A system for generating alerts for fraud detection in mobile device and a method thereof

Abstract

A system (100) for generating alerts for fraud detection in mobile device is disclosed. A conversion module (120) stores a voice call as a file in a user device operated by a user when the voice call is initiated between the user and a caller. The conversion module analyzes the voice call in a real-time and simultaneously split the file into a plurality of diminutive files. The conversion module converts the plurality of diminutive files into a text format. An analysis module ( 130) analyzes the text format to search for a one or more predefined terms by utilizing a natural language processing technique performed by a machine learning model and flags the voice call as a fraudulent call. The notification module (140) triggers an alert when the voice call is deemed suspicious based on a presence of the one or more predefined terms during the voice call.

Description

[0001]A SYSTEM FOR GENERATING ALERTS FOR FRAUD DETECTION IN MOBILE DEVICE AND A METHOD THEREOF EARLIEST PRIORITY DATE This Application claims priority from a complete patent application filed in India having Patent Application No.202431065684 filed on 30th day of August 2024 and titled A SYSTEM FOR GENERATING ALERTS FOR FRAUD DETECTION IN MOBILE DEVICE AND A METHOD THEREOF. FIELD OF INVENTION Embodiments of the present disclosure relate to the field of information security, and more particularly, a system for generating alerts for fraud detection in mobile device and a method thereof. BACKGROUND Information security is an act of safeguarding data and information systems against spammers or unauthorized access, usage and disruption of the data. Further, the information security encompasses various tactics and technologies aimed at ensuring confidentiality and availability of the data. Specifically, with respect to a mobile device, the information security plays a vital role due to storage and transmission of sensitive personal and financial data. Spam calls have direct implications to the information security as they are often a vector for phishing attacks and other social engineering tactics aimed at obtained sensitive information from a user. Currently, there are no such applications or instruments in a market specifically designed to help users identify the scam calls during phone calls. Further, fraudsters or scammers often rely on exploitative maneuvers, with One-Time Passwords (OTPs) being a critical element in the scam calls. During phone call conversations, the users might be deceived into disclosing sensitive information like OTPs, which can then be exploited to approve fraudulent transactions. Furthermore, absence of comprehensive tools to identify and warn the users about potential scams during the phone calls is a major issue despite the rising number of phone-based scams. Moreover, the users are left exposed to advanced scams that can result in substantial financial losses due to lack of scam detection techniques in real-time. Moreover, differentiating between genuine and deceptive calls becomes challenging for the users due to lack of the scam detection technique in the real-time. Traditionally, security measures like short message service (SMS) alerts and transaction monitoring only notify the users after unauthorized transactions or spammers have taken place, making reactive rather than proactive. Hence, there is a need for an improved system and method for detecting spam calls in real-time which addresses the aforementioned issue(s). OBJECTIVE OF THE INVENTION An objective of the invention is to generate a short message service alert or a vibration alert to a user device operated by a user when a suspicious phone call is detected to collect the user’s confidential account information. Another objective of the invention is to alert the user to perform specific checks to prevent against any possible financial fraud. Another objective of the invention is to tag a fraudulent call if the caller utilizes predefined terms during the phone call. BRIEF DESCRIPTION In accordance with an embodiment of the present disclosure, a system for generating alerts for fraud detection in mobile device is provided. The system includes a processing subsystem hosted on a server. The processing subsystem is configured to execute on a network to control bidirectional communications among a plurality of modules, wherein the processing subsystem is embedded in the user device. The processing subsystem includes a conversion module configured to store a voice call as a file in a user device operated by a user when the voice call is initiated between the user and a caller wherein the caller is a scammer. Further, the conversion module is also configured to analyze the voice call in a real-time when the user device receives the voice call from an unknown contact and simultaneously split the file into a plurality of diminutive files. Furthermore, the conversion module is configured to convert the plurality of diminutive files into a text format by utilizing an automated speech recognition technique. Further, an analysis module is operatively coupled to the conversion module wherein the analysis module is configured to analyze the text format to search for a one or more predefined terms by utilizing a natural language processing technique performed by a machine learning model. The analysis module is also configured to flag the voice call as a fraudulent call if the caller utters the one or more predefined terms during the voice call, wherein the predefined terms are contemplated as potential words of fraud. Moreover, a notification module is operatively coupled to the analysis module wherein the notification module is configured to trigger a haptic alert to the user device in the real-time if the caller utters the one or more predefined terms during the voice call between the user and the caller prior to disclose a confidential information. The notification module is also configured to trigger a short message service alert after conclusion of the voice call, when the voice call is deemed suspicious based on a presence of the one or more predefined terms prompting the user to perform check prior proceeding to initiate further transaction. In accordance with another embodiment of the present disclosure, a method for generating alerts for fraud detection in mobile device is provided. The method includes storing, by a conversion module, a voice call as a file in a user device operated by a user when the voice call is initiated between the user and a caller wherein the caller is a scammer. The method also includes analyzing, by the conversation module, the voice call in a real-time when the user device receives the voice call from an unknown contact and simultaneously split the file into a plurality of diminutive files. Further, the method includes converting, by the conversation module, the plurality of diminutive files into a text format by utilizing an automated speech recognition technique. Further, the method also includes analyzing, by the analysis module, the text format to search for a one or more predefined terms by utilizing a natural language processing technique performed by a machine learning model. Furthermore, the method includes flagging, by the analysis module, the voice call as a fraudulent call if the caller utters the one or more predefined terms during the voice call, wherein the predefined terms are contemplated as potential words of fraud Further, the method includes triggering a haptic alert to the user device in the real-time if the caller utters the one or more predefined terms during the voice call between the user and the caller prior to disclose a confidential information. Additionally, the method includes triggering, by a notification module, an short message service alert, after conclusion of the voice call, when the voice call is deemed suspicious based on a presence of the one or more predefined terms prompting the user to perform check prior to proceeding to initiate further transaction. To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures. BRIEF DESCRIPTION OF THE DRAWINGS The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which: FIG. 1 is a block diagram representation of a system for generating alerts for fraud detection in mobile device in accordance with an embodiment of the present disclosure; FIG.2 is a block diagram representation of an exemplary embodiment of the system for generating alerts for fraud detection in mobile device of FIG.1 in accordance with an embodiment of the present disclosure; FIG.3 is a block diagram of a computer or a server in accordance with an embodiment of the present disclosure; and FIG.4 illustrates a flow chart representing the steps involved in a method for generating alerts for fraud detection in mobile device in accordance with an embodiment of the present disclosure. Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein. DETAILED DESCRIPTION For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure. The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or subsystems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting. In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise. Embodiments of the present disclosure relates to system for generating alerts for fraud detection in a mobile device. The processing subsystem is configured to execute on a network to control bidirectional communications among a plurality of modules. The processing subsystem includes a conversion module configured to store a voice call as a file in a user device operated by a user when the voice call is initiated between the user and a caller wherein the caller is a scammer. Further, the conversion module is also configured to analyze the voice call in a real-time when the user device receives the voice call from an unknown contact and simultaneously split the file into a plurality of diminutive files. Furthermore, the conversion module is configured to convert the plurality of diminutive files into a text format by utilizing an automated speech recognition technique. Further, an analysis module operatively coupled to the conversion module wherein the analysis module is configured to analyze the text format to search for a one or more predefined terms by utilizing a natural language processing technique performed by a machine learning model. The analysis module is also configured to flag the voice call as a fraudulent call if the caller utters the one or more predefined terms during the voice call, wherein the predefined terms are contemplated as potential words of fraud. Moreover, a notification module operatively coupled to the analysis module wherein the notification module is configured to trigger a haptic alert to the user device in the real-time if the caller utters the one or more predefined terms during the voice call between the user and the caller prior to disclose a confidential information. Further, the notification module is configured to trigger an short message service alert when the voice call is deemed suspicious based on a presence of the one or more predefined terms prompting the user to perform check prior to proceeding to initiate further transaction. FIG. 1 is a block diagram representation of a system for generating alerts for fraud detection in mobile device in accordance with an embodiment of the present disclosure. The system (100) includes a processing subsystem (105) hosted on a server (108). In one embodiment, the server (108) may include a cloud-based server, located outside the user device. In another embodiment, parts of the server (108) may be a local server coupled to the user device (not shown in FIG.1). The processing subsystem (105) is configured to execute on a network (115) to control bidirectional communications among a plurality of modules. In one example, the network (115) may be a private or public local area network (LAN) or Wide Area Network (WAN), such as the Internet. In another embodiment, the network (115) may include both wired and wireless communications according to one or more standards and / or via one or more transport mediums. In one example, the network (115) may include wireless communications according to one of the 802.11 or Bluetooth specification sets, or another standard or proprietary wireless communication protocol. In yet another embodiment, the network (115) may also include communications over a terrestrial cellular network, including, a global system for mobile communications (GSM), code division multiple access (CDMA), and / or enhanced data for global evolution (EDGE) network. The processing subsystem (105) includes a conversion module (120), an analysis module (130) and a notification module (140). The conversion module (120) is configured to store a voice call as a file in a user device operated by a user when the voice call is initiated between the user and a caller. Typically, the caller is a scammer. The scammer is an individual who engages in fraudulent activities with an intent of deceiving the users to gain financial or personal benefits. The scammers employ various approaches to manipulate the user to collect the confidential information. The approaches include, but is not limited to, impersonating trusted entities, creating fake emergencies, and using social engineering techniques. Further, the scammers targets the user through the voice call and convinces the user to reveal the confidential information. The confidential information includes, but is not limited to passwords, bank account details, and one-time passwords (OTPs). Further, the conversion module (120) is also configured to analyze the voice call in real-time when the user device receives the voice call from an unknown contact and simultaneously split the file into a plurality of diminutive files. Furthermore, the conversion module (120) is configured to convert the plurality of diminutive files into a text format by utilizing an automated speech recognition technique. Typically, the Automated Speech Recognition (ASR) enables conversion of spoken language or the voice into the text format. Further, the ASR involves several stages to accurately convert the voice call. In one embodiment, the ASR technique captures the voice call and processes it to filter out noise to enhance the quality. Further, the conversion module (120) utilizes an Artificial Intelligence model to match the voice call with a corresponding text format. The AI model is trained with extensive machine learning on large datasets of one or more predefined words. The one or more predefined words includes, but is not limited to account number, card verification value, and one time password. It must be noted that a contact list is shared from the user to the system (100) to identify and filter the voice call listed in the contact list from being subjected to the voice call analysis. Typically, the file pertaining to the voice call is strictly confined to the user device. The file is stored and analysed in the user device thereby an entire machine learning model operates in the user device itself. Furthermore, the users can delete the file that is stored at any time, and by default, the system (100) recommends auto deleting the file after 7 days or 168 hours, though this period can be customized. The analysis module (130) is operatively coupled to the conversion module (120). The analysis module (130) is configured to analyze the text format to search for a one or more predefined terms by utilizing a natural language processing technique performed by the machine learning model. Typically, the one or more predefined terms includes, but is not limited to, account number, card verification value, and one time password. Typically, the natural language processing technique that flags the fraudulent call undergoes training intervals with the one or more predefined terms and scenarios thereby ensuring the natural language processing technique remains updated and resilient against evolving the fraudulent tactics and trends. Further, the analysis module (130) is configured to flag the voice call as a fraudulent call if the caller utters the one or more predefined terms during the voice call. Once the voice call is flagged as the fraudulent call, specific terms such as account number, card verification value, and one time password are identified based on the one or more predefined terms and a plurality of scenarios during the voice call. The inbuilt technique (machine learning model) generates an output based on the one or more predefined terms and 32 scenarios. Examples of the 32 scenarios includes, but is not limited to the following: Creating Mention of Mention of Mention of S. No Emergency Account Details CVV OTP Output 1 1 0 0 0 SMS 2 1 0 0 1 Haptic 3 1 0 1 0 SMS 4 1 1 0 0 SMS 5 1 0 1 1 Haptic 6 1 1 0 1 Haptic 7 1 1 1 0 SMS 8 1 1 1 1 Haptic 9 0 1 0 0 No Threat 10 0 1 0 1 Haptic 11 0 1 1 0 No Threat 12 1 1 0 0 SMS 13 0 1 1 1 Haptic 14 1 1 0 1 Haptic 15 1 1 1 0 SMS 16 1 1 1 1 Haptic 17 0 0 1 0 No Threat 18 0 0 1 1 Haptic 19 0 1 1 0 No Threat 20 1 0 1 0 SMS 21 0 1 1 1 Haptic 22 1 0 1 1 Haptic 23 1 1 1 0 SMS 24 1 1 1 1 Haptic 25 0 0 0 1 Haptic 26 0 0 1 1 Haptic 27 0 1 0 1 Haptic 28 1 0 0 1 Haptic 29 0 1 1 1 Haptic 30 1 0 1 1 Haptic 31 1 1 0 1 Haptic 32 1 1 1 1 Haptic Table 1: Illustrates a list of the alerts communicated to the user upon detecting the fraudulent calls during the voice call between the user and the caller. Further, the system (100) monitors the fraudulent calls for creation of an emergency, mention of account details, CVV, and OTP. For instance, if an emergency is created without mention of the account details, the CVV, and the OTP, the SMS alert is sent as mentioned in S. No. 1. If an OTP is mentioned during the emergency without mention of account details and CVV, the haptic alert is triggered to the user as mentioned in S No.2. If the CVV is mentioned during the emergency, without mention of the OTP and the account details, the SMS alert is sent to the user as mentioned in S. No 3. Further, if the CVV is mentioned, without mention of OTP and CVV during the emergency, the SMS alert is sent to the user as mentioned in S. No. 4. Further, if the CVV and OTP is mentioned, without mention of the account details during the emergency, the haptic alert is sent to the user as mentioned in S. No.5. Further, if the account details and the OTP is mentioned, without mention of the CVV during the emergency, the haptic alert is sent to the user as mentioned in S. No.6. If the account details and the CVV is mentioned, without mention of the OTP during the emergency, the SMS alert is sent to the user as mentioned in S. No. 7. If the account details, the CVV and the OTP are mentioned, without mention of the OTP during the emergency, the SMS alert is sent to the user as mentioned in S. No.8. Conversely, if no emergency is created and the CVV is mentioned, without mention of the account details and the OTP, no threat is detected as mentioned in S. No.9. Further, if no emergency is created and if the account details and the OTP is mentioned, then the haptic alert is sent to the user as mentioned in S. No. 10. If no emergency is created and if the CVV and the account details is mentioned, no threat is detected as mentioned in S. No. 11. If the account details and the CVV are mentioned, without mention of the account number and the OTP during the emergency, the SMS alert is sent to the user as mentioned in S. No.12. Further, If no emergency is created and if the CVV, the account details and the OTP is mentioned, the haptic alert is sent to the user as mentioned in S. No.13. If the account details and the OTP are mentioned, without mention of the CVV during the emergency, the haptic alert is sent to the user as mentioned in S. No.14. If the CVV and the account details are mentioned, without mention of the OTP during the emergency, the SMS alert is sent to the user as mentioned in S. No.15. Further, if the CVV, account details and the OTP are mentioned during the emergency, the haptic alert is sent to the user as mentioned in S. No.16. Furthermore, if the account details is mentioned, without mention of the CVV and the OTP, no threat is detected as mentioned in S. No. 17. If the account details and the OTP is mentioned, without mention of the CVV, the haptic alert is detected as mentioned in S. No. 18. Furthermore, if the CVV and account details is mentioned, without mention of the OTP, no threat is detected as mentioned in S. No. 19. If the account details is mentioned, without mention of the account new details number and the OTP, the SMS alert is detected as mentioned in S. No. 20. If the CVV, the OTP and the account details is mentioned, the haptic alert is sent as mentioned in S. No. 21. Further, if the account details and the OTP is mentioned, without mention of the CVV, the haptic alert is sent as mentioned in S. No.22. Furthermore, if the CVV account details is mentioned during the emergency without mention of the OTP, the SMS alert is sent to the user as mentioned in S. No.23. If the CVV, account details and the OTP is mentioned during the emergency, the haptic alert is sent to the user as mentioned in S. No.24. Conversely, if no emergency is created and the OTP is mentioned, the haptic alert is sent to the user as mentioned in S. No.25. Further, if no emergency is created, and the account details and the OTP is mentioned, without mention of the CVV, the haptic alert is sent to the user as mentioned in S. No. 26. If no emergency is created, and if the CVV and the OTP is mentioned, without mention of the account details, the haptic alert is sent to the user as mentioned in S. No.27. Further, if the OTP is mentioned, and without mention of the CVV and the account details, the haptic alert is sent to the user as mentioned in S. No.28. Conversely, if no emergency is created, and if the CVV, the account details and the OTP is mentioned, the haptic alert is sent to the user as mentioned in S. No.29. Further, if the account details and the OTP is mentioned, without mention oof the CVV, then the haptic alert is sent to the user as mentioned in S. No.30. If the CVV and the OTP is mentioned without mention of the account details during emergency, then the haptic alert is sent to the user as mentioned in S. No.31. Furthermore, if the account details and the OTP is mentioned, without mention of the CVV during emergency, then the haptic alert is sent to the user as mentioned in S. No.32. It is to be noted that the haptic alert or the vibration alert provides physical feedback to the user. The vibration alert guarantees that the user is quickly notified of any possible threats, even if the user is not actively looking at the mobile device. Further, the vibration alert is particularly useful in instances when a loud auditory alarm could be disruptive or go unnoticed in noisy surroundings. By generating a tactile feeling, the haptic alert or the vibration alert efficiently grabs the user's attention, motivating the users to take required actions to safeguard the confidential information from the potential fraud or the scammer. Typically, the fraudulent calls includes at least one of the imposter fraudulent call, online fraudulent call, real estate fraudulent call, investment fraudulent call, romance fraudulent call, technology fraudulent call, compromise fraudulent call, and natural disaster fraudulent call. The imposter fraudulent call involves a scammer pretending to be someone the user known trusts, such as a friend or family member, office mates from a recognized institution. For example, the scammer may claim to be in urgent need of money due to an emergency. The urgency and familiarity make the user more likely to comply without verifying an identity of the caller. The online fraudulent call typically involves the scammers pretending to be from an online service provider, such as a technical support representative from a well-known company. The scammer convinces the users that their mobile phone or bank account is compromised, and immediate action is required. The caller often asks the user to download an application that gives the scammer remote access to the users mobile phone, causing data loss and financial loss. The real estate fraudulent call involves the scammers posing as real estate agents or asset owners to deceive the users into making fraudulent transactions. Further, the real estate agents offer a property at low price, request an advance payment for a rental property that doesn’t exist, or sell a property they don’t own. The user who believes that the payment is legitimate for the property sends money or personal information, only to find out later that the asset or property was never available. Furthermore, the investment scam calls are intended to entice the users into dubious investment programs. The scammers pose as financial counsellors or investment gurus, promising high-return prospects that appear too good to be true. Further, the scammer urges victims to invest money immediately, frequently use sophisticated language and forged credentials to look trustworthy. After the user invests, the scammer or the caller vanishes with the money, leaving the user with substantial financial losses. The romance fraudulent calls involves, the scammers to utilize phone conversations and social media to create romantic connections with the users, taking advantage of emotional weaknesses of the users. Once the scammers or the callers acquired the user’s confidence and affection, the callers invent stories about financial trouble or emergency and demand money. The users, lured by emotional attachment, frequently transfer enormous quantities of money, which are never retrieved since the caller breaks communication once the funds are received. The technology fraudulent call involves the scammers to pose as a tech company or service provider and claim that there is a problem with the mobile device, account, or service that requires immediate attention. The user is then tricked into giving the scammer remote access to the mobile device, disclosing personal information, or paying for unnecessary services, which frequently leads to the theft of sensitive information or financial fraud. The compromise fraudulent call occurs when the callers or scammers pretend that the users account, credit card, or personal information has been hacked. Posing as bank representatives or security authorities and encourage the user to supply private information to “secure” the accounts. True objective is to obtain enough information to carry out illicit transactions or identity theft, leaving the user financially vulnerable. The natural disaster fraudulent call involves the scammers or the callers to take advantage of the confusion and panic by making the scam calls requesting money or help. The callers pose as representatives of philanthropic groups, relief agencies, or government entities, demanding cash assistance for the users. Unsuspecting the callers who wish to help those in need wind up giving to false charities, with their money going directly to the scammers rather than legitimate relief operations. Furthermore, the notification module (140) is operatively coupled to the analysis module (130). The notification module (140) is configured to trigger a haptic alert to the user device in the real-time if the caller utters the one or more predefined terms during the voice call between the user and the caller prior to disclose a confidential information. The notification module (140) is configured to trigger an short message service alert when the voice call is deemed to be suspicious based on a presence of the one or more predefined terms. Thereby, prompting the user to perform check prior to proceeding to initiate further transaction. Further, if the one or more predefined terms are not detected during the voice call, the voice call is classified as no threat, and no alert is transmitted to the user device. Examples of the check performed by the user includes, but is not limited to, the following: Type of fraudulent calls Predefined terms Short message service details Bank, utility company, phone provider, send funds, Please verify the recipient if you are going Imposter fraudulent call online banking, mobile banking, stop the alleged to send money or share fraud, send money to any personal yourself information. Purchase event tickets, Make sure to check the Online sales fraudulent adopt an animal, online reviews / complaints, call promotion, stores selling refund policies, goods, download an compare prices before application, send money doing any transactions. Make sure to do Vacation rental, purchasing background check or refinancing a home, before doing any Real estate fraudulent call settlement agent / attorney, transactions. last minute updates, get a quote for moving, hold your belongings Investment fraudulent call Investment managers, receive request, “great Do not share your investment opportunity.” personal information to promise guaranteed returns, unknown callers and be the chance to get rich. quick cautious before paying or double your money through crypto / digital currency. Romance fraudulent call Verify the caller Wire transfer, gift cards, identity before sharing flowers, book a diner any personal information. Verify any reported complaints against the website. Remotely access your Verify the identity and Technology fraudulent computer, employees of never grant device familiar companies, provide call access or download any remote access, download an application at the app, device has a virus request of any unknown caller. Verify the claims made, Compromise fraudulent Business, social media check the sender mail call details and install Antivirus software which flags such suspicious emails. Natural Disaster get clean up, repairs done Make sure you have fraudulent call quickly, Payment upfront, multiple quotes and insurance payouts check if the contractor is licensed. Avoid any upfront payments. Table 2: Illustration of the check performed by the user during the voice call prior to proceeding to disclose a confidential information to the caller. The notification module (140) also triggers a vibration alert to the user through the user device in the real-time when a conversation involves exchange of the confidential information during the voice call between the user and the caller. FIG.2 is a block diagram of an exemplary embodiment of the system for generating alerts for fraud detection in mobile device of FIG.1 in accordance with an embodiment of the present disclosure. In an example, consider a scenario where user ‘X’ receives a call from user ‘Y’ who claims to be from his / her bank, and informs the user ‘X’ about a suspicious activity on her / his account. The user ‘X’ is an operator of a mobile device (150) while the user ‘Y’ is a scammer. As a conversation begins, the user ‘X’ mobile device automatically starts recording the voice call in real-time and analyzes the conversation by utilizing the conversion module (120). When the caller begins asking for the confidential information, such as her OTP and account details, the analysis module (130) on the mobile device (150) or the user device (150) listens for occurrence of certain fraudulent terms. When the caller mentions "OTP" and "account number," the system (100) instantly recognizes these one or more terms as potential flags. Before the user ‘X’ can respond, the mobile phone or the user device triggers the haptic alert (160), warning the user ‘X’ that the call may be fraudulent and advising to verify the caller's identity. Heeding the haptic alert (160) , the user ‘X’ decides not to share information and instead contacts the bank directly through a known secure channel. Further, a vibration alert (170) is triggered to the user through the user device (150) in the real-time when the conversation involves exchange of the confidential information during the voice call between the user and the caller by utilizing the notification module (140). This timely warning helps the user ‘X’ avoid falling victim to a scam, ensuring personal and financial information remains safe. FIG.3 is a block diagram of a computer or a server in a user device in accordance with an embodiment of the present disclosure. The server (108) includes processor(s) (230), and memory (210) operatively coupled to the bus (220). The processor(s) (230), as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof. The memory (210) includes several subsystems stored in the form of executable program which instructs the processor (230) to perform the method steps illustrated in FIG. 1. The memory (210) includes a processing subsystem (105) of FIG.1. The processing subsystem (105) further has following modules a conversion module (120), an analysis module (130) and a notification module (140). A conversion module (120) configured to store a voice call as a file in a user device operated by a user when the voice call is initiated between the user and a caller wherein the caller is a scammer. Further, the conversion module (120) is also configured to analyze the voice call in a real-time when the user device receives the voice call from an unknown contact and simultaneously split the file into a plurality of diminutive files. Furthermore, the conversion module (120) is configured to convert the plurality of diminutive files into a text format by utilizing an automated speech recognition technique. Further, an analysis module (130) operatively coupled to the conversion module (120) wherein the analysis module (130) is configured to analyze the text format to search for a one or more predefined terms by utilizing a natural language processing technique performed by a machine learning model. The analysis module (130) is also configured to flag the voice call as a fraudulent call if the caller utters the one or more predefined terms during the voice call, wherein the predefined terms are contemplated as potential words of fraud. Moreover, a notification module (140) operatively coupled to the analysis module (130) wherein the notification module (140) is configured to trigger a haptic alert to the user device in the real-time if the caller utters the one or more predefined terms during the voice call between the user and the caller prior to disclose a confidential information. Further, the notification module (140) is configured to trigger an short message service alert when the voice call is deemed suspicious based on a presence of the one or more predefined terms prompting the user to perform check prior to proceeding to initiate further transaction. The bus (220) as used herein refers to internal memory channels or computer network that is used to connect computer components and transfer data between them. The bus (220) includes a serial bus or a parallel bus, wherein the serial bus transmits data in bit- serial format and the parallel bus transmits data across multiple wires. The bus (220) as used herein, may include but not limited to, a system bus, an internal bus, an external bus, an expansion bus, a frontside bus, a backside bus, and the like. FIG.4 illustrates a flow chart representing the steps involved in a method (300) method for generating alerts for fraud detection in mobile device with an embodiment of the present disclosure. The method (300) includes storing, by a conversion module, a voice call as a file in a user device operated by a user when the voice call is initiated between the user and a caller wherein the caller is a scammer in step 310. In one embodiment, the files remain within the user device and are analyzed within the user device thereby ensuring privacy of a data within the user device. The method (300) also includes analyzing, by the conversation module, the voice call in a real-time when the user device receives the voice call from an unknown contact and simultaneously split the file into a plurality of diminutive files in step 320. Further, the method (300) includes converting, by the conversation module, the plurality of diminutive files into a text format by utilizing an automated speech recognition technique in step 330. Furthermore, the method (300) includes analyzing, by the analysis module, the text format to search for a one or more predefined terms by utilizing a natural language processing technique performed by a machine learning model in step 340. In one embodiment, the natural language processing technique that flags the fraudulent call undergoes training intervals with the one or more predefined terms and scenarios thereby ensuring the natural language processing technique remains updated and resilient against evolving the fraudulent tactics and trends. In another embodiment, the machine learning model utilizes the one or more predefined terms as a training dataset to classify the text format as either scam call or a non-scam call. In one embodiment, the one or more predefined terms includes at least one of the account number, card verification value, and one time password. In another embodiment, the one or more predefined terms are stored in a database (shown in FIG.1) of the user device. Moreover, the method (300) includes flagging, by the analysis module, the voice call as a fraudulent call if the caller utters the one or more predefined terms during the voice call, wherein the predefined terms are contemplated as potential words of fraud in step 350. In one embodiment, the fraudulent call includes at least one of the imposter fraudulent call, online fraudulent call, real estate fraudulent call, investment fraudulent call, romance fraudulent call, technology fraudulent call, compromise fraudulent call, and natural disaster fraudulent call. The method (300) includes triggering, by a notification module, a haptic alert to the user device in the real-time if the caller utters the one or more predefined terms during the voice call between the user and the caller prior to disclose a confidential information in step 360. Additionally, the method (300) includes triggering, by a notification module, an short message service alert after conclusion of the voice call, when the voice call is deemed suspicious based on a presence of the one or more predefined terms prompting the user to perform check prior to proceeding to initiate further transaction., in step 370. In one embodiment, if the one or more predefined terms are not detected during the voice call, the voice call is classified as no threat, and no alert is transmitted to the user device. In another embodiment, the notification module (140) utilizes a threshold alert mechanism to communicate the alert to the user device. Typically, the threshold alert mechanism take care of sending the haptic alert and the SMS alert to the user device. Various embodiments of system (100) for generating alerts for fraud detection in mobile device as described above provides various benefits in improving security and preventing the user from the caller or fraud. The conversion module (120) and the analysis module (130) stores and analyzes the voice calls in real time, thereby detecting potential fraud in real-time. This immediate detection enables timely alerts to be sent to the user by utilizing the notification module (140), allowing the user to take proactive measures before exposing sensitive information to the caller. Further, the conversion module (120) utilizes the automated speech recognition technique and the natural language processing technique ensuring that complex frauds are detected. Moreover, the proactive approach reduces likelihood of a financial loss and identity the caller, providing the users with peace of mind and increased confidence in the voice call communications. In addition, the system (100) preserves privacy by processing and analyzing a data directly on the user's device and ensures that personal data is not transferred to external servers, which further protects user data. The techniques described in this disclosure may be implemented, at least in part, in hardware, software, firmware, or any combination thereof. For example, various aspects of the described techniques may be implemented within one or more processors, including one or more microprocessors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or any other equivalent integrated or discrete logic circuitry, as well as any combinations of such components. The term “processor” or “processing subsystem” may generally refer to any of the foregoing logic circuitry, alone or in combination with other logic circuitry, or any other equivalent circuitry. A control unit including hardware may also perform one or more of the techniques of this disclosure. Such hardware, software, and firmware may be implemented within the same device or within separate devices to support the various techniques described in this disclosure. In addition, any of the described units, modules, or components may be implemented together or separately as discrete but interoperable logic devices. Depiction of different features as modules or units is intended to highlight different functional aspects and does not necessarily imply that such modules or units must be realized by separate hardware, firmware, or software components. Rather, functionality associated with one or more modules or units may be performed by separate hardware, firmware, or software components, or integrated within common or separate hardware, firmware, or software components. It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the disclosure and are not intended to be restrictive thereof. While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein. The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, the order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.

Claims

I CLAIM:

1. A system (100) for generating alerts for fraud detection in mobile device comprising: characterized in that, a processing subsystem (105) hosted on a server (108), wherein the server (108) is hosted on a user device (125), wherein the processing subsystem (105) is configured to execute on a network (115) to control bidirectional communications among a plurality of modules, wherein the processing subsystem (105) is embedded in the user device comprising: a conversion module (120) configured to: store a voice call as a file in the user device (125) operated by a user when the voice call is initiated between the user and a caller wherein the caller is a scammer; analyze the voice call in a real-time when the user device receives a voice call from an unknown contact and simultaneously split the file into a plurality of diminutive files; and convert the plurality of diminutive files into a text format by utilizing an automated speech recognition technique; an analysis module (130) operatively coupled to the conversion module (120) wherein the analysis module (130) is configured to: analyze the text format to search for a one or more predefined terms by utilizing a natural language processing technique performed by a machine learning model; andflag the voice call as a fraudulent call if the caller utters the one or more predefined terms during the voice call, wherein the predefined terms are contemplated as potential words of fraud; and a notification module (140) operatively coupled to the analysis module (130) wherein the notification module (140) is configured to: trigger a haptic alert to the user device in the real-time if the caller utters the one or more predefined terms during the voice call between the user and the caller prior to disclose a confidential information; and trigger an short message service alert after conclusion of the voice call when the voice call is deemed suspicious based on a presence of the one or more predefined terms prompting the user to perform check prior to proceeding to initiate further transaction.

2. The system (100) as claimed in claim 1, wherein the one or more predefined terms comprises at least one of the account number, card verification value, and one time password.

3. The system (100) as claimed in claim 1, wherein the fraudulent call comprises at least one of the imposter fraudulent call, online fraudulent call, real estate fraudulent call, investment fraudulent call, romance fraudulent call, technology fraudulent call, compromise fraudulent call, and natural disaster fraudulent call.

4. The system (100) as claimed in claim 1, wherein the natural language processing technique that flags the fraudulent call undergoes training intervals with of the one or more predefined terms and scenarios thereby ensuring the naturallanguage processing technique remains updated and resilient against evolving the fraudulent tactics and trends.

5. The system (100) as claimed in claim 1, wherein the one or more predefined terms are stored in a database of the user device.

6. The system (100) as claimed in claim 1, wherein the machine learning model utilizes the one or more predefined terms as a training dataset to classify the text format as either scam call or a non-scam call.

7. The system (100) as claimed in claim 1, wherein the notification module (140) utilizes a threshold alert mechanism to communicate the alert to the user device.

8. The system (100) as claimed in claim 1, wherein the files remain within the user device and are analyzed within the user device thereby ensuring privacy of a data within the user device.

9. The system (100) as claimed in claim 1, wherein if the one or more predefined terms are not detected during the voice call, the voice call is classified as no threat, and no alert is transmitted to the user device.

10. A method (300) for generating alerts for fraud detection in mobile device comprising: characterized in that, storing, by a conversion module, a voice call as a file in a user device operated by a user when the voice call is initiated between the user and a caller wherein the caller is a scammer; (310)analyzing, by the conversation module, the voice call in a real-time when the user device receives the voice call from an unknown contact and simultaneously split the file into a plurality of diminutive files; (320) converting, by the conversation module, the plurality of diminutive files into a text format by utilizing an automated speech recognition technique; (330) analyzing, by the analysis module, the text format to search for a one or more predefined terms by utilizing a natural language processing technique performed by a machine learning model; (340) flagging, by the analysis module, the voice call as a fraudulent call if the caller utters the one or more predefined terms during the voice call, wherein the predefined terms are contemplated as potential words of fraud; (350) triggering, by a notification module, a haptic alert to the user device in the real-time if the caller utters the one or more predefined terms during the voice call between the user and the caller prior to disclose a confidential information; (360) and triggering, by the notification module, trigger an short message service alert after conclusion of the voice call when the voice call is deemed suspicious based on a presence of the one or more predefined terms prompting the user to perform check prior to proceeding to initiate further transaction. (370)

Images