech synthesis technology is a technology that converts text data into speech, and can notify the user of the warning message in real time. This allows the warning unit to quickly and reliably convey the warning message to the user. Furthermore, the warning unit can also use warning means that utilize visual or tactile senses, such as vibration or flashing lights. For example, it can use the vibration function of a smartphone to issue a warning to the user. In addition, the warning unit can combine multiple warning means to reliably convey the warning to the user. This allows the warning unit to quickly and reliably convey the warning message to the user and minimize the risks associated with generated audio.

[0075] The termination unit will end the call as needed. For example, if it determines that the call is generated audio, the termination unit can automatically terminate the call. Specifically, the termination unit forcibly terminates the call based on the determination result of the determination unit. This quickly protects the user from the risks associated with generated audio. The termination unit can also terminate the call based on the user's instructions. For example, the termination unit will terminate the call if the user presses the end call button. This allows the user to end the call at their own discretion. Furthermore, the termination unit can notify the user of the call content and determination result after the call has ended. For example, the termination unit will notify the user of the call content and determination result via email or message after the call has ended. This allows the user to review the call content and determination result and take appropriate measures. Furthermore, the termination unit can record the call content after the call has ended so that it can be reviewed later. This allows the user to review the call content later and take appropriate measures. In this way, the termination unit can quickly and reliably terminate the call for the user, minimizing the risks associated with generated audio.

[0076] The acquisition unit can acquire call audio data in real time. For example, the acquisition unit can acquire call audio data in real time and transmit that data to the analysis unit. The acquisition unit can also use noise cancellation technology to acquire audio data with high accuracy. For example, the acquisition unit can use noise cancellation technology to remove background noise during a call and acquire clear audio data. This allows for immediate analysis by acquiring call audio data in real time. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can acquire call audio data in real time, input that data into a generating AI, and have the generating AI analyze the audio data.

[0077] The analysis unit can analyze the frequency components and temporal variations of speech. For example, the analysis unit can analyze the frequency components of speech using the Fourier transform. The analysis unit can also analyze the temporal variations of speech using time-domain analysis. For example, the analysis unit analyzes the variations in the speech waveform and extracts the characteristics of the speech. This allows for a detailed understanding of the characteristics of speech by analyzing its frequency components and temporal variations. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input speech data into a generating AI, and the generating AI can perform the analysis of the speech data.

[0078] The determination unit can determine whether or not the audio was generated using the training data of the generation AI or the characteristics of known generated audio. For example, the determination unit can compare the features of the audio based on the training data of the generation AI and determine whether or not they match the generated audio. The determination unit can also determine whether or not the audio was generated using the characteristics of known generated audio. For example, the determination unit can obtain the characteristics of known generated audio from a database and compare them with the analyzed audio data. This allows for highly accurate determination of whether or not the audio was generated using the training data of the generation AI or the characteristics of known generated audio. Some or all of the above processing in the determination unit may be performed using AI, for example, or without AI. For example, the determination unit can input audio data into the generation AI, and the generation AI can perform the determination of the audio data.

[0079] The warning unit can display a warning message to the user if it determines that the voice is generated. The warning unit can, for example, display the warning message on the screen. The warning unit can also notify the user of the warning message by voice. For example, the warning unit can notify the user of the warning message by voice using speech synthesis technology. This allows the user to be alerted by displaying a warning message to the user if it determines that the voice is generated. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input a warning message into a generation AI, and the generation AI can generate the warning message.

[0080] The termination unit can automatically terminate a call as needed. For example, the termination unit can automatically terminate a call if it determines that the call is a generated voice. The termination unit can also forcibly terminate a call. Furthermore, the termination unit can terminate a call based on user instructions. For example, the termination unit terminates a call when the user presses the end call button. This protects the user from fraudulent calls by automatically terminating calls as needed. Some or all of the above-described processes in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input a call termination instruction to a generating AI, which can then perform the call termination process.

[0081] The acquisition unit can estimate the user's emotions and adjust the timing of voice data acquisition based on the estimated user emotions. For example, if the user is nervous, the AI ​​will quickly acquire voice data and start analysis in real time. For example, if the user is relaxed, the AI ​​will acquire voice data at a normal pace and proceed with analysis. For example, if the user is in a hurry, the AI ​​will prioritize acquiring voice data and start analysis immediately. This allows for voice data to be acquired at a more appropriate time by adjusting the timing of voice data acquisition based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using AI, or not using AI. For example, the acquisition unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0082] The acquisition unit can analyze the user's past call history before a call begins and select the optimal acquisition method. For example, if the user has made long calls in the past, the acquisition unit will select a method that allows the AI ​​to efficiently acquire the voice data. For example, if the user has made short calls in the past, the acquisition unit will select a method that allows the AI ​​to quickly acquire the voice data. For example, if the user has made calls in the past during a specific time period, the acquisition unit will select the optimal acquisition method for that time period. In this way, the optimal acquisition method can be selected by analyzing the user's past call history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's past call history data into a generating AI, and the generating AI can select the optimal acquisition method.

[0083] The acquisition unit can filter audio data based on the content and context of the call. For example, if the content of the call is business-related, the AI ​​will prioritize the acquisition of important keywords. If the content of the call is private, the AI ​​will filter out specific privacy-related information. For example, based on the context of the call, the AI ​​will remove noise and acquire clear audio data. This allows for the priority acquisition of important audio data by filtering based on the content and context of the call. Some or all of the above processing in the acquisition unit may be performed using AI, or not. For example, the acquisition unit can input the content and context data of the call into a generating AI, which can then perform the filtering.

[0084] The acquisition unit can estimate the user's emotions and determine the priority of audio data to acquire based on the estimated user emotions. For example, if the user is tense, the AI ​​will prioritize acquiring important audio data. If the user is relaxed, the AI ​​will acquire a balanced mix of audio data. If the user is in a hurry, the AI ​​will prioritize acquiring audio data that is immediately needed. This ensures that important audio data is acquired preferentially by prioritizing audio data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using or without AI. For example, the acquisition unit can input user emotion data into a generative AI, which can then perform emotion estimation.

[0085] The acquisition unit can prioritize the acquisition of highly relevant data based on the user's geographical location information when acquiring audio data. For example, if the user is in a specific region, the acquisition unit will prioritize the acquisition of audio data related to that region. For example, if the user is on the move, the acquisition unit will prioritize the acquisition of highly relevant audio data based on the user's current location. For example, if the user is in a specific location, the acquisition unit will prioritize the acquisition of audio data related to that location. By prioritizing the acquisition of highly relevant data based on the user's geographical location information, more useful audio data can be acquired. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's geographical location information data into a generating AI, and the generating AI can select highly relevant data.

[0086] The acquisition unit can analyze the user's social media activity and acquire relevant data when acquiring audio data. For example, if the user is talking about a specific topic on social media, the acquisition unit can acquire audio data related to that topic. For example, if the user is participating in a specific event on social media, the acquisition unit can acquire audio data related to that event. For example, if the user is checking in to a specific location on social media, the acquisition unit can acquire audio data related to that location. In this way, relevant audio data can be acquired by analyzing the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's social media activity data into a generating AI, and the generating AI can select relevant data.

[0087] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is nervous, the analysis unit displays the analysis results in a simple and easy-to-understand format. For example, if the user is relaxed, the analysis unit displays detailed analysis results. For example, if the user is in a hurry, the analysis unit displays concise analysis results. In this way, by adjusting the presentation of the analysis based on the user's emotions, the analysis results can be provided in an easy-to-understand format for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0088] The analysis unit can adjust the level of detail of the analysis based on the importance of the audio data. For example, the analysis unit performs a detailed analysis for important audio data. For example, the analysis unit performs a standard analysis for general audio data. For example, the analysis unit performs a simplified analysis for unnecessary audio data. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the audio. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI, and the generating AI can adjust the level of detail of the analysis.

[0089] The analysis unit can apply different analysis algorithms depending on the category of the audio data during analysis. For example, the analysis unit applies a business-oriented analysis algorithm to business-related audio data. For example, the analysis unit applies a private-use analysis algorithm to private audio data. For example, the analysis unit applies a field-specific analysis algorithm to audio data related to a particular field of expertise. By applying different analysis algorithms depending on the category of the audio, more accurate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input audio data into a generating AI, and the generating AI can apply the analysis algorithm.

[0090] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the user is in a hurry, the analysis unit will perform a short, concise analysis. If the user is relaxed, the analysis unit will perform a detailed analysis. If the user is excited, the analysis unit will perform an analysis with visually stimulating effects. By adjusting the length of the analysis based on the user's emotions, the analysis unit can provide the user with an analysis result of an appropriate length. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0091] The analysis unit can determine the priority of analysis based on the start time of the call when analyzing audio data. For example, the analysis unit may prioritize the analysis of audio data immediately after the start of the call. For example, the analysis unit may analyze audio data in the middle of the call in a standard manner. For example, the analysis unit may simplify the analysis of audio data near the end of the call. By determining the priority of analysis based on the start time of the call, important audio data can be analyzed preferentially. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input call start time data into a generating AI, and the generating AI can determine the priority of analysis.

[0092] The analysis unit can adjust the order of analysis based on the relevance of the audio data. For example, the analysis unit may prioritize the analysis of important audio data. For example, the analysis unit may analyze general audio data in a standard manner. For example, the analysis unit may postpone the analysis of unnecessary audio data. By adjusting the order of analysis based on the relevance of the audio data, efficient analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input relevance data of the audio data into a generating AI, and the generating AI can adjust the order of analysis.

[0093] The judgment unit can estimate the user's emotions and adjust the judgment criteria based on the estimated user emotions. For example, if the user is tense, the judgment unit will make a judgment using strict criteria. For example, if the user is relaxed, the judgment unit will make a judgment using standard criteria. For example, if the user is in a hurry, the judgment unit will make a judgment quickly. By adjusting the judgment criteria based on the user's emotions, more appropriate judgments can be made. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input user emotion data into a generative AI, and the generative AI can estimate the emotions.

[0094] The judgment unit can improve the accuracy of its judgment based on the interrelationships between audio data. For example, the judgment unit compares audio data before and after a call to confirm consistency. For example, the judgment unit compares audio data from different parts of a call to confirm interrelationships. For example, the judgment unit confirms the consistency between the content of the call and the audio data. By improving the accuracy of the judgment based on the interrelationships between audio data, more accurate judgments become possible. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input data on the interrelationships of audio data into a generating AI, and the generating AI can improve the accuracy of the judgment.

[0095] The judgment unit can make judgments based on the content and context of a call when judging voice data. For example, if the content of the call is business-related, the judgment unit will make a judgment based on that context. For example, if the content of the call is private, the judgment unit will make a judgment based on that context. For example, if the content of the call is related to a specific field of expertise, the judgment unit will make a judgment based on that context. This makes it possible to make more appropriate judgments by making judgments based on the content and context of the call. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without using AI. For example, the judgment unit can input the content and context data of the call into a generating AI, and the generating AI can make the judgment.

[0096] The judgment unit can estimate the user's emotions and adjust the order in which the judgment results are displayed based on the estimated user emotions. For example, if the user is nervous, the judgment unit will prioritize displaying important results. For example, if the user is relaxed, the judgment unit will display the overall results in a balanced manner. For example, if the user is in a hurry, the judgment unit will display the results quickly. By adjusting the order in which the judgment results are displayed based on the user's emotions, it becomes possible to display results in a way that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using AI, for example, or not using AI. For example, the judgment unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0097] The judgment unit can perform judgments on audio data based on the geographical distribution of the audio. For example, the judgment unit may prioritize the judgment of audio data related to a specific region. For example, the judgment unit may compare geographically dispersed audio data to confirm consistency. For example, the judgment unit may evaluate the reliability of the audio data based on geographical information. This makes it possible to perform more accurate judgments by performing judgments based on the geographical distribution of the audio. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit may input geographical distribution data of the audio data into a generating AI, and the generating AI may perform the judgment.

[0098] The judgment unit can improve the accuracy of its judgment based on relevant literature for the audio data. For example, the judgment unit can improve the accuracy of its judgment by referring to an existing audio database. For example, the judgment unit can strengthen the criteria for judgment by referring to relevant research papers. For example, the judgment unit can improve the accuracy of its judgment by referring to the characteristics of known generated audio. By improving the accuracy of judgment based on relevant literature for the audio, more accurate judgment becomes possible. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit can input relevant literature data for the audio data into a generating AI, and the generating AI can improve the accuracy of the judgment.

[0099] The warning unit can estimate the user's emotions and adjust how warnings are displayed based on the estimated emotions. For example, if the user is tense, the warning unit displays a simple and highly visible warning. If the user is relaxed, the warning unit displays detailed warning information. If the user is in a hurry, the warning unit displays a warning quickly. By adjusting how warnings are displayed based on the user's emotions, it becomes possible to display warnings that are easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the warning unit may be performed using AI, for example, or not using AI. For example, the warning unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0100] The warning unit can select the optimal display method by referring to the user's past warning history when displaying a warning. For example, the warning unit can analyze the content of warnings the user has received in the past and select the optimal method when displaying similar warnings. For example, the warning unit can select a more prominent method when displaying warnings that the user has ignored in the past. For example, the warning unit can select a similar display method when displaying warnings that the user has responded to promptly in the past. In this way, the optimal warning display method can be selected by referring to the user's past warning history. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's past warning history data into a generating AI, and the generating AI can select the optimal display method.

[0101] The warning unit can adjust the content of the warning based on the user's current situation when displaying a warning. For example, if the user is driving, the warning unit will issue an audible warning. For example, if the user is in a meeting, the warning unit will issue a vibration warning. For example, if the user is relaxed, the warning unit will display detailed warning information. This allows for more appropriate warnings by adjusting the content of the warning based on the user's current situation. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's current situation data into a generating AI, and the generating AI can adjust the content of the warning.

[0102] The alert unit can estimate the user's emotions and determine the priority of alerts based on the estimated emotions. For example, if the user is tense, the alert unit will prioritize important alerts. If the user is relaxed, the alert unit will display a balanced mix of alerts. If the user is in a hurry, the alert unit will quickly display important alerts. This ensures that important alerts are prioritized by determining the priority of alerts based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit can input user emotion data into a generative AI, which can then perform emotion estimation.

[0103] The warning unit can select the optimal display method based on the user's device information when displaying a warning. For example, if the user is using a smartphone, the warning unit will display a warning that is appropriate for the screen size. If the user is using a tablet, the warning unit will display a warning optimized for a larger screen. If the user is using a smartwatch, the warning unit will display a concise and highly visible warning. By selecting the optimal display method based on the user's device information, it becomes possible to display warnings that are easy for the user to see. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input user device information data into a generating AI, and the generating AI can select the optimal display method.

[0104] The warning unit can provide multilingual warnings according to the user's language settings when displaying a warning. For example, the warning unit can automatically set the warning language based on the language settings of the user's device. For example, the warning unit can provide a language switching function if the user uses multiple languages. For example, if the user selects a specific language, the warning unit can provide a warning in that language. This makes it possible to provide warnings that are easy for the user to understand by providing multilingual warnings according to the user's language settings. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can input the user's language setting data into a generating AI, and the generating AI can provide multilingual warnings.

[0105] The termination unit can estimate the user's emotions and adjust the timing of the call termination based on the estimated emotions. For example, if the user is tense, the termination unit will terminate the call quickly. If the user is relaxed, the termination unit will terminate the call at an appropriate time. If the user is in a hurry, the termination unit will terminate the call immediately. By adjusting the timing of the call termination based on the user's emotions, the call can be terminated at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the termination unit may be performed using AI or not using AI. For example, the termination unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0106] The termination unit can select the optimal termination method by referring to the user's past call history when a call ends. For example, if the user has ended a call quickly in the past, the termination unit will terminate the call in a similar manner. For example, if the user has continued a call for a long time in the past, the termination unit will terminate the call at an appropriate time. For example, if the user has ended a call during a specific time period in the past, the termination unit will terminate the call in a manner that is optimal for that time period. In this way, the optimal termination method can be selected by referring to the user's past call history. Some or all of the above processing in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input the user's past call history data into a generating AI, and the generating AI can select the optimal termination method.

[0107] The termination unit can adjust the termination method based on the user's current situation when a call ends. For example, if the user is driving, the termination unit will notify the user of the call ending by voice. For example, if the user is in a meeting, the termination unit will notify the user of the call ending by vibration. For example, if the user is relaxing, the termination unit will display detailed termination information. This allows for a more appropriate termination by adjusting the termination method based on the user's current situation. Some or all of the above processing in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input the user's current situation data into a generating AI, which can then adjust the termination method.

[0108] The termination unit can estimate the user's emotions and determine the priority of call termination based on the estimated emotions. For example, if the user is tense, the termination unit will prioritize ending important calls. If the user is relaxed, the termination unit will end calls in a balanced manner. If the user is in a hurry, the termination unit will quickly end important calls. This allows important calls to be terminated preferentially by determining the priority of call termination based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the termination unit may be performed using AI or not using AI. For example, the termination unit can input user emotion data into a generative AI, which can then perform emotion estimation.

[0109] The termination unit can select the optimal termination method based on the user's device information when a call ends. For example, if the user is using a smartphone, the termination unit provides an termination method that is appropriate for the screen size. For example, if the user is using a tablet, the termination unit provides an termination method optimized for a large screen. For example, if the user is using a smartwatch, the termination unit provides a concise and highly visible termination method. By selecting the optimal termination method based on the user's device information, it becomes possible to provide an appropriate termination method for the user. Some or all of the above processing in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input the user's device information data into a generating AI, and the generating AI can select the optimal termination method.

[0110] The termination unit can provide a scheduled termination method based on the user's calendar information when a call ends. For example, the termination unit refers to appointments registered in the user's calendar and terminates the call at an appropriate time. For example, the termination unit prioritizes terminating calls related to specific events based on the user's calendar information. For example, the termination unit provides an optimal termination method tailored to the appointment based on the user's calendar information. This enables an appropriate termination for the user by providing an appointment-based termination method based on the user's calendar information. Some or all of the above processing in the termination unit may be performed using AI, for example, or without AI. For example, the termination unit can input the user's calendar information data into a generating AI, and the generating AI can provide an appointment-based termination method.

[0111] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0112] The voice call security system may further include a summarization unit that estimates the user's emotions and summarizes the content of the call based on the estimated emotions. For example, if the user is nervous, the summarization unit will provide a concise summary of the key points. If the user is relaxed, the summarization unit will provide a detailed summary. If the user is in a hurry, the summarization unit will provide a quick summary of the main points. This makes it possible to provide information that is easy for the user to understand by summarizing the content of the call based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI or not using AI. For example, the summarization unit can input the user's emotion data into the generative AI, and the generative AI can perform emotion estimation.

[0113] The voice call security system may further include a suggestion unit that analyzes the user's past call history and proposes the optimal timing for starting a call. For example, if the user has made long calls in the past, the suggestion unit may suggest the optimal time to start a call. For example, if the user has made short calls in the past, the suggestion unit may suggest a time to start a call quickly. For example, if the user has made calls in the past during a specific time period, the suggestion unit may suggest the optimal timing for starting a call during that time period. In this way, the optimal timing for starting a call can be suggested by analyzing the user's past call history. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the user's past call history data into a generating AI, and the generating AI can then suggest the optimal timing for starting a call.

[0114] The voice call security system may further include a recording unit that estimates the user's emotions and automatically records the content of the call based on the estimated emotions. For example, if the user is nervous, the recording unit may prioritize recording important parts. For example, if the user is relaxed, the recording unit may record the overall content in a balanced manner. For example, if the user is in a hurry, the recording unit may quickly record the necessary parts. This ensures that important information is not missed by automatically recording the content of the call based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recording unit may be performed using AI or not using AI. For example, the recording unit can input user emotion data into a generative AI, which can then perform emotion estimation.

[0115] The voice call security system may further include a translation unit that estimates the user's emotions and translates the content of the call based on the estimated emotions. For example, if the user is nervous, the translation unit will provide a concise and easy-to-understand translation. For example, if the user is relaxed, the translation unit will provide a detailed translation. For example, if the user is in a hurry, the translation unit will provide a quick and to-the-point translation. This makes it possible to provide information that is easy for the user to understand by translating the content of the call based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input user emotion data into a generative AI, and the generative AI can perform emotion estimation.

[0116] The voice call security system may further include a filtering unit that estimates the user's emotions and filters the call content based on the estimated emotions. For example, if the user is tense, the filtering unit prioritizes filtering important information. If the user is relaxed, the filtering unit filters overall information in a balanced manner. If the user is in a hurry, the filtering unit filters out the information that is needed quickly. This ensures that important information is not missed by filtering the call content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filtering unit may be performed using AI or not using AI. For example, the filtering unit can input user emotion data into the generative AI, which can then perform emotion estimation.

[0117] The voice call security system may further include a summarization unit that automatically summarizes the content of a call. The summarization unit may, for example, concisely summarize the important points of the call. The summarization unit may, for example, summarize the overall content of the call in a balanced manner. The summarization unit may, for example, provide a summary that quickly summarizes the main points of the call. This makes it possible to provide information that is easy for the user to understand by automatically summarizing the content of the call. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can input the content data of the call into a generating AI, and the generating AI can perform the summarization.

[0118] The voice call security system may further include a translation unit that automatically translates the content of the call. The translation unit may, for example, provide a concise translation of the call content. The translation unit may, for example, provide a balanced translation of the overall content of the call. The translation unit may, for example, quickly translate the main points of the call. This makes it possible to provide information that is easy for the user to understand by automatically translating the content of the call. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input the call content data into a generating AI, and the generating AI can perform the translation.

[0119] The voice call security system may further include a filtering unit that automatically filters the content of calls. The filtering unit may, for example, prioritize filtering important information from the call. The filtering unit may, for example, filter the overall information of the call in a balanced manner. The filtering unit may, for example, quickly filter the key points of the call. This ensures that important information is not missed by automatically filtering the content of the call. Some or all of the above processing in the filtering unit may be performed using AI, for example, or without AI. For example, the filtering unit can input the call content data into a generating AI, and the generating AI can perform the filtering.

[0120] The voice call security system may further include a classification unit that automatically categorizes the content of calls. The classification unit may, for example, classify the content of calls into business-related, private-related, or other categories. The classification unit may, for example, classify the content of calls based on specific topics. The classification unit may, for example, classify the content of calls based on importance. This enables the provision of information that is easy for users to organize by automatically classifying the content of calls. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit may input the content of calls into a generating AI, and the generating AI may perform the classification.

[0121] The voice call security system may further include an analysis unit that automatically analyzes the content of calls. The analysis unit may, for example, analyze the content of calls in detail and extract important points. The analysis unit may, for example, analyze the overall content of calls in a balanced manner. The analysis unit may, for example, quickly analyze the key points of calls. This enables the provision of information that is easy for users to understand by automatically analyzing the content of calls. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the call content data into a generating AI, and the generating AI can perform the analysis.

[0122] The following briefly describes the processing flow for example form 2.

[0123] Step 1: The acquisition unit acquires audio data. For example, the acquisition unit acquires audio data from a call in real time and transmits that data to the analysis unit. The acquisition unit also uses noise cancellation technology to remove background noise during the call and acquires clear audio data. Step 2: The analysis unit analyzes the audio data acquired by the acquisition unit. The analysis unit can, for example, analyze the frequency components and temporal variations of the audio. It extracts audio features using Fourier transforms and time-domain analysis. Step 3: The determination unit determines whether or not the speech was generated based on the data analyzed by the analysis unit. The determination unit determines whether or not the speech was generated using the training data of the generation AI or known characteristics of generated speech. Step 4: The warning unit issues a warning to the user based on the result determined by the judgment unit. For example, if the warning unit determines that the sound is generated audio, it displays a warning message to the user or notifies them by voice. Step 5: The termination unit terminates the call as necessary. For example, if it is determined that the call is generated voice, the termination unit will automatically terminate the call, or terminate the call based on user instructions.

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0126] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0127] Each of the multiple elements described above, including the acquisition unit, analysis unit, determination unit, warning unit, and termination unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the acquisition unit acquires voice data using the microphone 38B of the smart device 14 and transmits it to the data processing unit 12 via the control unit 46A. The analysis unit analyzes the voice data using the identification processing unit 290 of the data processing unit 12. The determination unit determines, for example, whether the voice was generated based on the data analyzed by the identification processing unit 290 of the data processing unit 12. The warning unit issues a warning to the user using the display 40A or speaker 40B of the smart device 14. The termination unit, for example, issues an instruction to terminate the call via the identification processing unit 290 of the data processing unit 12, and terminates the call via the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0128] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0129] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0130] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0131] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0132] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0134] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0135] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0136] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0137] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0138] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0140] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0142] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0143] Each of the multiple elements described above, including the acquisition unit, analysis unit, determination unit, warning unit, and termination unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the acquisition unit acquires voice data using the microphone 238 of the smart glasses 214 and transmits it to the data processing unit 12 via the control unit 46A. The analysis unit analyzes the voice data using, for example, the identification processing unit 290 of the data processing unit 12. The determination unit determines, for example, whether or not the voice was generated based on the data analyzed by the identification processing unit 290 of the data processing unit 12. The warning unit issues a warning to the user using, for example, the speaker 240 of the smart glasses 214. The termination unit, for example, issues an instruction to terminate the call via the identification processing unit 290 of the data processing unit 12, and terminates the call via the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0144] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0145] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0146] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0147] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0148] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0150] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0151] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0152] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0153] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0154] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0155] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0156] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0158] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0159] Each of the multiple elements described above, including the acquisition unit, analysis unit, determination unit, warning unit, and termination unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit acquires voice data using the microphone 238 of the headset terminal 314 and transmits it to the data processing unit 12 via the control unit 46A. The analysis unit analyzes the voice data using the identification processing unit 290 of the data processing unit 12. The determination unit determines, for example, whether the voice was generated based on the data analyzed by the identification processing unit 290 of the data processing unit 12. The warning unit issues a warning to the user using the speaker 240 of the headset terminal 314. The termination unit issues an instruction to terminate the call via the identification processing unit 290 of the data processing unit 12, for example, and terminates the call via the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0160] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0161] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0162] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0163] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0164] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0166] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0167] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0168] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0169] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0170] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0171] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0172] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0173] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0174] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0175] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0176] Each of the multiple elements described above, including the acquisition unit, analysis unit, determination unit, warning unit, and termination unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit acquires voice data using the microphone 238 of the robot 414 and transmits it to the data processing unit 12 via the control unit 46A. The analysis unit analyzes the voice data using, for example, the identification processing unit 290 of the data processing unit 12. The determination unit determines, for example, whether or not the voice was generated based on the data analyzed by the identification processing unit 290 of the data processing unit 12. The warning unit issues a warning to the user using, for example, the speaker 240 of the robot 414. The termination unit, for example, issues an instruction to terminate the call via the identification processing unit 290 of the data processing unit 12, and terminates the call via the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0177] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0178] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0179] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0180] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0181] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0182] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0184] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0185] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0186] 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.

[0187] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0188] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0189] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0190] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0191] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0192] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0193] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0194] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0195] (Note 1) An acquisition unit that acquires audio data, An analysis unit analyzes the audio data acquired by the acquisition unit, A determination unit that determines whether or not the audio was generated based on the data analyzed by the analysis unit, A warning unit that issues a warning to the user based on the result determined by the determination unit, It includes an termination unit that terminates the call as needed. A system characterized by the following features. (Note 2) The acquisition unit is, Acquire call audio data in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Analyze the frequency components and temporal variations of audio. The system described in Appendix 1, characterized by the features described herein. (Note 4) The determination unit, This determines whether the speech was generated using the AI's training data or known characteristics of generated speech. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned warning unit is If it is determined that the audio is generated, a warning message will be displayed to the user. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned termination section is, Automatically end the call if necessary. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, The system estimates the user's emotions and adjusts the timing of voice data acquisition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, Before a call begins, the system analyzes the user's past call history and selects the most suitable method for obtaining it. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, When acquiring voice data, filtering is performed based on the content and context of the call. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, It estimates the user's emotions and determines the priority of audio data to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, When acquiring audio data, the system prioritizes acquiring data that is highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The acquisition unit is, When acquiring voice data, the system analyzes the user's social media activity and retrieves relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, When analyzing audio data, adjust the level of detail of the analysis based on the importance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing audio data, different analysis algorithms are applied depending on the audio category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, When analyzing voice data, the analysis priority is determined based on the start time of the call. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, When analyzing audio data, the order of analysis is adjusted based on the relevance of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 19) The determination unit, The system estimates the user's emotions and adjusts the criteria for judgment based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The determination unit, When analyzing audio data, the accuracy of the analysis is improved based on the interrelationships between the audio elements. The system described in Appendix 1, characterized by the features described herein. (Note 21) The determination unit, When analyzing audio data, the analysis is performed based on the content and context of the call. The system described in Appendix 1, characterized by the features described herein. (Note 22) The determination unit, It estimates the user's emotions and adjusts the order in which the judgment results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The determination unit, When analyzing audio data, the analysis is performed based on the geographical distribution of the audio. The system described in Appendix 1, characterized by the features described herein. (Note 24) The determination unit, When analyzing audio data, improve the accuracy of the analysis based on relevant literature related to the audio. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned warning unit is It estimates the user's emotions and adjusts how warnings are displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned warning unit is When displaying a warning, the system will refer to the user's past warning history to select the most appropriate display method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned warning unit is When a warning is displayed, the content of the warning is adjusted based on the user's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned warning unit is The system estimates the user's emotions and prioritizes warnings based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned warning unit is When a warning is displayed, the system selects the optimal display method based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned warning unit is When a warning is displayed, the system provides multilingual warnings according to the user's language settings. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned termination section is, The system estimates the user's emotions and adjusts the timing of call termination based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned termination section is, At the end of a call, the system will refer to the user's past call history to select the most appropriate termination method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned termination section is, When a call ends, the termination method will be adjusted based on the user's current status. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned termination section is, The system estimates the user's emotions and determines the priority for ending calls based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned termination section is, At the end of a call, the system selects the optimal termination method based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned termination section is, When a call ends, the system provides a scheduled termination method based on the user's calendar information. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0196] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An acquisition unit that acquires audio data, An analysis unit analyzes the audio data acquired by the acquisition unit, A determination unit that determines whether or not the audio was generated based on the data analyzed by the analysis unit, A warning unit that issues a warning to the user based on the result determined by the determination unit, It includes an termination unit that terminates the call as needed. A system characterized by the following features.

2. The acquisition unit is, Acquire call audio data in real time. The system according to feature 1.

3. The aforementioned analysis unit, Analyze the frequency components and temporal variations of audio. The system according to feature 1.

4. The determination unit, This determines whether the speech was generated using the AI's training data or known characteristics of generated speech. The system according to feature 1.

5. The aforementioned warning unit is If it is determined that the audio is generated, a warning message will be displayed to the user. The system according to feature 1.

6. The aforementioned termination section is, Automatically end the call if necessary. The system according to feature 1.

7. The acquisition unit is, The system estimates the user's emotions and adjusts the timing of voice data acquisition based on the estimated emotions. The system according to feature 1.

8. The acquisition unit is, Before a call begins, the system analyzes the user's past call history and selects the most suitable method for obtaining it. The system according to feature 1.

9. The acquisition unit is, When acquiring voice data, filtering is performed based on the content and context of the call. The system according to feature 1.

10. The acquisition unit is, It estimates the user's emotions and determines the priority of audio data to acquire based on the estimated user emotions. The system according to feature 1.

Images