IP Library Granted Patent US 11,036,839
Granted Patent B2
US 11,036,839 · App. 16/220,206 · Granted Jun 15, 2021

Password authentication with input pattern analysis

Inventors: Xuewen Qin (San Jose, CA); Liwei Ren (San Jose, CA)
Assignee: Beijing DiDi Infinity Technology and Development Co., Ltd.
G06F21/316G06F3/0482G06F21/40
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,036,839
App. No.
16/220,206
Granted
Jun 15, 2021
Kind
B2
Abstract

Password information and password input pattern information for a user may be obtained. The password information may define a password submitted by the user. The password input pattern information may define an input pattern with which the password was inputted by the user. The password may be compared with a predefined password for the user. The input pattern may be compared with a predefined input pattern for the user. The password may be authenticated based on a first match between the password and the predefined password and a second match between the input pattern and the predefined input pattern.

Claims (47)

1. A system for authenticating passwords, the system comprising:

one or more processors; and

a memory storing instructions that, when executed by the one or more processors, cause the system to perform:

obtaining password information for a user, the password information defining a password submitted by the user through a platform;

obtaining password input pattern information for the user, the password input pattern information defining an input pattern with which the password was inputted by the user, the input pattern including a character pattern and a timing pattern with which one or more characters of the password was inputted by the user;

comparing the password with a predefined password for the user;

comparing the input pattern with a predefined input pattern for the user,

wherein the predefined input pattern is a learned pattern generated for the platform by using machine learning that is trained based on observations of the user's previous input patterns for a predefined number of times or for a predefined duration of time, and

wherein the user has a corresponding predefined input pattern for each of a plurality of platforms, which is learned on the each of the plurality of platforms; and

authenticating the password upon a first match between the password and the predefined password and a second match between the input pattern and the corresponding predefined input pattern generated for the platform.

2. The system of claim 1 , wherein:

the character pattern is defined by the user's use of one or more edit inputs to define the password, the one or more edit inputs including one or more of a character addition input, a character deletion input, a shift input, a caps-lock input, a change in entry point input, a copy input, and/or a paste input; and

the timing pattern is defined by one or more durations of time between input of individual character of the password.

3. A system for authenticating passwords, the system comprising:

one or more processors; and

a memory storing instructions that, when executed by the one or more processors, cause the system to perform:

obtaining password information for a user, the password information defining a password submitted by the user through a platform;

obtaining password input pattern information for the user, the password input pattern information defining an input pattern with which the password was inputted by the user;

comparing the password with a predefined password for the user;

comparing the input pattern with a predefined input pattern for the user,

wherein the predefined input pattern is a learned pattern generated for the platform by using machine learning that is trained based on observations of the user's previous input patterns for a predefined number of times or for a predefined duration of time, and

wherein the user has a corresponding predefined input pattern for each of a plurality of platforms, which is learned on the each of the plurality of platforms; and

authenticating the password upon a first match between the password and the predefined password and a second match between the input pattern and the corresponding predefined input pattern generated for the platform.

4. The system of claim 3 , wherein the input pattern includes a character pattern with which one or more characters of the password was inputted by the user.

5. The system of claim 4 , wherein the character pattern is defined by the user's use of one or more edit inputs to define the password.

6. The system of claim 5 , wherein the one or more edit inputs include one or more of a character addition input, a character deletion input, a shift input, a caps-lock input, a change in entry point input, a copy input, and/or a paste input.

7. The system of claim 6 , wherein the user's use of the one or more edit inputs are determined based on the user' interaction with one or more of a keyboard, a mouse, and/or a touchscreen display.

8. The system of claim 3 , wherein the input pattern includes a timing pattern with which one or more characters of the password was inputted by the user.

9. The system of claim 8 , wherein the timing pattern is defined by one or more durations of time between input of individual character of the password.

10. The system of claim 3 , wherein the predefined input pattern for the user is associated with a platform with which the password was inputted by the user.

11. The system of claim 3 , wherein the predefined input pattern for the user is not associated with a platform with which the password was inputted by the user.

12. A method for authenticating passwords the method comprising:

obtaining password information for a user, the password information defining a password submitted by the user through a platform;

obtaining password input pattern information for the user, the password input pattern information defining an input pattern with which the password was inputted by the user, the input pattern including a character pattern and a timing pattern with which One or more characters of the password was inputted by the user;

comparing the password with a predefined password for the user;

comparing the input pattern with a predefined input pattern for the user,

wherein the predefined input pattern is a learned pattern generated for the platform by using machine learning that is trained based on observations of the user's previous input patterns for a predefined number of times or for a predefined duration of time, and

wherein the user has a corresponding predefined input pattern for each of a plurality of platforms, which is learned on the each of the plurality of platforms; and

authenticating the password upon a first match between the password and the predefined password and a second match between the input pattern and the corresponding predefined input pattern generated for the platform.

13. The method of claim 12 , wherein the input pattern includes a character pattern with which one or more characters of the password was inputted by the user.

14. The method of claim 13 , wherein the character pattern is defined by the user's use of one or more edit inputs to define the password.

15. The method of claim 14 , wherein the one or more edit inputs include one or more of a character addition input, a character deletion input, a shift input, a caps-lock input, a change in entry point input, a copy input, and/or a paste input.

16. The method of claim 15 , wherein the user's use of the one or more edit inputs are determined based on the user's interaction with one or more of a keyboard, a mouse, and/or a touchscreen display.

17. The method of claim 12 , wherein the input pattern includes a timing pattern with which one or more characters of the password was inputted by the user.

18. The method of claim 17 , wherein the timing pattern is defined by one or more durations of time between input of individual character of the password.

19. The method of claim 12 , wherein the predefined input pattern for the user is associated with a platform with which the password was inputted by the user.

20. The method of claim 12 , wherein the predefined input pattern for the user is not associated with a platform with which the password was inputted by the user.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 9, 2020
From: DIDI (HK) SCIENCE AND TECHNOLOGY LIMITED
To: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.
Reel/Frame 053180/0456 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 29, 2020
From: DIDI RESEARCH AMERICA, LLC
To: DIDI (HK) SCIENCE AND TECHNOLOGY LIMITED
Reel/Frame 053081/0934 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 14, 2018
From: QIN, XUEWEN; REN, LIWEI
To: DIDI RESEARCH AMERICA, LLC
Reel/Frame 047775/0701 →
Continuity (1)
Related Publication 20200193001A1 · Jun 18, 2020