Granted Patent B2

US 12,200,169 · App. 18/206,855 · Granted Jan 14, 2025

Inventor: Joel Ezell (New York, NY)

Assignee: LIVEPERSON, INC.

H04M3/4283G10L15/26

Abstract

Claims (82)

1. A computer-implemented method comprising:

establishing, by a server computer, a voice communication channel for a two-way voice communication session associated with an agent device and a user computing device;

establishing, by the server computer, a text communication channel for text communications associated with the agent device and the user computing device;

executing a hold bot;

communicating a functionality message associated with a hold status, wherein when the functionality message is received by the user computing device, the user computing device generates a voice message;

receiving the voice message during the hold status;

processing the voice message using the hold bot, wherein the voice message is processed by determining a plurality of bot operations, querying the plurality of bot operations for confidence scores, and determining that a confidence score of a bot operation exceeds a threshold;

generating a voice-to-text message when the confidence score exceeds the threshold;

transmitting the voice-to-text message, wherein when two-way voice communication is in the hold status, the agent device receives the voice-to-text message and transmits a text message;

processing, by the server computer, the text message, wherein the text message is processed by generating a real-time audio response to the voice message during the hold status; and

transmitting the real-time audio response over the voice communication channel.

2. The computer-implemented method of claim 1 , further comprising processing the voice message using a natural language processing system of the hold bot to identify an intent associated with the voice message;

identifying a hold bot response system associated with the intent; and

dynamically communicating instructions associated with the hold bot response system when a human agent response to the voice-to-text message is not received within a threshold period of time during the hold status.

3. The computer-implemented method of claim 1 , wherein the hold status is associated with a hold indication, and wherein the hold indication is a binary computer telephony integration (CTI) hold indicator.

4. The computer-implemented method of claim 1 , further comprising:

storing details of the two-way voice communication in an interaction database;

processing the details of the two-way voice communication in real-time to dynamically select an intent value for the two-way voice communication;

process the voice message in real-time to update the intent value and to generate a hold status intent value separate from the intent value for the two-way voice communication; and

transmit the intent value and the hold status intent value.

5. The computer-implemented method of claim 1 , further comprising:

streaming an audio message from the hold bot as a response to the voice-to-text message as part of the two-way voice communication; and

interrupting the audio message during transmission when the hold status ends during streaming of the audio message.

6. The computer-implemented method of claim 1 , further comprising:

communicating an audio message generated by the hold bot as a response to the voice-to-text message as part of the two-way voice communication; and

communicating audio interrupting the audio message during transmission when the hold status ends during streaming of the audio message.

7. A server computer comprising:

memory; and

one or more processors coupled to the memory and configured to perform operations comprising:

establishing, by the server computer, a voice communication channel for a two-way voice communication session associated with an agent device and a user computing device;

establishing, by the server computer, a text communication channel for text communications associated with the agent device and the user computing device;

executing a hold bot;

communicating a functionality message associated with a hold status, wherein when the functionality message is received by the user computing device, the user computing device generates a voice message;

receiving the voice message during the hold status;

processing the voice message using the hold bot, wherein the voice message is processed by determining a plurality of bot operations, querying the plurality of bot operations for confidence scores, and determining that a confidence score of a bot operation exceeds a threshold;

generating a voice-to-text message when the confidence score exceeds the threshold;

transmitting the voice-to-text message, wherein when two-way voice communication is in the hold status, the agent device receives the voice-to-text message and transmits a text message;

processing by the server computer, the text message, wherein the text message is processed by generating a real-time audio response to the voice message during the hold status; and

transmitting the real-time audio response over the voice communication channel.

8. The server computer of claim 7 , wherein the one or more processors are further configured for operations comprising:

processing the voice message using a natural language processing system of the hold bot to identify an intent associated with the voice message;

identifying a hold bot response system associated with the intent; and

dynamically communicating instructions associated with the hold bot response system when a human agent response to the voice-to-text message is not received within a threshold period of time during the hold status.

9. The server computer of claim 7 , wherein the hold status is associated with a hold indication, and wherein the hold indication is a binary computer telephony integration (CTI) hold indicator.

10. The server computer of claim 7 , wherein the one or more processors are further configured for operations comprising:

storing details of the two-way voice communication in an interaction database;

processing the details of the two-way voice communication in real-time to dynamically select an intent value for the two-way voice communication;

processing the voice message in real-time to update the intent value and to generate a hold status intent value separate from the intent value for the two-way voice communication; and

transmitting the intent value and the hold status intent value.

11. The server computer of claim 7 , wherein the one or more processors are further configured for operations comprising:

streaming an audio message from the hold bot as a response to the voice-to-text message as part of the two-way voice communication; and

interrupting the audio message during transmission when the hold status ends during streaming of the audio message.

12. The server computer of claim 7 , wherein the one or more processors are further configured for operations comprising:

communicating an audio message generated by the hold bot as a response to the voice-to-text message as part of the two-way voice communication; and

communicating audio interrupting the audio message during transmission when the hold status ends during streaming of the audio message.

13. A non-transitory computer readable medium comprising instructions that, when executed by one or more processors of a device, cause the device to perform operations comprising:

establishing, by a server computer, a voice communication channel for a two-way voice communication session associated with an agent device and a user computing device;

establishing, by the server computer, a text communication channel for text communications associated with the agent device and the user computing device;

executing a hold bot;

communicating a functionality message associated with a hold status, wherein when the functionality message is received by the user computing device, the user computing device generates a voice message;

receiving the voice message during the hold status;

processing the voice message using the hold bot, wherein the voice message is processed by determining a plurality of bot operations, querying the plurality of bot operations for confidence scores, and determining that a confidence score of a bot operation exceeds a threshold;

generating a voice-to-text message when the confidence score exceeds the threshold;

transmitting the voice-to-text message, wherein when two-way voice communication is in the hold status, the agent device receives the voice-to-text message and transmits a text message;

processing by the server computer the text message, wherein the text message is processed by generating a real-time audio response to the voice message during the hold status; and

transmitting the real-time audio response over the voice communication channel.

14. The non-transitory computer readable medium of claim 13 , wherein when executed by the one or more processors, the instructions further cause the device to perform operations comprising:

processing the voice message using a natural language processing system of the hold bot to identify an intent associated with the voice message;

identifying a hold bot response system associated with the intent; and

dynamically communicating instructions associated with the hold bot response system when a human agent response to the voice-to-text message is not received within a threshold period of time during the hold status.

15. The non-transitory computer readable medium of claim 13 , wherein the hold status is associated with a hold indication, and wherein the hold indication is a binary computer telephony integration (CTI) hold indicator.

16. The non-transitory computer readable medium of claim 13 , wherein when executed by the one or more processors, the instructions further cause the device to perform operations comprising:

storing details of the two-way voice communication in an interaction database;

processing the details of the two-way voice communication in real-time to dynamically select an intent value for the two-way voice communication;

process the voice message in real-time to update the intent value and to generate a hold status intent value separate from the intent value for the two-way voice communication; and

transmit the intent value and the hold status intent value.

17. The non-transitory computer readable medium of claim 13 , wherein when executed by the one or more processors, the instructions further cause the device to perform operations comprising:

streaming an audio message from the hold bot as a response to the voice-to-text message as part of the two-way voice communication; and

interrupting the audio message during transmission when the hold status ends during streaming of the audio message.

18. The non-transitory computer readable medium of claim 13 , wherein when executed by the one or more processors, the instructions further cause the device to perform operations comprising:

communicating an audio message generated by the hold bot as a response to the voice-to-text message as part of the two-way voice communication; and

communicating audio interrupting the audio message during transmission when the hold status ends during streaming of the audio message.

Assignments (4)

Continuity (2)

References Cited (17)