System, method and software program for enabling communications between customer service agents and users of communication devices

• US 9,386,154 B2
• Filed: 12/21/2007
• Issued: 07/05/2016
• Est. Priority Date: 12/21/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Baciu, Assaf, Stone, Kevin M., Winarsky, David A.
• Primary Examiner(s): ORTIZ SANCHEZ, MICHAEL
• Application Number:
  US12/005,050
• Publication Number:
  US 20090164214A1
• Time in Patent Office: 3,119 Days
• US Class Current: 1/1
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/39 using speech synthesis
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 2203/2061 Language aspects
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5191 interacting with the Internet
• CPC Class Codes: H04M 3/5322 for recording text messages

Abstract

The present invention provides a system, method and software application for enabling a customer service agent to efficiently communicate with users of a communication device. When a user enters speech input into his communication device, the speech is converted to text, and the text is displayed to the customer service agent on the agent'"'"'s computer screen. Alternately, the user'"'"'s speech input is provided to the customer service agent in the form of an audio file. The agent types a response, and the agent'"'"'s response is provided to the user on the user'"'"'s communication device. The agent'"'"'s response may be converted to speech and played to the user, and/or the agent'"'"'s response may be displayed as text on the display screen of the user'"'"'s communication device.

Claims

1. A method for enabling communication between a user of a mobile communication device and a customer service agent, the method comprising:

receiving speech input on a mobile communication device from a user for a customer service agent;

determining automatically by means of a server application executing on a server, independent of agent availability, whether an automated response can be provided to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response can be provided to the user, sending from the server application an automated response to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response cannot be provided to the user, performing the following;

converting the speech input into text on the mobile communication device;

determining if an open communication session exists for the user, wherein;

if an open communication session exists, updating the open communication session with the text from the user and identifying and selecting the customer service agent that previously handled the open communication session, and

if an open communication session does not exist, opening a new communication session for the user, updating the new communication session with the text from the user, and identifying and selecting the customer service agent based at least in part on the expertise of the customer service agent;

recording a speech response from the customer service agent in an audio file during the open communication session, wherein the audio file includes the customer service agent'"'"'s entire recorded response;

sending the audio file to the user'"'"'s mobile communication device during the open communication session; and

playing the customer service agent'"'"'s speech response to the user during the open communication session, wherein in addition to playing the speech to the user, converting the audio file into text on the mobile communication device, displaying the text from the customer service agent to the user on the user'"'"'s mobile communication device, and updating the open communication session with the text from the customer service agent.

2. A method for enabling a customer service agent to engage in simultaneous communication sessions with a plurality of users, wherein each user is using a mobile communication device, the method comprising:

receiving a plurality of requests to open a communication session with a customer service agent, wherein each request comes from a different user desiring to communicate with a customer service agent;

for each eligible user requesting to open a communication session with a customer service agent;

determining automatically by means of a server application executing on a server, independent of agent availability, whether an automated response can be provided to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response can be provided to the user, sending from the server application an automated response to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response cannot be provided to the user, performing the following;

determining if an open communication session exists for the user, wherein if an open communication session exists, updating the open communication session with the text from the user and wherein if an open communication session does not exist, opening a new communication session for the user and updating the new communication session with the text from the user,

identifying and selecting a customer service agent that is available to engage in the communication session with the user based at least in part on agent expertise,

wherein a single customer service agent may engage in multiple communication sessions simultaneously and wherein multiple customer service agents may be identified and selected to engage the user in an open communication session;

during each communication session between a user and a customer service agent, enabling the user to enter speech input for the customer service agent, wherein the speech is then converted to text on the mobile communication device and provided to the customer service agent in the form of text; and

during each communication session between a user and a customer service agent, recording a speech response from the customer service agent in an audio file during the open communication session, wherein the audio file includes the customer service agent'"'"'s entire recorded response, sending the audio file to the user'"'"'s mobile communication device during the open communication session, and playing the customer service agent'"'"'s speech response to the user during the open communication session, wherein in addition to playing the speech to the user, converting the audio file into text on the mobile communication device, displaying the text from the customer service agent to the user on the user'"'"'s mobile communication device, and updating the open communication session with the text from the customer service agent.

3. A method for enabling communication between a user of a mobile communication device and a customer service agent, the method comprising:

receiving speech input on a mobile communication device from a user for a customer service agent;

determining automatically by means of a server application executing on a server, independent of agent availability, whether an automated response can be provided to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response can be provided to the user, sending from the server application an automated response to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response cannot be provided to the user, performing the following;

converting the speech input into text on the mobile communication device;

determining if an open communication session exists for the user, wherein;

if an open communication session exists, updating the open communication session with the text from the user and identifying and selecting either the customer service agent that previously handled the open communication session or another customer service agent based on conventional load balancing techniques, and

if an open communication session does not exist, opening a new communication session for the user, updating the new communication session with the text from the user, and identifying and selecting the customer service agent based on conventional load balancing techniques, wherein the load balancing techniques factor in agent expertise;

recording a speech response from the customer service agent in an audio file during the open communication session, wherein the audio file includes the customer service agent'"'"'s entire recorded response;

sending the audio file to the user'"'"'s mobile communication device during the open communication session; and

playing the customer service agent'"'"'s speech response to the user during the open communication session, wherein in addition to playing the speech to the user, converting the audio file into text on the mobile communication device, displaying the text from the customer service agent to the user on the user'"'"'s mobile communication device, and updating the open communication session with the text from the customer service agent.

4. The method of claim 3, wherein the automated response is provided to the user in the form of speech.

5. The method of claim 3, wherein the automated response is provided to the user in the form of text.

6. The method of claim 3, wherein the automated response is provided to the user in the form of text and speech.

7. A computer-readable medium having computer-executable instructions for performing a method for enabling a customer service agent to engage in simultaneous communication sessions with a plurality of users, wherein each user is using a mobile communication device, the method comprising:

receiving a plurality of requests to open a communication session with a customer service agent, wherein each request comes from a different user desiring to communicate with a customer service agent;

for each eligible user requesting to open a communication session with a customer service agent;

determining automatically by means of a server application executing on a server, independent of agent availability, whether an automated response can be provided to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response can be provided to the user, sending from the server application an automated response to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response cannot be provided to the user, performing the following;

determining if an open communication session exists for the user, wherein if an open communication session exists, updating the open communication session with the text from the user and wherein if an open communication session does not exist, opening a new communication session for the user and updating the new communication session with the text from the user,

identifying and selecting a customer service agent that is available to engage in the communication session with the user based at least in part on agent expertise,

wherein a single customer service agent may engage in multiple communication sessions simultaneously and wherein multiple customer service agents may be identified and selected to engage the user in an open communication session;

during each communication session between a user and a customer service agent, enabling the user to enter speech input for the customer service agent, wherein the speech is then converted to text on the mobile communication device and provided to the customer service agent in the form of text; and

during each communication session between a user and a customer service agent, recording a speech response from the customer service agent in an audio file during the open communication session, wherein the audio file includes the customer service agent'"'"'s entire recorded response, sending the audio file to the user'"'"'s mobile communication device during the open communication session, and playing the customer service agent'"'"'s speech response to the user during the open communication session, wherein in addition to playing the speech to the user, converting the audio file into text on the mobile communication device, displaying the text from the customer service agent to the user on the user'"'"'s mobile communication device, and updating the open communication session with the text from the customer service agent.

8. The computer-readable medium of claim 7, further comprising also providing the customer service agent with an audio file of the user'"'"'s speech input.

9. A method for enabling communication between a user of a mobile communication device and a customer service agent, the method comprising:

receiving speech input on the mobile communication device from the user for the customer service agent, wherein the customer service agent is selected in part based on the agent'"'"'s expertise;

determining automatically by means of a server application executing on a server, independent of agent availability, whether an automated response can be provided to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response can be provided to the user, sending from the server application an automated response to the user;

in response to determining automatically by means of a server application executing on a server, independent of agent availability, that an automated response cannot be provided to the user, performing the following;

converting the speech input into text on the mobile communication device;

providing the text to the customer service agent;

recording a speech response from the customer service agent in an audio file during an open communication session, wherein the audio file includes the customer service agent'"'"'s entire recorded response;

sending the audio file to the user'"'"'s mobile communication device during the open communication session; and

playing the customer service agent'"'"'s speech response to the user during the open communication session, wherein in addition to playing the speech to the user, converting the audio file into text on the mobile communication device, displaying the text from the customer service agent to the user on the user'"'"'s mobile communication device, and updating the open communication session with the text from the customer service agent.