SYSTEM AND METHOD FOR SUGGESTING AUTOMATED ASSISTANTS BASED ON A SIMILARITY VECTOR IN A GRAPHICAL USER INTERFACE FOR MANAGING COMMUNICATION SESSIONS

• US 20110258544A1
• Filed: 12/27/2010
• Published: 10/20/2011
• Est. Priority Date: 04/16/2010
• Status: Active Grant

• Current Assignee: Arlington Technologies, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Avaya Incorporated
• Inventors: Geppert, Birgit, Dinh-Trong, Trung, Roessler, Frank
• Granted Patent: US 10,079,892 B2
• Time in Patent Office: Days
• US Class Current: 715/708
• CPC Class Codes: G06F 16/954 Navigation, e.g. using categorised browsing
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/14 Session management for real-time applications in data packet communications networks H04L65/1066
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for suggesting and inserting automated assistants in a graphical user interface for managing communication sessions. A system for suggesting an automated assistant generates a first vector describing a current context of a current communication session, and generates a comparison of the first vector and a second vector associated with a past context of an automated assistant in a past communication session. Then, if the comparison exceeds a similarity threshold, the system suggests the automated assistant to at least one user in the current communication session. Optionally, the system can predictively insert the automated assistant in a communication session if the comparison exceeds a similarity threshold. The graphical user interface for managing communication sessions displays automated assistants in a same manner as human participants.

Claims

1. A method of suggesting automated assistants in a graphical user interface for managing communication sessions that displays automated assistants in a same manner as human participants, the method comprising:

generating a first vector describing a current context of a current communication session;

generating a comparison of the first vector and a second vector associated with a past context of an automated assistant in a past communication session; and

if the comparison exceeds a similarity threshold, suggesting the automated assistant to at least one user in the current communication session.

2. The method of claim 1, wherein the first vector and the second vector are of different dimensionalities.

3. The method of claim 2, further comprising converting the first vector to a same dimensionality as the second vector.

4. The method of claim 1, wherein each dimension of the first vector describes a single attribute of the current communication session.

5. The method of claim 1, wherein each dimension of the second vector describes a single attribute of the past communication session.

6. The method of claim 1, further comprising:

receiving a similarity constraint; and

generating the comparison of the first vector and the second vector based on the similarity constraint.

7. The method of claim 6, wherein the similarity constraint comprises at least one of a set of users, a set of automated assistants, timing, communication session content, and communication session metadata.

8. The method of claim 1, further comprising inserting the automated assistant in the current communication session.

9. The method of claim 8, further comprising updating the second vector based on interactions with the automated assistant in the current communication session.

15. The system of claim 1, further comprising:

a fourth module configured to control the processor to receive a similarity constraint; and

a fifth module configured to control the processor to generate the comparison of the first vector and the second vector based on the similarity constraint.

10. A system for predictively inserting automated assistants in a communication session, the system comprising:

a processor;

a first module configured to control the processor to receive a first vector describing a current context of a current communication session;

a second module configured to control the processor to generate a comparison of the first vector and a second vector associated with a past context of an automated assistant in a past communication session; and

if the comparison exceeds a similarity threshold, a third module configured to control the processor to insert the automated assistant into the current communication session as depicted in a graphical user interface for managing communication sessions, wherein the graphical user interface displays automated assistants in a same manner as human participants.

11. The system of claim 10, wherein the first vector and the second vector are of different dimensionalities.

12. The system of claim 11, further comprising a fourth module configured to control the processor to convert the first vector to a same dimensionality as the second vector.

13. The system of claim 10, wherein each dimension of the first vector describes a single attribute of the current communication session.

14. The system of claim 10, wherein each dimension of the second vector describes a single attribute of the past communication session.

16. A non-transitory computer-readable storage medium storing instructions which, when executed by a computing device, cause the computing device to suggest automated assistants in a graphical user interface for managing communication sessions that displays automated assistants in a same manner as human participants, the instructions comprising:

generating a first vector describing a current context of a current communication session;

generating a comparison of the first vector and a second vector associated with a past context of an automated assistant in a past communication session; and

if the comparison exceeds a similarity threshold, suggesting the automated assistant to at least one user in the current communication session.

17. The non-transitory computer-readable storage medium of claim 16, the instructions further comprising:

receiving a similarity constraint; and

generating the comparison of the first vector and the second vector based on the similarity constraint.

18. The non-transitory computer-readable storage medium of claim 17, wherein the similarity constraint comprises at least one of a set of users, a set of automated assistants, timing, communication session content, and communication session metadata.

19. The non-transitory computer-readable storage medium of claim 16, the instructions further comprising inserting the automated assistant in the current communication session.

20. The non-transitory computer-readable storage medium of claim 19, the instructions further comprising updating the second vector based on interactions with the automated assistant in the current communication session.