system

Abstract

We provide the system. [Solution] A sensor for acquiring sound, A processing unit for converting acquired audio into text data, To assess the risk of fraud, an analysis device is used that compares text data with a pre-configured storage device. A warning device that issues a warning when there is a high possibility of fraud, A communication device for notifying users and contacts, An information processing system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Regarding frauds such as refund fraud, it is difficult to sufficiently protect the elderly and their families by conventional methods. Fraud victimization becomes a mental and economic burden on the victim himself / herself and is also a serious problem for the family. There is a need to provide means for effectively protecting the elderly from such frauds and preventing damage in advance.

Means for Solving the Problems

[0005] This invention provides a fraud prevention system that uses a voice input means to collect user conversations in real time and a conversion means to convert the voice into text data. Furthermore, an analysis means compares this text data with a pre-configured database to analyze the possibility of fraud and provides a notification means to alert the user to danger. This system can quickly detect signs of fraud and immediately notify family members and appropriate contacts. This reduces the risk of elderly people becoming victims of fraud and provides an environment in which they can live their daily lives with peace of mind.

[0006] "Sound" refers to vibrations in the air within a specific frequency range, and is a means of communication using human voice.

[0007] "Input means" refers to devices or mechanisms that receive information from an external source and transmit it to a processing unit as an electronic signal.

[0008] "Conversion means" refers to a process or device that converts data in one format into a different format.

[0009] "Analysis means" refers to processes and devices used to analyze data and make judgments or evaluations based on that analysis.

[0010] "Notification means" refers to functions or devices used to transmit information to recipients.

[0011] A "database" refers to a system that manages a collection of information organized and stored for a specific purpose.

[0012] A "fraud prevention system" refers to a system equipped with technical mechanisms to detect fraud-related behavior and prevent damage before it occurs. [Brief explanation of the drawing]

[0013] [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] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter will be described an example of an embodiment of a system according to the technology of the present disclosure with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention relates to a fraud prevention system equipped with voice input means, conversion means, analysis means, and notification means. The operation of the system is described below.

[0035] First, when a user starts a conversation, the device's voice input captures the conversation. Next, the captured audio data is sent from the device to the server via a secure communication protocol.

[0036] The server converts the received audio data into text data using a conversion device. This text data is then passed to an analysis device and compared against a database to detect potential fraud.

[0037] If fraud is suspected, the server's notification system will activate and send an alert to the designated emergency contacts (such as the user's family or the police). The device will also use its internal notification system to warn the user verbally or visually.

[0038] For example, if an elderly person is approached by a scammer over the phone about a tax refund, the device will capture the conversation in real time and immediately detect the risk of fraud through a subsequent process. The server will determine that the situation is urgent and notify the user's family using a notification system. By contacting the elderly person promptly, the family can prevent fraudulent transactions.

[0039] This invention provides users with a high level of security and enables the management and prevention of fraud risks in real time.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The device detects sounds around the user and captures those sounds in real time using a voice input device.

[0043] Step 2:

[0044] The terminal stores the audio data in a buffer and prepares to send that audio data to the server over the network at regular intervals.

[0045] Step 3:

[0046] The server converts the received audio data into text data using a conversion mechanism. This conversion is performed using speech recognition technology.

[0047] Step 4:

[0048] The server passes the text data to an analysis tool, which then matches the text against keywords and phrases related to fraud. The database used here contains records of past fraud patterns and known fraudulent techniques.

[0049] Step 5:

[0050] The server calculates a fraud score based on the matching results and determines whether there is a possibility of fraud. A threshold is set for this determination, and if it exceeds that threshold, it is considered fraud.

[0051] Step 6:

[0052] If a fraudulent activity is deemed highly likely, the server will send an alert to registered emergency contacts via a notification system.

[0053] Step 7:

[0054] At the same time, the device issues direct warnings to the user and provides information to draw their attention using voice or display.

[0055] These steps enable the system to efficiently detect fraud and protect users and their families.

[0056] (Example 1)

[0057] Next, we will describe 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."

[0058] The problem that this invention aims to solve is to prevent fraudulent transactions by early detection of potential fraud in voice communications and prompt notification to users and their related parties. This problem is particularly serious for the elderly and people with limited knowledge of fraud, and there is a need to provide an environment in which they can communicate with peace of mind on a daily basis.

[0059] 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.

[0060] In this invention, the server includes an input device for acquiring audio, a conversion device for converting the acquired audio into a standardized data format, and an analysis device for comparing text data with a pre-configured information set in order to evaluate the possibility using the data format. This makes it possible to analyze the risk of fraud from the content of the audio in real time and quickly notify the relevant parties.

[0061] "Speech" refers to data acquired as sound waveforms, and typically includes information such as human conversation.

[0062] An "input device" is a device that has the function of acquiring external audio and converting it into a format that can be incorporated into the system.

[0063] A "conversion device" is a device that converts acquired audio data into a standardized text data format.

[0064] An "analytical device" is a device that uses text data to assess the likelihood of fraud and processes information based on the results.

[0065] A "notification device" is a device that sends notifications generated based on analysis results to a specified recipient.

[0066] A "standardized data format" is a common format used to process data uniformly across different systems.

[0067] A "database" is a knowledge base that includes databases and rule sets that are referenced when assessing the likelihood of fraud.

[0068] The "evaluation score" is a score generated based on the analysis of text data, and it is a numerical value that indicates the likelihood of fraud.

[0069] This invention is a fraud prevention system that targets voice and has the following configuration.

[0070] A series of actions

[0071] When a user starts a conversation, the device captures the audio using its built-in voice input device. The smartphone's microphone is primarily used to acquire the audio data.

[0072] Next, the captured audio is converted to a digital format in real time and sent to the server using a secure communication protocol. HTTPS is used for transmission, and TLS technology is used to encrypt the data.

[0073] Processing of audio data

[0074] The server converts the acquired audio data into text data using speech recognition technology (e.g., Speech-to-Text API). This conversion technology transforms everyday language into a standardized data format that can be understood.

[0075] Subsequently, a natural language processing engine on the server runs to analyze the text data. This engine refers to a collection of past fraud patterns and keywords to assess the likelihood of fraud.

[0076] Notifications and alerts

[0077] If a potential scam is detected, the server sends a notification to the user's family and other registered recipients via a configured notification device. SMS and email are used to ensure rapid information dissemination.

[0078] Furthermore, the device will issue alerts to the user directly via voice and on the screen. The voice notification will include a message such as "This may be a scam."

[0079] Specific example

[0080] For example, if an elderly person is asked over the phone for their bank account information regarding a tax refund, the device recognizes the conversation and immediately analyzes it. If it is determined that there is a high risk of fraud, a warning is promptly sent to the family, preventing potential problems.

[0081] Example of a prompt

[0082] An example of a prompt to input into a generative AI model is, "Analyze the audio data and explain the results of the detection of suspicious keywords."

[0083] In this way, users can ensure a high level of security through the system and be protected from fraudulent activities.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] When a user starts a conversation, the device captures the audio via a voice input device. The input is real-time audio, and the output is digital audio data. Specifically, the smartphone's microphone is used to remove background noise and obtain a high-quality audio sample.

[0087] Step 2:

[0088] The terminal sends the captured audio data to the server using a secure communication protocol. It receives digital audio data as input and generates encrypted data packets as output. This step utilizes HTTPS and leverages TLS technology to securely transmit the data. This method prevents data disruption and unauthorized access during transmission.

[0089] Step 3:

[0090] The server converts received audio data into text data using speech recognition technology. It receives encrypted audio data as input and generates text data as output. Specifically, the Speech-to-Text API is used, and an advanced algorithm is employed to convert audio waveforms into text.

[0091] Step 4:

[0092] The server analyzes the converted text data and assesses the likelihood of fraud. It receives text data as input and outputs an evaluation result. This analysis involves a natural language processing engine, which calculates a risk score based on the information set. For example, if the word "refund" is detected, it is determined that the risk of fraud is high.

[0093] Step 5:

[0094] If potential fraud is detected, the server issues a notification to the user's family and registered contacts. It receives evaluation results as input and generates notifications in the form of messages or emails as output. Specifically, it uses SMS gateways and email servers to ensure rapid information dissemination.

[0095] Step 6:

[0096] Simultaneously, the device issues audio and visual warnings to the user. It receives evaluation results as input and outputs audio alerts and pop-up notifications. The device can automatically launch the app and inform the user that "this may be a scam."

[0097] This series of processes allows users to recognize fraud risks in real time and take appropriate action.

[0098] (Application Example 1)

[0099] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0100] Traditional fraud prevention systems have struggled to analyze voices in real time and immediately warn of potential fraud. Therefore, real-time fraud detection is required. Furthermore, a system that can smoothly notify users and their families is also necessary.

[0101] 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.

[0102] In this invention, the server includes sensor means for acquiring sound, computing device means for converting the acquired sound into text data, and analysis device means for comparing the text data with a pre-configured storage device to assess the risk of fraud. This makes it possible to analyze the sound in real time, quickly assess the possibility of fraud, and immediately notify the user or designated contacts.

[0103] A "sensor" is a device used to acquire sound, and it collects information by sensing sound waves from its surroundings.

[0104] A "processing unit" is a device that converts acquired speech into text data, and it processes speech into text format using speech recognition technology.

[0105] An "analysis device" is a device used to assess the risk of fraud by comparing text data with a pre-configured storage device.

[0106] A "warning device" is a device that issues a warning when there is a high probability of fraud, and it informs the user of the danger either audibly or visually.

[0107] A "communication device" is a device used to notify users and contacts, and has the function of transmitting information over a network.

[0108] The system implementing this invention first collects voice data acquired from the user through a voice sensor. The sensor detects voice and acquires data in real time. The acquired voice data is converted into text data by a processing unit. In this process, Google® Speech-to-Text API, which is speech recognition software, is used.

[0109] After the computing unit converts the data into text, the server's analysis unit compares it with a pre-configured storage device to assess the risk of fraud. The analysis unit uses natural language processing technology to search the database for known fraud phrases and behavioral patterns. This search calculates a fraud probability score.

[0110] If a system is determined to be highly likely to be fraudulent, it will issue an audible and visual warning to the user. The warning will be displayed on a smartphone or tablet.

[0111] Furthermore, the system notifies the user's registered contacts that the communication device is suspected of being fraudulent. This notification is sent via network communication to encourage a prompt response.

[0112] For example, if an elderly person receives a suspicious request for a refund over the phone, a sensor captures the conversation, and the system immediately displays a warning and notifies designated family contacts.

[0113] An example of a prompt that utilizes a generative AI model is: "Design a system that analyzes phone conversations in real time to detect signs of fraud and issues warning notifications if necessary." This means the invention provides an effective means of preventing the risk of fraud.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The terminal uses a voice sensor to acquire user voice input in real time. The input is voice waveform data, which is converted into a digital signal. Once data collection is complete, it prepares to be sent to the server.

[0117] Step 2:

[0118] The server receives digital audio data transmitted from the terminal. The received data is converted into text data by a processing unit. This process utilizes the Google Speech-to-Text API to convert audio to text. The output is text data.

[0119] Step 3:

[0120] The server's analysis device compares the acquired text data with a database. The input is converted text data. This data is analyzed by a natural language processing engine to calculate a fraud risk score. The output is the fraud probability score.

[0121] Step 4:

[0122] Based on calculations by the analysis device, if the fraud probability score exceeds a preset threshold, the warning device will issue an audible and visual warning to the user. The input is the score data, and the output is the warning trigger signal.

[0123] Step 5:

[0124] The server's communication device sends a warning message to pre-configured contacts if fraud is suspected. The input is the warning trigger signal, and the output is a notification message to emergency contacts. It verifies the connected contacts and records the completion of the notification.

[0125] 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.

[0126] This invention relates to a fraud prevention system equipped with an emotion engine in addition to voice input means, conversion means, analysis means, and notification means. This makes it possible to detect the user's emotions in real time and reflect them in the assessment of fraud risk.

[0127] First, when a user begins a conversation, the device captures the conversation using voice input. This voice data is then sent from the device to the server. When the server converts the voice to text, it simultaneously analyzes the user's emotional state using an emotion engine. This emotion analysis allows the system to determine whether the user is feeling anxious or confused.

[0128] This text data and sentiment data are cross-referenced with a database of fraud patterns using analytical tools. The server also considers the sentiment state in the fraud probability score to more precisely assess the probability of fraud.

[0129] If a user is determined to be highly likely to be a scam, the server's notification system creates an alert and sends it to the registered contacts. This alert may include detailed information tailored to the user's emotional state. For example, if the user is feeling very anxious, the urgency of the notification may be increased.

[0130] For example, if an elderly person receives a fraudulent phone call offering a refund, the device uses an emotion engine to analyze any unnatural tone or anxiety detected during the conversation. If the system determines that the call is highly likely to be fraudulent, it issues a more emphatic alert than a normal notification. This alert is quickly sent to family members or appropriate personnel, preventing potential fraud.

[0131] In this way, this system achieves a more sophisticated fraud prevention by incorporating not only voice input but also the user's emotional information.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The device captures the user's conversation in real time using voice input. The voice signal is acquired as digital data.

[0135] Step 2:

[0136] The acquired audio data is analyzed within the device using an emotion engine to determine the user's voice tone, pitch, and tempo, and to estimate their emotional state.

[0137] Step 3:

[0138] The device sends voice data and emotion data to the server. Communication takes place through an encrypted channel.

[0139] Step 4:

[0140] The server converts the audio data into text data using a conversion tool. Speech recognition technology is used in this process.

[0141] Step 5:

[0142] The server's analysis tool compares text data and sentiment data with a fraud pattern database to score the likelihood of fraud.

[0143] Step 6:

[0144] The likelihood of fraud is assessed by taking into account the emotional state, and the level of risk of fraud is determined. In this case, if the emotions indicate tension or anxiety, the score will be higher.

[0145] Step 7:

[0146] If a user is determined to be highly likely to be a scam, the server will activate a notification system and send an appropriate alert to the user's registered contacts.

[0147] Step 8:

[0148] The device also simultaneously issues a warning to the user, alerting them to danger through a visual display and voice guidance.

[0149] In this way, the system can take the user's emotional state into account, improving the accuracy of fraud detection and the speed of response.

[0150] (Example 2)

[0151] Next, we will describe 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".

[0152] Traditional fraud prevention systems converted voice data into text and simply compared it against a database to determine the likelihood of fraud. However, this approach failed to consider the user's emotional state, making it difficult to accurately assess the risk for users experiencing anxiety or confusion. This is particularly problematic for the elderly and those unfamiliar with technology, who may find it difficult to assess fraud risk, highlighting the need for more accurate detection methods.

[0153] 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.

[0154] In this invention, the server includes input means for collecting audio, conversion means for converting the collected audio into text data, analysis means for analyzing the user's emotional state, analysis means for comparing the text data and emotional data to determine the possibility of fraud, and notification means for adjusting the content and priority of notifications based on the emotional state when fraud is suspected. By incorporating emotional data, it becomes possible to perform fraud detection with higher accuracy and provide appropriate notifications.

[0155] "Input means for collecting voice" refers to a device or method for capturing a user's voice in real time and acquiring it in a format that can be processed as digital data.

[0156] "Conversion means for converting collected audio into text data" refers to a system or program that uses speech recognition technology to convert collected audio data into corresponding text information.

[0157] "Analysis methods for analyzing a user's emotional state" refers to technologies that analyze tone, pitch, and speech rate from a user's voice data to identify specific emotional states (e.g., anxiety or reassurance).

[0158] "An analytical means for determining the possibility of fraud by comparing text data and sentiment data with a pre-configured database" refers to a system that evaluates the possibility of fraud by comparing text converted from speech and analyzed sentiment information with fraud patterns stored in a database.

[0159] "A notification mechanism for adjusting the content and priority of notifications based on emotional state when fraud is suspected" refers to a mechanism that, when a high risk of fraud is determined, dynamically determines the content and urgency of a notification by considering the user's emotional information and sends it to the appropriate recipient.

[0160] The fraud prevention system of this invention combines voice input, sentiment analysis, data analysis, and notification functions. The system's configuration and operation are described in detail below.

[0161] The device, whether a smartphone or a dedicated device, captures the user's voice in real time. A microphone is used as the voice input for this purpose. The captured voice is converted into digital data and transmitted to a server via an internet connection.

[0162] The server converts the audio data into text data using speech recognition software. Examples of usable software include commonly used cloud-based speech recognition APIs. In parallel, an emotion analysis process is performed, analyzing speech tone, pitch, and speed to identify the user's emotional state. An emotion analysis engine is used for this process.

[0163] Text data and analyzed sentiment data are compared against a fraud pattern database. This comparison uses an analysis engine that combines AI algorithms and rule-based systems to calculate a fraud probability score.

[0164] If a situation is deemed highly likely to be fraudulent, the server generates an alert using notification methods. This alert's content and urgency are dynamically adjusted, taking into account the user's emotional state. The notification is sent to pre-registered contacts and communicated to the user via methods such as email or SMS.

[0165] As a concrete example, consider a case where an elderly person receives a fraudulent phone call requesting a refund. In this system, the terminal captures the audio, and if a voice pattern that is highly likely to be fraudulent is detected, the system uses sentiment analysis to identify the user's level of anxiety. The server immediately generates a highlighted alert and sends it to registered contacts to encourage a quick response.

[0166] Examples of prompt statements that can be used as input to a generative AI model are as follows:

[0167] "Please generate scenarios for how to analyze the emotions and assess the fraud risk when an elderly person receives a fraudulent phone call."

[0168] "Please generate notification messages that take into account the user's emotional state."

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] When a user starts a conversation, the device captures the conversation in real time using voice input. The input is analog audio, which is converted into digital audio data via the microphone. This digital audio is temporarily stored on the device. The operation is similar to how a smartphone's voice recorder app records audio.

[0172] Step 2:

[0173] The device captures digital audio data and sends it to a server via an internet connection. The input is the digital audio data from the device, and the output is the transfer of audio data to the server. This transfer is usually performed using a secure protocol such as HTTPS. The operation is similar to how a smartphone uploads files to a cloud service.

[0174] Step 3:

[0175] The server converts received digital audio data into text data using speech recognition software. The input is digital audio data, and the output is text data. During this process, the audio analysis engine analyzes the sound waveform and converts it into a corresponding string of characters. A specific example of this operation is the process of converting voice commands into text information.

[0176] Step 4:

[0177] The server performs sentiment analysis based on text data converted from speech. The input is text data, and the output is data indicating the user's emotional state. Utilizing natural language processing techniques, it analyzes specific keywords and context within the text to identify emotions. Specifically, it detects emotional categories such as "anxiety" and "anger" from the user's text statements.

[0178] Step 5:

[0179] The server compares the analyzed text data and sentiment data with a fraud pattern database. The input is text data and sentiment data, and the output is a fraud probability score. The AI ​​algorithm then calculates a score and assesses the risk of fraud. One operational method involves matching sets of keywords that trigger fraud.

[0180] Step 6:

[0181] If the fraud probability score is high, the server generates an alert that takes emotional state into account and sends it to pre-registered contacts via a notification system. The input is the fraud probability score and emotional data, and the output is the notified alert. Notifications can be set manually or automatically with different priorities. Specifically, an advanced notification system sends an urgent SMS message to the user's family members.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] With the advancement of modern communication technology, fraudulent activities have become more sophisticated, and many people are suffering from their effects. Fraudulent phone calls targeting the elderly are a particularly serious problem, and effective prevention measures are needed. However, conventional prevention systems simply convert voice to text and compare it with a database, without taking into account the user's emotional state. As a result, there is a possibility of missing signs of fraudulent activity. Against this backdrop, there is a need for technology that can analyze the user's emotional state in real time and accurately determine the possibility of fraud.

[0185] 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.

[0186] In this invention, the server includes receiving means for acquiring acoustic signals, conversion means for converting the acquired acoustic signals into textual information, and analysis means for evaluating emotions along with the textual information. This enables the system to accurately determine the possibility of fraud based on the user's emotional state and to send faster and more appropriate warnings.

[0187] An "acoustic signal" is an electrical conversion of sound waves generated by air vibrations.

[0188] "Receiving means" refers to a device or method that has the function of acquiring acoustic signals from an external source.

[0189] "Textual information" refers to symbolic information that is represented in the form of words or sentences converted from acoustic signals.

[0190] A "conversion method" is a technology for analyzing acoustic signals and converting them into textual information.

[0191] "Emotion" refers to the user's psychological or emotional state, which is analyzed from voice and other physiological signals.

[0192] "Analysis methods" refer to techniques and technologies used to make various decisions based on input data.

[0193] An "information aggregate" is a collection of textual information and reference data that serves as a standard for emotional evaluation in order to determine whether something is fraudulent.

[0194] "Verification means" refers to techniques or methods for comparing input data with an information aggregate.

[0195] A "warning" is a message intended to alert users and their associates to danger or require caution.

[0196] "Transmission means" refers to the technology or method used to deliver the generated warning to a specific recipient.

[0197] The present invention is implemented as a system that acquires acoustic signals and converts them into textual information and emotional evaluations. This system uses a device (such as a smartphone) for receiving acoustic signals, a server for conversion and analysis, and communication means for transmitting the results. Specific software that can be used includes a speech input API (e.g., Google Speech-to-Text) and an emotion analysis API (e.g., IBM Watson® Tone Analyzer).

[0198] The terminal receives an acoustic signal that detects the user's conversation. This signal is transmitted to a server via a wireless network. The server uses speech recognition technology to convert the acoustic signal into text information and further evaluates the emotions using sentiment analysis technology. The results of the emotion evaluation play a role in detecting potential fraudulent activity. This result is compared with an information aggregate in a database, and if fraud is suspected, the server sends a warning in real time.

[0199] For example, if an elderly person receives a suspicious phone call at home, and the device receives the conversation and the server detects an emotional response indicating distress, the system can immediately send a warning to registered contacts.

[0200] An example of a prompt message is, "Consider designing a system that analyzes a user's emotional state and detects unnatural tones in real time to prevent fraud." This makes it easier for other developers to understand the system's design principles.

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The terminal receives the user's conversation as an acoustic signal in real time. The input is voice information, and this signal is sent to the server as output. Specifically, the terminal's microphone captures the voice, converts the voice data into a digital format, and begins sending it to the server.

[0204] Step 2:

[0205] The server converts the received acoustic signal into text information using speech recognition software. The input for this step is the acoustic signal transmitted from the terminal, and the output is the converted text information. For data processing, an acoustic analysis algorithm is used to convert the speech to text.

[0206] Step 3:

[0207] The server performs sentiment analysis using textual information. The input for this step is textual information converted from speech, and the output is data indicating the user's emotional state. The sentiment analysis algorithm determines the user's emotional state (anxiety, confusion, etc.) from the textual information.

[0208] Step 4:

[0209] The server compares textual information and emotional assessment results with an information aggregate to evaluate the likelihood of fraud. The input is textual information and emotional data, and the output is a fraud likelihood score. At this stage, matching is performed with fraud patterns in the database to calculate the overall fraud risk.

[0210] Step 5:

[0211] The server determines whether a notification is necessary based on the fraud risk score and sends a warning if necessary. The input is the fraud risk score, and the output is a notification message. If the fraud risk is high, an enhanced warning is sent to the registered contact. It is also possible to generate notification content using a generative AI model.

[0212] 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.

[0213] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0228] This invention relates to a fraud prevention system equipped with voice input means, conversion means, analysis means, and notification means. The operation of the system is described below.

[0229] First, when a user starts a conversation, the device's voice input captures the conversation. Next, the captured audio data is sent from the device to the server via a secure communication protocol.

[0230] The server converts the received audio data into text data using a conversion device. This text data is then passed to an analysis device and compared against a database to detect potential fraud.

[0231] If fraud is suspected, the server's notification system will activate and send an alert to the designated emergency contacts (such as the user's family or the police). The device will also use its internal notification system to warn the user verbally or visually.

[0232] For example, if an elderly person is approached by a scammer over the phone about a tax refund, the device will capture the conversation in real time and immediately detect the risk of fraud through a subsequent process. The server will determine that the situation is urgent and notify the user's family using a notification system. By contacting the elderly person promptly, the family can prevent fraudulent transactions.

[0233] This invention provides users with a high level of security and enables the management and prevention of fraud risks in real time.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The device detects sounds around the user and captures those sounds in real time using a voice input device.

[0237] Step 2:

[0238] The terminal stores the audio data in a buffer and prepares to send that audio data to the server over the network at regular intervals.

[0239] Step 3:

[0240] The server converts the received audio data into text data using a conversion mechanism. This conversion is performed using speech recognition technology.

[0241] Step 4:

[0242] The server passes the text data to an analysis tool, which then matches the text against keywords and phrases related to fraud. The database used here contains records of past fraud patterns and known fraudulent techniques.

[0243] Step 5:

[0244] The server calculates a fraud score based on the matching results and determines whether there is a possibility of fraud. A threshold is set for this determination, and if it exceeds that threshold, it is considered fraud.

[0245] Step 6:

[0246] If a fraudulent activity is deemed highly likely, the server will send an alert to registered emergency contacts via a notification system.

[0247] Step 7:

[0248] At the same time, the device issues direct warnings to the user and provides information to draw their attention using voice or display.

[0249] These steps enable the system to efficiently detect fraud and protect users and their families.

[0250] (Example 1)

[0251] Next, we will describe 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."

[0252] The problem that this invention aims to solve is to prevent fraudulent transactions by early detection of potential fraud in voice communications and prompt notification to users and their related parties. This problem is particularly serious for the elderly and people with limited knowledge of fraud, and there is a need to provide an environment in which they can communicate with peace of mind on a daily basis.

[0253] 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.

[0254] In this invention, the server includes an input device for acquiring audio, a conversion device for converting the acquired audio into a standardized data format, and an analysis device for comparing text data with a pre-configured information set in order to evaluate the possibility using the data format. This makes it possible to analyze the risk of fraud from the content of the audio in real time and quickly notify the relevant parties.

[0255] "Speech" refers to data acquired as sound waveforms, and typically includes information such as human conversation.

[0256] An "input device" is a device that has the function of acquiring external audio and converting it into a format that can be incorporated into the system.

[0257] A "conversion device" is a device that converts acquired audio data into a standardized text data format.

[0258] An "analytical device" is a device that uses text data to assess the likelihood of fraud and processes information based on the results.

[0259] A "notification device" is a device that sends notifications generated based on analysis results to a specified recipient.

[0260] A "standardized data format" is a common format used to process data uniformly across different systems.

[0261] A "database" is a knowledge base that includes databases and rule sets that are referenced when assessing the likelihood of fraud.

[0262] The "evaluation score" is a score generated based on the analysis of text data, and it is a numerical value that indicates the likelihood of fraud.

[0263] This invention is a fraud prevention system that targets voice and has the following configuration.

[0264] A series of actions

[0265] When a user starts a conversation, the device captures the audio using its built-in voice input device. The smartphone's microphone is primarily used to acquire the audio data.

[0266] Next, the captured audio is converted to a digital format in real time and sent to the server using a secure communication protocol. HTTPS is used for transmission, and TLS technology is used to encrypt the data.

[0267] Processing of audio data

[0268] The server converts the acquired audio data into text data using speech recognition technology (e.g., Speech-to-Text API). This conversion technology transforms everyday language into a standardized data format that can be understood.

[0269] Subsequently, a natural language processing engine on the server runs to analyze the text data. This engine refers to a collection of past fraud patterns and keywords to assess the likelihood of fraud.

[0270] Notifications and alerts

[0271] If a potential scam is detected, the server sends a notification to the user's family and other registered recipients via a configured notification device. SMS and email are used to ensure rapid information dissemination.

[0272] Furthermore, the device will issue alerts to the user directly via voice and on the screen. The voice notification will include a message such as "This may be a scam."

[0273] Specific example

[0274] For example, if an elderly person is asked over the phone for their bank account information regarding a tax refund, the device recognizes the conversation and immediately analyzes it. If it is determined that there is a high risk of fraud, a warning is promptly sent to the family, preventing potential problems.

[0275] Example of a prompt

[0276] An example of a prompt to input into a generative AI model is, "Analyze the audio data and explain the results of the detection of suspicious keywords."

[0277] In this way, users can ensure a high level of security through the system and be protected from fraudulent activities.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] When a user starts a conversation, the device captures the audio via a voice input device. The input is real-time audio, and the output is digital audio data. Specifically, the smartphone's microphone is used to remove background noise and obtain a high-quality audio sample.

[0281] Step 2:

[0282] The terminal sends the captured audio data to the server using a secure communication protocol. It receives digital audio data as input and generates encrypted data packets as output. This step utilizes HTTPS and leverages TLS technology to securely transmit the data. This method prevents data disruption and unauthorized access during transmission.

[0283] Step 3:

[0284] The server converts the received voice data into text data using voice recognition technology. It receives encrypted voice data as input and generates text-formatted data as output. Specifically, the Speech-to-Text API is used, and an advanced algorithm for converting voice waveforms into text operates.

[0285] Step 4:

[0286] The server analyzes the converted text data and evaluates the possibility of fraud. It receives text data as input and obtains an evaluation result as output. This analysis involves a natural language processing engine, which calculates a risk score based on information collection. For example, if the word "refund" is detected, it is determined that the fraud risk is high.

[0287] Step 5:

[0288] If the possibility of fraud is detected, the server issues a notification to the user's family members or registered contacts. It receives the evaluation result as input and generates a notification in the form of a message or email as output. Specifically, it uses an SMS gateway or a mail server to perform rapid information transmission.

[0289] Step 6:

[0290] At the same time, the terminal issues a warning to the user audibly or visually. It receives the evaluation result as input and issues an audible alert or a pop-up notification as output. The terminal can automatically launch an app to inform the user that "there may be a possibility of fraud".

[0291] Through this series of processes, the user can recognize the fraud risk in real time and take appropriate actions.

[0292] (Application Example 1)

[0293] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0294] Traditional fraud prevention systems have struggled to analyze voices in real time and immediately warn of potential fraud. Therefore, real-time fraud detection is required. Furthermore, a system that can smoothly notify users and their families is also necessary.

[0295] 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.

[0296] In this invention, the server includes sensor means for acquiring sound, computing device means for converting the acquired sound into text data, and analysis device means for comparing the text data with a pre-configured storage device to assess the risk of fraud. This makes it possible to analyze the sound in real time, quickly assess the possibility of fraud, and immediately notify the user or designated contacts.

[0297] A "sensor" is a device used to acquire sound, and it collects information by sensing sound waves from its surroundings.

[0298] A "processing unit" is a device that converts acquired speech into text data, and it processes speech into text format using speech recognition technology.

[0299] An "analysis device" is a device used to assess the risk of fraud by comparing text data with a pre-configured storage device.

[0300] A "warning device" is a device that issues a warning when there is a high probability of fraud, and it informs the user of the danger either audibly or visually.

[0301] A "communication device" is a device used to notify users and contacts, and has the function of transmitting information over a network.

[0302] The system for implementing this invention first collects voice data obtained from the user through a voice sensor. The sensor senses the voice and acquires data in real time. The acquired voice data is converted into character data by an arithmetic unit. In this process, the Google Speech-to-Text API, which is voice recognition software, is used.

[0303] After the arithmetic unit converts it into character data, the analysis device of the server collates it with a pre-set storage device to evaluate the risk of fraud. The analysis device uses natural language processing technology to search for known fraud phrases and behavior patterns from a database. Through this search, a fraud probability score is calculated.

[0304] If it is determined that the probability of fraud is high, a warning device gives an audio and visual warning to the user. The warning content is a pattern displayed on a smartphone or tablet.

[0305] Furthermore, a communication device notifies a pre-set contact of the user that there is suspicion of fraud. This notification is carried out via network communication to prompt a prompt response.

[0306] As a specific example, when an elderly person receives a suspicious refund request by phone, the sensor captures the conversation, and the system immediately displays a warning and notifies the set family contacts.

[0307] An example of a prompt sentence using the generative AI model is "Design a system that analyzes phone conversations in real time, detects signs of fraud, and issues warning notifications if necessary." Thereby, the invention provides an effective means for preventing the risk of fraud.

[0308] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0309] Step 1:

[0310] The terminal uses a voice sensor to acquire user voice input in real time. The input is voice waveform data, which is converted into a digital signal. Once data collection is complete, it prepares to be sent to the server.

[0311] Step 2:

[0312] The server receives digital audio data transmitted from the terminal. The received data is converted into text data by a processing unit. This process utilizes the Google Speech-to-Text API to convert audio to text. The output is text data.

[0313] Step 3:

[0314] The server's analysis device compares the acquired text data with a database. The input is converted text data. This data is analyzed by a natural language processing engine to calculate a fraud risk score. The output is the fraud probability score.

[0315] Step 4:

[0316] Based on calculations by the analysis device, if the fraud probability score exceeds a preset threshold, the warning device will issue an audible and visual warning to the user. The input is the score data, and the output is the warning trigger signal.

[0317] Step 5:

[0318] The server's communication device sends a warning message to pre-configured contacts if fraud is suspected. The input is the warning trigger signal, and the output is a notification message to emergency contacts. It verifies the connected contacts and records the completion of the notification.

[0319] 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.

[0320] This invention relates to a fraud prevention system equipped with an emotion engine in addition to voice input means, conversion means, analysis means, and notification means. This makes it possible to detect the user's emotions in real time and reflect them in the assessment of fraud risk.

[0321] First, when a user begins a conversation, the device captures the conversation using voice input. This voice data is then sent from the device to the server. When the server converts the voice to text, it simultaneously analyzes the user's emotional state using an emotion engine. This emotion analysis allows the system to determine whether the user is feeling anxious or confused.

[0322] This text data and sentiment data are cross-referenced with a database of fraud patterns using analytical tools. The server also considers the sentiment state in the fraud probability score to more precisely assess the probability of fraud.

[0323] If a user is determined to be highly likely to be a scam, the server's notification system creates an alert and sends it to the registered contacts. This alert may include detailed information tailored to the user's emotional state. For example, if the user is feeling very anxious, the urgency of the notification may be increased.

[0324] For example, if an elderly person receives a fraudulent phone call offering a refund, the device uses an emotion engine to analyze any unnatural tone or anxiety detected during the conversation. If the system determines that the call is highly likely to be fraudulent, it issues a more emphatic alert than a normal notification. This alert is quickly sent to family members or appropriate personnel, preventing potential fraud.

[0325] In this way, this system achieves a more sophisticated fraud prevention by incorporating not only voice input but also the user's emotional information.

[0326] The following describes the processing flow.

[0327] Step 1:

[0328] The device captures the user's conversation in real time using voice input. The voice signal is acquired as digital data.

[0329] Step 2:

[0330] The acquired audio data is analyzed within the device using an emotion engine to determine the user's voice tone, pitch, and tempo, and to estimate their emotional state.

[0331] Step 3:

[0332] The device sends voice data and emotion data to the server. Communication takes place through an encrypted channel.

[0333] Step 4:

[0334] The server converts the audio data into text data using a conversion tool. Speech recognition technology is used in this process.

[0335] Step 5:

[0336] The server's analysis tool compares text data and sentiment data with a fraud pattern database to score the likelihood of fraud.

[0337] Step 6:

[0338] The likelihood of fraud is assessed by taking into account the emotional state, and the level of risk of fraud is determined. In this case, if the emotions indicate tension or anxiety, the score will be higher.

[0339] Step 7:

[0340] If a user is determined to be highly likely to be a scam, the server will activate a notification system and send an appropriate alert to the user's registered contacts.

[0341] Step 8:

[0342] The device also simultaneously issues a warning to the user, alerting them to danger through a visual display and voice guidance.

[0343] In this way, the system can take the user's emotional state into account, improving the accuracy of fraud detection and the speed of response.

[0344] (Example 2)

[0345] Next, we will describe 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".

[0346] Traditional fraud prevention systems converted voice data into text and simply compared it against a database to determine the likelihood of fraud. However, this approach failed to consider the user's emotional state, making it difficult to accurately assess the risk for users experiencing anxiety or confusion. This is particularly problematic for the elderly and those unfamiliar with technology, who may find it difficult to assess fraud risk, highlighting the need for more accurate detection methods.

[0347] 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.

[0348] In this invention, the server includes input means for collecting audio, conversion means for converting the collected audio into text data, analysis means for analyzing the user's emotional state, analysis means for comparing the text data and emotional data to determine the possibility of fraud, and notification means for adjusting the content and priority of notifications based on the emotional state when fraud is suspected. By incorporating emotional data, it becomes possible to perform fraud detection with higher accuracy and provide appropriate notifications.

[0349] "Input means for collecting voice" refers to a device or method for capturing a user's voice in real time and acquiring it in a format that can be processed as digital data.

[0350] "Conversion means for converting collected audio into text data" refers to a system or program that uses speech recognition technology to convert collected audio data into corresponding text information.

[0351] "Analysis methods for analyzing a user's emotional state" refers to technologies that analyze tone, pitch, and speech rate from a user's voice data to identify specific emotional states (e.g., anxiety or reassurance).

[0352] "An analytical means for determining the possibility of fraud by comparing text data and sentiment data with a pre-configured database" refers to a system that evaluates the possibility of fraud by comparing text converted from speech and analyzed sentiment information with fraud patterns stored in a database.

[0353] "A notification mechanism for adjusting the content and priority of notifications based on emotional state when fraud is suspected" refers to a mechanism that, when a high risk of fraud is determined, dynamically determines the content and urgency of a notification by considering the user's emotional information and sends it to the appropriate recipient.

[0354] The fraud prevention system of this invention combines voice input, sentiment analysis, data analysis, and notification functions. The system's configuration and operation are described in detail below.

[0355] The device, whether a smartphone or a dedicated device, captures the user's voice in real time. A microphone is used as the voice input for this purpose. The captured voice is converted into digital data and transmitted to a server via an internet connection.

[0356] The server converts the audio data into text data using speech recognition software. Examples of usable software include commonly used cloud-based speech recognition APIs. In parallel, an emotion analysis process is performed, analyzing speech tone, pitch, and speed to identify the user's emotional state. An emotion analysis engine is used for this process.

[0357] Text data and analyzed sentiment data are compared against a fraud pattern database. This comparison uses an analysis engine that combines AI algorithms and rule-based systems to calculate a fraud probability score.

[0358] If a situation is deemed highly likely to be fraudulent, the server generates an alert using notification methods. This alert's content and urgency are dynamically adjusted, taking into account the user's emotional state. The notification is sent to pre-registered contacts and communicated to the user via methods such as email or SMS.

[0359] As a concrete example, consider a case where an elderly person receives a fraudulent phone call requesting a refund. In this system, the terminal captures the audio, and if a voice pattern that is highly likely to be fraudulent is detected, the system uses sentiment analysis to identify the user's level of anxiety. The server immediately generates a highlighted alert and sends it to registered contacts to encourage a quick response.

[0360] Examples of prompt statements that can be used as input to a generative AI model are as follows:

[0361] "Please generate scenarios for how to analyze the emotions and assess the fraud risk when an elderly person receives a fraudulent phone call."

[0362] "Please generate notification messages that take into account the user's emotional state."

[0363] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0364] Step 1:

[0365] When a user starts a conversation, the device captures the conversation in real time using voice input. The input is analog audio, which is converted into digital audio data via the microphone. This digital audio is temporarily stored on the device. The operation is similar to how a smartphone's voice recorder app records audio.

[0366] Step 2:

[0367] The device captures digital audio data and sends it to a server via an internet connection. The input is the digital audio data from the device, and the output is the transfer of audio data to the server. This transfer is usually performed using a secure protocol such as HTTPS. The operation is similar to how a smartphone uploads files to a cloud service.

[0368] Step 3:

[0369] The server converts received digital audio data into text data using speech recognition software. The input is digital audio data, and the output is text data. During this process, the audio analysis engine analyzes the sound waveform and converts it into a corresponding string of characters. A specific example of this operation is the process of converting voice commands into text information.

[0370] Step 4:

[0371] The server performs sentiment analysis based on text data converted from speech. The input is text data, and the output is data indicating the user's emotional state. Utilizing natural language processing techniques, it analyzes specific keywords and context within the text to identify emotions. Specifically, it detects emotional categories such as "anxiety" and "anger" from the user's text statements.

[0372] Step 5:

[0373] The server compares the analyzed text data and sentiment data with a fraud pattern database. The input is text data and sentiment data, and the output is a fraud probability score. The AI ​​algorithm then calculates a score and assesses the risk of fraud. One operational method involves matching sets of keywords that trigger fraud.

[0374] Step 6:

[0375] If the fraud probability score is high, the server generates an alert that takes emotional state into account and sends it to pre-registered contacts via a notification system. The input is the fraud probability score and emotional data, and the output is the notified alert. Notifications can be set manually or automatically with different priorities. Specifically, an advanced notification system sends an urgent SMS message to the user's family members.

[0376] (Application Example 2)

[0377] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0378] With the advancement of modern communication technology, fraudulent activities have become more sophisticated, and many people are suffering from their effects. Fraudulent phone calls targeting the elderly are a particularly serious problem, and effective prevention measures are needed. However, conventional prevention systems simply convert voice to text and compare it with a database, without taking into account the user's emotional state. As a result, there is a possibility of missing signs of fraudulent activity. Against this backdrop, there is a need for technology that can analyze the user's emotional state in real time and accurately determine the possibility of fraud.

[0379] 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.

[0380] In this invention, the server includes receiving means for acquiring acoustic signals, conversion means for converting the acquired acoustic signals into textual information, and analysis means for evaluating emotions along with the textual information. This enables the system to accurately determine the possibility of fraud based on the user's emotional state and to send faster and more appropriate warnings.

[0381] An "acoustic signal" is an electrical conversion of sound waves generated by air vibrations.

[0382] "Receiving means" refers to a device or method that has the function of acquiring acoustic signals from an external source.

[0383] "Textual information" refers to symbolic information that is represented in the form of words or sentences converted from acoustic signals.

[0384] A "conversion method" is a technology for analyzing acoustic signals and converting them into textual information.

[0385] "Emotion" refers to the user's psychological or emotional state, which is analyzed from voice and other physiological signals.

[0386] "Analysis methods" refer to techniques and technologies used to make various decisions based on input data.

[0387] An "information aggregate" is a collection of textual information and reference data that serves as a standard for emotional evaluation in order to determine whether something is fraudulent.

[0388] "Verification means" refers to techniques or methods for comparing input data with an information aggregate.

[0389] A "warning" is a message intended to alert users and their associates to danger or require caution.

[0390] "Transmission means" refers to the technology or method used to deliver the generated warning to a specific recipient.

[0391] The present invention is implemented as a system that acquires acoustic signals and converts them into textual information and emotional evaluations. This system uses a device (such as a smartphone) for receiving acoustic signals, a server for conversion and analysis, and communication means for transmitting the results. Specific software that can be used includes a speech input API (e.g., Google Speech-to-Text) and an emotion analysis API (e.g., IBM Watson Tone Analyzer).

[0392] The terminal receives an acoustic signal that detects the user's conversation. This signal is transmitted to a server via a wireless network. The server uses speech recognition technology to convert the acoustic signal into text information and further evaluates the emotions using sentiment analysis technology. The results of the emotion evaluation play a role in detecting potential fraudulent activity. This result is compared with an information aggregate in a database, and if fraud is suspected, the server sends a warning in real time.

[0393] For example, if an elderly person receives a suspicious phone call at home, and the device receives the conversation and the server detects an emotional response indicating distress, the system can immediately send a warning to registered contacts.

[0394] An example of a prompt message is, "Consider designing a system that analyzes a user's emotional state and detects unnatural tones in real time to prevent fraud." This makes it easier for other developers to understand the system's design principles.

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1:

[0397] The terminal receives the user's conversation as an acoustic signal in real time. The input is voice information, and this signal is sent to the server as output. Specifically, the terminal's microphone captures the voice, converts the voice data into a digital format, and begins sending it to the server.

[0398] Step 2:

[0399] The server converts the received acoustic signal into text information using speech recognition software. The input for this step is the acoustic signal transmitted from the terminal, and the output is the converted text information. For data processing, an acoustic analysis algorithm is used to convert the speech to text.

[0400] Step 3:

[0401] The server performs sentiment analysis using textual information. The input for this step is textual information converted from speech, and the output is data indicating the user's emotional state. The sentiment analysis algorithm determines the user's emotional state (anxiety, confusion, etc.) from the textual information.

[0402] Step 4:

[0403] The server compares textual information and emotional assessment results with an information aggregate to evaluate the likelihood of fraud. The input is textual information and emotional data, and the output is a fraud likelihood score. At this stage, matching is performed with fraud patterns in the database to calculate the overall fraud risk.

[0404] Step 5:

[0405] The server determines whether a notification is necessary based on the fraud risk score and sends a warning if necessary. The input is the fraud risk score, and the output is a notification message. If the fraud risk is high, an enhanced warning is sent to the registered contact. It is also possible to generate notification content using a generative AI model.

[0406] 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.

[0407] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0408] 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.

[0409] [Third Embodiment]

[0410] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0411] 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.

[0412] 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).

[0413] 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.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0422] This invention relates to a fraud prevention system equipped with voice input means, conversion means, analysis means, and notification means. The operation of the system is described below.

[0423] First, when a user starts a conversation, the device's voice input captures the conversation. Next, the captured audio data is sent from the device to the server via a secure communication protocol.

[0424] The server converts the received audio data into text data using a conversion device. This text data is then passed to an analysis device and compared against a database to detect potential fraud.

[0425] If fraud is suspected, the server's notification system will activate and send an alert to the designated emergency contacts (such as the user's family or the police). The device will also use its internal notification system to warn the user verbally or visually.

[0426] For example, if an elderly person is approached by a scammer over the phone about a tax refund, the device will capture the conversation in real time and immediately detect the risk of fraud through a subsequent process. The server will determine that the situation is urgent and notify the user's family using a notification system. By contacting the elderly person promptly, the family can prevent fraudulent transactions.

[0427] This invention provides users with a high level of security and enables the management and prevention of fraud risks in real time.

[0428] The following describes the processing flow.

[0429] Step 1:

[0430] The device detects sounds around the user and captures those sounds in real time using a voice input device.

[0431] Step 2:

[0432] The terminal stores the audio data in a buffer and prepares to send that audio data to the server over the network at regular intervals.

[0433] Step 3:

[0434] The server converts the received audio data into text data using a conversion mechanism. This conversion is performed using speech recognition technology.

[0435] Step 4:

[0436] The server passes the text data to an analysis tool, which then matches the text against keywords and phrases related to fraud. The database used here contains records of past fraud patterns and known fraudulent techniques.

[0437] Step 5:

[0438] The server calculates a fraud score based on the matching results and determines whether there is a possibility of fraud. A threshold is set for this determination, and if it exceeds that threshold, it is considered fraud.

[0439] Step 6:

[0440] If a fraudulent activity is deemed highly likely, the server will send an alert to registered emergency contacts via a notification system.

[0441] Step 7:

[0442] At the same time, the device issues direct warnings to the user and provides information to draw their attention using voice or display.

[0443] These steps enable the system to efficiently detect fraud and protect users and their families.

[0444] (Example 1)

[0445] Next, we will describe 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."

[0446] The problem that this invention aims to solve is to prevent fraudulent transactions by early detection of potential fraud in voice communications and prompt notification to users and their related parties. This problem is particularly serious for the elderly and people with limited knowledge of fraud, and there is a need to provide an environment in which they can communicate with peace of mind on a daily basis.

[0447] 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.

[0448] In this invention, the server includes an input device for acquiring audio, a conversion device for converting the acquired audio into a standardized data format, and an analysis device for comparing text data with a pre-configured information set in order to evaluate the possibility using the data format. This makes it possible to analyze the risk of fraud from the content of the audio in real time and quickly notify the relevant parties.

[0449] "Speech" refers to data acquired as sound waveforms, and typically includes information such as human conversation.

[0450] An "input device" is a device that has the function of acquiring external audio and converting it into a format that can be incorporated into the system.

[0451] A "conversion device" is a device that converts acquired audio data into a standardized text data format.

[0452] An "analytical device" is a device that uses text data to assess the likelihood of fraud and processes information based on the results.

[0453] A "notification device" is a device that sends notifications generated based on analysis results to a specified recipient.

[0454] A "standardized data format" is a common format used to process data uniformly across different systems.

[0455] A "database" is a knowledge base that includes databases and rule sets that are referenced when assessing the likelihood of fraud.

[0456] The "evaluation score" is a score generated based on the analysis of text data, and it is a numerical value that indicates the likelihood of fraud.

[0457] This invention is a fraud prevention system that targets voice and has the following configuration.

[0458] A series of actions

[0459] When a user starts a conversation, the device captures the audio using its built-in voice input device. The smartphone's microphone is primarily used to acquire the audio data.

[0460] Next, the captured audio is converted to a digital format in real time and sent to the server using a secure communication protocol. HTTPS is used for transmission, and TLS technology is used to encrypt the data.

[0461] Processing of audio data

[0462] The server converts the acquired audio data into text data using speech recognition technology (e.g., Speech-to-Text API). This conversion technology transforms everyday language into a standardized data format that can be understood.

[0463] Subsequently, a natural language processing engine on the server runs to analyze the text data. This engine refers to a collection of past fraud patterns and keywords to assess the likelihood of fraud.

[0464] Notifications and alerts

[0465] If a potential scam is detected, the server sends a notification to the user's family and other registered recipients via a configured notification device. SMS and email are used to ensure rapid information dissemination.

[0466] Furthermore, the device will issue alerts to the user directly via voice and on the screen. The voice notification will include a message such as "This may be a scam."

[0467] Specific example

[0468] For example, if an elderly person is asked over the phone for their bank account information regarding a tax refund, the device recognizes the conversation and immediately analyzes it. If it is determined that there is a high risk of fraud, a warning is promptly sent to the family, preventing potential problems.

[0469] Example of a prompt

[0470] An example of a prompt to input into a generative AI model is, "Analyze the audio data and explain the results of the detection of suspicious keywords."

[0471] In this way, users can ensure a high level of security through the system and be protected from fraudulent activities.

[0472] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0473] Step 1:

[0474] When a user starts a conversation, the device captures the audio via a voice input device. The input is real-time audio, and the output is digital audio data. Specifically, the smartphone's microphone is used to remove background noise and obtain a high-quality audio sample.

[0475] Step 2:

[0476] The terminal sends the captured audio data to the server using a secure communication protocol. It receives digital audio data as input and generates encrypted data packets as output. This step utilizes HTTPS and leverages TLS technology to securely transmit the data. This method prevents data disruption and unauthorized access during transmission.

[0477] Step 3:

[0478] The server converts received audio data into text data using speech recognition technology. It receives encrypted audio data as input and generates text data as output. Specifically, the Speech-to-Text API is used, and an advanced algorithm is employed to convert audio waveforms into text.

[0479] Step 4:

[0480] The server analyzes the converted text data and assesses the likelihood of fraud. It receives text data as input and outputs an evaluation result. This analysis involves a natural language processing engine, which calculates a risk score based on the information set. For example, if the word "refund" is detected, it is determined that the risk of fraud is high.

[0481] Step 5:

[0482] If potential fraud is detected, the server issues a notification to the user's family and registered contacts. It receives evaluation results as input and generates notifications in the form of messages or emails as output. Specifically, it uses SMS gateways and email servers to ensure rapid information dissemination.

[0483] Step 6:

[0484] Simultaneously, the device issues audio and visual warnings to the user. It receives evaluation results as input and outputs audio alerts and pop-up notifications. The device can automatically launch the app and inform the user that "this may be a scam."

[0485] This series of processes allows users to recognize fraud risks in real time and take appropriate action.

[0486] (Application Example 1)

[0487] Next, we will explain Application Example 1. In the following explanation, 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."

[0488] Traditional fraud prevention systems have struggled to analyze voices in real time and immediately warn of potential fraud. Therefore, real-time fraud detection is required. Furthermore, a system that can smoothly notify users and their families is also necessary.

[0489] 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.

[0490] In this invention, the server includes sensor means for acquiring sound, computing device means for converting the acquired sound into text data, and analysis device means for comparing the text data with a pre-configured storage device to assess the risk of fraud. This makes it possible to analyze the sound in real time, quickly assess the possibility of fraud, and immediately notify the user or designated contacts.

[0491] A "sensor" is a device used to acquire sound, and it collects information by sensing sound waves from its surroundings.

[0492] A "processing unit" is a device that converts acquired speech into text data, and it processes speech into text format using speech recognition technology.

[0493] An "analysis device" is a device used to assess the risk of fraud by comparing text data with a pre-configured storage device.

[0494] A "warning device" is a device that issues a warning when there is a high probability of fraud, and it informs the user of the danger either audibly or visually.

[0495] A "communication device" is a device used to notify users and contacts, and has the function of transmitting information over a network.

[0496] The system implementing this invention first collects voice data acquired from the user through a voice sensor. The sensor detects voice and acquires data in real time. The acquired voice data is converted into text data by a processing unit. In this process, the Google Speech-to-Text API, which is speech recognition software, is used.

[0497] After the computing unit converts the data into text, the server's analysis unit compares it with a pre-configured storage device to assess the risk of fraud. The analysis unit uses natural language processing technology to search the database for known fraud phrases and behavioral patterns. This search calculates a fraud probability score.

[0498] If a system is determined to be highly likely to be fraudulent, it will issue an audible and visual warning to the user. The warning will be displayed on a smartphone or tablet.

[0499] Furthermore, the system notifies the user's registered contacts that the communication device is suspected of being fraudulent. This notification is sent via network communication to encourage a prompt response.

[0500] For example, if an elderly person receives a suspicious request for a refund over the phone, a sensor captures the conversation, and the system immediately displays a warning and notifies designated family contacts.

[0501] An example of a prompt that utilizes a generative AI model is: "Design a system that analyzes phone conversations in real time to detect signs of fraud and issues warning notifications if necessary." This means the invention provides an effective means of preventing the risk of fraud.

[0502] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0503] Step 1:

[0504] The terminal uses a voice sensor to acquire user voice input in real time. The input is voice waveform data, which is converted into a digital signal. Once data collection is complete, it prepares to be sent to the server.

[0505] Step 2:

[0506] The server receives digital audio data transmitted from the terminal. The received data is converted into text data by a processing unit. This process utilizes the Google Speech-to-Text API to convert audio to text. The output is text data.

[0507] Step 3:

[0508] The server's analysis device compares the acquired text data with a database. The input is converted text data. This data is analyzed by a natural language processing engine to calculate a fraud risk score. The output is the fraud probability score.

[0509] Step 4:

[0510] Based on calculations by the analysis device, if the fraud probability score exceeds a preset threshold, the warning device will issue an audible and visual warning to the user. The input is the score data, and the output is the warning trigger signal.

[0511] Step 5:

[0512] The server's communication device sends a warning message to pre-configured contacts if fraud is suspected. The input is the warning trigger signal, and the output is a notification message to emergency contacts. It verifies the connected contacts and records the completion of the notification.

[0513] 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.

[0514] This invention relates to a fraud prevention system equipped with an emotion engine in addition to voice input means, conversion means, analysis means, and notification means. This makes it possible to detect the user's emotions in real time and reflect them in the assessment of fraud risk.

[0515] First, when a user begins a conversation, the device captures the conversation using voice input. This voice data is then sent from the device to the server. When the server converts the voice to text, it simultaneously analyzes the user's emotional state using an emotion engine. This emotion analysis allows the system to determine whether the user is feeling anxious or confused.

[0516] This text data and sentiment data are cross-referenced with a database of fraud patterns using analytical tools. The server also considers the sentiment state in the fraud probability score to more precisely assess the probability of fraud.

[0517] If a user is determined to be highly likely to be a scam, the server's notification system creates an alert and sends it to the registered contacts. This alert may include detailed information tailored to the user's emotional state. For example, if the user is feeling very anxious, the urgency of the notification may be increased.

[0518] For example, if an elderly person receives a fraudulent phone call offering a refund, the device uses an emotion engine to analyze any unnatural tone or anxiety detected during the conversation. If the system determines that the call is highly likely to be fraudulent, it issues a more emphatic alert than a normal notification. This alert is quickly sent to family members or appropriate personnel, preventing potential fraud.

[0519] In this way, this system achieves a more sophisticated fraud prevention by incorporating not only voice input but also the user's emotional information.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] The device captures the user's conversation in real time using voice input. The voice signal is acquired as digital data.

[0523] Step 2:

[0524] The acquired audio data is analyzed within the device using an emotion engine to determine the user's voice tone, pitch, and tempo, and to estimate their emotional state.

[0525] Step 3:

[0526] The device sends voice data and emotion data to the server. Communication takes place through an encrypted channel.

[0527] Step 4:

[0528] The server converts the audio data into text data using a conversion tool. Speech recognition technology is used in this process.

[0529] Step 5:

[0530] The server's analysis tool compares text data and sentiment data with a fraud pattern database to score the likelihood of fraud.

[0531] Step 6:

[0532] The likelihood of fraud is assessed by taking into account the emotional state, and the level of risk of fraud is determined. In this case, if the emotions indicate tension or anxiety, the score will be higher.

[0533] Step 7:

[0534] If a user is determined to be highly likely to be a scam, the server will activate a notification system and send an appropriate alert to the user's registered contacts.

[0535] Step 8:

[0536] The device also simultaneously issues a warning to the user, alerting them to danger through a visual display and voice guidance.

[0537] In this way, the system can take the user's emotional state into account, improving the accuracy of fraud detection and the speed of response.

[0538] (Example 2)

[0539] Next, we will describe 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."

[0540] Traditional fraud prevention systems converted voice data into text and simply compared it against a database to determine the likelihood of fraud. However, this approach failed to consider the user's emotional state, making it difficult to accurately assess the risk for users experiencing anxiety or confusion. This is particularly problematic for the elderly and those unfamiliar with technology, who may find it difficult to assess fraud risk, highlighting the need for more accurate detection methods.

[0541] 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.

[0542] In this invention, the server includes input means for collecting audio, conversion means for converting the collected audio into text data, analysis means for analyzing the user's emotional state, analysis means for comparing the text data and emotional data to determine the possibility of fraud, and notification means for adjusting the content and priority of notifications based on the emotional state when fraud is suspected. By incorporating emotional data, it becomes possible to perform fraud detection with higher accuracy and provide appropriate notifications.

[0543] "Input means for collecting voice" refers to a device or method for capturing a user's voice in real time and acquiring it in a format that can be processed as digital data.

[0544] "Conversion means for converting collected audio into text data" refers to a system or program that uses speech recognition technology to convert collected audio data into corresponding text information.

[0545] "Analysis methods for analyzing a user's emotional state" refers to technologies that analyze tone, pitch, and speech rate from a user's voice data to identify specific emotional states (e.g., anxiety or reassurance).

[0546] "An analytical means for determining the possibility of fraud by comparing text data and sentiment data with a pre-configured database" refers to a system that evaluates the possibility of fraud by comparing text converted from speech and analyzed sentiment information with fraud patterns stored in a database.

[0547] "A notification mechanism for adjusting the content and priority of notifications based on emotional state when fraud is suspected" refers to a mechanism that, when a high risk of fraud is determined, dynamically determines the content and urgency of a notification by considering the user's emotional information and sends it to the appropriate recipient.

[0548] The fraud prevention system of this invention combines voice input, sentiment analysis, data analysis, and notification functions. The system's configuration and operation are described in detail below.

[0549] The device, whether a smartphone or a dedicated device, captures the user's voice in real time. A microphone is used as the voice input for this purpose. The captured voice is converted into digital data and transmitted to a server via an internet connection.

[0550] The server converts the audio data into text data using speech recognition software. Examples of usable software include commonly used cloud-based speech recognition APIs. In parallel, an emotion analysis process is performed, analyzing speech tone, pitch, and speed to identify the user's emotional state. An emotion analysis engine is used for this process.

[0551] Text data and analyzed sentiment data are compared against a fraud pattern database. This comparison uses an analysis engine that combines AI algorithms and rule-based systems to calculate a fraud probability score.

[0552] If a situation is deemed highly likely to be fraudulent, the server generates an alert using notification methods. This alert's content and urgency are dynamically adjusted, taking into account the user's emotional state. The notification is sent to pre-registered contacts and communicated to the user via methods such as email or SMS.

[0553] As a concrete example, consider a case where an elderly person receives a fraudulent phone call requesting a refund. In this system, the terminal captures the audio, and if a voice pattern that is highly likely to be fraudulent is detected, the system uses sentiment analysis to identify the user's level of anxiety. The server immediately generates a highlighted alert and sends it to registered contacts to encourage a quick response.

[0554] Examples of prompt statements that can be used as input to a generative AI model are as follows:

[0555] "Please generate scenarios for how to analyze the emotions and assess the fraud risk when an elderly person receives a fraudulent phone call."

[0556] "Please generate notification messages that take into account the user's emotional state."

[0557] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0558] Step 1:

[0559] When a user starts a conversation, the device captures the conversation in real time using voice input. The input is analog audio, which is converted into digital audio data via the microphone. This digital audio is temporarily stored on the device. The operation is similar to how a smartphone's voice recorder app records audio.

[0560] Step 2:

[0561] The device captures digital audio data and sends it to a server via an internet connection. The input is the digital audio data from the device, and the output is the transfer of audio data to the server. This transfer is usually performed using a secure protocol such as HTTPS. The operation is similar to how a smartphone uploads files to a cloud service.

[0562] Step 3:

[0563] The server converts received digital audio data into text data using speech recognition software. The input is digital audio data, and the output is text data. During this process, the audio analysis engine analyzes the sound waveform and converts it into a corresponding string of characters. A specific example of this operation is the process of converting voice commands into text information.

[0564] Step 4:

[0565] The server performs sentiment analysis based on text data converted from speech. The input is text data, and the output is data indicating the user's emotional state. Utilizing natural language processing techniques, it analyzes specific keywords and context within the text to identify emotions. Specifically, it detects emotional categories such as "anxiety" and "anger" from the user's text statements.

[0566] Step 5:

[0567] The server compares the analyzed text data and sentiment data with a fraud pattern database. The input is text data and sentiment data, and the output is a fraud probability score. The AI ​​algorithm then calculates a score and assesses the risk of fraud. One operational method involves matching sets of keywords that trigger fraud.

[0568] Step 6:

[0569] If the fraud probability score is high, the server generates an alert that takes emotional state into account and sends it to pre-registered contacts via a notification system. The input is the fraud probability score and emotional data, and the output is the notified alert. Notifications can be set manually or automatically with different priorities. Specifically, an advanced notification system sends an urgent SMS message to the user's family members.

[0570] (Application Example 2)

[0571] Next, we will explain application example 2. In the following explanation, 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."

[0572] With the advancement of modern communication technology, fraudulent activities have become more sophisticated, and many people are suffering from their effects. Fraudulent phone calls targeting the elderly are a particularly serious problem, and effective prevention measures are needed. However, conventional prevention systems simply convert voice to text and compare it with a database, without taking into account the user's emotional state. As a result, there is a possibility of missing signs of fraudulent activity. Against this backdrop, there is a need for technology that can analyze the user's emotional state in real time and accurately determine the possibility of fraud.

[0573] 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.

[0574] In this invention, the server includes receiving means for acquiring acoustic signals, conversion means for converting the acquired acoustic signals into textual information, and analysis means for evaluating emotions along with the textual information. This enables the system to accurately determine the possibility of fraud based on the user's emotional state and to send faster and more appropriate warnings.

[0575] An "acoustic signal" is an electrical conversion of sound waves generated by air vibrations.

[0576] "Receiving means" refers to a device or method that has the function of acquiring acoustic signals from an external source.

[0577] "Textual information" refers to symbolic information that is represented in the form of words or sentences converted from acoustic signals.

[0578] A "conversion method" is a technology for analyzing acoustic signals and converting them into textual information.

[0579] "Emotion" refers to the user's psychological or emotional state, which is analyzed from voice and other physiological signals.

[0580] "Analysis methods" refer to techniques and technologies used to make various decisions based on input data.

[0581] An "information aggregate" is a collection of textual information and reference data that serves as a standard for emotional evaluation in order to determine whether something is fraudulent.

[0582] "Verification means" refers to techniques or methods for comparing input data with an information aggregate.

[0583] A "warning" is a message intended to alert users and their associates to danger or require caution.

[0584] "Transmission means" refers to the technology or method used to deliver the generated warning to a specific recipient.

[0585] The present invention is implemented as a system that acquires acoustic signals and converts them into textual information and emotional evaluations. This system uses a device (such as a smartphone) for receiving acoustic signals, a server for conversion and analysis, and communication means for transmitting the results. Specific software that can be used includes a speech input API (e.g., Google Speech-to-Text) and an emotion analysis API (e.g., IBM Watson Tone Analyzer).

[0586] The terminal receives an acoustic signal that detects the user's conversation. This signal is transmitted to a server via a wireless network. The server uses speech recognition technology to convert the acoustic signal into text information and further evaluates the emotions using sentiment analysis technology. The results of the emotion evaluation play a role in detecting potential fraudulent activity. This result is compared with an information aggregate in a database, and if fraud is suspected, the server sends a warning in real time.

[0587] For example, if an elderly person receives a suspicious phone call at home, and the device receives the conversation and the server detects an emotional response indicating distress, the system can immediately send a warning to registered contacts.

[0588] An example of a prompt message is, "Consider designing a system that analyzes a user's emotional state and detects unnatural tones in real time to prevent fraud." This makes it easier for other developers to understand the system's design principles.

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The terminal receives the user's conversation as an acoustic signal in real time. The input is voice information, and this signal is sent to the server as output. Specifically, the terminal's microphone captures the voice, converts the voice data into a digital format, and begins sending it to the server.

[0592] Step 2:

[0593] The server converts the received acoustic signal into text information using speech recognition software. The input for this step is the acoustic signal transmitted from the terminal, and the output is the converted text information. For data processing, an acoustic analysis algorithm is used to convert the speech to text.

[0594] Step 3:

[0595] The server performs sentiment analysis using textual information. The input for this step is textual information converted from speech, and the output is data indicating the user's emotional state. The sentiment analysis algorithm determines the user's emotional state (anxiety, confusion, etc.) from the textual information.

[0596] Step 4:

[0597] The server compares textual information and emotional assessment results with an information aggregate to evaluate the likelihood of fraud. The input is textual information and emotional data, and the output is a fraud likelihood score. At this stage, matching is performed with fraud patterns in the database to calculate the overall fraud risk.

[0598] Step 5:

[0599] The server determines whether a notification is necessary based on the fraud risk score and sends a warning if necessary. The input is the fraud risk score, and the output is a notification message. If the fraud risk is high, an enhanced warning is sent to the registered contact. It is also possible to generate notification content using a generative AI model.

[0600] 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.

[0601] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0602] 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.

[0603] [Fourth Embodiment]

[0604] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0605] 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.

[0606] 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).

[0607] 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.

[0608] 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.

[0609] 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).

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0617] This invention relates to a fraud prevention system equipped with voice input means, conversion means, analysis means, and notification means. The operation of the system is described below.

[0618] First, when a user starts a conversation, the device's voice input captures the conversation. Next, the captured audio data is sent from the device to the server via a secure communication protocol.

[0619] The server converts the received audio data into text data using a conversion device. This text data is then passed to an analysis device and compared against a database to detect potential fraud.

[0620] If fraud is suspected, the server's notification system will activate and send an alert to the designated emergency contacts (such as the user's family or the police). The device will also use its internal notification system to warn the user verbally or visually.

[0621] For example, if an elderly person is approached by a scammer over the phone about a tax refund, the device will capture the conversation in real time and immediately detect the risk of fraud through a subsequent process. The server will determine that the situation is urgent and notify the user's family using a notification system. By contacting the elderly person promptly, the family can prevent fraudulent transactions.

[0622] This invention provides users with a high level of security and enables the management and prevention of fraud risks in real time.

[0623] The following describes the processing flow.

[0624] Step 1:

[0625] The device detects sounds around the user and captures those sounds in real time using a voice input device.

[0626] Step 2:

[0627] The terminal stores the audio data in a buffer and prepares to send that audio data to the server over the network at regular intervals.

[0628] Step 3:

[0629] The server converts the received audio data into text data using a conversion mechanism. This conversion is performed using speech recognition technology.

[0630] Step 4:

[0631] The server passes the text data to an analysis tool, which then matches the text against keywords and phrases related to fraud. The database used here contains records of past fraud patterns and known fraudulent techniques.

[0632] Step 5:

[0633] The server calculates a fraud score based on the matching results and determines whether there is a possibility of fraud. A threshold is set for this determination, and if it exceeds that threshold, it is considered fraud.

[0634] Step 6:

[0635] If a fraudulent activity is deemed highly likely, the server will send an alert to registered emergency contacts via a notification system.

[0636] Step 7:

[0637] At the same time, the device issues direct warnings to the user and provides information to draw their attention using voice or display.

[0638] These steps enable the system to efficiently detect fraud and protect users and their families.

[0639] (Example 1)

[0640] Next, we will describe 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".

[0641] The problem that this invention aims to solve is to prevent fraudulent transactions by early detection of potential fraud in voice communications and prompt notification to users and their related parties. This problem is particularly serious for the elderly and people with limited knowledge of fraud, and there is a need to provide an environment in which they can communicate with peace of mind on a daily basis.

[0642] 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.

[0643] In this invention, the server includes an input device for acquiring audio, a conversion device for converting the acquired audio into a standardized data format, and an analysis device for comparing text data with a pre-configured information set in order to evaluate the possibility using the data format. This makes it possible to analyze the risk of fraud from the content of the audio in real time and quickly notify the relevant parties.

[0644] "Speech" refers to data acquired as sound waveforms, and typically includes information such as human conversation.

[0645] An "input device" is a device that has the function of acquiring external audio and converting it into a format that can be incorporated into the system.

[0646] A "conversion device" is a device that converts acquired audio data into a standardized text data format.

[0647] An "analytical device" is a device that uses text data to assess the likelihood of fraud and processes information based on the results.

[0648] A "notification device" is a device that sends notifications generated based on analysis results to a specified recipient.

[0649] A "standardized data format" is a common format used to process data uniformly across different systems.

[0650] A "database" is a knowledge base that includes databases and rule sets that are referenced when assessing the likelihood of fraud.

[0651] The "evaluation score" is a score generated based on the analysis of text data, and it is a numerical value that indicates the likelihood of fraud.

[0652] This invention is a fraud prevention system that targets voice and has the following configuration.

[0653] A series of actions

[0654] When a user starts a conversation, the device captures the audio using its built-in voice input device. The smartphone's microphone is primarily used to acquire the audio data.

[0655] Next, the captured audio is converted to a digital format in real time and sent to the server using a secure communication protocol. HTTPS is used for transmission, and TLS technology is used to encrypt the data.

[0656] Processing of audio data

[0657] The server converts the acquired audio data into text data using speech recognition technology (e.g., Speech-to-Text API). This conversion technology transforms everyday language into a standardized data format that can be understood.

[0658] Subsequently, a natural language processing engine on the server runs to analyze the text data. This engine refers to a collection of past fraud patterns and keywords to assess the likelihood of fraud.

[0659] Notifications and alerts

[0660] If a potential scam is detected, the server sends a notification to the user's family and other registered recipients via a configured notification device. SMS and email are used to ensure rapid information dissemination.

[0661] Furthermore, the device will issue alerts to the user directly via voice and on the screen. The voice notification will include a message such as "This may be a scam."

[0662] Specific example

[0663] For example, if an elderly person is asked over the phone for their bank account information regarding a tax refund, the device recognizes the conversation and immediately analyzes it. If it is determined that there is a high risk of fraud, a warning is promptly sent to the family, preventing potential problems.

[0664] Example of a prompt

[0665] An example of a prompt to input into a generative AI model is, "Analyze the audio data and explain the results of the detection of suspicious keywords."

[0666] In this way, users can ensure a high level of security through the system and be protected from fraudulent activities.

[0667] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0668] Step 1:

[0669] When a user starts a conversation, the device captures the audio via a voice input device. The input is real-time audio, and the output is digital audio data. Specifically, the smartphone's microphone is used to remove background noise and obtain a high-quality audio sample.

[0670] Step 2:

[0671] The terminal sends the captured audio data to the server using a secure communication protocol. It receives digital audio data as input and generates encrypted data packets as output. This step utilizes HTTPS and leverages TLS technology to securely transmit the data. This method prevents data disruption and unauthorized access during transmission.

[0672] Step 3:

[0673] The server converts received audio data into text data using speech recognition technology. It receives encrypted audio data as input and generates text data as output. Specifically, the Speech-to-Text API is used, and an advanced algorithm is employed to convert audio waveforms into text.

[0674] Step 4:

[0675] The server analyzes the converted text data and assesses the likelihood of fraud. It receives text data as input and outputs an evaluation result. This analysis involves a natural language processing engine, which calculates a risk score based on the information set. For example, if the word "refund" is detected, it is determined that the risk of fraud is high.

[0676] Step 5:

[0677] If potential fraud is detected, the server issues a notification to the user's family and registered contacts. It receives evaluation results as input and generates notifications in the form of messages or emails as output. Specifically, it uses SMS gateways and email servers to ensure rapid information dissemination.

[0678] Step 6:

[0679] Simultaneously, the device issues audio and visual warnings to the user. It receives evaluation results as input and outputs audio alerts and pop-up notifications. The device can automatically launch the app and inform the user that "this may be a scam."

[0680] This series of processes allows users to recognize fraud risks in real time and take appropriate action.

[0681] (Application Example 1)

[0682] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0683] Traditional fraud prevention systems have struggled to analyze voices in real time and immediately warn of potential fraud. Therefore, real-time fraud detection is required. Furthermore, a system that can smoothly notify users and their families is also necessary.

[0684] 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.

[0685] In this invention, the server includes sensor means for acquiring sound, computing device means for converting the acquired sound into text data, and analysis device means for comparing the text data with a pre-configured storage device to assess the risk of fraud. This makes it possible to analyze the sound in real time, quickly assess the possibility of fraud, and immediately notify the user or designated contacts.

[0686] A "sensor" is a device used to acquire sound, and it collects information by sensing sound waves from its surroundings.

[0687] A "processing unit" is a device that converts acquired speech into text data, and it processes speech into text format using speech recognition technology.

[0688] An "analysis device" is a device used to assess the risk of fraud by comparing text data with a pre-configured storage device.

[0689] A "warning device" is a device that issues a warning when there is a high probability of fraud, and it informs the user of the danger either audibly or visually.

[0690] A "communication device" is a device used to notify users and contacts, and has the function of transmitting information over a network.

[0691] The system implementing this invention first collects voice data acquired from the user through a voice sensor. The sensor detects voice and acquires data in real time. The acquired voice data is converted into text data by a processing unit. In this process, the Google Speech-to-Text API, which is speech recognition software, is used.

[0692] After the computing unit converts the data into text, the server's analysis unit compares it with a pre-configured storage device to assess the risk of fraud. The analysis unit uses natural language processing techniques to search the database for known fraud phrases and behavioral patterns. This search calculates a fraud probability score.

[0693] If a system is determined to be highly likely to be fraudulent, it will issue an audible and visual warning to the user. The warning will be displayed on a smartphone or tablet.

[0694] Furthermore, the system notifies the user's registered contacts that the communication device is suspected of being fraudulent. This notification is sent via network communication to encourage a prompt response.

[0695] For example, if an elderly person receives a suspicious request for a refund over the phone, a sensor captures the conversation, and the system immediately displays a warning and notifies designated family contacts.

[0696] An example of a prompt that utilizes a generative AI model is: "Design a system that analyzes phone conversations in real time to detect signs of fraud and issues warning notifications if necessary." This means the invention provides an effective means of preventing the risk of fraud.

[0697] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0698] Step 1:

[0699] The terminal uses a voice sensor to acquire user voice input in real time. The input is voice waveform data, which is converted into a digital signal. Once data collection is complete, it prepares to be sent to the server.

[0700] Step 2:

[0701] The server receives digital audio data transmitted from the terminal. The received data is converted into text data by a processing unit. This process utilizes the Google Speech-to-Text API to convert audio to text. The output is text data.

[0702] Step 3:

[0703] The server's analysis device compares the acquired text data with a database. The input is converted text data. This data is analyzed by a natural language processing engine to calculate a fraud risk score. The output is the fraud probability score.

[0704] Step 4:

[0705] Based on calculations by the analysis device, if the fraud probability score exceeds a preset threshold, the warning device will issue an audible and visual warning to the user. The input is the score data, and the output is the warning trigger signal.

[0706] Step 5:

[0707] The server's communication device sends a warning message to pre-configured contacts if fraud is suspected. The input is the warning trigger signal, and the output is a notification message to emergency contacts. It verifies the connected contacts and records the completion of the notification.

[0708] 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.

[0709] This invention relates to a fraud prevention system equipped with an emotion engine in addition to voice input means, conversion means, analysis means, and notification means. This makes it possible to detect the user's emotions in real time and reflect them in the assessment of fraud risk.

[0710] First, when a user begins a conversation, the device captures the conversation using voice input. This voice data is then sent from the device to the server. When the server converts the voice to text, it simultaneously analyzes the user's emotional state using an emotion engine. This emotion analysis allows the system to determine whether the user is feeling anxious or confused.

[0711] This text data and sentiment data are cross-referenced with a database of fraud patterns using analytical tools. The server also considers the sentiment state in the fraud probability score to more precisely assess the probability of fraud.

[0712] If a user is determined to be highly likely to be a scam, the server's notification system creates an alert and sends it to the registered contacts. This alert may include detailed information tailored to the user's emotional state. For example, if the user is feeling very anxious, the urgency of the notification may be increased.

[0713] For example, if an elderly person receives a fraudulent phone call offering a refund, the device uses an emotion engine to analyze any unnatural tone or anxiety detected during the conversation. If the system determines that the call is highly likely to be fraudulent, it issues a more emphatic alert than a normal notification. This alert is quickly sent to family members or appropriate personnel, preventing potential fraud.

[0714] In this way, this system achieves a more sophisticated fraud prevention by incorporating not only voice input but also the user's emotional information.

[0715] The following describes the processing flow.

[0716] Step 1:

[0717] The device captures the user's conversation in real time using voice input. The voice signal is acquired as digital data.

[0718] Step 2:

[0719] The acquired audio data is analyzed within the device using an emotion engine to determine the user's voice tone, pitch, and tempo, and to estimate their emotional state.

[0720] Step 3:

[0721] The device sends voice data and emotion data to the server. Communication takes place through an encrypted channel.

[0722] Step 4:

[0723] The server converts the audio data into text data using a conversion tool. Speech recognition technology is used in this process.

[0724] Step 5:

[0725] The server's analysis tool compares text data and sentiment data with a fraud pattern database to score the likelihood of fraud.

[0726] Step 6:

[0727] The likelihood of fraud is assessed by taking into account the emotional state, and the level of risk of fraud is determined. In this case, if the emotions indicate tension or anxiety, the score will be higher.

[0728] Step 7:

[0729] If a user is determined to be highly likely to be a scam, the server will activate a notification system and send an appropriate alert to the user's registered contacts.

[0730] Step 8:

[0731] The device also simultaneously issues a warning to the user, alerting them to danger through a visual display and voice guidance.

[0732] In this way, the system can take the user's emotional state into account, improving the accuracy of fraud detection and the speed of response.

[0733] (Example 2)

[0734] Next, we will describe 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".

[0735] Traditional fraud prevention systems converted voice data into text and simply compared it against a database to determine the likelihood of fraud. However, this approach failed to consider the user's emotional state, making it difficult to accurately assess the risk for users experiencing anxiety or confusion. This is particularly problematic for the elderly and those unfamiliar with technology, who may find it difficult to assess fraud risk, highlighting the need for more accurate detection methods.

[0736] 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.

[0737] In this invention, the server includes input means for collecting audio, conversion means for converting the collected audio into text data, analysis means for analyzing the user's emotional state, analysis means for comparing the text data and emotional data to determine the possibility of fraud, and notification means for adjusting the content and priority of notifications based on the emotional state when fraud is suspected. By incorporating emotional data, it becomes possible to perform fraud detection with higher accuracy and provide appropriate notifications.

[0738] "Input means for collecting voice" refers to a device or method for capturing a user's voice in real time and acquiring it in a format that can be processed as digital data.

[0739] "Conversion means for converting collected audio into text data" refers to a system or program that uses speech recognition technology to convert collected audio data into corresponding text information.

[0740] "Analysis methods for analyzing a user's emotional state" refers to technologies that analyze tone, pitch, and speech rate from a user's voice data to identify specific emotional states (e.g., anxiety or reassurance).

[0741] "An analytical means for determining the possibility of fraud by comparing text data and sentiment data with a pre-configured database" refers to a system that evaluates the possibility of fraud by comparing text converted from speech and analyzed sentiment information with fraud patterns stored in a database.

[0742] "A notification mechanism for adjusting the content and priority of notifications based on emotional state when fraud is suspected" refers to a mechanism that, when a high risk of fraud is determined, dynamically determines the content and urgency of a notification by considering the user's emotional information and sends it to the appropriate recipient.

[0743] The fraud prevention system of this invention combines voice input, sentiment analysis, data analysis, and notification functions. The system's configuration and operation are described in detail below.

[0744] The device, whether a smartphone or a dedicated device, captures the user's voice in real time. A microphone is used as the voice input for this purpose. The captured voice is converted into digital data and transmitted to a server via an internet connection.

[0745] The server converts the audio data into text data using speech recognition software. Examples of usable software include commonly used cloud-based speech recognition APIs. In parallel, an emotion analysis process is performed, analyzing speech tone, pitch, and speed to identify the user's emotional state. An emotion analysis engine is used for this process.

[0746] Text data and analyzed sentiment data are compared against a fraud pattern database. This comparison uses an analysis engine that combines AI algorithms and rule-based systems to calculate a fraud probability score.

[0747] If a situation is deemed highly likely to be fraudulent, the server generates an alert using notification methods. This alert's content and urgency are dynamically adjusted, taking into account the user's emotional state. The notification is sent to pre-registered contacts and communicated to the user via methods such as email or SMS.

[0748] As a concrete example, consider a case where an elderly person receives a fraudulent phone call requesting a refund. In this system, the terminal captures the audio, and if a voice pattern that is highly likely to be fraudulent is detected, the system uses sentiment analysis to identify the user's level of anxiety. The server immediately generates a highlighted alert and sends it to registered contacts to encourage a quick response.

[0749] Examples of prompt statements that can be used as input to a generative AI model are as follows:

[0750] "Please generate scenarios for how to analyze the emotions and assess the fraud risk when an elderly person receives a fraudulent phone call."

[0751] "Please generate notification messages that take into account the user's emotional state."

[0752] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0753] Step 1:

[0754] When a user starts a conversation, the device captures the conversation in real time using voice input. The input is analog audio, which is converted into digital audio data via the microphone. This digital audio is temporarily stored on the device. The operation is similar to how a smartphone's voice recorder app records audio.

[0755] Step 2:

[0756] The device captures digital audio data and sends it to a server via an internet connection. The input is the digital audio data from the device, and the output is the transfer of audio data to the server. This transfer is usually performed using a secure protocol such as HTTPS. The operation is similar to how a smartphone uploads files to a cloud service.

[0757] Step 3:

[0758] The server converts received digital audio data into text data using speech recognition software. The input is digital audio data, and the output is text data. During this process, the audio analysis engine analyzes the sound waveform and converts it into a corresponding string of characters. A specific example of this operation is the process of converting voice commands into text information.

[0759] Step 4:

[0760] The server performs sentiment analysis based on text data converted from speech. The input is text data, and the output is data indicating the user's emotional state. Utilizing natural language processing techniques, it analyzes specific keywords and context within the text to identify emotions. Specifically, it detects emotional categories such as "anxiety" and "anger" from the user's text statements.

[0761] Step 5:

[0762] The server compares the analyzed text data and sentiment data with a fraud pattern database. The input is text data and sentiment data, and the output is a fraud probability score. The AI ​​algorithm then calculates a score and assesses the risk of fraud. One operational method involves matching sets of keywords that trigger fraud.

[0763] Step 6:

[0764] If the fraud probability score is high, the server generates an alert that takes emotional state into account and sends it to pre-registered contacts via a notification system. The input is the fraud probability score and emotional data, and the output is the notified alert. Notifications can be set manually or automatically with different priorities. Specifically, an advanced notification system sends an urgent SMS message to the user's family members.

[0765] (Application Example 2)

[0766] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0767] With the advancement of modern communication technology, fraudulent activities have become more sophisticated, and many people are suffering from their effects. Fraudulent phone calls targeting the elderly are a particularly serious problem, and effective prevention measures are needed. However, conventional prevention systems simply convert voice to text and compare it with a database, without taking into account the user's emotional state. As a result, there is a possibility of missing signs of fraudulent activity. Against this backdrop, there is a need for technology that can analyze the user's emotional state in real time and accurately determine the possibility of fraud.

[0768] 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.

[0769] In this invention, the server includes receiving means for acquiring acoustic signals, conversion means for converting the acquired acoustic signals into textual information, and analysis means for evaluating emotions along with the textual information. This enables the system to accurately determine the possibility of fraud based on the user's emotional state and to send faster and more appropriate warnings.

[0770] An "acoustic signal" is an electrical conversion of sound waves generated by air vibrations.

[0771] "Receiving means" refers to a device or method that has the function of acquiring acoustic signals from an external source.

[0772] "Textual information" refers to symbolic information that is represented in the form of words or sentences converted from acoustic signals.

[0773] A "conversion method" is a technology for analyzing acoustic signals and converting them into textual information.

[0774] "Emotion" refers to the user's psychological or emotional state, which is analyzed from voice and other physiological signals.

[0775] "Analysis methods" refer to techniques and technologies used to make various decisions based on input data.

[0776] An "information aggregate" is a collection of textual information and reference data that serves as a standard for emotional evaluation in order to determine whether something is fraudulent.

[0777] "Verification means" refers to techniques or methods for comparing input data with an information aggregate.

[0778] A "warning" is a message intended to alert users and their associates to danger or require caution.

[0779] "Transmission means" refers to the technology or method used to deliver the generated warning to a specific recipient.

[0780] The present invention is implemented as a system that acquires acoustic signals and converts them into textual information and emotional evaluations. This system uses a device (such as a smartphone) for receiving acoustic signals, a server for conversion and analysis, and communication means for transmitting the results. Specific software that can be used includes a speech input API (e.g., Google Speech-to-Text) and an emotion analysis API (e.g., IBM Watson Tone Analyzer).

[0781] The terminal receives an acoustic signal that detects the user's conversation. This signal is transmitted to a server via a wireless network. The server uses speech recognition technology to convert the acoustic signal into text information and further evaluates the emotions using sentiment analysis technology. The results of the emotion evaluation play a role in detecting potential fraudulent activity. This result is compared with an information aggregate in a database, and if fraud is suspected, the server sends a warning in real time.

[0782] For example, if an elderly person receives a suspicious phone call at home, and the device receives the conversation and the server detects an emotional response indicating distress, the system can immediately send a warning to registered contacts.

[0783] An example of a prompt message is, "Consider designing a system that analyzes a user's emotional state and detects unnatural tones in real time to prevent fraud." This makes it easier for other developers to understand the system's design principles.

[0784] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0785] Step 1:

[0786] The terminal receives the user's conversation as an acoustic signal in real time. The input is voice information, and this signal is sent to the server as output. Specifically, the terminal's microphone captures the voice, converts the voice data into a digital format, and begins sending it to the server.

[0787] Step 2:

[0788] The server converts the received acoustic signal into text information using speech recognition software. The input for this step is the acoustic signal transmitted from the terminal, and the output is the converted text information. For data processing, an acoustic analysis algorithm is used to convert the speech to text.

[0789] Step 3:

[0790] The server performs sentiment analysis using textual information. The input for this step is textual information converted from speech, and the output is data indicating the user's emotional state. The sentiment analysis algorithm determines the user's emotional state (anxiety, confusion, etc.) from the textual information.

[0791] Step 4:

[0792] The server compares textual information and emotional assessment results with an information aggregate to evaluate the likelihood of fraud. The input is textual information and emotional data, and the output is a fraud likelihood score. At this stage, matching is performed with fraud patterns in the database to calculate the overall fraud risk.

[0793] Step 5:

[0794] The server determines whether a notification is necessary based on the fraud risk score and sends a warning if necessary. The input is the fraud risk score, and the output is a notification message. If the fraud risk is high, an enhanced warning is sent to the registered contact. It is also possible to generate notification content using a generative AI model.

[0795] 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.

[0796] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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."

[0804] 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.

[0805] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0806] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] The following is further disclosed regarding the embodiments described above.

[0817] (Claim 1)

[0818] An input means for collecting sound,

[0819] A conversion means for converting collected audio into text data,

[0820] To determine the possibility of fraud, an analysis means is used to compare text data with a pre-configured database,

[0821] A notification method for sending notifications when there is a possibility of fraud,

[0822] A fraud prevention system that includes this.

[0823] (Claim 2)

[0824] The fraud prevention system according to claim 1, further comprising a setting means for limiting the recipients of notifications to pre-registered contacts.

[0825] (Claim 3)

[0826] The fraud prevention system according to claim 1, wherein the analysis means calculates a fraud score, and the notification means sets the notification priority based on that score.

[0827] "Example 1"

[0828] (Claim 1)

[0829] An input device for acquiring sound,

[0830] A conversion device for converting acquired audio into a standardized data format,

[0831] An analytical device that compares text data with a pre-configured information set in order to evaluate possibilities using data format,

[0832] A notification device for sending notifications based on evaluation results,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, further comprising a setting device that limits the recipients of notifications to pre-registered destinations.

[0836] (Claim 3)

[0837] The system according to claim 1, wherein the analytical device calculates an evaluation value, and the notification device sets the importance level of the notification based on that value.

[0838] "Application Example 1"

[0839] (Claim 1)

[0840] A sensor for acquiring sound,

[0841] A processing unit for converting acquired audio into text data,

[0842] To assess the risk of fraud, an analysis device is used that compares text data with a pre-configured storage device.

[0843] A warning device that issues a warning when there is a high possibility of fraud,

[0844] A communication device for notifying users and contacts,

[0845] An information processing system that includes this.

[0846] (Claim 2)

[0847] The information processing system according to claim 1, further comprising a function for managing the destination to which notifications are sent using a pre-configured data recording device.

[0848] (Claim 3)

[0849] The information processing system according to claim 1, wherein the analysis device calculates a fraud probability score, and the warning device determines the urgency of the warning based on that score.

[0850] "Example 2 of combining an emotion engine"

[0851] (Claim 1)

[0852] An input means for collecting sound,

[0853] A conversion means for converting collected audio into text data,

[0854] An analytical method for analyzing the emotional state of a user,

[0855] An analytical method for determining the possibility of fraud by comparing text data and sentiment data with a pre-configured database,

[0856] A notification mechanism to adjust the content and priority of notifications based on emotional state when fraud is suspected,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, further comprising a setting means for limiting the recipients of notifications to pre-registered contacts.

[0860] (Claim 3)

[0861] The system according to claim 1, wherein the analysis means calculates a fraud score, and the notification means sets the priority of notifications based on the score and the user's emotional state.

[0862] "Application example 2 when combining with an emotional engine"

[0863] (Claim 1)

[0864] A receiving means for acquiring an acoustic signal,

[0865] A conversion means for converting acquired acoustic signals into text information,

[0866] An analytical means for evaluating emotions along with textual information,

[0867] A matching means that compares textual information and emotional evaluations with a pre-set information aggregate to determine the possibility of fraud,

[0868] A means of sending a warning when it is determined that there is a high probability of fraud,

[0869] Security systems including a security system.

[0870] (Claim 2)

[0871] The security system according to claim 1, further comprising a setting means for limiting the recipients to whom warnings are sent to pre-registered contact methods.

[0872] (Claim 3)

[0873] The crime prevention system according to claim 1, wherein the analysis means calculates a fraud score, and the transmission means sets the importance of a warning based on the score and emotional evaluation. [Explanation of Symbols]

[0874] 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. A sensor for acquiring sound, A processing unit for converting acquired audio into text data, To assess the risk of fraud, an analysis device is used that compares text data with a pre-configured storage device. A warning device that issues a warning when there is a high possibility of fraud, A communication device for notifying users and contacts, An information processing system that includes this.

2. The information processing system according to claim 1, further comprising a function for managing the destination to which notifications are sent using a pre-configured data recording device.

3. The information processing system according to claim 1, wherein the analysis device calculates a fraud probability score, and the warning device determines the urgency of the warning based on that score.

Images