AUTONOMOUS BEHAVIOR REASONING ANALYSIS

• US 20190196932A1
• Filed: 02/23/2017
• Published: 06/27/2019
• Est. Priority Date: 06/08/2016
• Status: Active Grant

• Current Assignee: WalkMe Ltd.
• Original Assignee: WalkMe Ltd.
• Inventors: Adika, Dan, Sweary, Rephael, Ilievsky, David, Bien, Gal, Eiland, Ilan, Eyal, Omri
• Granted Patent: US 11,307,956 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 11/3438 monitoring of user actions tracking the activity of the user H04L67/535
• CPC Class Codes: G06F 11/3447 Performance evaluation by modeling
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 8/38 for implementing user interfaces
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]

Abstract

A computer implemented method of adapting an application according to user interaction comprising using one or more processors for executing a code for collecting autonomously a plurality of action events describing a plurality of actions taken by a plurality of users to navigate through a plurality of pages presented by an application to accomplish one or more goals of the application, the plurality of pages are presented on a GUI at a plurality of user devices used by the plurality of users, analyzing the action events to identify one or more behavioral patterns of at least some of the users for accomplishing the goal(s) and generating automatically one or more recommended adaptations for the application according to the behavioral pattern(s) to adapt a layout of the application in order to increase a probability for one or more users to successfully accomplish the goal(s).

Claims

1. A computer implemented method of adapting an application according to user interaction, comprising:

using at least one processor for executing a code for;

collecting autonomously a plurality of action events describing a plurality of actions taken by a plurality of users to navigate through a plurality of pages presented by an application to accomplish at least one goal of said application, said plurality of pages are presented on a graphical user interface (GUI) at a plurality of user devices used by said plurality of users;

analyzing said plurality of action events to identify at least one behavioral pattern of at least some of said plurality of users for accomplishing said at least one goal; and

generating automatically at least one recommended adaptation for said application according to said at least one behavioral pattern to adapt a layout of said application in order to increase a probability for at least one user to successfully accomplish said at least one goal.

2. The computer implemented method of claim 1, wherein said application is a web based application accessible by a web browser used by at least one of said plurality of users.

3. The computer implemented method of claim 1, wherein said application is a local application executed locally by a device associated with one of said plurality of users.

4. The computer implemented method of claim 1, wherein said autonomous collection of said plurality of actions is conducted independently of said application with no prior knowledge of said application.

5. The computer implemented method of claim 1, further comprising each of said plurality of users is assigned a unique identification tag to identify said each user in a plurality of sessions in which said each user uses said applications.

6. The computer implemented method of claim 1, wherein at least a subset of said plurality of action events initiated by a respective one of said plurality of users is retrieved once said subset exceeds a pre-defined threshold level.

7. The computer implemented method of claim 1, wherein said plurality of action events are identified by identifying at least one of a plurality of displayed objects in each of said plurality of pages and detecting at least one action of said plurality of actions made by at least one of said plurality of users to interact with said at least one displayed objects, said action is a member of a group consisting of:

select, point, click, swipe, hoover and type.

8. The computer implemented method of claim 1, wherein said analysis is conducted on a flow graph model created to represent said application, said flow graph model includes a plurality of nodes each associated with one of said plurality of pages and a plurality of edges each connecting a pair of said plurality of nodes, each of said plurality of edges is assigned with a weight indicating a probability of transition between a respective pair of said plurality of pages.

9. The computer implemented method of claim 1, wherein said analysis comprises analyzing said plurality of action events taken by at least one of said plurality of users over a plurality of sessions in which said each user uses said applications.

10. The computer implemented method of claim 1, wherein said analysis automatically identifies said at least one goal by analyzing at least some of said plurality of actions.

11. The computer implemented method of claim 1, wherein said analysis comprises identifying at least one error made by at least one of said plurality of users in at least one of said plurality of pages.

12. The computer implemented method of claim 1, wherein said analysis comprises clustering said plurality of users to a plurality of user segments to associate said at least one behavioral pattern with at least one of said plurality of user segments.

13. The computer implemented method of claim 1, wherein said analysis comprises identifying at least one barrier page of said plurality of pages, said at least one barrier page reduces said probability for at least some of said plurality of users to successfully accomplish said at least one goal.

14. The computer implemented method of claim 1, wherein said analysis further comprises rating a significance of each of said plurality of action events with respect to said probability.

15. The computer implemented method of claim 1, wherein said analysis further comprises analyzing an active time duration and an idle time duration spent by each of said plurality of users in each of said plurality of pages in order to determine a level of understanding of said each page by said each user.

16. The computer implemented method of claim 1, wherein said analysis further comprises analyzing at least one context characteristic of at least some of said plurality of action events to identify said at least one behavioral pattern, said at least one context characteristic is a member of a group consisting of:

a time of day, a date and a location of said user.

17. The computer implemented method of claim 1, wherein said analysis further comprises estimating at least one intention of at least one of said plurality of users by analyzing said plurality of action events initiated by said at least one user.

18. The computer implemented method of claim 1, wherein said at least one recommended adaptation includes a suggested modification to change a navigation path of said application.

19. The computer implemented method of claim 1, further comprising said at least one recommended adaptation includes a suggested modification to manipulate a user interface of at least one of said plurality of pages in order to improve a user experience provided by said application.

20. The computer implemented method of claim 1, further comprising said at least one recommended adaptation includes a suggested modification to manipulate at least one object displayed in at least one of said plurality of pages, said manipulation is selected from a group consisting of:

addition, removal, change and relocation.

21. The computer implemented method of claim 1, further comprising said at least one recommended adaptation includes a suggested modification to manipulate at least one guidance instruction presented for said application in at least one of said plurality of pages to assist said plurality of users in said navigation, said manipulation is selected from a group consisting of:

addition, removal, change and relocation.

22. The computer implemented method of claim 1, further comprising providing said at least one recommended adaptation to a provider of said application.

23. The computer implemented method of claim 1, further comprising alerting a provider of said application in case a change is detected in said at least one behavioral pattern.

24. The computer implemented method of claim 1, further comprising automatically adapting said application according to said at least one recommended adaptation.

25. A system for adapting an application according to user interaction, comprising:

at least one processor adapted to execute a code, said code comprising;

code instructions to collect a plurality of action events describing a plurality of actions taken by a plurality of users to navigate through a plurality of pages presented by an application to accomplish at least one goal of said application, said plurality of pages are presented on a graphical user interface (GUI) at a plurality of user devices used by said plurality of users;

code instructions to analyze said plurality of action events to identify at least one behavioral pattern of at least some of said plurality of users for accomplishing said at least one goal; and

code instructions to generate automatically at least one recommended adaptation for said application according to said at least one behavioral pattern to adapt a layout of said application in order to increase a probability for at least one user to successfully accomplish said at least one goal.