Protecting privacy of a customer and an agent using face recognition in a video contact center environment

• US 9,848,165 B2
• Filed: 12/16/2015
• Issued: 12/19/2017
• Est. Priority Date: 08/14/2012
• Status: Active Grant

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Incorporated
• Inventors: Pai, Deep Subhash, Bhalerao, Jaydeep Deepak
• Primary Examiner(s): Nguyen, Joseph J
• Application Number:
  US14/971,073
• Publication Number:
  US 20160105638A1
• Time in Patent Office: 734 Days
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: H04M 2201/50 Telephonic communication in combination with video communication
• CPC Class Codes: H04M 2203/252 where a voice mode is enhanced with visual information
• CPC Class Codes: H04M 2203/306 Prerecordings to be used during a voice call
• CPC Class Codes: H04M 2203/6009 Personal information, e.g. profiles or personal directories being only provided to authorised persons
• CPC Class Codes: H04M 3/51 Centralised call answering arrangements requiring operator intervention , e.g. call or contact centers for telemarketing
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements
• CPC Class Codes: H04N 7/147 Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals selecting H04Q

Abstract

A method, apparatus and computer program product for protecting privacy of a customer and an agent using face recognition in a video contact center environment is presented. A video call is initiated by a customer to a contact center. The customer video is muted while audio of the customer is provided to an agent of the contact center. A determination is made regarding whether a face is present in a video image of the customer. When a presence of a face is determined in the video image of the customer, then video of the customer is enabled. When a presence of a face is not present in the video image of the customer then the customer is notified so the customer can take appropriate action.

Claims

1. An interactive voice and video response system, comprising:

receiving, by an agent computer system of a contact center, a video call from a customer computer system;

automatically answering the video call by the agent computer system, the video call comprising a video stream and an audio stream generated by the agent computer system;

determining, by the agent computer system, whether a face of an agent associated with the agent computer system is present in the video stream;

delaying, by the agent computer system, connection of the video stream and the audio stream to the customer computer system when the face of the agent is determined to not be present in the video stream;

enabling, by the agent computer system, connection of the video stream and the audio stream to the customer computer system when the face of the agent is determined to be present in the video stream; and

notifying, by the agent computer system, the agent associated with the agent computer system when the face of the agent is determined to not be present in the video stream.

2. The method of claim 1 further comprising

receiving, by the agent computer system, input from the agent associated with the agent computer system to enable connection of the video stream and the audio stream to the customer computer system when the face of the agent is determined to not be present in the video stream.

3. The method of claim 1 wherein the audio stream comprises audio information received from the agent associated with the agent computer system and the video stream comprises video information received from the agent associated with the agent computer system.

4. The method of claim 1 wherein said determining whether the face of the agent associated with the agent computer system is present in the video stream comprises using facial recognition.

5. The method of claim 1 wherein said notifying the agent associated with the agent computer system when the face of the agent is determined to not be present in the video stream comprises providing a message on a display screen of the agent computer system.

11. The method of claim 1 wherein determining whether the face of the agent is present in the video stream comprises determining whether the agent is looking into a camera associated with the agent computer system.

6. A non-transitory computer-readable medium having instructions stored thereon that are executable by a computing device to perform operations comprising:

receiving a video call from a customer computer system;

automatically answering the video call, the video call comprising a video stream and an audio stream generated by the computing device;

determining whether a face of an agent associated with the computing device is present in the video stream;

delaying connection of the video stream and the audio stream to the customer computer system when the face of the agent is determined to not be present in the video stream;

enabling connection of the video stream and the audio stream to the customer computer system when the face of the agent is determined to be present in the video stream; and

notifying the agent associated with the computing device when the face of the agent is determined to not be present in the video stream.

7. The non-transitory computer-readable medium of claim 6 having instructions stored thereon that are executable by the computing device to perform operations comprising:

receiving input from the agent associated with the computing device to enable connection of the video stream and the audio stream to the customer computer system when the face of the agent is determined to not be present in the video stream.

8. The non-transitory computer-readable medium of claim 6 wherein the audio stream comprises audio information received from the agent associated with the computing device and the video stream comprises video information received from the agent associated with the computing device.

9. The non-transitory computer-readable medium of claim 6 wherein said determining whether the face of the agent associated with the computing device is present in the video stream comprises using facial recognition.

10. The non-transitory computer-readable medium of claim 6 wherein said notifying the agent associated with the computing device when the face of the agent is determined to not be present in the video stream comprises providing a message on a display screen of the computing device.

12. The non-transitory computer-readable medium of claim 6 wherein determining whether the face of the agent is present in the video stream comprises determining whether the agent is looking into a camera associated with the computing device.