system

Abstract

We provide the system. [Solution] A system including means for detecting incoming calls from phone numbers not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples found on the internet, and means for issuing a warning based on the comparison results.

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 executed by at least one processor, the method comprising the steps of: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence associated with a description related to a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a problem that when elderly people or ordinary people answer a call such as a "it's me" scam call or a sales call, they may be led by the other party's pace and fail to notice that it is a scam, or end up purchasing unnecessary products.

Means for Solving the Problems

[0005] The present invention detects an incoming call from a telephone number not registered in the telephone directory, and analyzes the voice thereof. The analysis result is compared with cases on the Internet, and based on the comparison result, a warning such as "Is this a scam call?" or "Is this a sales call for a product you intend to purchase?" is issued. This makes it possible for the user to prevent falling victim to scams or purchasing unnecessary products in advance.

Brief Description of the Drawings

[0006] [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 the data processing device and 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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 1 of Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2. [Figure 15] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 3 of Example 3. [Figure 16]This is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3. [Figure 17] This is a sequence diagram showing the processing flow of the data processing system in Example 1 of the Form 1 when an emotion engine is combined. [Figure 18] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] This is a sequence diagram showing the processing flow of a data processing system in another embodiment. [Modes for carrying out the invention]

[0007] 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.

[0008] First, let's explain the terminology used in the following explanation.

[0009] 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®).

[0010] 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.

[0011] In the following embodiments, the storage with a reference sign is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include a flash memory (SSD (Solid State Drive)), a magnetic disk (for example, a hard disk), or a magnetic tape, and the like.

[0012] In the following embodiments, the communication I / F (Interface) with a reference sign is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0013] 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, may be only B, or may be a combination of A and B. Further, in the present specification, when three or more matters are expressed in combination by "and / or", the same concept as that for "A and / or B" is applied.

[0014] [First Embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] As shown in FIG. 1, the data processing system 10 includes a data processing apparatus 12 and a smart device 14. An example of the data processing apparatus 12 includes a server.

[0017] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0019] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0021] 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.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] The 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0026] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0027] "Example of form 1"

[0028] One embodiment of this system is one that can be implemented in communication devices such as smartphones and personal computers. This system has a function to detect incoming calls from phone numbers not registered in the phone book. When a call comes in, the system analyzes the voice and compares the analysis results with examples found online. Based on the comparison results, it then issues a warning to the user, such as "Is this a scam call?" or "Is this a sales call from someone intending to buy something?" The warning is issued in the form of a push notification or similar, allowing the user to check it immediately.

[0029] "Example of form 2"

[0030] As a concrete example, consider a case where an elderly person is using a smartphone. When a call comes in from an unregistered phone number, the system of this invention analyzes the voice and compares the analysis results with examples found online. Then, it sends a push notification warning, "Is this a scam call?" This can significantly reduce the risk of elderly people encountering scams such as "ore-ore" (impersonation) scams.

[0031] The following describes the processing flow for each example of the form.

[0032] "Example of form 1"

[0033] Step 1: A system implemented in communication devices such as smartphones and personal computers detects incoming calls from phone numbers not registered in the phonebook.

[0034] Step 2: The system analyzes the incoming audio. This analysis is performed using speech recognition technology.

[0035] Step 3: Compare the analysis results with examples found online. This comparison is done by comparing the patterns and characteristics of the audio.

[0036] Step 4: Based on the comparison results, a warning is issued to the user, such as "Is this a scam call?" or "Is this a sales call from someone with an intention to buy?". This warning is issued in the form of a push notification or similar.

[0037] "Example of form 2"

[0038] Step 1: If an elderly person is using a smartphone, and they receive a call from an unregistered phone number, the system of the present invention analyzes the voice of that call.

[0039] Step 2: Compare the analysis results with examples found online. This comparison is done by comparing the patterns and characteristics of the audio.

[0040] Step 3: Send a push notification warning, "Is this a scam call?" This significantly reduces the risk of elderly people falling victim to scams such as "It's me" scams.

[0041] (Example 1)

[0042] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0043] In today's communication environment, there has been an increase in communications originating from unregistered identifiers, leading to fraudulent activities and unwanted sales activities that pose a significant problem for users. Traditional methods have made it difficult to effectively identify these communications and provide warnings to users. Therefore, there is a need for a system that can quickly and accurately analyze communications from unregistered identifiers and provide appropriate warnings to users.

[0044] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0045] In this invention, the server includes means for detecting communications from unregistered identification information in a communication device, means for analyzing the voice information of the communications, and means for comparing the analysis results with examples in the information resource. This makes it possible to quickly analyze communications from unregistered identification information and warn users of the possibility of fraudulent activity or unnecessary sales activities.

[0046] "Communication equipment" refers to electronic devices used for transmitting and receiving voice and data, and includes telephones, computers, and other similar devices.

[0047] "Identification information" refers to information used to identify the source of a communication, and includes things like telephone numbers and IP addresses.

[0048] "Voice information" refers to voice data transmitted and received during communication, and is the subject of analysis.

[0049] "Analysis" refers to the process of converting audio information into text data and understanding its content.

[0050] "Information resources" refer to databases and case studies available on the internet, which are used to compare and contrast analysis results.

[0051] "Warning information" refers to notifications generated based on analysis results, informing users of potential fraudulent activity or unnecessary sales activities.

[0052] "Notification" refers to a means of conveying warning information to users, and includes push notifications and alert messages.

[0053] As an embodiment of this invention, a system is constructed in a communication device that detects communications from unregistered identification information in the phone book and analyzes the voice information. When a terminal receives a communications from unregistered identification information, it records the voice and sends it to a server. The server converts the voice data into text using voice analysis software. In this process, the Google® Cloud Speech-to-Text API can be used.

[0054] The server uses a generative AI model to compare the converted text with examples in the information resources. Specifically, it uses OpenAI's GPT model to determine whether the text is related to fraudulent activity or unwanted sales activities. In this process, the server inputs the prompt "Is this call potentially fraudulent?" into the generative AI model.

[0055] Based on the analysis results, the server generates warning information and sends it to the device. The device displays the warning to the user via push notification. This allows the user to quickly understand if communications from unregistered identification information may be fraudulent or related to unwanted sales activities.

[0056] As a concrete example, if a user receives a call from "0123-456-7890," the device records the audio and sends it to the server. The server converts the audio to text and inputs the prompt "Is this call possibly a scam?" into a generating AI model. The generating AI model compares this with past data and generates a warning, "Is this a scam call?" The warning is sent to the user's device as a push notification, allowing the user to check it immediately.

[0057] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0058] Step 1:

[0059] The terminal detects communications originating from unregistered identifiers in the phonebook. It receives the communication's identifier as input and compares it against the phonebook. The output is the identification information confirmed to be unregistered. This process allows for the identification of unregistered communications.

[0060] Step 2:

[0061] The terminal records audio from communications originating from unregistered identification information. It receives audio data during communication as input and saves it as a digital audio file using a recording device. The recorded audio data is obtained as output. This operation prepares the audio data necessary for subsequent analysis.

[0062] Step 3:

[0063] The terminal sends the recorded audio data to the server. It receives the recorded audio data as input and sends it to the server via the communication network. The audio data is then transferred to the server as output. This process provides the server with the audio data for analysis.

[0064] Step 4:

[0065] The server uses speech analysis software to convert speech data into text. It uses speech data received from the terminal as input and converts it into text data using the Google Cloud Speech-to-Text API. The output is the converted text data. This process converts speech information into a parseable text format.

[0066] Step 5:

[0067] The server analyzes text data using a generative AI model and compares it with examples in the information resources. It uses the transformed text data as input and performs analysis using OpenAI's GPT model. The analysis results are obtained as output. This process allows for determining whether the text data is related to fraudulent activity or unwanted sales activities.

[0068] Step 6:

[0069] The server generates warning information based on the analysis results. It uses the analysis results as input to generate a warning message. The output is the warning information itself. This process prepares the server to provide appropriate warnings to the user.

[0070] Step 7:

[0071] The server sends the generated warning information to the terminal. It uses the warning information as input and transmits it to the terminal via the communication network. The warning information is then transferred to the terminal as output. This process provides the user with the warning information.

[0072] Step 8:

[0073] The device displays the received warning information to the user as a push notification. It uses the warning information received from the server as input and displays it to the user using the device's notification function. The user confirms the warning information as output. This process allows the user to quickly receive warnings about communications from unregistered identification information.

[0074] (Application Example 1)

[0075] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0076] In modern society, the risk of fraud and illegal sales calls from unregistered phone numbers is increasing. While users are required to respond quickly and accurately to such calls, traditional methods make this decision difficult.

[0077] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0078] In this invention, the server includes means for detecting incoming calls from unregistered phone numbers, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, means for speech recognition to convert the audio into text, means for analyzing the possibility of fraud using a generative AI model, and means for issuing a warning based on the analysis results. This enables users to quickly determine the possibility of fraud when receiving calls from unregistered phone numbers and take appropriate action.

[0079] "Unregistered phone numbers" refer to numbers that are not stored on the user's communication device and for which specific information is not registered when an incoming call is received.

[0080] "Means for detecting incoming calls" refers to a device or program in a communication device that has the function of sensing an incoming call from an external source and acquiring that information.

[0081] "Means for analyzing speech" refers to technology or equipment for processing received speech data and understanding or classifying its content.

[0082] "Case examples on information networks" refers to a collection of past similar events or data that exist on the internet or other digital networks.

[0083] "Speech recognition means" refers to a technology or device for converting speech data into text data.

[0084] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate a specific output based on input data.

[0085] "Means for analyzing the possibility of fraud" refers to technology or equipment used to determine whether the content of received data constitutes fraudulent activity.

[0086] A "means of issuing a warning" refers to a device or program that has a notification function for alerting or providing information to the user.

[0087] The system for implementing this invention mainly consists of a server and a user terminal. The server detects incoming calls from numbers not registered in the phonebook and runs a program to analyze the voice. For voice analysis, the Google Cloud Speech-to-Text API is used to convert the voice data into text data. The converted text data is analyzed using the generative AI model OpenAI GPT to determine the likelihood of fraud.

[0088] The user's device receives a push notification if there is a potential scam based on analysis results from the server. This warning is designed to allow the user to respond quickly.

[0089] For example, if a user receives a call from "0120-XXXX-XXXX", the server converts the audio into text and inputs the following prompt into the AI ​​generation model: "Is this text potentially a scam? Content: You have won a special campaign." If the AI ​​generation model determines that it is "highly likely to be a scam," a warning message "This may be a scam. Please be careful." is sent to the user's device.

[0090] In this way, users can quickly determine the possibility of fraud when receiving calls from unregistered numbers and take appropriate action.

[0091] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0092] Step 1:

[0093] The server receives incoming call information from the user's terminal. The input is incoming call data from a call number not registered in the phonebook. The server prepares to analyze this data.

[0094] Step 2:

[0095] The server receives incoming audio data and converts it to text using the Google Cloud Speech-to-Text API. The input is audio data, and the output is text data. This conversion makes the audio content available as text information.

[0096] Step 3:

[0097] The server inputs text data into the OpenAI GPT generative AI model and analyzes its likelihood of being a scam. The input is text data, and the output is the analysis result regarding the likelihood of fraud. The server generates a prompt sentence and asks the model, "Is this text likely to be a scam?"

[0098] Step 4:

[0099] The server receives the analysis results from the generated AI model and generates a warning based on those results. The input is the analysis result, and the output is the warning message. The server creates a warning such as "This may be a scam. Please be careful." if there is a high probability of fraud.

[0100] Step 5:

[0101] The server sends the generated warning message as a push notification to the user's device. The input is the warning message, and the output is the notification displayed on the user's device. The user receives this notification and can take appropriate action regarding the incoming message.

[0102] (Example 2)

[0103] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0104] Many users, including the elderly, are vulnerable to unauthorized connections from unregistered identification numbers. In particular, there is a growing need for effective measures to mitigate these risks, especially given the increasing prevalence of fraudulent activities and unethical sales practices.

[0105] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0106] In this invention, the server includes means for detecting connections from unregistered identification numbers in the communication device, means for acquiring audio information of said connections, and means for converting said audio information into text information. This makes it possible to quickly detect the possibility of fraudulent activity from unregistered identification numbers and notify the user of a warning.

[0107] "Communication equipment" refers to electronic devices used for sending and receiving voice and data, including telephones and smartphones.

[0108] An "identification number" is a unique number assigned to a communication device, such as a telephone number or IP address.

[0109] "Connection" refers to the establishment of a communication link between communication devices, including the initiation of voice calls and data communications.

[0110] "Voice information" refers to voice data transmitted via communication devices, including the content of phone calls.

[0111] "Textual information" refers to text data obtained by converting audio information, and is generated using speech recognition technology.

[0112] "Analysis" refers to the process of processing acquired data and understanding its content and meaning.

[0113] An "information database" is a collection of data that stores past cases and related information, and is used to verify analysis results.

[0114] A "warning" is a notification intended to alert users and may include information about the possibility of fraudulent activity.

[0115] "Notification" refers to a means of conveying information to users, including push notifications and alert messages.

[0116] To implement this invention, the terminal first detects a connection from an unregistered identification number. When a connection is established, the terminal records the call content and sends it to the server as audio information. The server converts the received audio information into text information using the Google Cloud Speech-to-Text API. This API provides highly accurate speech recognition and quickly converts speech to text.

[0117] Next, the server inputs the converted text information into a generative AI model. Specifically, it uses a model such as OpenAI's GPT model and inputs the prompt "Is this phone call potentially a scam?". The generative AI model analyzes the text information and determines the likelihood of it being a scam.

[0118] Based on the analysis results, the server generates a warning. The warning includes the message, "Is this potentially fraudulent activity?", and is immediately sent as a push notification to the device. By receiving this notification, users can become more vigilant against potentially fraudulent connections.

[0119] As a concrete example, if a user receives a call from an unregistered number, the device automatically records the audio and sends it to a server. The server converts the audio to text and inputs prompt text into a generative AI model. Based on the model's analysis, the server sends a warning to the user. This entire process allows users to anticipate the risk of fraudulent calls and take appropriate action.

[0120] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0121] Step 1:

[0122] The terminal detects connections from unregistered identification numbers. Once a connection is established, the terminal records the call and prepares the data as audio information. This audio information becomes input for the next processing step.

[0123] Step 2:

[0124] The device sends the recorded audio information to the server. The server converts the received audio information into text using the Google Cloud Speech-to-Text API. This conversion process involves speech recognition to convert the audio data into text data. The output is text information for analysis.

[0125] Step 3:

[0126] The server inputs the converted text information into the generating AI model. Specifically, it uses the prompt "Is this phone call potentially a scam?" to request analysis from the generating AI model. The model analyzes the text information and determines the likelihood of it being a scam. This analysis result becomes the output for the next step.

[0127] Step 4:

[0128] The server generates a warning based on the analysis results obtained from the generated AI model. The warning includes the message "Is this a possible case of fraudulent activity?" and is immediately sent as a push notification to the device. This notification is what is output to the user.

[0129] Step 5:

[0130] The user checks the warning notification received from their device. Based on this notification, the user can become more vigilant against potentially fraudulent connections and take appropriate action if necessary.

[0131] (Application Example 2)

[0132] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0133] There is a need for a means to enable users, including the elderly, to quickly assess the risk of fraud and illegal transactions from connections made using unregistered identification information, and to prevent damage before it occurs. However, conventional technologies have made it difficult to analyze these risks in real time and provide appropriate warnings.

[0134] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0135] In this invention, the server includes means for detecting connections from unregistered identification information in the communication device, means for analyzing the voice information of the connection, and means for comparing the analysis results with examples on the information network. This enables users to determine the possibility of fraud or illegal transactions in real time and receive a warning quickly.

[0136] "Communication equipment" refers to devices used for sending and receiving voice and data, and includes smartphones and computers.

[0137] "Unregistered identification information" refers to information such as phone numbers and IDs that are not registered in the user's database.

[0138] "Connection" refers to the exchange of voice and data that takes place via communication devices.

[0139] "Voice information" refers to voice data from phone calls or recordings, and is the subject of analysis.

[0140] "Analysis" refers to the process of converting audio information into text data and then analyzing its content.

[0141] An "information network" refers to the internet and other digital networks used for matching and searching data.

[0142] "Case examples" refer to specific cases of fraud or illegal transactions that have been recorded in the past.

[0143] A "warning" refers to a notification or message intended to inform users of potential fraud or misconduct.

[0144] "Real-time" refers to processing and analysis being performed almost instantly, meaning that delays are minimized.

[0145] The system for implementing this invention primarily uses a communication device, a server, and an information network. The communication device is a terminal such as a smartphone, which detects connections from unregistered identification information. The server analyzes the connected voice information and converts it into text data using a generative AI model. This analysis uses a voice analysis library such as the Google Cloud Speech-to-Text API.

[0146] The analyzed text data is compared against a case database on the information network. The database records past cases of fraud and illicit transactions, and the server uses this to determine the likelihood of fraud. If fraud is determined to be possible, the server sends an alert to the user's communication device using a push notification service (e.g., Firebase Cloud Messaging).

[0147] For example, if a user receives a call from an unregistered number and the caller says, "Your bank account is at risk," the server analyzes the audio and compares it to a database of fraud cases. If it is determined that there is a high probability of fraud, it sends a warning to the user asking, "Is this a scam?"

[0148] An example of a prompt to input into the generating AI model is: "Please determine if this voice message is potentially fraudulent. Message content: 'Your bank account is at risk.'"

[0149] In this way, users can assess the risk of fraud and illegal transactions in real time and take swift action.

[0150] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0151] Step 1:

[0152] The terminal detects connections from unregistered identification information. The input is the incoming phone number, and the output is the result of determining that it is unregistered. The terminal compares it with the phonebook database, and if it is unregistered, proceeds to the next step.

[0153] Step 2:

[0154] The terminal collects connected audio information and sends it to the server. The input is the audio data during the call, and the output is the transfer of the audio data to the server. The terminal captures the audio data in real time and streams it to the server.

[0155] Step 3:

[0156] The server analyzes the received audio data and converts it into text data. The input is audio data sent from the terminal, and the output is text data. The server uses the Google Cloud Speech-to-Text API to convert the audio to text.

[0157] Step 4:

[0158] The server analyzes text data using a generative AI model to determine the likelihood of fraud. The input is the transformed text data, and the output is the evaluation result of the likelihood of fraud. The server inputs the text data as a prompt into the generative AI model and evaluates the likelihood of fraud.

[0159] Step 5:

[0160] If the server determines that there is a high probability of fraud, it generates a push notification and sends it to the device. The input is the result of the fraud probability assessment, and the output is a warning message. The server uses Firebase Cloud Messaging to send the user a warning asking, "Is this a scam?"

[0161] Step 6:

[0162] The user reviews the warning message displayed on the device and, if necessary, ends the call or takes further action. The input is the warning message displayed on the device, and the output is the user's action. The user either ends the call after receiving the warning or takes additional confirmation.

[0163] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0164] "Example of form 1"

[0165] One embodiment of the present invention is a system incorporating an emotion engine. This system detects incoming calls from phone numbers not registered in the phone book and analyzes the incoming call's audio. It compares the analysis results with online examples and issues a warning based on the comparison. Furthermore, this system includes an emotion engine that recognizes the user's emotions. The emotion engine recognizes the user's emotions from their tone of voice and word choice, and changes the content and display method of the warning according to those emotions. "Example 2"

[0166] As a concrete example, consider a scenario where an elderly person is using a smartphone. When a call comes in from an unregistered phone number, the system of this invention analyzes the voice. The analysis results are compared with examples found online, and a warning is issued, such as, "Could this be a scam call?" Furthermore, the emotion engine recognizes the elderly person's emotions from their tone of voice and word choice. For example, if it detects that the elderly person is feeling anxious or frightened, the warning is made more specific, such as, "This is likely a scam. Please be careful," and the warning display method is changed to larger font and stronger vibration. This significantly reduces the risk of elderly people encountering scams such as "ore-ore" (impersonation) scams.

[0167] The following describes the processing flow for each example of the form.

[0168] "Example of form 1"

[0169] Step 1: Detect incoming calls from phone numbers not registered in the phonebook.

[0170] Step 2: Analyze the incoming call audio.

[0171] Step 3: Compare the analysis results with examples found online.

[0172] Step 4: Issue a warning based on the comparison results.

[0173] Step 5: Recognize the user's emotions from their tone of voice and word choice.

[0174] Step 6: Change the content and display method of the warning according to the emotion.

[0175] "Example of form 2"

[0176] Step 1: If an elderly person is using a smartphone, analyze the audio when a call comes in from an unregistered phone number.

[0177] Step 2: Compare the analysis results with online examples and issue a warning asking, "Could this be a scam call?"

[0178] Step 3: Recognize the emotions of the elderly person from their tone of voice and word choice.

[0179] Step 4: For example, if you recognize that an elderly person is feeling anxious or frightened, make the warning more specific, such as "This is likely a scam. Please be careful," and change the way the warning is displayed, such as using larger fonts or stronger vibrations.

[0180] (Example 1)

[0181] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0182] In today's communication environment, incoming calls from numbers not registered in phonebooks are increasing, and the resulting fraud and illegal business activities are becoming a social problem. Traditional systems struggle to provide users with appropriate warnings about these incoming calls, often causing them anxiety. Furthermore, the inability to respond flexibly to user emotions limits the effectiveness of warnings.

[0183] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0184] In this invention, the server includes means for detecting incoming calls from destinations not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, and means for recognizing the user's emotions and adjusting the content and display method of the warning according to those emotions. This enables the server to quickly and accurately warn the user of the possibility of fraud or illegal business activities, and to respond flexibly according to the user's emotions.

[0185] A "telephone directory" is a database that lists contact information registered on communication devices, and mainly includes names and phone numbers.

[0186] "Unregistered contacts" refers to contacts not registered in the phone book, meaning that the caller's identification information is unknown when they receive a call.

[0187] An "incoming call" refers to an external call being made to a communication device, and it is a signal that prompts the start of a voice call.

[0188] "Means of analyzing speech" refers to technical methods for converting speech data into text data and analyzing its content.

[0189] "Case studies on information networks" refers to databases that collect similar past events and cases that exist on networks such as the internet.

[0190] "Means of issuing warnings" refers to methods and technologies for notifying users of cautions and dangerous information.

[0191] "Means of recognizing emotions" refers to technologies that analyze a user's tone of voice and word choice to determine their emotional state.

[0192] "Means for adjusting the content and display method of warnings" refers to technologies that change the content and display format of warning messages according to the user's emotional state.

[0193] This invention is a system for detecting incoming calls from unregistered destinations in communication equipment and providing appropriate warnings to the user. Specific embodiments of this system are described below.

[0194] The device detects incoming calls from numbers not registered in the phonebook. Upon receiving a call, the device uses voice analysis software to convert the incoming audio into text data. This voice analysis utilizes speech recognition technology.

[0195] The server compares the analyzed text data with a case database on the information network. This database contains a collection of past fraud and sales activity cases, and the server uses this to assess the risk of incoming calls.

[0196] Furthermore, the device uses an emotion engine to analyze the user's tone of voice and word choice, recognizing the user's emotions. Based on this emotion recognition, the content and display method of warnings are adjusted according to the user's emotions.

[0197] For example, if a call comes in from an unregistered number, the device records the audio and sends it to the server. Based on the analysis, the server determines that there is a "possible scam" and sends a warning to the device. If the user responds with an anxious voice, the emotion engine recognizes that emotion and displays the warning message emphatically as "Caution! This may be a scam."

[0198] Examples of prompts include, "Please describe a system that analyzes incoming calls from unregistered destinations to determine if they are potentially fraudulent," and "Please provide a specific example of a system that uses an emotion engine to issue warnings based on the user's emotions."

[0199] In this way, the system can provide users with prompt and accurate warnings, thereby improving the security of communications.

[0200] The flow of the specific processing in Example 1 will be explained using Figure 15.

[0201] Step 1:

[0202] The terminal detects incoming calls from numbers not registered in the phonebook. The input is an incoming call signal, and the output is information about the unregistered caller. This information is used in subsequent processing steps. Specifically, the terminal checks the phonebook upon receiving an incoming call to confirm that the number is not registered.

[0203] Step 2:

[0204] The terminal records incoming audio and converts it into text data using speech analysis software. The input is the recorded audio data, and the output is the analyzed text data. This text data is used for subsequent database matching. Specifically, the terminal uses speech recognition technology to convert speech into text information.

[0205] Step 3:

[0206] The server compares the analyzed text data with a case database on the information network. The input is text data, and the output is a risk assessment of fraud and sales activities. Specifically, the server searches for phrases and patterns that match known fraud and sales cases.

[0207] Step 4:

[0208] The device uses an emotion engine to analyze the user's voice tone and vocabulary to recognize their emotions. The input is the user's voice data, and the output is the user's emotional state. This emotional state is used to adjust the content and display method of warnings. Specifically, the device analyzes the pitch and speed of the voice to estimate the emotion.

[0209] Step 5:

[0210] The device generates a warning message and notifies the user based on the risk assessment results from the server and the user's emotional state. The inputs are the risk assessment results and the emotional state, and the output is a tailored warning message. Specifically, the device displays the warning to the user using push notifications.

[0211] (Application Example 1)

[0212] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0213] In modern society, the number of incoming calls from numbers not registered in phone directories is increasing, raising the risk of fraud and illegal sales activities. Furthermore, prompt and accurate information is required for users to respond appropriately to these calls. However, conventional systems fail to provide warnings that take into account the user's feelings, thus failing to alleviate user stress.

[0214] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0215] In this invention, the server includes means for detecting incoming calls from destinations not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, means for recognizing the user's emotions, and means for changing the content and display method of warnings according to those emotions. This enables the server to quickly and accurately warn users of the possibility of fraud or illegal sales activities, and to provide appropriate information according to the user's emotions.

[0216] "Means for detecting incoming calls from numbers not registered in the phonebook" refers to a function in a communication device that identifies and detects incoming calls from numbers not registered in the user's phonebook.

[0217] "Methods for analyzing speech" refer to technologies for processing audio data received during an incoming call and converting its content into text data or feature vectors.

[0218] "Methods for comparing with examples on information networks" refer to methods for comparing analyzed audio data with existing databases and examples on the internet to evaluate similarities and relationships.

[0219] "Means of issuing warnings" refers to a function that displays alerts or warning messages to users based on analysis results.

[0220] "Means of recognizing user emotions" refers to technologies that analyze a user's tone of voice and word choice to determine their emotional state.

[0221] "Means of changing the content and display method of warnings according to emotions" refers to a function that adjusts the content and display format of warning messages based on the recognized emotions of the user.

[0222] The system for implementing this invention mainly consists of a server and a user terminal. The server detects incoming calls from destinations not registered in the phone book and analyzes the voice. For the analysis, it uses the Python speech_recognition library to convert the voice data into text. In addition, it performs a process of comparing the analysis results with existing databases in order to compare them with examples on the information network.

[0223] Furthermore, the server uses the emotion_recognition library to recognize the user's emotions. This library analyzes the user's tone of voice and word choice to determine their emotional state. Based on the recognized emotion, processing is performed to change the content and display method of the warning. The warning is sent as a push notification to the user's device so that the user can check it immediately.

[0224] For example, if a user receives a phone call asking, "Would you like to purchase a new insurance product?", voice analysis will detect the keyword "purchase" and determine that it may be a scam. If the user is feeling stressed, an emphasized warning will be displayed saying, "This may be a scam. Please be careful!"

[0225] An example of a prompt message for a generative AI model would be: "Analyze this audio data to determine if it is potentially fraudulent or a sales pitch. Also, recognize the user's emotions and emphasize warnings if they are feeling stressed."

[0226] The flow of a specific process in Application Example 1 will be explained using Figure 16.

[0227] Step 1:

[0228] The server detects that there is an incoming call on the terminal. The input is the incoming call notification from the terminal. The server receives this notification and checks whether the incoming call is from a contact not registered in the phonebook. The output is the result of the determination of whether or not it is an unregistered incoming call.

[0229] Step 2:

[0230] The server retrieves audio data if it determines that the incoming call is unregistered. The input is audio data from the terminal. The server uses the Python speech_recognition library to convert this audio data into text. The output is the text data of the audio.

[0231] Step 3:

[0232] The server compares the converted text data with examples on the information network. The input is audio-to-text data. The server compares it with existing databases to assess the likelihood of fraud or sales. The output is the assessment result regarding the likelihood of fraud or sales.

[0233] Step 4:

[0234] The server recognizes the user's emotions from the audio data. The input is audio data from the terminal. The server uses the emotion_recognition library to analyze the user's voice tone and word choice to determine their emotional state. The output is the user's emotional state.

[0235] Step 5:

[0236] The server determines the content and display method of warnings based on the likelihood of fraud or sales and the user's emotional state. The inputs are the evaluation results regarding the likelihood of fraud or sales and the user's emotional state. The server generates a warning message and adjusts its display method according to the user's emotional state. The output is the warning message.

[0237] Step 6:

[0238] The server sends the generated warning message to the device as a push notification. The input is the warning message. The server sends this message to the device so the user can immediately acknowledge it. The output is the warning message displayed on the device.

[0239] (Example 2)

[0240] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0241] Users, including the elderly, may be unable to adequately respond to fraudulent activity or commercial communications originating from unregistered identification numbers, putting them at risk of becoming involved in scams or unnecessary commercial activities. It is essential to mitigate such risks and provide an environment where users can use communication devices with peace of mind.

[0242] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0243] In this invention, the server includes means for detecting connections from identification numbers not registered with the communication device, means for analyzing the voice information of the connection, and means for comparing the analysis results with examples on the information network. This enables users to receive prompt and appropriate warnings about fraudulent activity or communications for commercial purposes.

[0244] "Communication equipment" refers to electronic devices used for sending and receiving voice and data, including telephones and smartphones.

[0245] An "identification number" is a unique number assigned to a communication device, such as a telephone number or IP address.

[0246] "Connection" refers to a state in which voice and data can be exchanged between communication devices.

[0247] "Voice information" refers to voice data transmitted via communication devices.

[0248] "Analysis" refers to the process of processing audio information and converting its content into an understandable format.

[0249] An "information network" refers to a system for sharing digital information, such as the internet.

[0250] A "case" refers to a specific event or pattern that has been recorded in the past.

[0251] "Matching" refers to the process of comparing analyzed data with existing cases to determine if they match.

[0252] A "warning" refers to a message or notification intended to draw the user's attention.

[0253] "Emotional state" refers to the user's psychological state and can be inferred from their tone of voice and choice of words.

[0254] "Enhancement" refers to adjusting the content and presentation of a warning to make it more effective.

[0255] This invention is a system that uses a communication device to detect connections from unregistered identification numbers and analyzes the voice information. Specifically, when a terminal detects a connection from an unregistered identification number, it records the voice information and converts it into text data using speech recognition software. General speech recognition technology can be used in this process.

[0256] The server receives text data sent from the terminal and compares it against a case database on the information network. This comparison uses machine learning models to detect characteristics of fraudulent or commercially motivated communications. Based on the comparison results, the server generates an alert and sends it to the terminal.

[0257] The device notifies the user of any warnings it receives. These notifications are made through on-screen messages and vibrations. Furthermore, the device uses emotion recognition technology to assess the user's emotional state. If it determines that the user is experiencing anxiety or fear, the content and presentation of the warning are enhanced.

[0258] For example, when a user receives a call from an unregistered number on their smartphone, the device automatically records the call and converts the audio to text. The server then compares the text to a fraud database and generates a warning if it determines that the call may be fraudulent. If the system analyzes that the user is feeling uneasy, the warning is enhanced, and the device notifies the user with larger text and vibration.

[0259] Examples of prompts to input into a generative AI model:

[0260] "A call was received from an unregistered phone number. Please perform voice analysis to determine if it is a scam. Also, analyze the user's emotions and strengthen the warning as needed."

[0261] The flow of the specific processing in Example 2 will be explained using Figure 17.

[0262] Step 1:

[0263] The device detects a connection from an unregistered identification number. It receives the incoming identification number as input. The device verifies that this identification number is not registered in the phonebook and begins recording the connection. It generates the recorded audio data as output.

[0264] Step 2:

[0265] The terminal inputs recorded audio data into speech recognition software and converts it into text data. It receives audio data as input. The terminal analyzes the audio using speech recognition technology and outputs data in text format. This text data is used for subsequent analysis.

[0266] Step 3:

[0267] The server receives text data sent from the terminal and compares it with a case database on the information network. It receives text data as input. The server uses a machine learning model to detect characteristics of fraudulent or commercially motivated communications. It generates an assessment of the likelihood of fraud as output.

[0268] Step 4:

[0269] The server generates a warning message based on the evaluation results and sends it to the terminal. It receives the evaluation results as input. If the server detects a potential fraud, it generates a warning such as "This may be fraudulent activity." It generates a warning message as output and sends it to the terminal.

[0270] Step 5:

[0271] The device notifies the user of any warning messages it receives. It receives warning messages as input. The device displays the message on the screen and, if necessary, vibrates to alert the user. It then sends a warning notification to the user as output.

[0272] Step 6:

[0273] The device uses emotion recognition technology to evaluate the user's emotional state. It receives the user's voice data as input. The device analyzes the tone and word choice of the voice to evaluate the user's emotional state. It then generates an evaluation result regarding the emotional state as output.

[0274] Step 7:

[0275] The server enhances warnings based on the user's emotional state. It receives an assessment of the user's emotional state as input. If the server determines that the user is feeling anxious or fearful, it enhances the content and presentation of the warning. As output, it generates an enhanced warning message and sends it to the user's device.

[0276] (Application Example 2)

[0277] Next, Application Example 2 of Embodiment Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0278] There is a demand to reduce the risk that elderly people encounter scam calls from unregistered telephone numbers. In addition, it is necessary to provide appropriate warnings when elderly people feel anxiety or fear regarding the content of a call.

[0279] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is implemented by each of the following units.

[0280] In the present invention, the server includes a unit that detects an incoming call from a telephone number not registered in the telephone directory, a unit that analyzes the voice of the incoming call, a unit that compares the analysis result with cases on the network, a unit that recognizes emotions from the tone and wording of the elderly person's voice, and a unit that adjusts the content and display method of the warning based on the emotion recognition result. This makes it possible to reduce the risk of elderly people encountering scam calls and provide appropriate warnings tailored to their emotions.

[0281] The "unit that detects an incoming call from a telephone number not registered in the telephone directory" is a function that identifies an incoming call from a telephone number not registered in the user's telephone directory and notifies the system of that information.

[0282] The "unit that analyzes voice" is a technology that processes voice data received at the time of an incoming call and converts the content thereof into text data.

[0283] The "unit that compares with cases on the network" is a process that compares the analyzed voice data with a scam case database existing on the Internet to evaluate the possibility of fraud.

[0284] A "warning mechanism" is a function that displays or notifies users of a message to warn them if it is determined that there is a possibility of fraud.

[0285] "Means of recognizing emotions" refers to technology that analyzes the tone of a user's voice and word choice to determine their emotional state at that time.

[0286] "Means for adjusting the content and display method of warnings" refers to a function that optimizes the content and display method of warning messages based on recognized emotions, thereby conveying information to the user in an appropriate manner.

[0287] The system for implementing this invention mainly consists of a server and a user terminal. The server runs a program to detect incoming calls from phone numbers not registered in the phonebook. The user terminal records the voice when a call comes in and sends the voice data to the server. The server converts the voice data into text using a speech analysis library (e.g., Google Cloud Speech-to-Text). The converted text is compared against an online database of fraud cases. Furthermore, the server uses an emotion recognition engine (e.g., IBM Watson® Tone Analyzer) to recognize emotions from the tone of the user's voice and word choice.

[0288] If the server determines that a scam is highly likely, it will send a warning notification to the user's device via push notification. The content and display method of this warning are adjusted based on the results of emotion recognition. For example, if the server detects that the user is feeling anxious, the warning will be displayed in large letters and accompanied by a strong vibration, stating, "This is likely a scam. Please be careful."

[0289] For example, if a user says "I'm worried," the server recognizes that emotion and highlights the warning. An example of a prompt to the generating AI model is, "Please evaluate the likelihood that this voice is a scam call. Voice content: 'Hello, your bank account is at risk. Immediate action is required.'" In this way, it is possible to reduce the risk of elderly people encountering scam calls and provide appropriate warnings that are tailored to their emotions.

[0290] The flow of a specific process in Application Example 2 will be explained using Figure 18.

[0291] Step 1:

[0292] The user's device detects an incoming call from a phone number not registered in the phonebook. The input is the incoming phone number, and the output is a confirmation that the number is not registered. Based on this information, the device starts recording audio.

[0293] Step 2:

[0294] The user's device records audio upon receiving a call and sends the audio data to the server. The input is the recorded audio data, and the output is the transmission of the audio data to the server. The device converts the audio data to the appropriate format and transfers it to the server.

[0295] Step 3:

[0296] The server uses a speech analysis library (e.g., Google Cloud Speech-to-Text) to convert received audio data into text. The input is audio data, and the output is text data. The server performs speech analysis and generates text data.

[0297] Step 4:

[0298] The server checks the converted text against a fraud case database on the network. The input is text data, and the output is an evaluation result regarding the possibility of fraud. The server searches the database and evaluates the possibility of fraud.

[0299] Step 5:

[0300] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice tone and wording. The input is voice data, and the output is an emotion recognition result. The server analyzes the voice data and identifies the user's emotion.

[0301] Step 6:

[0302] When the server determines that the possibility of fraud is high, it sends a warning to the user's terminal via a push notification. The inputs are the fraud possibility evaluation result and the emotion recognition result, and the output is a warning message. The server adjusts the content and display method of the warning and notifies the user.

[0303] Step 7:

[0304] The user's terminal displays the received warning and provides feedback such as vibration as needed. The input is a warning message, and the output is visual and tactile feedback to the user. The terminal displays the warning on the screen to alert the user.

[0305] (Other Embodiments)

[0306] Next, other embodiments will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0307] In recent years, there has been an increase in communications originating from unregistered identifiers in phone directories, raising the risk of fraud and illegal activities. Traditional systems struggle to respond quickly and accurately to these communications, potentially leaving users vulnerable to such activities. To address this problem, a system is needed that can effectively detect, analyze, and warn about communications originating from unregistered identifiers.

[0308] The identification process performed by the identification processing unit 290 of the data processing device 12 in other embodiments is realized by the following means.

[0309] In this invention, the server includes means for detecting communications from unregistered identification information in the phone book, means for acquiring voice information and converting it into text data using speech recognition technology, and means for generating prompts to instruct the analysis of the text data and inputting them into a generating AI model. This makes it possible to respond quickly and accurately to communications from unregistered identification information.

[0310] A "communication device" is a device that detects communications from identification information not registered in the telephone directory and acquires voice information.

[0311] "Speech recognition technology" is a technology for converting acquired speech information into text data, and includes the process of analyzing speech data and converting it into text information.

[0312] A "prompt" is an input sentence used to instruct a generative AI model to analyze text data, and it serves to clearly indicate the purpose and content of the analysis.

[0313] A "generative AI model" is an artificial intelligence model that analyzes text data based on prompts and generates analysis results.

[0314] "Warning information" refers to a message intended to alert users, generated based on the analysis results of a generation AI model and comparison with examples in information resources.

[0315] This invention provides a system that detects communications originating from unregistered identification information in the telephone directory and evaluates the possibility of fraud or illegal activity. Specific embodiments of this system are described below.

[0316] The server uses communication equipment to monitor and detect communications from unregistered identifiers in the phonebook in real time. When a communication is detected, the terminal acquires the audio information of that communication. The acquired audio data is converted into text data using speech recognition software such as the Google Cloud Speech-to-Text API. This conversion transforms the audio information into parseable text information.

[0317] Next, the server generates a prompt for parsing the converted text data. This prompt is input to a generating AI model (e.g., OpenAI GPT-3®). An example of a prompt is "Parse the following text and evaluate the possibility of fraudulent activity:", followed by the converted text data.

[0318] The generative AI model analyzes text data based on prompt messages received from the server and generates analysis results. These results include an assessment of the likelihood of fraud and other risks. The server compares the analysis results obtained from the generative AI model with examples in its information resources (e.g., a database of past fraud cases). This comparison determines whether or not there is a high probability of fraud.

[0319] Based on its assessment, the server generates a warning. This warning is then communicated to the user via the terminal. The terminal immediately displays the warning message visually through its user interface. A typical warning message might read something like, "This may be fraudulent activity. Please check the details."

[0320] Users can view warning messages on their devices and investigate further if necessary. This system allows users to respond quickly and effectively to communications from unregistered identities.

[0321] The flow of a specific process in another embodiment will be explained using Figure 19.

[0322] Step 1:

[0323] The server uses a communication device to monitor and detect communications from unregistered identifiers in the phonebook in real time. The input is the identifier from the communication device, and the output is an event indicating that unregistered identifiers have been detected. This event triggers subsequent processing.

[0324] Step 2:

[0325] The terminal acquires audio information from detected communications. The input is a communication event, and the output is audio data. The terminal uses a microphone to capture the audio data and saves it in digital format.

[0326] Step 3:

[0327] The device converts acquired audio data into text data using the Google Cloud Speech-to-Text API. The input is audio data, and the output is generated text data. In this conversion process, the audio signal is analyzed, and the corresponding string is generated.

[0328] Step 4:

[0329] The server generates prompts for parsing text data. The input is text data, and the output is a prompt. Specifically, the prompt is created in the format "Parse the following text and evaluate the possibility of fraudulent activity:", followed by the text data.

[0330] Step 5:

[0331] The generative AI model analyzes text data based on prompt messages received from the server and generates analysis results. The input is a prompt message, and the output is the generated analysis result. The generative AI model uses natural language processing techniques to evaluate the text content and determine the likelihood of fraud.

[0332] Step 6:

[0333] The server compares the analysis results obtained from the generated AI model with case examples in the information resources. The input is the analysis results, and the output is the comparison results. In this process, the server compares the results with a database of past fraud cases to evaluate whether the case is likely to be fraudulent.

[0334] Step 7:

[0335] The server generates warning information based on the comparison results. The input is the comparison results, and the output is the generated warning information. The warning information includes a message to alert the user.

[0336] Step 8:

[0337] The terminal instantly displays warning information received from the server visually through the user interface. The input is warning information, and the output is a warning message displayed to the user. A specific message might be something like, "This may be fraudulent activity. Please check the details."

[0338] Step 9:

[0339] The user views the warning message on their device and investigates further if necessary. The input is the warning message, and the output determines the user's response. Based on the warning, the user can take appropriate action.

[0340] 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.

[0341] 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 the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0342] Other examples of generative AI include Gemini® (registered trademark) (Internet search). <url: https: gemini.google.com ?hl="ja">) are some examples.

[0343] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0344] [Second Embodiment]

[0345] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0346] 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.

[0347] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0348] 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.

[0349] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0350] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0351] 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.

[0352] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0353] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0354] The 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.

[0355] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0356] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0357] "Example of form 1"

[0358] One embodiment of this system is one that can be implemented in communication devices such as smartphones and personal computers. This system has a function to detect incoming calls from phone numbers not registered in the phone book. When a call comes in, the system analyzes the voice and compares the analysis results with examples found online. Based on the comparison results, it then issues a warning to the user, such as "Is this a scam call?" or "Is this a sales call from someone intending to buy something?" The warning is issued in the form of a push notification or similar, allowing the user to check it immediately.

[0359] "Example of form 2"

[0360] As a concrete example, consider a case where an elderly person is using a smartphone. When a call comes in from an unregistered phone number, the system of this invention analyzes the voice and compares the analysis results with examples found online. Then, it sends a push notification warning, "Is this a scam call?" This can significantly reduce the risk of elderly people encountering scams such as "ore-ore" (impersonation) scams.

[0361] The following describes the processing flow for each example of the form.

[0362] "Example of form 1"

[0363] Step 1: A system implemented in communication devices such as smartphones and personal computers detects incoming calls from phone numbers not registered in the phonebook.

[0364] Step 2: The system analyzes the incoming audio. This analysis is performed using speech recognition technology.

[0365] Step 3: Compare the analysis results with examples found online. This comparison is done by comparing the patterns and characteristics of the audio.

[0366] Step 4: Based on the comparison results, a warning is issued to the user, such as "Is this a scam call?" or "Is this a sales call from someone with an intention to buy?". This warning is issued in the form of a push notification or similar.

[0367] "Example of form 2"

[0368] Step 1: If an elderly person is using a smartphone, and they receive a call from an unregistered phone number, the system of the present invention analyzes the voice of that call.

[0369] Step 2: Compare the analysis results with examples found online. This comparison is done by comparing the patterns and characteristics of the audio.

[0370] Step 3: Send a push notification warning, "Is this a scam call?" This significantly reduces the risk of elderly people falling victim to scams such as "It's me" scams.

[0371] (Example 1)

[0372] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0373] In today's communication environment, there has been an increase in communications originating from unregistered identifiers, leading to fraudulent activities and unwanted sales activities that pose a significant problem for users. Traditional methods have made it difficult to effectively identify these communications and provide warnings to users. Therefore, there is a need for a system that can quickly and accurately analyze communications from unregistered identifiers and provide appropriate warnings to users.

[0374] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0375] In this invention, the server includes means for detecting communications from unregistered identification information in a communication device, means for analyzing the voice information of the communications, and means for comparing the analysis results with examples in the information resource. This makes it possible to quickly analyze communications from unregistered identification information and warn users of the possibility of fraudulent activity or unnecessary sales activities.

[0376] "Communication equipment" refers to electronic devices used for transmitting and receiving voice and data, and includes telephones, computers, and other similar devices.

[0377] "Identification information" refers to information used to identify the source of a communication, and includes things like telephone numbers and IP addresses.

[0378] "Voice information" refers to voice data transmitted and received during communication, and is the subject of analysis.

[0379] "Analysis" refers to the process of converting audio information into text data and understanding its content.

[0380] "Information resources" refer to databases and case studies available on the internet, which are used to compare and contrast analysis results.

[0381] "Warning information" refers to notifications generated based on analysis results, informing users of potential fraudulent activity or unnecessary sales activities.

[0382] "Notification" refers to a means of conveying warning information to users, and includes push notifications and alert messages.

[0383] As an embodiment of this invention, a system is constructed in a communication device that detects communications from unregistered identification information in the phone book and analyzes the voice information. When a terminal receives a communications from unregistered identification information, it records the voice and sends it to a server. The server converts the voice data into text using voice analysis software. In this case, the Google Cloud Speech-to-Text API can be used.

[0384] The server uses a generative AI model to compare the converted text with examples in the information resource. Specifically, it uses OpenAI's GPT model to determine whether the text is related to fraudulent activity or unwanted sales activities. In this process, the server inputs the prompt "Is this call potentially fraudulent?" into the generative AI model.

[0385] Based on the analysis results, the server generates warning information and sends it to the device. The device displays the warning to the user via push notification. This allows the user to quickly understand if communications from unregistered identification information may be fraudulent or related to unwanted sales activities.

[0386] As a concrete example, if a user receives a call from "0123-456-7890," the device records the audio and sends it to the server. The server converts the audio to text and inputs the prompt "Is this call possibly a scam?" into a generating AI model. The generating AI model compares this with past data and generates a warning, "Is this a scam call?" The warning is sent to the user's device as a push notification, allowing the user to check it immediately.

[0387] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0388] Step 1:

[0389] The terminal detects communications originating from unregistered identifiers in the phonebook. It receives the communication's identifier as input and compares it against the phonebook. The output is the identification information confirmed to be unregistered. This process allows for the identification of unregistered communications.

[0390] Step 2:

[0391] The terminal records audio from communications originating from unregistered identification information. It receives audio data during communication as input and saves it as a digital audio file using a recording device. The recorded audio data is obtained as output. This operation prepares the audio data necessary for subsequent analysis.

[0392] Step 3:

[0393] The terminal sends the recorded audio data to the server. It receives the recorded audio data as input and sends it to the server via the communication network. The audio data is then transferred to the server as output. This process provides the server with the audio data for analysis.

[0394] Step 4:

[0395] The server uses speech analysis software to convert speech data into text. It uses speech data received from the terminal as input and converts it into text data using the Google Cloud Speech-to-Text API. The output is the converted text data. This process converts speech information into a parseable text format.

[0396] Step 5:

[0397] The server analyzes text data using a generative AI model and compares it with examples in the information resources. It uses the transformed text data as input and performs analysis using OpenAI's GPT model. The analysis results are obtained as output. This process allows for determining whether the text data is related to fraudulent activity or unwanted sales activities.

[0398] Step 6:

[0399] The server generates warning information based on the analysis results. It uses the analysis results as input to generate a warning message. The output is the warning information itself. This process prepares the server to provide appropriate warnings to the user.

[0400] Step 7:

[0401] The server sends the generated warning information to the terminal. It uses the warning information as input and transmits it to the terminal via the communication network. The warning information is then transferred to the terminal as output. This process provides the user with the warning information.

[0402] Step 8:

[0403] The device displays the received warning information to the user as a push notification. It uses the warning information received from the server as input and displays it to the user using the device's notification function. The user confirms the warning information as output. This process allows the user to quickly receive warnings about communications from unregistered identification information.

[0404] (Application Example 1)

[0405] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0406] In modern society, the risk of fraud and illegal sales calls from unregistered phone numbers is increasing. While users are required to respond quickly and accurately to such calls, traditional methods make this decision difficult.

[0407] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0408] In this invention, the server includes means for detecting incoming calls from unregistered phone numbers, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, means for speech recognition to convert the audio into text, means for analyzing the possibility of fraud using a generative AI model, and means for issuing a warning based on the analysis results. This enables users to quickly determine the possibility of fraud when receiving calls from unregistered phone numbers and take appropriate action.

[0409] "Unregistered phone numbers" refer to numbers that are not stored on the user's communication device and for which specific information is not registered when an incoming call is received.

[0410] "Means for detecting incoming calls" refers to a device or program in a communication device that has the function of sensing an incoming call from an external source and acquiring that information.

[0411] "Means for analyzing speech" refers to technology or equipment for processing received speech data and understanding or classifying its content.

[0412] "Case examples on information networks" refers to a collection of past similar events or data that exist on the internet or other digital networks.

[0413] "Speech recognition means" refers to a technology or device for converting speech data into text data.

[0414] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate a specific output based on input data.

[0415] "Means for analyzing the possibility of fraud" refers to technology or equipment used to determine whether the content of received data constitutes fraudulent activity.

[0416] A "means of issuing a warning" refers to a device or program that has a notification function for alerting or providing information to the user.

[0417] The system for implementing this invention mainly consists of a server and a user terminal. The server detects incoming calls from numbers not registered in the phonebook and runs a program to analyze the voice. For voice analysis, the Google Cloud Speech-to-Text API is used to convert the voice data into text data. The converted text data is analyzed using the generative AI model OpenAI GPT to determine the likelihood of fraud.

[0418] The user's device receives a push notification if there is a potential scam based on analysis results from the server. This warning is designed to allow the user to respond quickly.

[0419] For example, if a user receives a call from "0120-XXXX-XXXX", the server converts the audio into text and inputs the following prompt into the AI ​​generation model: "Is this text potentially a scam? Content: You have won a special campaign." If the AI ​​generation model determines that it is "highly likely to be a scam," a warning message "This may be a scam. Please be careful." is sent to the user's device.

[0420] In this way, users can quickly determine the possibility of fraud when receiving calls from unregistered numbers and take appropriate action.

[0421] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0422] Step 1:

[0423] The server receives incoming call information from the user's terminal. The input is incoming call data from a call number not registered in the phonebook. The server prepares to analyze this data.

[0424] Step 2:

[0425] The server receives incoming audio data and converts it to text using the Google Cloud Speech-to-Text API. The input is audio data, and the output is text data. This conversion makes the audio content available as text information.

[0426] Step 3:

[0427] The server inputs text data into the OpenAI GPT generative AI model and analyzes its likelihood of being a scam. The input is text data, and the output is the analysis result regarding the likelihood of fraud. The server generates a prompt sentence and asks the model, "Is this text likely to be a scam?"

[0428] Step 4:

[0429] The server receives the analysis results from the generated AI model and generates a warning based on those results. The input is the analysis result, and the output is the warning message. The server creates a warning such as "This may be a scam. Please be careful." if there is a high probability of fraud.

[0430] Step 5:

[0431] The server sends the generated warning message as a push notification to the user's device. The input is the warning message, and the output is the notification displayed on the user's device. The user receives this notification and can take appropriate action regarding the incoming message.

[0432] (Example 2)

[0433] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0434] Many users, including the elderly, are vulnerable to unauthorized connections from unregistered identification numbers. In particular, there is a growing need for effective measures to mitigate these risks, especially given the increasing prevalence of fraudulent activities and unethical sales practices.

[0435] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0436] In this invention, the server includes means for detecting connections from unregistered identification numbers in the communication device, means for acquiring audio information of said connections, and means for converting said audio information into text information. This makes it possible to quickly detect the possibility of fraudulent activity from unregistered identification numbers and notify the user of a warning.

[0437] "Communication equipment" refers to electronic devices used for sending and receiving voice and data, including telephones and smartphones.

[0438] An "identification number" is a unique number assigned to a communication device, such as a telephone number or IP address.

[0439] "Connection" refers to the establishment of a communication link between communication devices, including the initiation of voice calls and data communications.

[0440] "Voice information" refers to voice data transmitted via communication devices, including the content of phone calls.

[0441] "Textual information" refers to text data obtained by converting audio information, and is generated using speech recognition technology.

[0442] "Analysis" refers to the process of processing acquired data and understanding its content and meaning.

[0443] An "information database" is a collection of data that stores past cases and related information, and is used to verify analysis results.

[0444] A "warning" is a notification intended to alert users and may include information about the possibility of fraudulent activity.

[0445] "Notification" refers to a means of conveying information to users, including push notifications and alert messages.

[0446] To implement this invention, the terminal first detects a connection from an unregistered identification number. When a connection is established, the terminal records the call content and sends it to the server as audio information. The server converts the received audio information into text information using the Google Cloud Speech-to-Text API. This API provides highly accurate speech recognition and quickly converts speech to text.

[0447] Next, the server inputs the converted text information into a generative AI model. Specifically, it uses a model such as OpenAI's GPT model and inputs the prompt "Is this phone call potentially a scam?". The generative AI model analyzes the text information and determines the likelihood of it being a scam.

[0448] Based on the analysis results, the server generates a warning. The warning includes the message, "Is this potentially fraudulent activity?", and is immediately sent as a push notification to the device. By receiving this notification, users can become more vigilant against potentially fraudulent connections.

[0449] As a concrete example, if a user receives a call from an unregistered number, the device automatically records the audio and sends it to a server. The server converts the audio to text and inputs prompt text into a generative AI model. Based on the model's analysis, the server sends a warning to the user. This entire process allows users to anticipate the risk of fraudulent calls and take appropriate action.

[0450] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0451] Step 1:

[0452] The terminal detects connections from unregistered identification numbers. Once a connection is established, the terminal records the call and prepares the data as audio information. This audio information becomes input for the next processing step.

[0453] Step 2:

[0454] The device sends the recorded audio information to the server. The server converts the received audio information into text using the Google Cloud Speech-to-Text API. This conversion process involves speech recognition to convert the audio data into text data. The output is text information for analysis.

[0455] Step 3:

[0456] The server inputs the converted text information into the generating AI model. Specifically, it uses the prompt "Is this phone call potentially a scam?" to request analysis from the generating AI model. The model analyzes the text information and determines the likelihood of it being a scam. This analysis result becomes the output for the next step.

[0457] Step 4:

[0458] The server generates a warning based on the analysis results obtained from the generated AI model. The warning includes the message "Is this a possible case of fraudulent activity?" and is immediately sent as a push notification to the device. This notification is what is output to the user.

[0459] Step 5:

[0460] The user checks the warning notification received from their device. Based on this notification, the user can become more vigilant against potentially fraudulent connections and take appropriate action if necessary.

[0461] (Application Example 2)

[0462] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0463] There is a need for a means to enable users, including the elderly, to quickly assess the risk of fraud and illegal transactions from connections made using unregistered identification information, and to prevent damage before it occurs. However, conventional technologies have made it difficult to analyze these risks in real time and provide appropriate warnings.

[0464] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0465] In this invention, the server includes means for detecting connections from unregistered identification information in the communication device, means for analyzing the voice information of the connection, and means for comparing the analysis results with examples on the information network. This enables users to determine the possibility of fraud or illegal transactions in real time and receive a warning quickly.

[0466] "Communication equipment" refers to devices used for sending and receiving voice and data, and includes smartphones and computers.

[0467] "Unregistered identification information" refers to information such as phone numbers and IDs that are not registered in the user's database.

[0468] "Connection" refers to the exchange of voice and data that takes place via communication devices.

[0469] "Voice information" refers to voice data from phone calls or recordings, and is the subject of analysis.

[0470] "Analysis" refers to the process of converting audio information into text data and then analyzing its content.

[0471] An "information network" refers to the internet and other digital networks used for matching and searching data.

[0472] "Case examples" refer to specific cases of fraud or illegal transactions that have been recorded in the past.

[0473] A "warning" refers to a notification or message intended to inform users of potential fraud or misconduct.

[0474] "Real-time" refers to processing and analysis being performed almost instantly, meaning that delays are minimized.

[0475] The system for implementing this invention primarily uses a communication device, a server, and an information network. The communication device is a terminal such as a smartphone, which detects connections from unregistered identification information. The server analyzes the connected voice information and converts it into text data using a generative AI model. This analysis uses a voice analysis library such as the Google Cloud Speech-to-Text API.

[0476] The analyzed text data is compared against a case database on the information network. The database records past cases of fraud and illicit transactions, and the server uses this to determine the likelihood of fraud. If fraud is determined to be possible, the server sends an alert to the user's communication device using a push notification service (e.g., Firebase Cloud Messaging).

[0477] For example, if a user receives a call from an unregistered number and the caller says, "Your bank account is at risk," the server analyzes the audio and compares it to a database of fraud cases. If it is determined that there is a high probability of fraud, it sends a warning to the user asking, "Is this a scam?"

[0478] An example of a prompt to input into the generating AI model is: "Please determine if this voice message is potentially fraudulent. Message content: 'Your bank account is at risk.'"

[0479] In this way, users can assess the risk of fraud and illegal transactions in real time and take swift action.

[0480] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0481] Step 1:

[0482] The terminal detects connections from unregistered identification information. The input is the incoming phone number, and the output is the result of determining that it is unregistered. The terminal compares it with the phonebook database, and if it is unregistered, proceeds to the next step.

[0483] Step 2:

[0484] The terminal collects connected audio information and sends it to the server. The input is the audio data during the call, and the output is the transfer of the audio data to the server. The terminal captures the audio data in real time and streams it to the server.

[0485] Step 3:

[0486] The server analyzes the received audio data and converts it into text data. The input is audio data sent from the terminal, and the output is text data. The server uses the Google Cloud Speech-to-Text API to convert the audio to text.

[0487] Step 4:

[0488] The server analyzes text data using a generative AI model to determine the likelihood of fraud. The input is the transformed text data, and the output is the evaluation result of the likelihood of fraud. The server inputs the text data as a prompt into the generative AI model and evaluates the likelihood of fraud.

[0489] Step 5:

[0490] If the server determines that there is a high probability of fraud, it generates a push notification and sends it to the device. The input is the result of the fraud probability assessment, and the output is a warning message. The server uses Firebase Cloud Messaging to send the user a warning asking, "Is this a scam?"

[0491] Step 6:

[0492] The user reviews the warning message displayed on the device and, if necessary, ends the call or takes further action. The input is the warning message displayed on the device, and the output is the user's action. The user either ends the call after receiving the warning or takes additional confirmation.

[0493] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0494] "Example of form 1"

[0495] One embodiment of the present invention is a system incorporating an emotion engine. This system detects incoming calls from phone numbers not registered in the phone book and analyzes the incoming call's audio. It compares the analysis results with online examples and issues a warning based on the comparison. Furthermore, this system includes an emotion engine that recognizes the user's emotions. The emotion engine recognizes the user's emotions from their tone of voice and word choice, and changes the content and display method of the warning according to those emotions. "Example 2"

[0496] As a concrete example, consider a scenario where an elderly person is using a smartphone. When a call comes in from an unregistered phone number, the system of this invention analyzes the voice. The analysis results are compared with examples found online, and a warning is issued, such as, "Could this be a scam call?" Furthermore, the emotion engine recognizes the elderly person's emotions from their tone of voice and word choice. For example, if it detects that the elderly person is feeling anxious or frightened, the warning is made more specific, such as, "This is likely a scam. Please be careful," and the warning display method is changed to larger font and stronger vibration. This significantly reduces the risk of elderly people encountering scams such as "ore-ore" (impersonation) scams.

[0497] The following describes the processing flow for each example of the form.

[0498] "Example of form 1"

[0499] Step 1: Detect incoming calls from phone numbers not registered in the phonebook.

[0500] Step 2: Analyze the incoming call audio.

[0501] Step 3: Compare the analysis results with examples found online.

[0502] Step 4: Issue a warning based on the comparison results.

[0503] Step 5: Recognize the user's emotions from their tone of voice and word choice.

[0504] Step 6: Change the content and display method of the warning according to the emotion.

[0505] "Example of form 2"

[0506] Step 1: If an elderly person is using a smartphone, analyze the audio when a call comes in from an unregistered phone number.

[0507] Step 2: Compare the analysis results with online examples and issue a warning asking, "Could this be a scam call?"

[0508] Step 3: Recognize the emotions of the elderly person from their tone of voice and word choice.

[0509] Step 4: For example, if you recognize that an elderly person is feeling anxious or frightened, make the warning more specific, such as "This is likely a scam. Please be careful," and change the way the warning is displayed, such as using larger fonts or stronger vibrations.

[0510] (Example 1)

[0511] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0512] In today's communication environment, incoming calls from numbers not registered in phonebooks are increasing, and the resulting fraud and illegal business activities are becoming a social problem. Traditional systems struggle to provide users with appropriate warnings about these incoming calls, often causing them anxiety. Furthermore, the inability to respond flexibly to user emotions limits the effectiveness of warnings.

[0513] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0514] In this invention, the server includes means for detecting incoming calls from destinations not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, and means for recognizing the user's emotions and adjusting the content and display method of the warning according to those emotions. This enables the server to quickly and accurately warn the user of the possibility of fraud or illegal business activities, and to respond flexibly according to the user's emotions.

[0515] A "telephone directory" is a database that lists contact information registered on communication devices, and mainly includes names and phone numbers.

[0516] "Unregistered contacts" refers to contacts not registered in the phone book, meaning that the caller's identification information is unknown when they receive a call.

[0517] An "incoming call" refers to an external call being made to a communication device, and it is a signal that prompts the start of a voice call.

[0518] "Means of analyzing speech" refers to technical methods for converting speech data into text data and analyzing its content.

[0519] "Case studies on information networks" refers to databases that collect similar past events and cases that exist on networks such as the internet.

[0520] "Means of issuing warnings" refers to methods and technologies for notifying users of cautions and dangerous information.

[0521] "Means of recognizing emotions" refers to technologies that analyze a user's tone of voice and word choice to determine their emotional state.

[0522] "Means for adjusting the content and display method of warnings" refers to technologies that change the content and display format of warning messages according to the user's emotional state.

[0523] This invention is a system for detecting incoming calls from unregistered destinations in communication equipment and providing appropriate warnings to the user. Specific embodiments of this system are described below.

[0524] The device detects incoming calls from numbers not registered in the phonebook. Upon receiving a call, the device uses voice analysis software to convert the incoming audio into text data. This voice analysis utilizes speech recognition technology.

[0525] The server compares the analyzed text data with a case database on the information network. This database contains a collection of past fraud and sales activity cases, and the server uses this to assess the risk of incoming calls.

[0526] Furthermore, the device uses an emotion engine to analyze the user's tone of voice and word choice, recognizing the user's emotions. Based on this emotion recognition, the content and display method of warnings are adjusted according to the user's emotions.

[0527] For example, if a call comes in from an unregistered number, the device records the audio and sends it to the server. Based on the analysis, the server determines that there is a "possible scam" and sends a warning to the device. If the user responds with an anxious voice, the emotion engine recognizes that emotion and displays the warning message emphatically as "Caution! This may be a scam."

[0528] Examples of prompts include, "Please describe a system that analyzes incoming calls from unregistered destinations to determine if they are potentially fraudulent," and "Please provide a specific example of a system that uses an emotion engine to issue warnings based on the user's emotions."

[0529] In this way, the system can provide users with prompt and accurate warnings, thereby improving the security of communications.

[0530] The flow of the specific processing in Example 1 will be explained using Figure 15.

[0531] Step 1:

[0532] The terminal detects incoming calls from numbers not registered in the phonebook. The input is an incoming call signal, and the output is information about the unregistered caller. This information is used in subsequent processing steps. Specifically, the terminal checks the phonebook upon receiving an incoming call to confirm that the number is not registered.

[0533] Step 2:

[0534] The terminal records incoming audio and converts it into text data using speech analysis software. The input is the recorded audio data, and the output is the analyzed text data. This text data is used for subsequent database matching. Specifically, the terminal uses speech recognition technology to convert speech into text information.

[0535] Step 3:

[0536] The server compares the analyzed text data with a case database on the information network. The input is text data, and the output is a risk assessment of fraud and sales activities. Specifically, the server searches for phrases and patterns that match known fraud and sales cases.

[0537] Step 4:

[0538] The device uses an emotion engine to analyze the user's voice tone and vocabulary to recognize their emotions. The input is the user's voice data, and the output is the user's emotional state. This emotional state is used to adjust the content and display method of warnings. Specifically, the device analyzes the pitch and speed of the voice to estimate the emotion.

[0539] Step 5:

[0540] The device generates a warning message and notifies the user based on the risk assessment results from the server and the user's emotional state. The inputs are the risk assessment results and the emotional state, and the output is a tailored warning message. Specifically, the device displays the warning to the user using push notifications.

[0541] (Application Example 1)

[0542] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0543] In modern society, the number of incoming calls from numbers not registered in phone directories is increasing, raising the risk of fraud and illegal sales activities. Furthermore, prompt and accurate information is required for users to respond appropriately to these calls. However, conventional systems fail to provide warnings that take into account the user's feelings, thus failing to alleviate user stress.

[0544] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0545] In this invention, the server includes means for detecting incoming calls from destinations not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, means for recognizing the user's emotions, and means for changing the content and display method of warnings according to those emotions. This enables the server to quickly and accurately warn users of the possibility of fraud or illegal sales activities, and to provide appropriate information according to the user's emotions.

[0546] "Means for detecting incoming calls from numbers not registered in the phonebook" refers to a function in a communication device that identifies and detects incoming calls from numbers not registered in the user's phonebook.

[0547] "Methods for analyzing speech" refer to technologies for processing audio data received during an incoming call and converting its content into text data or feature vectors.

[0548] "Methods for comparing with examples on information networks" refer to methods for comparing analyzed audio data with existing databases and examples on the internet to evaluate similarities and relationships.

[0549] "Means of issuing warnings" refers to a function that displays alerts or warning messages to users based on analysis results.

[0550] "Means of recognizing user emotions" refers to technologies that analyze a user's tone of voice and word choice to determine their emotional state.

[0551] "Means of changing the content and display method of warnings according to emotions" refers to a function that adjusts the content and display format of warning messages based on the recognized emotions of the user.

[0552] The system for implementing this invention mainly consists of a server and a user terminal. The server detects incoming calls from destinations not registered in the phone book and analyzes the voice. For the analysis, it uses the Python speech_recognition library to convert the voice data into text. In addition, it performs a process of comparing the analysis results with existing databases in order to compare them with examples on the information network.

[0553] Furthermore, the server uses the emotion_recognition library to recognize the user's emotions. This library analyzes the user's tone of voice and word choice to determine their emotional state. Based on the recognized emotion, processing is performed to change the content and display method of the warning. The warning is sent as a push notification to the user's device so that the user can check it immediately.

[0554] For example, if a user receives a phone call asking, "Would you like to purchase a new insurance product?", voice analysis will detect the keyword "purchase" and determine that it may be a scam. If the user is feeling stressed, an emphasized warning will be displayed saying, "This may be a scam. Please be careful!"

[0555] An example of a prompt message for a generative AI model would be: "Analyze this audio data to determine if it is potentially fraudulent or a sales pitch. Also, recognize the user's emotions and emphasize warnings if they are feeling stressed."

[0556] The flow of a specific process in Application Example 1 will be explained using Figure 16.

[0557] Step 1:

[0558] The server detects that there is an incoming call on the terminal. The input is the incoming call notification from the terminal. The server receives this notification and checks whether the incoming call is from a contact not registered in the phonebook. The output is the result of the determination of whether or not it is an unregistered incoming call.

[0559] Step 2:

[0560] The server retrieves audio data if it determines that the incoming call is unregistered. The input is audio data from the terminal. The server uses the Python speech_recognition library to convert this audio data into text. The output is the text data of the audio.

[0561] Step 3:

[0562] The server compares the converted text data with examples on the information network. The input is audio-to-text data. The server compares it with existing databases to assess the likelihood of fraud or sales. The output is the assessment result regarding the likelihood of fraud or sales.

[0563] Step 4:

[0564] The server recognizes the user's emotions from the audio data. The input is audio data from the terminal. The server uses the emotion_recognition library to analyze the user's voice tone and word choice to determine their emotional state. The output is the user's emotional state.

[0565] Step 5:

[0566] The server determines the content and display method of warnings based on the likelihood of fraud or sales and the user's emotional state. The inputs are the evaluation results regarding the likelihood of fraud or sales and the user's emotional state. The server generates a warning message and adjusts its display method according to the user's emotional state. The output is the warning message.

[0567] Step 6:

[0568] The server sends the generated warning message to the device as a push notification. The input is the warning message. The server sends this message to the device so the user can immediately acknowledge it. The output is the warning message displayed on the device.

[0569] (Example 2)

[0570] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0571] Users, including the elderly, may be unable to adequately respond to fraudulent activity or commercial communications originating from unregistered identification numbers, putting them at risk of becoming involved in scams or unnecessary commercial activities. It is essential to mitigate such risks and provide an environment where users can use communication devices with peace of mind.

[0572] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0573] In this invention, the server includes means for detecting connections from identification numbers not registered with the communication device, means for analyzing the voice information of the connection, and means for comparing the analysis results with examples on the information network. This enables users to receive prompt and appropriate warnings about fraudulent activity or communications for commercial purposes.

[0574] "Communication equipment" refers to electronic devices used for sending and receiving voice and data, including telephones and smartphones.

[0575] An "identification number" is a unique number assigned to a communication device, such as a telephone number or IP address.

[0576] "Connection" refers to a state in which voice and data can be exchanged between communication devices.

[0577] "Voice information" refers to voice data transmitted via communication devices.

[0578] "Analysis" refers to the process of processing audio information and converting its content into an understandable format.

[0579] An "information network" refers to a system for sharing digital information, such as the internet.

[0580] A "case" refers to a specific event or pattern that has been recorded in the past.

[0581] "Matching" refers to the process of comparing analyzed data with existing cases to determine if they match.

[0582] A "warning" refers to a message or notification intended to draw the user's attention.

[0583] "Emotional state" refers to the user's psychological state and can be inferred from their tone of voice and choice of words.

[0584] "Enhancement" refers to adjusting the content and presentation of a warning to make it more effective.

[0585] This invention is a system that uses a communication device to detect connections from unregistered identification numbers and analyzes the voice information. Specifically, when a terminal detects a connection from an unregistered identification number, it records the voice information and converts it into text data using speech recognition software. General speech recognition technology can be used in this process.

[0586] The server receives text data sent from the terminal and compares it against a case database on the information network. This comparison uses machine learning models to detect characteristics of fraudulent or commercially motivated communications. Based on the comparison results, the server generates an alert and sends it to the terminal.

[0587] The device notifies the user of any warnings it receives. These notifications are made through on-screen messages and vibrations. Furthermore, the device uses emotion recognition technology to assess the user's emotional state. If it determines that the user is experiencing anxiety or fear, the content and presentation of the warning are enhanced.

[0588] For example, when a user receives a call from an unregistered number on their smartphone, the device automatically records the call and converts the audio to text. The server then compares the text to a fraud database and generates a warning if it determines that the call may be fraudulent. If the system analyzes that the user is feeling uneasy, the warning is enhanced, and the device notifies the user with larger text and vibration.

[0589] Examples of prompts to input into a generative AI model:

[0590] "A call was received from an unregistered phone number. Please perform voice analysis to determine if it is a scam. Also, analyze the user's emotions and strengthen the warning as needed."

[0591] The flow of the specific processing in Example 2 will be explained using Figure 17.

[0592] Step 1:

[0593] The device detects a connection from an unregistered identification number. It receives the incoming identification number as input. The device verifies that this identification number is not registered in the phonebook and begins recording the connection. It generates the recorded audio data as output.

[0594] Step 2:

[0595] The terminal inputs recorded audio data into speech recognition software and converts it into text data. It receives audio data as input. The terminal analyzes the audio using speech recognition technology and outputs data in text format. This text data is used for subsequent analysis.

[0596] Step 3:

[0597] The server receives text data sent from the terminal and compares it with a case database on the information network. It receives text data as input. The server uses a machine learning model to detect characteristics of fraudulent or commercially motivated communications. It generates an assessment of the likelihood of fraud as output.

[0598] Step 4:

[0599] The server generates a warning message based on the evaluation results and sends it to the terminal. It receives the evaluation results as input. If the server detects a potential fraud, it generates a warning such as "This may be fraudulent activity." It generates a warning message as output and sends it to the terminal.

[0600] Step 5:

[0601] The device notifies the user of any warning messages it receives. It receives warning messages as input. The device displays the message on the screen and, if necessary, vibrates to alert the user. It then sends a warning notification to the user as output.

[0602] Step 6:

[0603] The device uses emotion recognition technology to evaluate the user's emotional state. It receives the user's voice data as input. The device analyzes the tone and word choice of the voice to evaluate the user's emotional state. It then generates an evaluation result regarding the emotional state as output.

[0604] Step 7:

[0605] The server enhances warnings based on the user's emotional state. It receives an assessment of the user's emotional state as input. If the server determines that the user is feeling anxious or fearful, it enhances the content and presentation of the warning. As output, it generates an enhanced warning message and sends it to the user's device.

[0606] (Application Example 2)

[0607] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0608] There is a need to reduce the risk of elderly people encountering fraudulent calls from unregistered phone numbers. Furthermore, it is necessary to provide appropriate warnings to elderly people if they feel anxious or frightened by the content of a phone call.

[0609] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0610] In this invention, the server includes means for detecting incoming calls from phone numbers not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples found on the internet, means for recognizing emotions from the tone of voice and word choice of the elderly person, and means for adjusting the content and display method of the warning based on the emotion recognition results. This makes it possible to reduce the risk of elderly people encountering fraudulent calls and to provide appropriate warnings that are tailored to their emotions.

[0611] "Means for detecting incoming calls from phone numbers not registered in the phonebook" refers to a function that identifies incoming calls from phone numbers not registered in the user's phonebook and notifies the system of that information.

[0612] "Methods for analyzing voice" refers to technology that processes voice data received during an incoming call and converts its content into text data.

[0613] "Methods of comparing with online cases" refer to the process of comparing the analyzed audio data with a database of fraud cases existing on the internet to assess the likelihood of fraud.

[0614] A "warning mechanism" is a function that displays or notifies users of a message to warn them if it is determined that there is a possibility of fraud.

[0615] "Means of recognizing emotions" refers to technology that analyzes the tone of a user's voice and word choice to determine their emotional state at that time.

[0616] "Means for adjusting the content and display method of warnings" refers to a function that optimizes the content and display method of warning messages based on recognized emotions, thereby conveying information to the user in an appropriate manner.

[0617] The system for implementing this invention mainly consists of a server and a user terminal. The server runs a program to detect incoming calls from phone numbers not registered in the phonebook. The user terminal records the voice when a call comes in and sends the voice data to the server. The server converts the voice data into text using a speech analysis library (e.g., Google Cloud Speech-to-Text). The converted text is compared against an online database of fraud cases. Furthermore, the server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice tone and word choice.

[0618] If the server determines that a scam is highly likely, it will send a warning notification to the user's device via push notification. The content and display method of this warning are adjusted based on the results of emotion recognition. For example, if the server detects that the user is feeling anxious, the warning will be displayed in large letters and accompanied by a strong vibration, stating, "This is likely a scam. Please be careful."

[0619] For example, if a user says "I'm worried," the server recognizes that emotion and highlights the warning. An example of a prompt to the generating AI model is, "Please evaluate the likelihood that this voice is a scam call. Voice content: 'Hello, your bank account is at risk. Immediate action is required.'" In this way, it is possible to reduce the risk of elderly people encountering scam calls and provide appropriate warnings that are tailored to their emotions.

[0620] The flow of a specific process in Application Example 2 will be explained using Figure 18.

[0621] Step 1:

[0622] The user's device detects an incoming call from a phone number not registered in the phonebook. The input is the incoming phone number, and the output is a confirmation that the number is not registered. Based on this information, the device starts recording audio.

[0623] Step 2:

[0624] The user's device records audio upon receiving a call and sends the audio data to the server. The input is the recorded audio data, and the output is the transmission of the audio data to the server. The device converts the audio data to the appropriate format and transfers it to the server.

[0625] Step 3:

[0626] The server uses a speech analysis library (e.g., Google Cloud Speech-to-Text) to convert received audio data into text. The input is audio data, and the output is text data. The server performs speech analysis and generates text data.

[0627] Step 4:

[0628] The server compares the converted text against an online database of fraud cases. The input is text data, and the output is an assessment of the likelihood of fraud. The server searches the database and evaluates the likelihood of fraud.

[0629] Step 5:

[0630] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice tone and vocabulary. The input is audio data, and the output is the result of emotion recognition. The server analyzes the audio data to identify the user's emotions.

[0631] Step 6:

[0632] If the server determines that there is a high probability of fraud, it sends a warning notification to the user's device via push notification. The input is the fraud probability assessment result and the sentiment recognition result, and the output is a warning message. The server adjusts the content and display method of the warning and notifies the user.

[0633] Step 7:

[0634] The user's device displays received warnings and provides feedback, such as vibration, as needed. The input is the warning message, and the output is visual and haptic feedback to the user. The device displays the warning on the screen to alert the user.

[0635] (Other examples)

[0636] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[0637] 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.

[0638] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0639] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[0640] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0641] [Third Embodiment]

[0642] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0643] 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.

[0644] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0645] 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.

[0646] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0647] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0648] 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.

[0649] 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.

[0650] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0651] The 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.

[0652] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0653] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0654] "Example of form 1"

[0655] One embodiment of this system is one that can be implemented in communication devices such as smartphones and personal computers. This system has a function to detect incoming calls from phone numbers not registered in the phone book. When a call comes in, the system analyzes the voice and compares the analysis results with examples found online. Based on the comparison results, it then issues a warning to the user, such as "Is this a scam call?" or "Is this a sales call from someone intending to buy something?" The warning is issued in the form of a push notification or similar, allowing the user to check it immediately.

[0656] "Example of form 2"

[0657] As a concrete example, consider a case where an elderly person is using a smartphone. When a call comes in from an unregistered phone number, the system of this invention analyzes the voice and compares the analysis results with examples found online. Then, it sends a push notification warning, "Is this a scam call?" This can significantly reduce the risk of elderly people encountering scams such as "ore-ore" (impersonation) scams.

[0658] The following describes the processing flow for each example of the form.

[0659] "Example of form 1"

[0660] Step 1: A system implemented in communication devices such as smartphones and personal computers detects incoming calls from phone numbers not registered in the phonebook.

[0661] Step 2: The system analyzes the incoming audio. This analysis is performed using speech recognition technology.

[0662] Step 3: Compare the analysis results with examples found online. This comparison is done by comparing the patterns and characteristics of the audio.

[0663] Step 4: Based on the comparison results, a warning is issued to the user, such as "Is this a scam call?" or "Is this a sales call from someone with an intention to buy?". This warning is issued in the form of a push notification or similar.

[0664] "Example of form 2"

[0665] Step 1: If an elderly person is using a smartphone, and they receive a call from an unregistered phone number, the system of the present invention analyzes the voice of that call.

[0666] Step 2: Compare the analysis results with examples found online. This comparison is done by comparing the patterns and characteristics of the audio.

[0667] Step 3: Send a push notification warning, "Is this a scam call?" This significantly reduces the risk of elderly people falling victim to scams such as "It's me" scams.

[0668] (Example 1)

[0669] Next, we will describe Embodiment 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0670] In today's communication environment, there has been an increase in communications originating from unregistered identifiers, leading to fraudulent activities and unwanted sales activities that pose a significant problem for users. Traditional methods have made it difficult to effectively identify these communications and provide warnings to users. Therefore, there is a need for a system that can quickly and accurately analyze communications from unregistered identifiers and provide appropriate warnings to users.

[0671] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0672] In this invention, the server includes means for detecting communications from unregistered identification information in a communication device, means for analyzing the voice information of the communications, and means for comparing the analysis results with examples in the information resource. This makes it possible to quickly analyze communications from unregistered identification information and warn users of the possibility of fraudulent activity or unnecessary sales activities.

[0673] "Communication equipment" refers to electronic devices used for transmitting and receiving voice and data, and includes telephones, computers, and other similar devices.

[0674] "Identification information" refers to information used to identify the source of a communication, and includes things like telephone numbers and IP addresses.

[0675] "Voice information" refers to voice data transmitted and received during communication, and is the subject of analysis.

[0676] "Analysis" refers to the process of converting audio information into text data and understanding its content.

[0677] "Information resources" refer to databases and case studies available on the internet, which are used to compare and contrast analysis results.

[0678] "Warning information" refers to notifications generated based on analysis results, informing users of potential fraudulent activity or unnecessary sales activities.

[0679] "Notification" refers to a means of conveying warning information to users, and includes push notifications and alert messages.

[0680] As an embodiment of this invention, a system is constructed in a communication device that detects communications from unregistered identification information in the phone book and analyzes the voice information. When a terminal receives a communications from unregistered identification information, it records the voice and sends it to a server. The server converts the voice data into text using voice analysis software. In this case, the Google Cloud Speech-to-Text API can be used.

[0681] The server uses a generative AI model to compare the converted text with examples in the information resource. Specifically, it uses OpenAI's GPT model to determine whether the text is related to fraudulent activity or unwanted sales activities. In this process, the server inputs the prompt "Is this call potentially fraudulent?" into the generative AI model.

[0682] Based on the analysis results, the server generates warning information and sends it to the device. The device displays the warning to the user via push notification. This allows the user to quickly understand if communications from unregistered identification information may be fraudulent or related to unwanted sales activities.

[0683] As a concrete example, if a user receives a call from "0123-456-7890," the device records the audio and sends it to the server. The server converts the audio to text and inputs the prompt "Is this call possibly a scam?" into a generating AI model. The generating AI model compares this with past data and generates a warning, "Is this a scam call?" The warning is sent to the user's device as a push notification, allowing the user to check it immediately.

[0684] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0685] Step 1:

[0686] The terminal detects communications originating from unregistered identifiers in the phonebook. It receives the communication's identifier as input and compares it against the phonebook. The output is the identification information confirmed to be unregistered. This process allows for the identification of unregistered communications.

[0687] Step 2:

[0688] The terminal records audio from communications originating from unregistered identification information. It receives audio data during communication as input and saves it as a digital audio file using a recording device. The recorded audio data is obtained as output. This operation prepares the audio data necessary for subsequent analysis.

[0689] Step 3:

[0690] The terminal sends the recorded audio data to the server. It receives the recorded audio data as input and sends it to the server via the communication network. The audio data is then transferred to the server as output. This process provides the server with the audio data for analysis.

[0691] Step 4:

[0692] The server uses speech analysis software to convert speech data into text. It uses speech data received from the terminal as input and converts it into text data using the Google Cloud Speech-to-Text API. The output is the converted text data. This process converts speech information into a parseable text format.

[0693] Step 5:

[0694] The server analyzes text data using a generative AI model and compares it with examples in the information resources. It uses the transformed text data as input and performs analysis using OpenAI's GPT model. The analysis results are obtained as output. This process allows for determining whether the text data is related to fraudulent activity or unwanted sales activities.

[0695] Step 6:

[0696] The server generates warning information based on the analysis results. It uses the analysis results as input to generate a warning message. The output is the warning information itself. This process prepares the server to provide appropriate warnings to the user.

[0697] Step 7:

[0698] The server sends the generated warning information to the terminal. It uses the warning information as input and transmits it to the terminal via the communication network. The warning information is then transferred to the terminal as output. This process provides the user with the warning information.

[0699] Step 8:

[0700] The device displays the received warning information to the user as a push notification. It uses the warning information received from the server as input and displays it to the user using the device's notification function. The user confirms the warning information as output. This process allows the user to quickly receive warnings about communications from unregistered identification information.

[0701] (Application Example 1)

[0702] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0703] In modern society, the risk of fraud and illegal sales calls from unregistered phone numbers is increasing. While users are required to respond quickly and accurately to such calls, traditional methods make this decision difficult.

[0704] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0705] In this invention, the server includes means for detecting incoming calls from unregistered phone numbers, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, means for speech recognition to convert the audio into text, means for analyzing the possibility of fraud using a generative AI model, and means for issuing a warning based on the analysis results. This enables users to quickly determine the possibility of fraud when receiving calls from unregistered phone numbers and take appropriate action.

[0706] "Unregistered phone numbers" refer to numbers that are not stored on the user's communication device and for which specific information is not registered when an incoming call is received.

[0707] "Means for detecting incoming calls" refers to a device or program in a communication device that has the function of sensing an incoming call from an external source and acquiring that information.

[0708] "Means for analyzing speech" refers to technology or equipment for processing received speech data and understanding or classifying its content.

[0709] "Case examples on information networks" refers to a collection of past similar events or data that exist on the internet or other digital networks.

[0710] "Speech recognition means" refers to a technology or device for converting speech data into text data.

[0711] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate a specific output based on input data.

[0712] "Means for analyzing the possibility of fraud" refers to technology or equipment used to determine whether the content of received data constitutes fraudulent activity.

[0713] A "means of issuing a warning" refers to a device or program that has a notification function for alerting or providing information to the user.

[0714] The system for implementing this invention mainly consists of a server and a user terminal. The server detects incoming calls from numbers not registered in the phonebook and runs a program to analyze the voice. For voice analysis, the Google Cloud Speech-to-Text API is used to convert the voice data into text data. The converted text data is analyzed using the generative AI model OpenAI GPT to determine the likelihood of fraud.

[0715] The user's device receives a push notification if there is a potential scam based on analysis results from the server. This warning is designed to allow the user to respond quickly.

[0716] For example, if a user receives a call from "0120-XXXX-XXXX", the server converts the audio into text and inputs the following prompt into the AI ​​generation model: "Is this text potentially a scam? Content: You have won a special campaign." If the AI ​​generation model determines that it is "highly likely to be a scam," a warning message "This may be a scam. Please be careful." is sent to the user's device.

[0717] In this way, users can quickly determine the possibility of fraud when receiving calls from unregistered numbers and take appropriate action.

[0718] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0719] Step 1:

[0720] The server receives incoming call information from the user's terminal. The input is incoming call data from a call number not registered in the phonebook. The server prepares to analyze this data.

[0721] Step 2:

[0722] The server receives incoming audio data and converts it to text using the Google Cloud Speech-to-Text API. The input is audio data, and the output is text data. This conversion makes the audio content available as text information.

[0723] Step 3:

[0724] The server inputs text data into the OpenAI GPT generative AI model and analyzes its likelihood of being a scam. The input is text data, and the output is the analysis result regarding the likelihood of fraud. The server generates a prompt sentence and asks the model, "Is this text likely to be a scam?"

[0725] Step 4:

[0726] The server receives the analysis results from the generated AI model and generates a warning based on those results. The input is the analysis result, and the output is the warning message. The server creates a warning such as "This may be a scam. Please be careful." if there is a high probability of fraud.

[0727] Step 5:

[0728] The server sends the generated warning message as a push notification to the user's device. The input is the warning message, and the output is the notification displayed on the user's device. The user receives this notification and can take appropriate action regarding the incoming message.

[0729] (Example 2)

[0730] Next, we will describe Example 2 of the Form Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0731] Many users, including the elderly, are vulnerable to unauthorized connections from unregistered identification numbers. In particular, there is a growing need for effective measures to mitigate these risks, especially given the increasing prevalence of fraudulent activities and unethical sales practices.

[0732] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0733] In this invention, the server includes means for detecting connections from unregistered identification numbers in the communication device, means for acquiring audio information of said connections, and means for converting said audio information into text information. This makes it possible to quickly detect the possibility of fraudulent activity from unregistered identification numbers and notify the user of a warning.

[0734] "Communication equipment" refers to electronic devices used for sending and receiving voice and data, including telephones and smartphones.

[0735] An "identification number" is a unique number assigned to a communication device, such as a telephone number or IP address.

[0736] "Connection" refers to the establishment of a communication link between communication devices, including the initiation of voice calls and data communications.

[0737] "Voice information" refers to voice data transmitted via communication devices, including the content of phone calls.

[0738] "Textual information" refers to text data obtained by converting audio information, and is generated using speech recognition technology.

[0739] "Analysis" refers to the process of processing acquired data and understanding its content and meaning.

[0740] An "information database" is a collection of data that stores past cases and related information, and is used to verify analysis results.

[0741] A "warning" is a notification intended to alert users and may include information about the possibility of fraudulent activity.

[0742] "Notification" refers to a means of conveying information to users, including push notifications and alert messages.

[0743] To implement this invention, the terminal first detects a connection from an unregistered identification number. When a connection is established, the terminal records the call content and sends it to the server as audio information. The server converts the received audio information into text information using the Google Cloud Speech-to-Text API. This API provides highly accurate speech recognition and quickly converts speech to text.

[0744] Next, the server inputs the converted text information into a generative AI model. Specifically, it uses a model such as OpenAI's GPT model and inputs the prompt "Is this phone call potentially a scam?". The generative AI model analyzes the text information and determines the likelihood of it being a scam.

[0745] Based on the analysis results, the server generates a warning. The warning includes the message, "Is this potentially fraudulent activity?", and is immediately sent as a push notification to the device. By receiving this notification, users can become more vigilant against potentially fraudulent connections.

[0746] As a concrete example, if a user receives a call from an unregistered number, the device automatically records the audio and sends it to a server. The server converts the audio to text and inputs prompt text into a generative AI model. Based on the model's analysis, the server sends a warning to the user. This entire process allows users to anticipate the risk of fraudulent calls and take appropriate action.

[0747] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0748] Step 1:

[0749] The terminal detects connections from unregistered identification numbers. Once a connection is established, the terminal records the call and prepares the data as audio information. This audio information becomes input for the next processing step.

[0750] Step 2:

[0751] The device sends the recorded audio information to the server. The server converts the received audio information into text using the Google Cloud Speech-to-Text API. This conversion process involves speech recognition to convert the audio data into text data. The output is text information for analysis.

[0752] Step 3:

[0753] The server inputs the converted text information into the generating AI model. Specifically, it uses the prompt "Is this phone call potentially a scam?" to request analysis from the generating AI model. The model analyzes the text information and determines the likelihood of it being a scam. This analysis result becomes the output for the next step.

[0754] Step 4:

[0755] The server generates a warning based on the analysis results obtained from the generated AI model. The warning includes the message "Is this a possible case of fraudulent activity?" and is immediately sent as a push notification to the device. This notification is what is output to the user.

[0756] Step 5:

[0757] The user checks the warning notification received from their device. Based on this notification, the user can become more vigilant against potentially fraudulent connections and take appropriate action if necessary.

[0758] (Application Example 2)

[0759] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server," and the headset-type terminal 314 will be referred to as a "terminal."

[0760] There is a need for a means to enable users, including the elderly, to quickly assess the risk of fraud and illegal transactions from connections made using unregistered identification information, and to prevent damage before it occurs. However, conventional technologies have made it difficult to analyze these risks in real time and provide appropriate warnings.

[0761] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0762] In this invention, the server includes means for detecting connections from unregistered identification information in the communication device, means for analyzing the voice information of the connection, and means for comparing the analysis results with examples on the information network. This enables users to determine the possibility of fraud or illegal transactions in real time and receive a warning quickly.

[0763] "Communication equipment" refers to devices used for sending and receiving voice and data, and includes smartphones and computers.

[0764] "Unregistered identification information" refers to information such as phone numbers and IDs that are not registered in the user's database.

[0765] "Connection" refers to the exchange of voice and data that takes place via communication devices.

[0766] "Voice information" refers to voice data from phone calls or recordings, and is the subject of analysis.

[0767] "Analysis" refers to the process of converting audio information into text data and then analyzing its content.

[0768] An "information network" refers to the internet and other digital networks used for matching and searching data.

[0769] "Case examples" refer to specific cases of fraud or illegal transactions that have been recorded in the past.

[0770] A "warning" refers to a notification or message intended to inform users of potential fraud or misconduct.

[0771] "Real-time" refers to processing and analysis being performed almost instantly, meaning that delays are minimized.

[0772] The system for implementing this invention primarily uses a communication device, a server, and an information network. The communication device is a terminal such as a smartphone, which detects connections from unregistered identification information. The server analyzes the connected voice information and converts it into text data using a generative AI model. This analysis uses a voice analysis library such as the Google Cloud Speech-to-Text API.

[0773] The analyzed text data is compared against a case database on the information network. The database records past cases of fraud and illicit transactions, and the server uses this to determine the likelihood of fraud. If fraud is determined to be possible, the server sends an alert to the user's communication device using a push notification service (e.g., Firebase Cloud Messaging).

[0774] For example, if a user receives a call from an unregistered number and the caller says, "Your bank account is at risk," the server analyzes the audio and compares it to a database of fraud cases. If it is determined that there is a high probability of fraud, it sends a warning to the user asking, "Is this a scam?"

[0775] An example of a prompt to input into the generating AI model is: "Please determine if this voice message is potentially fraudulent. Message content: 'Your bank account is at risk.'"

[0776] In this way, users can assess the risk of fraud and illegal transactions in real time and take swift action.

[0777] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0778] Step 1:

[0779] The terminal detects connections from unregistered identification information. The input is the incoming phone number, and the output is the result of determining that it is unregistered. The terminal compares it with the phonebook database, and if it is unregistered, proceeds to the next step.

[0780] Step 2:

[0781] The terminal collects connected audio information and sends it to the server. The input is the audio data during the call, and the output is the transfer of the audio data to the server. The terminal captures the audio data in real time and streams it to the server.

[0782] Step 3:

[0783] The server analyzes the received audio data and converts it into text data. The input is audio data sent from the terminal, and the output is text data. The server uses the Google Cloud Speech-to-Text API to convert the audio to text.

[0784] Step 4:

[0785] The server analyzes text data using a generative AI model to determine the likelihood of fraud. The input is the transformed text data, and the output is the evaluation result of the likelihood of fraud. The server inputs the text data as a prompt into the generative AI model and evaluates the likelihood of fraud.

[0786] Step 5:

[0787] If the server determines that there is a high probability of fraud, it generates a push notification and sends it to the device. The input is the result of the fraud probability assessment, and the output is a warning message. The server uses Firebase Cloud Messaging to send the user a warning asking, "Is this a scam?"

[0788] Step 6:

[0789] The user reviews the warning message displayed on the device and, if necessary, ends the call or takes further action. The input is the warning message displayed on the device, and the output is the user's action. The user either ends the call after receiving the warning or takes additional confirmation.

[0790] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0791] "Example of form 1"

[0792] One embodiment of the present invention is a system incorporating an emotion engine. This system detects incoming calls from phone numbers not registered in the phone book and analyzes the incoming call's audio. It compares the analysis results with online examples and issues a warning based on the comparison. Furthermore, this system includes an emotion engine that recognizes the user's emotions. The emotion engine recognizes the user's emotions from their tone of voice and word choice, and changes the content and display method of the warning according to those emotions. "Example 2"

[0793] As a concrete example, consider a scenario where an elderly person is using a smartphone. When a call comes in from an unregistered phone number, the system of this invention analyzes the voice. The analysis results are compared with examples found online, and a warning is issued, such as, "Could this be a scam call?" Furthermore, the emotion engine recognizes the elderly person's emotions from their tone of voice and word choice. For example, if it detects that the elderly person is feeling anxious or frightened, the warning is made more specific, such as, "This is likely a scam. Please be careful," and the warning display method is changed to larger font and stronger vibration. This significantly reduces the risk of elderly people encountering scams such as "ore-ore" (impersonation) scams.

[0794] The following describes the processing flow for each example of the form.

[0795] "Example of form 1"

[0796] Step 1: Detect incoming calls from phone numbers not registered in the phonebook.

[0797] Step 2: Analyze the incoming call audio.

[0798] Step 3: Compare the analysis results with examples found online.

[0799] Step 4: Issue a warning based on the comparison results.

[0800] Step 5: Recognize the user's emotions from their tone of voice and word choice.

[0801] Step 6: Change the content and display method of the warning according to the emotion.

[0802] "Example of form 2"

[0803] Step 1: If an elderly person is using a smartphone, analyze the audio when a call comes in from an unregistered phone number.

[0804] Step 2: Compare the analysis results with online examples and issue a warning asking, "Could this be a scam call?"

[0805] Step 3: Recognize the emotions of the elderly person from their tone of voice and word choice.

[0806] Step 4: For example, if you recognize that an elderly person is feeling anxious or frightened, make the warning more specific, such as "This is likely a scam. Please be careful," and change the way the warning is displayed, such as using larger fonts or stronger vibrations.

[0807] (Example 1)

[0808] Next, we will describe Embodiment 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0809] In today's communication environment, incoming calls from numbers not registered in phonebooks are increasing, and the resulting fraud and illegal business activities are becoming a social problem. Traditional systems struggle to provide users with appropriate warnings about these incoming calls, often causing them anxiety. Furthermore, the inability to respond flexibly to user emotions limits the effectiveness of warnings.

[0810] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0811] In this invention, the server includes means for detecting incoming calls from destinations not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, and means for recognizing the user's emotions and adjusting the content and display method of the warning according to those emotions. This enables the server to quickly and accurately warn the user of the possibility of fraud or illegal business activities, and to respond flexibly according to the user's emotions.

[0812] A "telephone directory" is a database that lists contact information registered on communication devices, and mainly includes names and phone numbers.

[0813] "Unregistered contacts" refers to contacts not registered in the phone book, meaning that the caller's identification information is unknown when they receive a call.

[0814] An "incoming call" refers to an external call being made to a communication device, and it is a signal that prompts the start of a voice call.

[0815] "Means of analyzing speech" refers to technical methods for converting speech data into text data and analyzing its content.

[0816] "Case studies on information networks" refers to databases that collect similar past events and cases that exist on networks such as the internet.

[0817] "Means of issuing warnings" refers to methods and technologies for notifying users of cautions and dangerous information.

[0818] "Means of recognizing emotions" refers to technologies that analyze a user's tone of voice and word choice to determine their emotional state.

[0819] "Means for adjusting the content and display method of warnings" refers to technologies that change the content and display format of warning messages according to the user's emotional state.

[0820] This invention is a system for detecting incoming calls from unregistered destinations in communication equipment and providing appropriate warnings to the user. Specific embodiments of this system are described below.

[0821] The device detects incoming calls from numbers not registered in the phonebook. Upon receiving a call, the device uses voice analysis software to convert the incoming audio into text data. This voice analysis utilizes speech recognition technology.

[0822] The server compares the analyzed text data with a case database on the information network. This database contains a collection of past fraud and sales activity cases, and the server uses this to assess the risk of incoming calls.

[0823] Furthermore, the device uses an emotion engine to analyze the user's tone of voice and word choice, recognizing the user's emotions. Based on this emotion recognition, the content and display method of warnings are adjusted according to the user's emotions.

[0824] For example, if a call comes in from an unregistered number, the device records the audio and sends it to the server. Based on the analysis, the server determines that there is a "possible scam" and sends a warning to the device. If the user responds with an anxious voice, the emotion engine recognizes that emotion and displays the warning message emphatically as "Caution! This may be a scam."

[0825] Examples of prompts include, "Please describe a system that analyzes incoming calls from unregistered destinations to determine if they are potentially fraudulent," and "Please provide a specific example of a system that uses an emotion engine to issue warnings based on the user's emotions."

[0826] In this way, the system can provide users with prompt and accurate warnings, thereby improving the security of communications.

[0827] The flow of the specific processing in Example 1 will be explained using Figure 15.

[0828] Step 1:

[0829] The terminal detects incoming calls from numbers not registered in the phonebook. The input is an incoming call signal, and the output is information about the unregistered caller. This information is used in subsequent processing steps. Specifically, the terminal checks the phonebook upon receiving an incoming call to confirm that the number is not registered.

[0830] Step 2:

[0831] The terminal records incoming audio and converts it into text data using speech analysis software. The input is the recorded audio data, and the output is the analyzed text data. This text data is used for subsequent database matching. Specifically, the terminal uses speech recognition technology to convert speech into text information.

[0832] Step 3:

[0833] The server compares the analyzed text data with a case database on the information network. The input is text data, and the output is a risk assessment of fraud and sales activities. Specifically, the server searches for phrases and patterns that match known fraud and sales cases.

[0834] Step 4:

[0835] The device uses an emotion engine to analyze the user's voice tone and vocabulary to recognize their emotions. The input is the user's voice data, and the output is the user's emotional state. This emotional state is used to adjust the content and display method of warnings. Specifically, the device analyzes the pitch and speed of the voice to estimate the emotion.

[0836] Step 5:

[0837] The device generates a warning message and notifies the user based on the risk assessment results from the server and the user's emotional state. The inputs are the risk assessment results and the emotional state, and the output is a tailored warning message. Specifically, the device displays the warning to the user using push notifications.

[0838] (Application Example 1)

[0839] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0840] In modern society, the number of incoming calls from numbers not registered in phone directories is increasing, raising the risk of fraud and illegal sales activities. Furthermore, prompt and accurate information is required for users to respond appropriately to these calls. However, conventional systems fail to provide warnings that take into account the user's feelings, thus failing to alleviate user stress.

[0841] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0842] In this invention, the server includes means for detecting incoming calls from destinations not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, means for recognizing the user's emotions, and means for changing the content and display method of warnings according to those emotions. This enables the server to quickly and accurately warn users of the possibility of fraud or illegal sales activities, and to provide appropriate information according to the user's emotions.

[0843] "Means for detecting incoming calls from numbers not registered in the phonebook" refers to a function in a communication device that identifies and detects incoming calls from numbers not registered in the user's phonebook.

[0844] "Methods for analyzing speech" refer to technologies for processing audio data received during an incoming call and converting its content into text data or feature vectors.

[0845] "Methods for comparing with examples on information networks" refer to methods for comparing analyzed audio data with existing databases and examples on the internet to evaluate similarities and relationships.

[0846] "Means of issuing warnings" refers to a function that displays alerts or warning messages to users based on analysis results.

[0847] "Means of recognizing user emotions" refers to technologies that analyze a user's tone of voice and word choice to determine their emotional state.

[0848] "Means of changing the content and display method of warnings according to emotions" refers to a function that adjusts the content and display format of warning messages based on the recognized emotions of the user.

[0849] The system for implementing this invention mainly consists of a server and a user terminal. The server detects incoming calls from destinations not registered in the phone book and analyzes the voice. For the analysis, it uses the Python speech_recognition library to convert the voice data into text. In addition, it performs a process of comparing the analysis results with existing databases in order to compare them with examples on the information network.

[0850] Furthermore, the server uses the emotion_recognition library to recognize the user's emotions. This library analyzes the user's tone of voice and word choice to determine their emotional state. Based on the recognized emotion, processing is performed to change the content and display method of the warning. The warning is sent as a push notification to the user's device so that the user can check it immediately.

[0851] For example, if a user receives a phone call asking, "Would you like to purchase a new insurance product?", voice analysis will detect the keyword "purchase" and determine that it may be a scam. If the user is feeling stressed, an emphasized warning will be displayed saying, "This may be a scam. Please be careful!"

[0852] An example of a prompt message for a generative AI model would be: "Analyze this audio data to determine if it is potentially fraudulent or a sales pitch. Also, recognize the user's emotions and emphasize warnings if they are feeling stressed."

[0853] The flow of a specific process in Application Example 1 will be explained using Figure 16.

[0854] Step 1:

[0855] The server detects that there is an incoming call on the terminal. The input is the incoming call notification from the terminal. The server receives this notification and checks whether the incoming call is from a contact not registered in the phonebook. The output is the result of the determination of whether or not it is an unregistered incoming call.

[0856] Step 2:

[0857] The server retrieves audio data if it determines that the incoming call is unregistered. The input is audio data from the terminal. The server uses the Python speech_recognition library to convert this audio data into text. The output is the text data of the audio.

[0858] Step 3:

[0859] The server compares the converted text data with examples on the information network. The input is audio-to-text data. The server compares it with existing databases to assess the likelihood of fraud or sales. The output is the assessment result regarding the likelihood of fraud or sales.

[0860] Step 4:

[0861] The server recognizes the user's emotions from the audio data. The input is audio data from the terminal. The server uses the emotion_recognition library to analyze the user's voice tone and word choice to determine their emotional state. The output is the user's emotional state.

[0862] Step 5:

[0863] The server determines the content and display method of warnings based on the likelihood of fraud or sales and the user's emotional state. The inputs are the evaluation results regarding the likelihood of fraud or sales and the user's emotional state. The server generates a warning message and adjusts its display method according to the user's emotional state. The output is the warning message.

[0864] Step 6:

[0865] The server sends the generated warning message to the device as a push notification. The input is the warning message. The server sends this message to the device so the user can immediately acknowledge it. The output is the warning message displayed on the device.

[0866] (Example 2)

[0867] Next, we will describe Example 2 of the Form Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0868] Users, including the elderly, may be unable to adequately respond to fraudulent activity or commercial communications originating from unregistered identification numbers, putting them at risk of becoming involved in scams or unnecessary commercial activities. It is essential to mitigate such risks and provide an environment where users can use communication devices with peace of mind.

[0869] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0870] In this invention, the server includes means for detecting connections from identification numbers not registered with the communication device, means for analyzing the voice information of the connection, and means for comparing the analysis results with examples on the information network. This enables users to receive prompt and appropriate warnings about fraudulent activity or communications for commercial purposes.

[0871] "Communication equipment" refers to electronic devices used for sending and receiving voice and data, including telephones and smartphones.

[0872] An "identification number" is a unique number assigned to a communication device, such as a telephone number or IP address.

[0873] "Connection" refers to a state in which voice and data can be exchanged between communication devices.

[0874] "Voice information" refers to voice data transmitted via communication devices.

[0875] "Analysis" refers to the process of processing audio information and converting its content into an understandable format.

[0876] An "information network" refers to a system for sharing digital information, such as the internet.

[0877] A "case" refers to a specific event or pattern that has been recorded in the past.

[0878] "Matching" refers to the process of comparing analyzed data with existing cases to determine if they match.

[0879] A "warning" refers to a message or notification intended to draw the user's attention.

[0880] "Emotional state" refers to the user's psychological state and can be inferred from their tone of voice and choice of words.

[0881] "Enhancement" refers to adjusting the content and presentation of a warning to make it more effective.

[0882] This invention is a system that uses a communication device to detect connections from unregistered identification numbers and analyzes the voice information. Specifically, when a terminal detects a connection from an unregistered identification number, it records the voice information and converts it into text data using speech recognition software. General speech recognition technology can be used in this process.

[0883] The server receives text data sent from the terminal and compares it against a case database on the information network. This comparison uses machine learning models to detect characteristics of fraudulent or commercially motivated communications. Based on the comparison results, the server generates an alert and sends it to the terminal.

[0884] The device notifies the user of any warnings it receives. These notifications are made through on-screen messages and vibrations. Furthermore, the device uses emotion recognition technology to assess the user's emotional state. If it determines that the user is experiencing anxiety or fear, the content and presentation of the warning are enhanced.

[0885] For example, when a user receives a call from an unregistered number on their smartphone, the device automatically records the call and converts the audio to text. The server then compares the text to a fraud database and generates a warning if it determines that the call may be fraudulent. If the system analyzes that the user is feeling uneasy, the warning is enhanced, and the device notifies the user with larger text and vibration.

[0886] Examples of prompts to input into a generative AI model:

[0887] "A call was received from an unregistered phone number. Please perform voice analysis to determine if it is a scam. Also, analyze the user's emotions and strengthen the warning as needed."

[0888] The flow of the specific processing in Example 2 will be explained using Figure 17.

[0889] Step 1:

[0890] The device detects a connection from an unregistered identification number. It receives the incoming identification number as input. The device verifies that this identification number is not registered in the phonebook and begins recording the connection. It generates the recorded audio data as output.

[0891] Step 2:

[0892] The terminal inputs recorded audio data into speech recognition software and converts it into text data. It receives audio data as input. The terminal analyzes the audio using speech recognition technology and outputs data in text format. This text data is used for subsequent analysis.

[0893] Step 3:

[0894] The server receives text data sent from the terminal and compares it with a case database on the information network. It receives text data as input. The server uses a machine learning model to detect characteristics of fraudulent or commercially motivated communications. It generates an assessment of the likelihood of fraud as output.

[0895] Step 4:

[0896] The server generates a warning message based on the evaluation results and sends it to the terminal. It receives the evaluation results as input. If the server detects a potential fraud, it generates a warning such as "This may be fraudulent activity." It generates a warning message as output and sends it to the terminal.

[0897] Step 5:

[0898] The device notifies the user of any warning messages it receives. It receives warning messages as input. The device displays the message on the screen and, if necessary, vibrates to alert the user. It then sends a warning notification to the user as output.

[0899] Step 6:

[0900] The device uses emotion recognition technology to evaluate the user's emotional state. It receives the user's voice data as input. The device analyzes the tone and word choice of the voice to evaluate the user's emotional state. It then generates an evaluation result regarding the emotional state as output.

[0901] Step 7:

[0902] The server enhances warnings based on the user's emotional state. It receives an assessment of the user's emotional state as input. If the server determines that the user is feeling anxious or fearful, it enhances the content and presentation of the warning. As output, it generates an enhanced warning message and sends it to the user's device.

[0903] (Application Example 2)

[0904] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server," and the headset-type terminal 314 will be referred to as a "terminal."

[0905] There is a need to reduce the risk of elderly people encountering fraudulent calls from unregistered phone numbers. Furthermore, it is necessary to provide appropriate warnings to elderly people if they feel anxious or frightened by the content of a phone call.

[0906] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0907] In this invention, the server includes means for detecting incoming calls from phone numbers not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples found on the internet, means for recognizing emotions from the tone of voice and word choice of the elderly person, and means for adjusting the content and display method of the warning based on the emotion recognition results. This makes it possible to reduce the risk of elderly people encountering fraudulent calls and to provide appropriate warnings that are tailored to their emotions.

[0908] "Means for detecting incoming calls from phone numbers not registered in the phonebook" refers to a function that identifies incoming calls from phone numbers not registered in the user's phonebook and notifies the system of that information.

[0909] "Methods for analyzing voice" refers to technology that processes voice data received during an incoming call and converts its content into text data.

[0910] "Methods of comparing with online cases" refer to the process of comparing the analyzed audio data with a database of fraud cases existing on the internet to assess the likelihood of fraud.

[0911] A "warning mechanism" is a function that displays or notifies users of a message to warn them if it is determined that there is a possibility of fraud.

[0912] "Means of recognizing emotions" refers to technology that analyzes the tone of a user's voice and word choice to determine their emotional state at that time.

[0913] "Means for adjusting the content and display method of warnings" refers to a function that optimizes the content and display method of warning messages based on recognized emotions, thereby conveying information to the user in an appropriate manner.

[0914] The system for implementing this invention mainly consists of a server and a user terminal. The server runs a program to detect incoming calls from phone numbers not registered in the phonebook. The user terminal records the voice when a call comes in and sends the voice data to the server. The server converts the voice data into text using a speech analysis library (e.g., Google Cloud Speech-to-Text). The converted text is compared against an online database of fraud cases. Furthermore, the server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice tone and word choice.

[0915] If the server determines that a scam is highly likely, it will send a warning notification to the user's device via push notification. The content and display method of this warning are adjusted based on the results of emotion recognition. For example, if the server detects that the user is feeling anxious, the warning will be displayed in large letters and accompanied by a strong vibration, stating, "This is likely a scam. Please be careful."

[0916] For example, if a user says "I'm worried," the server recognizes that emotion and highlights the warning. An example of a prompt to the generating AI model is, "Please evaluate the likelihood that this voice is a scam call. Voice content: 'Hello, your bank account is at risk. Immediate action is required.'" In this way, it is possible to reduce the risk of elderly people encountering scam calls and provide appropriate warnings that are tailored to their emotions.

[0917] The flow of a specific process in Application Example 2 will be explained using Figure 18.

[0918] Step 1:

[0919] The user's device detects an incoming call from a phone number not registered in the phonebook. The input is the incoming phone number, and the output is a confirmation that the number is not registered. Based on this information, the device starts recording audio.

[0920] Step 2:

[0921] The user's device records audio upon receiving a call and sends the audio data to the server. The input is the recorded audio data, and the output is the transmission of the audio data to the server. The device converts the audio data to the appropriate format and transfers it to the server.

[0922] Step 3:

[0923] The server uses a speech analysis library (e.g., Google Cloud Speech-to-Text) to convert received audio data into text. The input is audio data, and the output is text data. The server performs speech analysis and generates text data.

[0924] Step 4:

[0925] The server compares the converted text against an online database of fraud cases. The input is text data, and the output is an assessment of the likelihood of fraud. The server searches the database and evaluates the likelihood of fraud.

[0926] Step 5:

[0927] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice tone and vocabulary. The input is audio data, and the output is the result of emotion recognition. The server analyzes the audio data to identify the user's emotions.

[0928] Step 6:

[0929] If the server determines that there is a high probability of fraud, it sends a warning notification to the user's device via push notification. The input is the fraud probability assessment result and the sentiment recognition result, and the output is a warning message. The server adjusts the content and display method of the warning and notifies the user.

[0930] Step 7:

[0931] The user's device displays received warnings and provides feedback, such as vibration, as needed. The input is the warning message, and the output is visual and haptic feedback to the user. The device displays the warning on the screen to alert the user.

[0932] (Other examples)

[0933] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[0934] 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.

[0935] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0936] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[0937] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0938] [Fourth Embodiment]

[0939] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0940] 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.

[0941] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0942] 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.

[0943] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0944] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0945] 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.

[0946] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0947] 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.

[0948] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0949] The 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.

[0950] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0951] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0952] "Example of form 1"

[0953] One embodiment of this system is one that can be implemented in communication devices such as smartphones and personal computers. This system has a function to detect incoming calls from phone numbers not registered in the phone book. When a call comes in, the system analyzes the voice and compares the analysis results with examples found online. Based on the comparison results, it then issues a warning to the user, such as "Is this a scam call?" or "Is this a sales call from someone intending to buy something?" The warning is issued in the form of a push notification or similar, allowing the user to check it immediately.

[0954] "Example of form 2"

[0955] As a concrete example, consider a case where an elderly person is using a smartphone. When a call comes in from an unregistered phone number, the system of this invention analyzes the voice and compares the analysis results with examples found online. Then, it sends a push notification warning, "Is this a scam call?" This can significantly reduce the risk of elderly people encountering scams such as "ore-ore" (impersonation) scams.

[0956] The following describes the processing flow for each example of the form.

[0957] "Example of form 1"

[0958] Step 1: A system implemented in communication devices such as smartphones and personal computers detects incoming calls from phone numbers not registered in the phonebook.

[0959] Step 2: The system analyzes the incoming audio. This analysis is performed using speech recognition technology.

[0960] Step 3: Compare the analysis results with examples found online. This comparison is done by comparing the patterns and characteristics of the audio.

[0961] Step 4: Based on the comparison results, a warning is issued to the user, such as "Is this a scam call?" or "Is this a sales call from someone with an intention to buy?". This warning is issued in the form of a push notification or similar.

[0962] "Example of form 2"

[0963] Step 1: If an elderly person is using a smartphone, and they receive a call from an unregistered phone number, the system of the present invention analyzes the voice of that call.

[0964] Step 2: Compare the analysis results with examples found online. This comparison is done by comparing the patterns and characteristics of the audio.

[0965] Step 3: Send a push notification warning, "Is this a scam call?" This significantly reduces the risk of elderly people falling victim to scams such as "It's me" scams.

[0966] (Example 1)

[0967] Next, we will describe Embodiment 1 of Example Form 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0968] In today's communication environment, there has been an increase in communications originating from unregistered identifiers, leading to fraudulent activities and unwanted sales activities that pose a significant problem for users. Traditional methods have made it difficult to effectively identify these communications and provide warnings to users. Therefore, there is a need for a system that can quickly and accurately analyze communications from unregistered identifiers and provide appropriate warnings to users.

[0969] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0970] In this invention, the server includes means for detecting communications from unregistered identification information in a communication device, means for analyzing the voice information of the communications, and means for comparing the analysis results with examples in the information resource. This makes it possible to quickly analyze communications from unregistered identification information and warn users of the possibility of fraudulent activity or unnecessary sales activities.

[0971] "Communication equipment" refers to electronic devices used for transmitting and receiving voice and data, and includes telephones, computers, and other similar devices.

[0972] "Identification information" refers to information used to identify the source of a communication, and includes things like telephone numbers and IP addresses.

[0973] "Voice information" refers to voice data transmitted and received during communication, and is the subject of analysis.

[0974] "Analysis" refers to the process of converting audio information into text data and understanding its content.

[0975] "Information resources" refer to databases and case studies available on the internet, which are used to compare and contrast analysis results.

[0976] "Warning information" refers to notifications generated based on analysis results, informing users of potential fraudulent activity or unnecessary sales activities.

[0977] "Notification" refers to a means of conveying warning information to users, and includes push notifications and alert messages.

[0978] As an embodiment of this invention, a system is constructed in a communication device that detects communications from unregistered identification information in the phone book and analyzes the voice information. When a terminal receives a communications from unregistered identification information, it records the voice and sends it to a server. The server converts the voice data into text using voice analysis software. In this case, the Google Cloud Speech-to-Text API can be used.

[0979] The server uses a generative AI model to compare the converted text with examples in the information resource. Specifically, it uses OpenAI's GPT model to determine whether the text is related to fraudulent activity or unwanted sales activities. In this process, the server inputs the prompt "Is this call potentially fraudulent?" into the generative AI model.

[0980] Based on the analysis results, the server generates warning information and sends it to the device. The device displays the warning to the user via push notification. This allows the user to quickly understand if communications from unregistered identification information may be fraudulent or related to unwanted sales activities.

[0981] As a concrete example, if a user receives a call from "0123-456-7890," the device records the audio and sends it to the server. The server converts the audio to text and inputs the prompt "Is this call possibly a scam?" into a generating AI model. The generating AI model compares this with past data and generates a warning, "Is this a scam call?" The warning is sent to the user's device as a push notification, allowing the user to check it immediately.

[0982] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0983] Step 1:

[0984] The terminal detects communications originating from unregistered identifiers in the phonebook. It receives the communication's identifier as input and compares it against the phonebook. The output is the identification information confirmed to be unregistered. This process allows for the identification of unregistered communications.

[0985] Step 2:

[0986] The terminal records audio from communications originating from unregistered identification information. It receives audio data during communication as input and saves it as a digital audio file using a recording device. The recorded audio data is obtained as output. This operation prepares the audio data necessary for subsequent analysis.

[0987] Step 3:

[0988] The terminal sends the recorded audio data to the server. It receives the recorded audio data as input and sends it to the server via the communication network. The audio data is then transferred to the server as output. This process provides the server with the audio data for analysis.

[0989] Step 4:

[0990] The server uses speech analysis software to convert speech data into text. It uses speech data received from the terminal as input and converts it into text data using the Google Cloud Speech-to-Text API. The output is the converted text data. This process converts speech information into a parseable text format.

[0991] Step 5:

[0992] The server analyzes text data using a generative AI model and compares it with examples in the information resources. It uses the transformed text data as input and performs analysis using OpenAI's GPT model. The analysis results are obtained as output. This process allows for determining whether the text data is related to fraudulent activity or unwanted sales activities.

[0993] Step 6:

[0994] The server generates warning information based on the analysis results. It uses the analysis results as input to generate a warning message. The output is the warning information itself. This process prepares the server to provide appropriate warnings to the user.

[0995] Step 7:

[0996] The server sends the generated warning information to the terminal. It uses the warning information as input and transmits it to the terminal via the communication network. The warning information is then transferred to the terminal as output. This process provides the user with the warning information.

[0997] Step 8:

[0998] The device displays the received warning information to the user as a push notification. It uses the warning information received from the server as input and displays it to the user using the device's notification function. The user confirms the warning information as output. This process allows the user to quickly receive warnings about communications from unregistered identification information.

[0999] (Application Example 1)

[1000] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1001] In modern society, the risk of fraud and illegal sales calls from unregistered phone numbers is increasing. While users are required to respond quickly and accurately to such calls, traditional methods make this decision difficult.

[1002] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1003] In this invention, the server includes means for detecting incoming calls from unregistered phone numbers, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, means for speech recognition to convert the audio into text, means for analyzing the possibility of fraud using a generative AI model, and means for issuing a warning based on the analysis results. This enables users to quickly determine the possibility of fraud when receiving calls from unregistered phone numbers and take appropriate action.

[1004] "Unregistered phone numbers" refer to numbers that are not stored on the user's communication device and for which specific information is not registered when an incoming call is received.

[1005] "Means for detecting incoming calls" refers to a device or program in a communication device that has the function of sensing an incoming call from an external source and acquiring that information.

[1006] "Means for analyzing speech" refers to technology or equipment for processing received speech data and understanding or classifying its content.

[1007] "Case examples on information networks" refers to a collection of past similar events or data that exist on the internet or other digital networks.

[1008] "Speech recognition means" refers to a technology or device for converting speech data into text data.

[1009] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate a specific output based on input data.

[1010] "Means for analyzing the possibility of fraud" refers to technology or equipment used to determine whether the content of received data constitutes fraudulent activity.

[1011] A "means of issuing a warning" refers to a device or program that has a notification function for alerting or providing information to the user.

[1012] The system for implementing this invention mainly consists of a server and a user terminal. The server detects incoming calls from numbers not registered in the phonebook and runs a program to analyze the voice. For voice analysis, the Google Cloud Speech-to-Text API is used to convert the voice data into text data. The converted text data is analyzed using the generative AI model OpenAI GPT to determine the likelihood of fraud.

[1013] The user's device receives a push notification if there is a potential scam based on analysis results from the server. This warning is designed to allow the user to respond quickly.

[1014] For example, if a user receives a call from "0120-XXXX-XXXX", the server converts the audio into text and inputs the following prompt into the AI ​​generation model: "Is this text potentially a scam? Content: You have won a special campaign." If the AI ​​generation model determines that it is "highly likely to be a scam," a warning message "This may be a scam. Please be careful." is sent to the user's device.

[1015] In this way, users can quickly determine the possibility of fraud when receiving calls from unregistered numbers and take appropriate action.

[1016] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1017] Step 1:

[1018] The server receives incoming call information from the user's terminal. The input is incoming call data from a call number not registered in the phonebook. The server prepares to analyze this data.

[1019] Step 2:

[1020] The server receives incoming audio data and converts it to text using the Google Cloud Speech-to-Text API. The input is audio data, and the output is text data. This conversion makes the audio content available as text information.

[1021] Step 3:

[1022] The server inputs text data into the OpenAI GPT generative AI model and analyzes its likelihood of being a scam. The input is text data, and the output is the analysis result regarding the likelihood of fraud. The server generates a prompt sentence and asks the model, "Is this text likely to be a scam?"

[1023] Step 4:

[1024] The server receives the analysis results from the generated AI model and generates a warning based on those results. The input is the analysis result, and the output is the warning message. The server creates a warning such as "This may be a scam. Please be careful." if there is a high probability of fraud.

[1025] Step 5:

[1026] The server sends the generated warning message as a push notification to the user's device. The input is the warning message, and the output is the notification displayed on the user's device. The user receives this notification and can take appropriate action regarding the incoming message.

[1027] (Example 2)

[1028] Next, we will describe Example 2 of the morphological example. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1029] Many users, including the elderly, are vulnerable to unauthorized connections from unregistered identification numbers. In particular, there is a growing need for effective measures to mitigate these risks, especially given the increasing prevalence of fraudulent activities and unethical sales practices.

[1030] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1031] In this invention, the server includes means for detecting connections from unregistered identification numbers in the communication device, means for acquiring audio information of said connections, and means for converting said audio information into text information. This makes it possible to quickly detect the possibility of fraudulent activity from unregistered identification numbers and notify the user of a warning.

[1032] "Communication equipment" refers to electronic devices used for sending and receiving voice and data, including telephones and smartphones.

[1033] An "identification number" is a unique number assigned to a communication device, such as a telephone number or IP address.

[1034] "Connection" refers to the establishment of a communication link between communication devices, including the initiation of voice calls and data communications.

[1035] "Voice information" refers to voice data transmitted via communication devices, including the content of phone calls.

[1036] "Textual information" refers to text data obtained by converting audio information, and is generated using speech recognition technology.

[1037] "Analysis" refers to the process of processing acquired data and understanding its content and meaning.

[1038] An "information database" is a collection of data that stores past cases and related information, and is used to verify analysis results.

[1039] A "warning" is a notification intended to alert users and may include information about the possibility of fraudulent activity.

[1040] "Notification" refers to a means of conveying information to users, including push notifications and alert messages.

[1041] To implement this invention, the terminal first detects a connection from an unregistered identification number. When a connection is established, the terminal records the call content and sends it to the server as audio information. The server converts the received audio information into text information using the Google Cloud Speech-to-Text API. This API provides highly accurate speech recognition and quickly converts speech to text.

[1042] Next, the server inputs the converted text information into a generative AI model. Specifically, it uses a model such as OpenAI's GPT model and inputs the prompt "Is this phone call potentially a scam?". The generative AI model analyzes the text information and determines the likelihood of it being a scam.

[1043] Based on the analysis results, the server generates a warning. The warning includes the message, "Is this potentially fraudulent activity?", and is immediately sent as a push notification to the device. By receiving this notification, users can become more vigilant against potentially fraudulent connections.

[1044] As a concrete example, if a user receives a call from an unregistered number, the device automatically records the audio and sends it to a server. The server converts the audio to text and inputs prompt text into a generative AI model. Based on the model's analysis, the server sends a warning to the user. This entire process allows users to anticipate the risk of fraudulent calls and take appropriate action.

[1045] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1046] Step 1:

[1047] The terminal detects connections from unregistered identification numbers. Once a connection is established, the terminal records the call and prepares the data as audio information. This audio information becomes input for the next processing step.

[1048] Step 2:

[1049] The device sends the recorded audio information to the server. The server converts the received audio information into text using the Google Cloud Speech-to-Text API. This conversion process involves speech recognition to convert the audio data into text data. The output is text information for analysis.

[1050] Step 3:

[1051] The server inputs the converted text information into the generating AI model. Specifically, it uses the prompt "Is this phone call potentially a scam?" to request analysis from the generating AI model. The model analyzes the text information and determines the likelihood of it being a scam. This analysis result becomes the output for the next step.

[1052] Step 4:

[1053] The server generates a warning based on the analysis results obtained from the generated AI model. The warning includes the message "Is this a possible case of fraudulent activity?" and is immediately sent as a push notification to the device. This notification is what is output to the user.

[1054] Step 5:

[1055] The user checks the warning notification received from their device. Based on this notification, the user can become more vigilant against potentially fraudulent connections and take appropriate action if necessary.

[1056] (Application Example 2)

[1057] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1058] There is a need for a means to enable users, including the elderly, to quickly assess the risk of fraud and illegal transactions from connections made using unregistered identification information, and to prevent damage before it occurs. However, conventional technologies have made it difficult to analyze these risks in real time and provide appropriate warnings.

[1059] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1060] In this invention, the server includes means for detecting connections from unregistered identification information in the communication device, means for analyzing the voice information of the connection, and means for comparing the analysis results with examples on the information network. This enables users to determine the possibility of fraud or illegal transactions in real time and receive a warning quickly.

[1061] "Communication equipment" refers to devices used for sending and receiving voice and data, and includes smartphones and computers.

[1062] "Unregistered identification information" refers to information such as phone numbers and IDs that are not registered in the user's database.

[1063] "Connection" refers to the exchange of voice and data that takes place via communication devices.

[1064] "Voice information" refers to voice data from phone calls or recordings, and is the subject of analysis.

[1065] "Analysis" refers to the process of converting audio information into text data and then analyzing its content.

[1066] An "information network" refers to the internet and other digital networks used for matching and searching data.

[1067] "Case examples" refer to specific cases of fraud or illegal transactions that have been recorded in the past.

[1068] A "warning" refers to a notification or message intended to inform users of potential fraud or misconduct.

[1069] "Real-time" refers to processing and analysis being performed almost instantly, meaning that delays are minimized.

[1070] The system for implementing this invention primarily uses a communication device, a server, and an information network. The communication device is a terminal such as a smartphone, which detects connections from unregistered identification information. The server analyzes the connected voice information and converts it into text data using a generative AI model. This analysis uses a voice analysis library such as the Google Cloud Speech-to-Text API.

[1071] The analyzed text data is compared against a case database on the information network. The database records past cases of fraud and illicit transactions, and the server uses this to determine the likelihood of fraud. If fraud is determined to be possible, the server sends an alert to the user's communication device using a push notification service (e.g., Firebase Cloud Messaging).

[1072] For example, if a user receives a call from an unregistered number and the caller says, "Your bank account is at risk," the server analyzes the audio and compares it to a database of fraud cases. If it is determined that there is a high probability of fraud, it sends a warning to the user asking, "Is this a scam?"

[1073] An example of a prompt to input into the generating AI model is: "Please determine if this voice message is potentially fraudulent. Message content: 'Your bank account is at risk.'"

[1074] In this way, users can assess the risk of fraud and illegal transactions in real time and take swift action.

[1075] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1076] Step 1:

[1077] The terminal detects connections from unregistered identification information. The input is the incoming phone number, and the output is the result of determining that it is unregistered. The terminal compares it with the phonebook database, and if it is unregistered, proceeds to the next step.

[1078] Step 2:

[1079] The terminal collects connected audio information and sends it to the server. The input is the audio data during the call, and the output is the transfer of the audio data to the server. The terminal captures the audio data in real time and streams it to the server.

[1080] Step 3:

[1081] The server analyzes the received audio data and converts it into text data. The input is audio data sent from the terminal, and the output is text data. The server uses the Google Cloud Speech-to-Text API to convert the audio to text.

[1082] Step 4:

[1083] The server analyzes text data using a generative AI model to determine the likelihood of fraud. The input is the transformed text data, and the output is the evaluation result of the likelihood of fraud. The server inputs the text data as a prompt into the generative AI model and evaluates the likelihood of fraud.

[1084] Step 5:

[1085] If the server determines that there is a high probability of fraud, it generates a push notification and sends it to the device. The input is the result of the fraud probability assessment, and the output is a warning message. The server uses Firebase Cloud Messaging to send the user a warning asking, "Is this a scam?"

[1086] Step 6:

[1087] The user reviews the warning message displayed on the device and, if necessary, ends the call or takes further action. The input is the warning message displayed on the device, and the output is the user's action. The user either ends the call after receiving the warning or takes additional confirmation.

[1088] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1089] "Example of form 1"

[1090] One embodiment of the present invention is a system incorporating an emotion engine. This system detects incoming calls from phone numbers not registered in the phone book and analyzes the incoming call's audio. It compares the analysis results with online examples and issues a warning based on the comparison. Furthermore, this system includes an emotion engine that recognizes the user's emotions. The emotion engine recognizes the user's emotions from their tone of voice and word choice, and changes the content and display method of the warning according to those emotions. "Example 2"

[1091] As a concrete example, consider a scenario where an elderly person is using a smartphone. When a call comes in from an unregistered phone number, the system of this invention analyzes the voice. The analysis results are compared with examples found online, and a warning is issued, such as, "Could this be a scam call?" Furthermore, the emotion engine recognizes the elderly person's emotions from their tone of voice and word choice. For example, if it detects that the elderly person is feeling anxious or frightened, the warning is made more specific, such as, "This is likely a scam. Please be careful," and the warning display method is changed to larger font and stronger vibration. This significantly reduces the risk of elderly people encountering scams such as "ore-ore" (impersonation) scams.

[1092] The following describes the processing flow for each example of the form.

[1093] "Example of form 1"

[1094] Step 1: Detect incoming calls from phone numbers not registered in the phonebook.

[1095] Step 2: Analyze the incoming call audio.

[1096] Step 3: Compare the analysis results with examples found online.

[1097] Step 4: Issue a warning based on the comparison results.

[1098] Step 5: Recognize the user's emotions from their tone of voice and word choice.

[1099] Step 6: Change the content and display method of the warning according to the emotion.

[1100] "Example of form 2"

[1101] Step 1: If an elderly person is using a smartphone, analyze the audio when a call comes in from an unregistered phone number.

[1102] Step 2: Compare the analysis results with online examples and issue a warning asking, "Could this be a scam call?"

[1103] Step 3: Recognize the emotions of the elderly person from their tone of voice and word choice.

[1104] Step 4: For example, if you recognize that an elderly person is feeling anxious or frightened, make the warning more specific, such as "This is likely a scam. Please be careful," and change the way the warning is displayed, such as using larger fonts or stronger vibrations.

[1105] (Example 1)

[1106] Next, we will describe Embodiment 1 of Example Form 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1107] In today's communication environment, incoming calls from numbers not registered in phonebooks are increasing, and the resulting fraud and illegal business activities are becoming a social problem. Traditional systems struggle to provide users with appropriate warnings about these incoming calls, often causing them anxiety. Furthermore, the inability to respond flexibly to user emotions limits the effectiveness of warnings.

[1108] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1109] In this invention, the server includes means for detecting incoming calls from destinations not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, and means for recognizing the user's emotions and adjusting the content and display method of the warning according to those emotions. This enables the server to quickly and accurately warn the user of the possibility of fraud or illegal business activities, and to respond flexibly according to the user's emotions.

[1110] A "telephone directory" is a database that lists contact information registered on communication devices, and mainly includes names and phone numbers.

[1111] "Unregistered contacts" refers to contacts not registered in the phone book, meaning that the caller's identification information is unknown when they receive a call.

[1112] An "incoming call" refers to an external call being made to a communication device, and it is a signal that prompts the start of a voice call.

[1113] "Means of analyzing speech" refers to technical methods for converting speech data into text data and analyzing its content.

[1114] "Case studies on information networks" refers to databases that collect similar past events and cases that exist on networks such as the internet.

[1115] "Means of issuing warnings" refers to methods and technologies for notifying users of cautions and dangerous information.

[1116] "Means of recognizing emotions" refers to technologies that analyze a user's tone of voice and word choice to determine their emotional state.

[1117] "Means for adjusting the content and display method of warnings" refers to technologies that change the content and display format of warning messages according to the user's emotional state.

[1118] This invention is a system for detecting incoming calls from unregistered destinations in communication equipment and providing appropriate warnings to the user. Specific embodiments of this system are described below.

[1119] The device detects incoming calls from numbers not registered in the phonebook. Upon receiving a call, the device uses voice analysis software to convert the incoming audio into text data. This voice analysis utilizes speech recognition technology.

[1120] The server compares the analyzed text data with a case database on the information network. This database contains a collection of past fraud and sales activity cases, and the server uses this to assess the risk of incoming calls.

[1121] Furthermore, the device uses an emotion engine to analyze the user's tone of voice and word choice, recognizing the user's emotions. Based on this emotion recognition, the content and display method of warnings are adjusted according to the user's emotions.

[1122] For example, if a call comes in from an unregistered number, the device records the audio and sends it to the server. Based on the analysis, the server determines that there is a "possible scam" and sends a warning to the device. If the user responds with an anxious voice, the emotion engine recognizes that emotion and displays the warning message emphatically as "Caution! This may be a scam."

[1123] Examples of prompts include, "Please describe a system that analyzes incoming calls from unregistered destinations to determine if they are potentially fraudulent," and "Please provide a specific example of a system that uses an emotion engine to issue warnings based on the user's emotions."

[1124] In this way, the system can provide users with prompt and accurate warnings, thereby improving the security of communications.

[1125] The flow of the specific processing in Example 1 will be explained using Figure 15.

[1126] Step 1:

[1127] The terminal detects incoming calls from numbers not registered in the phonebook. The input is an incoming call signal, and the output is information about the unregistered caller. This information is used in subsequent processing steps. Specifically, the terminal checks the phonebook upon receiving an incoming call to confirm that the number is not registered.

[1128] Step 2:

[1129] The terminal records incoming audio and converts it into text data using speech analysis software. The input is the recorded audio data, and the output is the analyzed text data. This text data is used for subsequent database matching. Specifically, the terminal uses speech recognition technology to convert speech into text information.

[1130] Step 3:

[1131] The server compares the analyzed text data with a case database on the information network. The input is text data, and the output is a risk assessment of fraud and sales activities. Specifically, the server searches for phrases and patterns that match known fraud and sales cases.

[1132] Step 4:

[1133] The device uses an emotion engine to analyze the user's voice tone and vocabulary to recognize their emotions. The input is the user's voice data, and the output is the user's emotional state. This emotional state is used to adjust the content and display method of warnings. Specifically, the device analyzes the pitch and speed of the voice to estimate the emotion.

[1134] Step 5:

[1135] The device generates a warning message and notifies the user based on the risk assessment results from the server and the user's emotional state. The inputs are the risk assessment results and the emotional state, and the output is a tailored warning message. Specifically, the device displays the warning to the user using push notifications.

[1136] (Application Example 1)

[1137] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1138] In modern society, the number of incoming calls from numbers not registered in phone directories is increasing, raising the risk of fraud and illegal sales activities. Furthermore, prompt and accurate information is required for users to respond appropriately to these calls. However, conventional systems fail to provide warnings that take into account the user's feelings, thus failing to alleviate user stress.

[1139] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1140] In this invention, the server includes means for detecting incoming calls from destinations not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples on the information network, means for recognizing the user's emotions, and means for changing the content and display method of warnings according to those emotions. This enables the server to quickly and accurately warn users of the possibility of fraud or illegal sales activities, and to provide appropriate information according to the user's emotions.

[1141] "Means for detecting incoming calls from numbers not registered in the phonebook" refers to a function in a communication device that identifies and detects incoming calls from numbers not registered in the user's phonebook.

[1142] "Methods for analyzing speech" refer to technologies for processing audio data received during an incoming call and converting its content into text data or feature vectors.

[1143] "Methods for comparing with examples on information networks" refer to methods for comparing analyzed audio data with existing databases and examples on the internet to evaluate similarities and relationships.

[1144] "Means of issuing warnings" refers to a function that displays alerts or warning messages to users based on analysis results.

[1145] "Means of recognizing user emotions" refers to technologies that analyze a user's tone of voice and word choice to determine their emotional state.

[1146] "Means of changing the content and display method of warnings according to emotions" refers to a function that adjusts the content and display format of warning messages based on the recognized emotions of the user.

[1147] The system for implementing this invention mainly consists of a server and a user terminal. The server detects incoming calls from destinations not registered in the phone book and analyzes the voice. For the analysis, it uses the Python speech_recognition library to convert the voice data into text. In addition, it performs a process of comparing the analysis results with existing databases in order to compare them with examples on the information network.

[1148] Furthermore, the server uses the emotion_recognition library to recognize the user's emotions. This library analyzes the user's tone of voice and word choice to determine their emotional state. Based on the recognized emotion, processing is performed to change the content and display method of the warning. The warning is sent as a push notification to the user's device so that the user can check it immediately.

[1149] For example, if a user receives a phone call asking, "Would you like to purchase a new insurance product?", voice analysis will detect the keyword "purchase" and determine that it may be a scam. If the user is feeling stressed, an emphasized warning will be displayed saying, "This may be a scam. Please be careful!"

[1150] An example of a prompt message for a generative AI model would be: "Analyze this audio data to determine if it is potentially fraudulent or a sales pitch. Also, recognize the user's emotions and emphasize warnings if they are feeling stressed."

[1151] The flow of a specific process in Application Example 1 will be explained using Figure 16.

[1152] Step 1:

[1153] The server detects that there is an incoming call on the terminal. The input is the incoming call notification from the terminal. The server receives this notification and checks whether the incoming call is from a contact not registered in the phonebook. The output is the result of the determination of whether or not it is an unregistered incoming call.

[1154] Step 2:

[1155] The server retrieves audio data if it determines that the incoming call is unregistered. The input is audio data from the terminal. The server uses the Python speech_recognition library to convert this audio data into text. The output is the text data of the audio.

[1156] Step 3:

[1157] The server compares the converted text data with examples on the information network. The input is audio-to-text data. The server compares it with existing databases to assess the likelihood of fraud or sales. The output is the assessment result regarding the likelihood of fraud or sales.

[1158] Step 4:

[1159] The server recognizes the user's emotions from the audio data. The input is audio data from the terminal. The server uses the emotion_recognition library to analyze the user's voice tone and word choice to determine their emotional state. The output is the user's emotional state.

[1160] Step 5:

[1161] The server determines the content and display method of warnings based on the likelihood of fraud or sales and the user's emotional state. The inputs are the evaluation results regarding the likelihood of fraud or sales and the user's emotional state. The server generates a warning message and adjusts its display method according to the user's emotional state. The output is the warning message.

[1162] Step 6:

[1163] The server sends the generated warning message to the device as a push notification. The input is the warning message. The server sends this message to the device so the user can immediately acknowledge it. The output is the warning message displayed on the device.

[1164] (Example 2)

[1165] Next, we will describe Example 2 of the morphological example. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1166] Users, including the elderly, may be unable to adequately respond to fraudulent activity or commercial communications originating from unregistered identification numbers, putting them at risk of becoming involved in scams or unnecessary commercial activities. It is essential to mitigate such risks and provide an environment where users can use communication devices with peace of mind.

[1167] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1168] In this invention, the server includes means for detecting connections from identification numbers not registered with the communication device, means for analyzing the voice information of the connection, and means for comparing the analysis results with examples on the information network. This enables users to receive prompt and appropriate warnings about fraudulent activity or communications for commercial purposes.

[1169] "Communication equipment" refers to electronic devices used for sending and receiving voice and data, including telephones and smartphones.

[1170] An "identification number" is a unique number assigned to a communication device, such as a telephone number or IP address.

[1171] "Connection" refers to a state in which voice and data can be exchanged between communication devices.

[1172] "Voice information" refers to voice data transmitted via communication devices.

[1173] "Analysis" refers to the process of processing audio information and converting its content into an understandable format.

[1174] An "information network" refers to a system for sharing digital information, such as the internet.

[1175] A "case" refers to a specific event or pattern that has been recorded in the past.

[1176] "Matching" refers to the process of comparing analyzed data with existing cases to determine if they match.

[1177] A "warning" refers to a message or notification intended to draw the user's attention.

[1178] "Emotional state" refers to the user's psychological state and can be inferred from their tone of voice and choice of words.

[1179] "Enhancement" refers to adjusting the content and presentation of a warning to make it more effective.

[1180] This invention is a system that uses a communication device to detect connections from unregistered identification numbers and analyzes the voice information. Specifically, when a terminal detects a connection from an unregistered identification number, it records the voice information and converts it into text data using speech recognition software. General speech recognition technology can be used in this process.

[1181] The server receives text data sent from the terminal and compares it against a case database on the information network. This comparison uses machine learning models to detect characteristics of fraudulent or commercially motivated communications. Based on the comparison results, the server generates an alert and sends it to the terminal.

[1182] The device notifies the user of any warnings it receives. These notifications are made through on-screen messages and vibrations. Furthermore, the device uses emotion recognition technology to assess the user's emotional state. If it determines that the user is experiencing anxiety or fear, the content and presentation of the warning are enhanced.

[1183] For example, when a user receives a call from an unregistered number on their smartphone, the device automatically records the call and converts the audio to text. The server then compares the text to a fraud database and generates a warning if it determines that the call may be fraudulent. If the system analyzes that the user is feeling uneasy, the warning is enhanced, and the device notifies the user with larger text and vibration.

[1184] Examples of prompts to input into a generative AI model:

[1185] "A call was received from an unregistered phone number. Please perform voice analysis to determine if it is a scam. Also, analyze the user's emotions and strengthen the warning as needed."

[1186] The flow of the specific processing in Example 2 will be explained using Figure 17.

[1187] Step 1:

[1188] The device detects a connection from an unregistered identification number. It receives the incoming identification number as input. The device verifies that this identification number is not registered in the phonebook and begins recording the connection. It generates the recorded audio data as output.

[1189] Step 2:

[1190] The terminal inputs recorded audio data into speech recognition software and converts it into text data. It receives audio data as input. The terminal analyzes the audio using speech recognition technology and outputs data in text format. This text data is used for subsequent analysis.

[1191] Step 3:

[1192] The server receives text data sent from the terminal and compares it with a case database on the information network. It receives text data as input. The server uses a machine learning model to detect characteristics of fraudulent or commercially motivated communications. It generates an assessment of the likelihood of fraud as output.

[1193] Step 4:

[1194] The server generates a warning message based on the evaluation results and sends it to the terminal. It receives the evaluation results as input. If the server detects a potential fraud, it generates a warning such as "This may be fraudulent activity." It generates a warning message as output and sends it to the terminal.

[1195] Step 5:

[1196] The device notifies the user of any warning messages it receives. It receives warning messages as input. The device displays the message on the screen and, if necessary, vibrates to alert the user. It then sends a warning notification to the user as output.

[1197] Step 6:

[1198] The device uses emotion recognition technology to evaluate the user's emotional state. It receives the user's voice data as input. The device analyzes the tone and word choice of the voice to evaluate the user's emotional state. It then generates an evaluation result regarding the emotional state as output.

[1199] Step 7:

[1200] The server enhances warnings based on the user's emotional state. It receives an assessment of the user's emotional state as input. If the server determines that the user is feeling anxious or fearful, it enhances the content and presentation of the warning. As output, it generates an enhanced warning message and sends it to the user's device.

[1201] (Application Example 2)

[1202] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1203] There is a need to reduce the risk of elderly people encountering fraudulent calls from unregistered phone numbers. Furthermore, it is necessary to provide appropriate warnings to elderly people if they feel anxious or frightened by the content of a phone call.

[1204] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1205] In this invention, the server includes means for detecting incoming calls from phone numbers not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples found on the internet, means for recognizing emotions from the tone of voice and word choice of the elderly person, and means for adjusting the content and display method of the warning based on the emotion recognition results. This makes it possible to reduce the risk of elderly people encountering fraudulent calls and to provide appropriate warnings that are tailored to their emotions.

[1206] "Means for detecting incoming calls from phone numbers not registered in the phonebook" refers to a function that identifies incoming calls from phone numbers not registered in the user's phonebook and notifies the system of that information.

[1207] "Methods for analyzing voice" refers to technology that processes voice data received during an incoming call and converts its content into text data.

[1208] "Methods of comparing with online cases" refer to the process of comparing the analyzed audio data with a database of fraud cases existing on the internet to assess the likelihood of fraud.

[1209] A "warning mechanism" is a function that displays or notifies users of a message to warn them if it is determined that there is a possibility of fraud.

[1210] "Means of recognizing emotions" refers to technology that analyzes the tone of a user's voice and word choice to determine their emotional state at that time.

[1211] "Means for adjusting the content and display method of warnings" refers to a function that optimizes the content and display method of warning messages based on recognized emotions, thereby conveying information to the user in an appropriate manner.

[1212] The system for implementing this invention mainly consists of a server and a user terminal. The server runs a program to detect incoming calls from phone numbers not registered in the phonebook. The user terminal records the voice when a call comes in and sends the voice data to the server. The server converts the voice data into text using a speech analysis library (e.g., Google Cloud Speech-to-Text). The converted text is compared against an online database of fraud cases. Furthermore, the server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice tone and word choice.

[1213] If the server determines that a scam is highly likely, it will send a warning notification to the user's device via push notification. The content and display method of this warning are adjusted based on the results of emotion recognition. For example, if the server detects that the user is feeling anxious, the warning will be displayed in large letters and accompanied by a strong vibration, stating, "This is likely a scam. Please be careful."

[1214] For example, if a user says "I'm worried," the server recognizes that emotion and highlights the warning. An example of a prompt to the generating AI model is, "Please evaluate the likelihood that this voice is a scam call. Voice content: 'Hello, your bank account is at risk. Immediate action is required.'" In this way, it is possible to reduce the risk of elderly people encountering scam calls and provide appropriate warnings that are tailored to their emotions.

[1215] The flow of a specific process in Application Example 2 will be explained using Figure 18.

[1216] Step 1:

[1217] The user's device detects an incoming call from a phone number not registered in the phonebook. The input is the incoming phone number, and the output is a confirmation that the number is not registered. Based on this information, the device starts recording audio.

[1218] Step 2:

[1219] The user's device records audio upon receiving a call and sends the audio data to the server. The input is the recorded audio data, and the output is the transmission of the audio data to the server. The device converts the audio data to the appropriate format and transfers it to the server.

[1220] Step 3:

[1221] The server uses a speech analysis library (e.g., Google Cloud Speech-to-Text) to convert received audio data into text. The input is audio data, and the output is text data. The server performs speech analysis and generates text data.

[1222] Step 4:

[1223] The server compares the converted text against an online database of fraud cases. The input is text data, and the output is an assessment of the likelihood of fraud. The server searches the database and evaluates the likelihood of fraud.

[1224] Step 5:

[1225] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice tone and vocabulary. The input is audio data, and the output is the result of emotion recognition. The server analyzes the audio data to identify the user's emotions.

[1226] Step 6:

[1227] If the server determines that there is a high probability of fraud, it sends a warning notification to the user's device via push notification. The input is the fraud probability assessment result and the sentiment recognition result, and the output is a warning message. The server adjusts the content and display method of the warning and notifies the user.

[1228] Step 7:

[1229] The user's device displays received warnings and provides feedback, such as vibration, as needed. The input is the warning message, and the output is visual and haptic feedback to the user. The device displays the warning on the screen to alert the user.

[1230] (Other examples)

[1231] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[1232] 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.

[1233] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1234] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[1235] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1236] 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.

[1237] Figure 9 shows an 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.

[1238] 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.

[1239] 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.

[1240] 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, motorcycles, etc., 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, for example, based 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.

[1241] 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."

[1242] 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.

[1243] 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.

[1244] 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.

[1245] 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.

[1246] 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.

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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.

[1251] 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 the like 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.

[1252] 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 as being incorporated by reference.

[1253] The following is further disclosed regarding the embodiments described above.

[1254] (Claim 1)

[1255] A system including means for detecting incoming calls from phone numbers not registered in the phone book, means for analyzing the audio of the incoming call, means for comparing the analysis results with examples found on the internet, and means for issuing a warning based on the comparison results.

[1256] (Claim 2)

[1257] The system according to claim 1, further comprising means for issuing the aforementioned warning via push notification or the like.

[1258] (Claim 3)

[1259] The system according to claim 1, wherein the warning includes statements such as "Is this a scam call?" or "Is this a sales call from someone who intends to buy?".

[1260] (Claim 4)

[1261] The system according to claim 1, wherein the system includes an emotion engine that recognizes the user's emotions.

[1262] (Claim 5)

[1263] The system according to claim 4, wherein the emotion engine recognizes emotions from the tone of the user's voice and word choice.

[1264] (Claim 6)

[1265] The system according to claim 4, wherein the emotion engine changes the content and display method of the warning according to the user's emotions.

[1266] "Example 1"

[1267] (Claim 1)

[1268] A means for detecting communication from identification information not registered in the telephone directory,

[1269] A means for analyzing the audio information of the communication,

[1270] A means for comparing the analysis results with examples in information resources,

[1271] A means for generating warning information based on the comparison results,

[1272] A system including means for notifying the warning information.

[1273] (Claim 2)

[1274] The system according to claim 1, further comprising means for displaying the warning information immediately.

[1275] (Claim 3)

[1276] The system according to claim 1, wherein the warning information includes statements such as "Is this a possible fraudulent activity?" or "Is this a sales activity with intent to purchase?".

[1277] "Application Example 1"

[1278] (Claim 1)

[1279] A means of detecting incoming calls from communication numbers not registered in the phone book,

[1280] A means for analyzing the audio of the incoming call,

[1281] A means for comparing the analysis results with examples on an information network,

[1282] A means of issuing a warning based on the results of the comparison,

[1283] A speech recognition method that converts speech to text,

[1284] A method for analyzing the likelihood of fraud using a generative AI model,

[1285] A system including means for issuing a warning based on the analysis results.

[1286] (Claim 2)

[1287] The system according to claim 1, further comprising means for issuing the aforementioned warning by push notification.

[1288] (Claim 3)

[1289] The system according to claim 1, wherein the warning includes the statement, "This may be a scam. Please be careful."

[1290] Example 2

[1291] (Claim 1)

[1292] A means for detecting connections from unregistered identification numbers in a communication device,

[1293] Means for acquiring audio information of the connection,

[1294] Means for converting the audio information into text information,

[1295] A means for analyzing the character information,

[1296] A means for comparing the analysis results with an information database,

[1297] Means for generating a warning based on the matching result,

[1298] A system including means for notifying the warning.

[1299] (Claim 2)

[1300] The system according to claim 1, further comprising means for immediately transmitting the warning.

[1301] (Claim 3)

[1302] The system according to claim 1, wherein the warning includes the statement, "Is this a possible case of fraudulent activity?"

[1303] "Application Example 2"

[1304] (Claim 1)

[1305] A means for detecting connections from unregistered identification information in a communication device,

[1306] A means for analyzing the audio information of the connection,

[1307] A means for comparing the analysis results with examples on an information network,

[1308] A means of issuing a warning based on the results of the comparison,

[1309] A system including means for notifying the user of the warning.

[1310] (Claim 2)

[1311] The system according to claim 1, further comprising means for analyzing the warning in real time and determining the possibility of fraud.

[1312] (Claim 3)

[1313] The system according to claim 1, wherein the warning includes the following: "Is this a potential scam?" or "Is this a potential fraudulent transaction?"

[1314] "Example 1 of combining an emotion engine"

[1315] (Claim 1)

[1316] A means of detecting incoming calls from numbers not registered in the phone book,

[1317] A means for analyzing the audio of the incoming call,

[1318] A means for comparing the analysis results with examples on an information network,

[1319] A means of issuing a warning based on the results of the comparison,

[1320] A means for recognizing the user's emotions and adjusting the content and display method of warnings according to those emotions,

[1321] A system that includes this.

[1322] (Claim 2)

[1323] The system according to claim 1, further comprising means for issuing the aforementioned warning by notification.

[1324] (Claim 3)

[1325] The system according to claim 1, wherein the warning includes statements such as "This may be a scam" or "This may be a sales call from someone intending to buy."

[1326] "Application example 1 of combining emotional engines"

[1327] (Claim 1)

[1328] A means of detecting incoming calls from numbers not registered in the phone book,

[1329] A means for analyzing the audio of the incoming call,

[1330] A means for comparing the analysis results with examples on an information network,

[1331] A means of issuing a warning based on the results of the comparison,

[1332] Means of recognizing user emotions,

[1333] Means for changing the content and display method of the warning according to the emotion,

[1334] A system that includes this.

[1335] (Claim 2)

[1336] The system according to claim 1, further comprising means for issuing the aforementioned warning by notification.

[1337] (Claim 3)

[1338] The system according to claim 1, wherein the warning includes statements such as "This may be a scam" or "Is this a sales call from someone who intends to buy?".

[1339] "Example 2 of combining an emotion engine"

[1340] (Claim 1)

[1341] A means for detecting connections from unregistered identification numbers in a communication device,

[1342] A means for analyzing the audio information of the connection,

[1343] A means for comparing the analysis results with examples on an information network,

[1344] Means for generating a warning based on the matching result,

[1345] Means for presenting the warning,

[1346] A means of evaluating the user's emotional state,

[1347] A system including means for reinforcing warnings based on the emotional state.

[1348] (Claim 2)

[1349] The system according to claim 1, wherein the aforementioned warning is presented by a notification means.

[1350] (Claim 3)

[1351] The system according to claim 1, wherein the warning includes statements such as "This may be fraudulent activity" or "Is this a commercial communication?".

[1352] "Application example 2 when combining with an emotional engine"

[1353] (Claim 1)

[1354] A means of detecting incoming calls from phone numbers not registered in the phone book,

[1355] A means for analyzing the audio of the incoming call,

[1356] A means of comparing the analysis results with examples on the internet,

[1357] A means of issuing a warning based on the results of the comparison,

[1358] Methods for recognizing emotions from the tone of voice and word choice of elderly people,

[1359] A system including means for adjusting the content and display method of a warning based on the emotion recognition result.

[1360] (Claim 2)

[1361] The system according to claim 1, further comprising means for issuing the aforementioned warning via push notification or the like.

[1362] (Claim 3)

[1363] The system according to claim 1, wherein the warning includes the statement, "This is likely a scam. Please be careful." [Explanation of symbols]

[1364] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Equipped with a processor, The aforementioned processor, It detects communications from identification information not registered in the phone book, The audio information of the communication is acquired and converted into text data using speech recognition technology. Generate a prompt to instruct the AI ​​model to analyze the text data, and input it into the generating AI model. The analysis results obtained from the generated AI model are compared with examples in the information resources. Based on the comparison results, warning information is generated. The warning information will be notified to the user. system.

2. The system according to claim 1, wherein the processor visually presents a warning message via a user interface in order to immediately display the warning information.

3. The system according to claim 1, wherein the processor includes specific content such as "Is this a potential fraudulent activity?" or "Is this a sales activity with intent to purchase?", and allows the user to check the details of the warning.

Images