Patent Issued for Systems and methods for detecting fraudulent calls using virtual assistants (USPTO 11539834): United Services Automobile Association

2023 JAN 16 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Buentello, Andre Rene (San Antonio, TX, US), Lopez, Mark Anthony (Helotes, TX, US), Meyer, Gregory Brian (Plano, TX, US), Philbrick, Ashley Raine (San Antonio, TX, US), Rapport, Garrett Rielly (San Antonio, TX, US), Romero, Jr., Jose L. (San Antonio, TX, US), Szentes, Michael Jay (San Antonio, TX, US), filed on April 21, 2021, was published online on December 27, 2022.

The patent’s assignee for patent number 11539834 is United Services Automobile Association (San Antonio, Texas, United States).

News editors obtained the following quote from the background information supplied by the inventors: “The present disclosure relates generally to detecting fraudulent activity received via telephone calls. More specifically, the present disclosure relates to analyzing certain behavior to detect and predict potential fraudulent actors associated with a caller.

“This section is intended to introduce the reader to various aspects of art that may be related to various aspects of the present disclosure, which are described and/or claimed below. This discussion is believed to be helpful in providing the reader with background information to facilitate a better understanding of the various aspects of the present disclosure. Accordingly, it may be understood that these statements are to be read in this light, and not as admissions of prior art.

“Gaining access to private information via hacking or fraud is a well-established and growing problem. There are many systems of communication that are targets for hacking and fraudsters desire for private data. For example, potential fraudsters or individuals who pose as an existing client may contact an individual via a phone call to offer services, collect information, present financial opportunities, or the like. Some individuals who receive these calls may be unaware of the potential fraudulent nature of the call. Indeed, certain individuals may provide the caller with information that may then be used to perform fraudulent activities (e.g., identity theft) against the call recipient. As such, improved systems and methods for efficiently and effectively detecting potential fraudsters and fraudulent activities are desirable.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventors’ summary information for this patent: “One or more specific embodiments will be described below. In an effort to provide a concise description of these embodiments, not all features of an actual implementation are described in the specification. It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers’ specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another. Moreover, it should be appreciated that such a development effort might be complex and time consuming, but would nevertheless be a routine undertaking of design, fabrication, and manufacture for those of ordinary skill having the benefit of this disclosure.

“When introducing elements of various embodiments of the present disclosure, the articles “a,” “an,” and “the” are intended to mean that there are one or more of the elements. The terms “comprising,” “including,” and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements. Additionally, it should be understood that references to “one embodiment” or “an embodiment” of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features.

“As mentioned above, individuals are increasingly becoming victims to various types fraudulent activities that are aimed at gaining access to private information, providing an opportunity to invest in a fraudulent fund, provide predatory credit loans, solicit for donation to fraudulent charities, or the like. To prevent individuals from continuously receiving calls from potential scammers, the presently disclosed embodiments detail certain systems and methods for identifying potential fraudulent callers and directing these callers to a virtual assistant application. The virtual assistant application may cross reference data (e.g. audio, phone number) related to the received call with data related to known fraudulent calls to identify potential fraudulent callers. In addition, the virtual assistant application may include an artificial intelligence module or component that may generate simulated voice audio that may be provided to the caller. The simulated voice audio may be designed to prompt the caller to provide certain details regarding the purpose of his or her call, such that the virtual assistant application may better gauge whether the call is likely related to a fraudulent activity.

“By way of introduction, FIG. 1 illustrates a caller interaction network 10 that includes certain components, electronic devices, and a collection of electronic devices that enable a caller interaction system to perform the methods described herein. As shown in FIG. 1, the caller interaction network 10 may include a caller interaction system 12 that may be communicatively coupled to a network 14. The network 14 may be any suitable computer network that enables different electronic devices to communicate with each other. As such, the network 14 may include a collection of computing devices (e.g., servers), communication components (e.g., routers), and the like that facilitate the interconnections between the caller interaction system 12 and other components that may be part of the caller interaction network 10.

“The caller interaction system 12 may be any suitable computing device, which is discussed in more detail below with reference to FIG. 2. In certain embodiments, the caller interaction system 12 may be a mobile phone or smartphone that is capable of receiving voice phone calls over cellular towers, satellites, or other suitable telecommunication mediums.”

The claims supplied by the inventors are:

“1. A method, comprising: receiving, via a processor, first audio data associated with a voicemail message from a first incoming communication of a first caller; comparing, via the processor, the first audio data with a plurality of waveforms associated with one or more fraudulent caller activities, wherein the plurality of waveforms is stored on one or more databases; determining, via the processor, that the first caller is associated with at least one of the one or more fraudulent caller activities based on a comparison of the first audio data with the plurality of waveforms; deleting, via the processor, the voicemail message in response to determining that the first caller is associated with the at least a first one of the one or more fraudulent caller activities; receiving, via the processor, a second incoming communication from a second caller; receiving, via the processor, a request to route the second incoming communication from the second caller to a virtual assistant application, wherein the virtual assistant application is configured to interact with the second caller and determine that the second caller is associated with the at least the first one or a second one of the one or more fraudulent caller activities based on identifying a sound waveform that corresponds to an automatic calling machine switching over to a live caller in response to the virtual assistant application interacting with the second caller; receiving, via the processor, an indication from the virtual assistant application that the second caller is associated with the at least the first one or the second one of the one or more fraudulent caller activities; and forwarding, via the processor, the second incoming communication to another party in response to receiving the indication.

“2. The method of claim 1, comprising updating, via the processor, a list stored on a storage component accessible to the processor with identification information associated with the first caller or the second caller in response to determining that the first caller or the second caller is associated with the at least the first one or the second one of the one or more fraudulent caller activities.

“3. The method of claim 2, comprising: receiving, via the processor, a third incoming communication from a third caller; determining, via the processor, whether additional identification information associated with the third incoming communication is stored in the list; and blocking, via the processor, the third incoming communication in response to determining that the additional identification information associated with the third incoming communication is stored in the list.

“4. The method of claim 1, wherein the virtual assistant application is executable by the processor.

“5. The method of claim 1, wherein the virtual assistant application is configured to interact with the second caller using natural language.

“6. The method of claim 1, wherein the one or more databases comprise crowd source data acquired from a plurality of individuals, wherein the crowd source data comprises one or more phone numbers, one or more voice messages, or both classified as fraudulent by the plurality of individuals.

“7. A system, comprising: one or more databases configured to store data associated with one or more fraudulent caller activities; a computing device configured to execute computer-executable instructions that cause a processor to: receive first audio data associated with a voicemail message from a first incoming communication of a first caller; compare the first audio data with a plurality of waveforms associated with the one or more fraudulent caller activities, wherein the plurality of waveforms is stored on the one or more databases; determine that the first caller is associated with at least a first one of the one or more fraudulent caller activities based on a comparison of the first audio data with the plurality of waveforms; and delete the voicemail message in response to determining that the first caller is associated with the at least the first one of the one or more fraudulent caller activities; receive second audio data associated with a second incoming communication of a second caller; receive a request to route the second incoming communication from the second caller to a virtual assistant application, wherein the virtual assistant application is configured to interact with the second caller and determine that the second caller is associated with the at least the first one or a second one of the one or more fraudulent caller activities based on identifying a sound waveform that corresponds to an automatic calling machine switching over to a live caller in response to the virtual assistant application interacting with the second caller; receive an indication from the virtual assistant application that the second caller is associated with the at least the first one or the second one of the one or more fraudulent caller activities; and forward the second incoming communication to another party in response to receiving the indication.

“8. The system of claim 7, where the computing device is configured to convert the first audio data to text data, wherein the text data is stored in the one or more databases.

“9. The system of claim 8, wherein the computing device is configured to extract language usage rules associated with the text data from the one or more databases to identify language rules that correspond to the one or more fraudulent caller activities.

“10. The system of claim 9, wherein the computing device is configured to: detect an additional incoming communication; convert the additional incoming communication to additional text data; compare the additional text data to the extracted language usage rules; and block the additional incoming communication in response to determining that the additional text data is associated with the extracted language rules corresponding to the one or more fraudulent caller activities.

“11. The system of claim 7, wherein the one or more databases comprise crowd source data acquired from a plurality of individuals, wherein the crowd source data comprises one or more phone numbers, one or more voice messages, or both classified as fraudulent by the plurality of individuals.

“12. A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, are configured to cause a processor to: receive first audio data associated with a voicemail message from a first incoming communication of a first caller; compare the first audio data with a plurality of waveforms associated with one or more fraudulent caller activities, wherein the plurality of waveforms is stored on one or more databases determine that the first caller is associated with at least a first one of the one or more fraudulent caller activities based on a comparison of the first audio data with the plurality of waveforms; and delete the voicemail message in response to determining that the first caller is associated with the at least the first one of the one or more fraudulent caller activities; receive second audio data associated with a second incoming communication of a second caller; receive a request to route the second incoming communication from the second caller to a virtual assistant application, wherein the virtual assistant application is configured to interact with the second caller and determine that the second caller is associated with the at least the first one or a second one of the one or more fraudulent caller activities based on identifying a sound waveform that corresponds to an automatic calling machine switching over to a live caller in response to the virtual assistant application interacting with the second caller; receive an indication from the virtual assistant application that the second caller is associated with the at least the first one or the second one of the one or more fraudulent caller activities; and forward the second incoming communication to another party in response to receiving the indication.

“13. The non-transitory computer-readable medium of claim 12, wherein the computer-executable instructions are configured to cause the processor to: receive an additional incoming communication; determine whether additional identification information associated with the additional incoming communication is associated with the one or more fraudulent activities; and block the additional incoming communication in response to determining that the additional identification information associated with the additional incoming communication is stored in the one or more databases associated with the one or more fraudulent activities.

“14. The non-transitory computer-readable medium of claim 12, wherein the virtual assistant application is configured to interact with the second caller using natural language.

“15. The non-transitory computer-readable medium of claim 12, wherein the virtual assistant application is configured to interact with the second caller using one or more audio samples.

“16. The non-transitory computer-readable medium of claim 12, wherein the computer-executable instructions are configured to cause the processor to add caller identification information associated with the first caller of the voicemail message identified as being related to the at least the first one of the one or more fraudulent activities to a blocked call list.

“17. The non-transitory computer-readable medium of claim 12, wherein the computer-executable instructions are configured to cause the processor to send a notification indicating that the voicemail message is available for user access in response to the voicemail being unrelated to the one or more fraudulent activities.”

For additional information on this patent, see: Buentello, Andre Rene. Systems and methods for detecting fraudulent calls using virtual assistants. U.S. Patent Number 11539834, filed April 21, 2021, and published online on December 27, 2022. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11539834)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)