Granted Patent B2

US 12,288,222 · App. 16/653,776 · Granted Apr 29, 2025

Inventors: Anuj Khanna Sohum (Singapore, SG); Charles Yong Jien Foong (Singapore, SG); Madhusudana Ramakrishna (Singapore, SG)

Assignee: Affle (India) Limited

G06Q30/0248H04L63/1425H04L63/1483H04L67/535H04W12/12

Abstract

Claims (38)

1. A computer-implemented method for application installation and detection of fraud in advertisement, the computer-implemented method comprising:

displaying, at a fraud identification system with a processor, one or more advertisements on mobile applications and web applications on a plurality of media devices, wherein the plurality of media devices are associated with a plurality of users, wherein the one or more advertisements are displayed based on interest of the plurality of users, wherein the one or more advertisements are displayed for installing an application, wherein the one or more advertisements are displayed on a plurality of publishers, wherein the one or more advertisements are displayed in real time;

receiving, at the fraud identification system with the processor, a plurality of users requests for downloading and installing the application through the plurality of media devices, wherein a request for installing the application is generated by clicking on the one or more advertisements displayed on the plurality of media devices, wherein a request for installing the application is received in real time;

providing, at the fraud identification system with the processor, one or more methods to the plurality of users, wherein the one or more methods are provided to the plurality of users for installing the application, wherein the one or more methods comprises ways for authenticating the plurality of users, wherein the one or more methods includes instructions to the plurality of users to point towards a source of an augmented reality and press a button in the augmented reality to download the application, and wherein the one or more methods are provided in real time;

fetching, at the fraud identification system with the processor, a first set of data from a database and the plurality of media devices, wherein the first set of data is associated with past typing behavior of each user of the plurality of users, wherein the first set of data includes touch delay, touch length, typing behavior, typing language, voice command length, voice recognition, touch pattern and gesture recognition, wherein the first set of data is fetched in real time;

obtaining, at the fraud identification system with the processor, a second set of data from the plurality of media devices, wherein the second set of data is associated with a plurality of hardware components comprising a barometer, wherein the second set of data comprises location of media device, user data, type of media device, pre-installed applications and available storage, wherein the second set of data is obtained in real time;

analyzing, at the fraud identification system with the processor, the first set of data and the second set of data in real-time, wherein the first set of data and the second set of data are analyzed using one or more machine learning algorithm, wherein the analysis is performed for authenticating one or more users of the plurality of users for installing the application, wherein the first set of data and the second set of data are analyzed for identifying whether the one or more users of the plurality of users are committing fraud, wherein the identification of the fraud is performed by comparing the past typing behavior and present typing behavior of the one or more users of the plurality of users in real time; and

blocking, at the fraud identification system with the processor, one or more publishers of the plurality of publishers and the one or more users of the plurality of users committing the fraud, wherein the one or more publishers of the plurality of publishers and the one or more users of the plurality of users committing the fraud are identified based on analysis of the first set of data and the second set of data, wherein the one or more publishers and the one or more users are blocked in real time.

2. The computer-implemented method as recited in claim 1 , wherein the plurality of publishers comprises at least one of web pages, websites, mobile application and blogs.

3. The computer-implemented method as recited in claim 1 , wherein the one or more methods comprises making a pattern, solving a puzzle, speaking a sentence, scanning a barcode, writing a captcha and scanning an eye movement.

4. The computer-implemented method as recited in claim 1 , wherein the plurality of hardware components comprises a gyroscope, an accelerometer, a proximity sensor, a light sensor, magnetometer, microphone, fingerprint sensor, image sensor and touch screen.

5. The computer-implemented method as recited in claim 1 , wherein the one or more machine learning algorithm comprises linear discriminant analysis, learning vector quantization, linear regression, logistic regression, sum of vector machine, decision tree, random forest, K-nearest neighbor function and time series.

6. The computer-implemented method as recited in claim 1 , further

comprising generating, at the fraud identification system with the processor, a report, wherein the report includes a list of the one or more users and the one or more publishers committing the fraud.

7. A computer system comprising:

one or more processors; and

a memory coupled to the one or more processors, the memory for storing instructions which, when executed by the one or more processors, cause the one or more processors to perform a method for application installation and detection of fraud in advertisement, the method comprising:

displaying, at a fraud identification system, one or more advertisements on mobile applications and web applications on a plurality of media devices, wherein the plurality of media devices are associated with a plurality of users, wherein the one or more advertisements are displayed based on interest of the plurality of users, wherein the one or more advertisements are displayed for installing an application, wherein the one or more advertisements are displayed on a plurality of publishers, wherein the one or more advertisements are displayed in real time;

receiving, at the fraud identification system, a plurality of users requests for downloading and installing the application through the plurality of media devices, wherein a request for installing the application is generated by clicking on the one or more advertisements displayed on the plurality of media devices, wherein a request for installing the application is received in real time;

providing, at the fraud identification system, one or more methods to the plurality of users, wherein the one or more methods are provided to the plurality of users for installing the application, wherein the one or more methods comprises ways for authenticating the plurality of users, wherein the one or more methods includes instructions to the plurality of user to point towards a source of an augmented reality and press a button in the augmented reality to download the application, and wherein the one or more methods are provided in real time;

fetching, at the fraud identification system, a first set of data from a database and the plurality of media devices, wherein the first set of data is associated with past typing behavior of each user of the plurality of users, wherein the first set of data includes touch delay, touch length, typing behavior, typing language, voice command length, voice recognition, touch pattern and gesture recognition, wherein the first set of data is fetched in real time;

obtaining, at the fraud identification system, a second set of data from the plurality of media devices, wherein the second set of data is associated with a plurality of hardware components comprising a barometer, wherein the second set of data comprises location of media device, user data, type of media device, pre-installed applications and available storage, wherein the second set of data is obtained in real time;

analyzing, at the fraud identification system, the first set of data and the second set of data in real-time, wherein the first set of data and the second set of data are analyzed using one or more machine learning algorithm, wherein the analysis is performed for authenticating one or more users of the plurality of users for installing the application, wherein the first set of data and the second set of data are analyzed for identifying whether the one or more users of the plurality of users are committing fraud, wherein the identification of the fraud is performed by comparing the past typing behavior and present typing behavior of the one or more users of the plurality of users in real time; and

blocking, at the fraud identification system, one or more publishers of the plurality of publishers and the one or more users of the plurality of users committing the fraud, wherein the one or more publishers of the plurality of publishers and the one or more users of the plurality of users committing the fraud are identified based on analysis of the first set of data and the second set of data, wherein the one or more publishers and the one or more users are blocked in real time.

8. The computer system as recited in claim 7 , wherein the plurality of publishers comprises at least one of web pages, websites, mobile application and blogs.

9. The computer system as recited in claim 7 , wherein the one or more methods comprises making a pattern, solving a puzzle, speaking a sentence, scanning a barcode, writing a captcha and scanning an eye movement.

10. The computer system as recited in claim 7 , wherein the plurality of hardware components comprises a gyroscope, an accelerometer, a proximity sensor, a light sensor, magnetometer, microphone, fingerprint sensor, image sensor and touch screen.

11. The computer system as recited in claim 7 , wherein the one or more machine learning algorithm comprises linear discriminant analysis, learning vector quantization, linear regression, logistic regression, sum of vector machine, decision tree, random forest, K-nearest neighbor function and time series.

12. The computer system as recited in claim 7 , further comprising generating, at the fraud identification system, a report, wherein the report includes a list of the one or more users and the one or more publishers committing the fraud.

13. A non-transitory computer-readable storage medium encoding computer executable instructions that, when executed by at least one processor, performs a method for application installation and detection of fraud in advertisement, the method comprising:

displaying, at a computing device, one or more advertisements on mobile applications and web applications on a plurality of media devices, wherein the plurality of media devices are associated with a plurality of users, wherein the one or more advertisements are displayed based on interest of the plurality of users, wherein the one or more advertisements are displayed for installing an application, wherein the one or more advertisements are displayed on a plurality of publishers, wherein the one or more advertisements are displayed in real time;

receiving, at the computing device, a plurality of users requests for downloading and installing the application through the plurality of media devices, wherein a request for installing the application is generated by clicking on the one or more advertisements displayed on the plurality of media devices, wherein a request for installing the application is received in real time;

providing, at the computing device, one or more methods to the plurality of users, wherein the one or more methods are provided to the plurality of users for installing the application, wherein the one or more methods comprises ways for authenticating the plurality of users, wherein the one or more methods includes instructions to the plurality of user to point towards a source of an augmented reality and press a button in the augmented reality to download the application, and wherein the one or more methods are provided in real time;

fetching, at the computing device, a first set of data from a database and the plurality of media devices, wherein the first set of data is associated with past typing behavior of each user of the plurality of users, wherein the first set of data includes touch delay, touch length, typing behavior, typing language, voice command length, voice recognition, touch pattern and gesture recognition, wherein the first set of data is fetched in real time;

obtaining, at the computing device, a second set of data from the plurality of media devices, wherein the second set of data is associated with a plurality of hardware components comprising a barometer, wherein the second set of data comprises location of media device, user data, type of media device, pre-installed applications and available storage, wherein the second set of data is obtained in real time;

analyzing, at the computing device, the first set of data and the second set of data in real-time, wherein the first set of data and the second set of data are analyzed using one or more machine learning algorithm, wherein the analysis is performed for authenticating one or more users of the plurality of users for installing the application, wherein the first set of data and the second set of data are analyzed for identifying whether the one or more users of the plurality of users are committing the fraud, wherein the identification of the fraud is performed by comparing the past typing behavior and present typing behavior of the one or more users of the plurality of users in real time; and

blocking, at the computing device, one or more publishers of the plurality of publishers and the one or more users of the plurality of users committing the fraud, wherein the one or more publishers of the plurality of publishers and the one or more users of the plurality of users committing the fraud are identified based on analysis of the first set of data and the second set of data, wherein the one or more publishers and the one or more users are blocked in real time.

14. The non-transitory computer-readable storage medium as recited in claim 13 , wherein the one or more methods comprises making a pattern, solving a puzzle, speaking a sentence, scanning a barcode, writing a captcha and scanning an eye movement.

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (104)