RULE-BASED MESSAGING AND DIALOG ENGINE

• US 20140344709A1
• Filed: 05/14/2013
• Published: 11/20/2014
• Est. Priority Date: 05/14/2013
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Roberts, Michael, Bellotti, Victoria M.E., Ahern, Shane P.
• Granted Patent: US 9,893,904 B2
• Time in Patent Office: Days
• US Class Current: 715/752
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: H04L 12/1859 adapted to provide push services, e.g. data channels
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

One embodiment of the present invention provides a system for generating a message. During operation, the system receives user interaction event data. The user interaction event data describes explicit or implicit interactions of a user with a web application and/or mobile application. Next, the system modifies a graph describing the user'"'"'s current context associated with the user based on an analysis of the user interaction event data, as interpreted by the system learning from previous processing of user interaction event data. The context graph includes information about the user'"'"'s state, behavior, and interests, and some or all portions of the context graph may be shared between users. The system determines a set of rules associated with a group of users that includes the user, and then applies the determined set of rules to any context graph associated with the user to generate the message.

Claims

1. A computer-executable method performed by a messaging server to generate a message, comprising:

receiving user interaction event data, wherein the user interaction event data describes explicit or implicit interactions of a user with a web application and/or mobile application;

modifying a graph describing the user'"'"'s current context associated with the user based on an analysis of the user interaction event data, wherein the analysis comprises applying machine-learning techniques to prior user interaction event data, and wherein the context graph includes information about the user'"'"'s state, behavior and/or interests, and some or all portions of the context graph may be shared between users;

determining a set of rules associated with a group of users that includes the user; and

applying the determined set of rules to any context graph associated with the user to generate the message.

2. The method of claim 1, further comprising:

generating a sequence of related messages that suggest a user perform an action;

tracking user responses to the related messages with a state machine;

generating a new message based on the tracked user responses and the state of the user'"'"'s context graph; and

updating the context graph using data from the state machine.

3. The method of claim 1, further comprising:

selecting a message item associated with the set of rules; and

generating the message based on the selected message item.

4. The method of claim 1, wherein the message is retrieved by a collector/presenter and ranked with other messages to facilitate choosing a message for presentation to the user.

5. The method of claim 1, wherein the method further comprises:

receiving the user interaction event data from a collector/presenter that monitors explicit or implicit user interactions with the web application and/or mobile application.

6. The method of claim 1, further comprising:

sending a series of related messages to the user;

engaging the user in a dialog;

updating the context graph with data from the dialog and/or modifies the message based on the dialog and state of the user'"'"'s context graph.

7. The method of claim 1, wherein the rules are conditional statements referencing nodes and edges of the context graph.

8. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for generating a message, the method comprising:

receiving user interaction event data, wherein the user interaction event data describes explicit or implicit interactions of a user with a web application and/or mobile application;

modifying a graph describing the user'"'"'s current context associated with the user based on an analysis of the user interaction event data, wherein the analysis comprises applying machine-learning techniques to prior user interaction event data, and wherein the context graph includes information about the user'"'"'s state, behavior, and/or interests, and some or all portions of the context graph may be shared between users;

determining a set of rules associated with a group of users that includes the user; and

applying the determined set of rules to any context graph associated with the user to generate the message.

9. The computer-readable storage medium of claim 8, wherein the computer-readable storage medium stores additional instructions that, when executed, cause the computer to perform additional steps comprising:

generating a sequence of related messages that suggest a user perform an action;

tracking user responses to the related messages with a state machine;

generating a new message based on the tracked user responses and the state of the user'"'"'s context graph; and

updating the context graph using data from the state machine.

10. The computer-readable storage medium of claim 8, wherein the computer-readable storage medium stores additional instructions that, when executed, cause the computer to perform additional steps comprising:

selecting a message item associated with the set of rules; and

generating the message based on the selected message item.

11. The computer-readable storage medium of claim 8, wherein the message is retrieved by a collector/presenter and ranked with other messages to facilitate choosing a message for presentation to the user.

12. The computer-readable storage medium of claim 8, wherein the computer-readable storage medium stores additional instructions that, when executed, cause the computer to perform additional steps comprising:

receiving the user interaction event data from a collector/presenter that monitors explicit or implicit user interactions with the web application and/or mobile application.

13. The computer-readable storage medium of claim 8, wherein the computer-readable storage medium stores additional instructions that, when executed, cause the computer to perform additional steps comprising:

sending a series of related messages to the user;

engaging the user in a dialog;

updating the context graph with data from the dialog and/or modifies the message based on the dialog and state of the user'"'"'s context graph.

14. The computer-readable storage medium of claim 8, wherein the rules are conditional statements referencing nodes and edges of the context graph.

15. A computing system for generating a message, the system comprising:

one or more processors,

a computer-readable medium coupled to the one or more processors having instructions stored thereon that, when executed by the one or more processors, cause the one or more processors to perform operations comprising;

receiving user interaction event data, wherein the user interaction event data describes explicit or implicit interactions of a user with a web application and/or mobile application;

modifying a graph describing the user'"'"'s current context associated with the user based on an analysis of the user interaction event data, wherein the analysis comprises applying machine-learning techniques to prior user interaction event data, and wherein the context graph includes information about the user'"'"'s state, behavior, and/or interests, and some or all portions of the context graph may be shared between users;

determining a set of rules associated with a group of users that includes the user; and

applying the determined set of rules to any context graph associated with the user to generate the message.

16. The computing system of claim 15, wherein the computer-readable storage medium stores additional instructions that, when executed, cause the one or more processors to perform additional steps comprising:

generating a sequence of related messages that suggest a user perform an action;

tracking user responses to the related messages with a state machine;

generating a new message based on the tracked user responses and the state of the user'"'"'s context graph; and

updating the context graph using data from the state machine.

17. The computing system of claim 15, wherein the computer-readable storage medium stores additional instructions that, when executed, cause the one or more processors to perform additional steps comprising:

selecting a message item associated with the set of rules; and

generating the message based on the selected message item.

18. The computing system of claim 15, wherein the message is retrieved by a collector/presenter and ranked with other messages to facilitate choosing a message for presentation to the user.

19. The computing system of claim 15, wherein the method further comprises:

receiving the user interaction event data from a collector/presenter that monitors explicit or implicit user interactions with the web application and/or mobile application.

20. The computing system of claim 15, wherein the computer-readable storage medium stores additional instructions that, when executed, cause the computing system to perform additional steps comprising:

sending a series of related messages to the user;

engaging the user in a dialog;

updating the context graph with data from the dialog and/or modifies the message based on the dialog and state of the user'"'"'s context graph.