Intelligent dialogue recovery for virtual assistant communication sessions
Methods and apparatuses are described for intelligent dialogue recovery in virtual assistant communication sessions. A chat session is established between a virtual assistant (VA) and a remote device. A primary dialogue is created between the VA and the remote device, including (i) requesting from a first natural language processing (NLP) service an intent associated with user messages and (ii) waiting for a corresponding response. A secondary dialogue is created between the VA and the remote device that is synchronized to a state of the primary dialogue. When the response from the first NLP service succeeds, primary messages are generated and transmitted to the remote device in the primary dialogue. When the response from the first NLP service fails, an intent is requested from the second NLP service, and secondary messages are generated and transmitted to the remote device in the secondary dialogue.
1. A computer system for intelligent dialogue recovery in virtual assistant communication sessions, the system comprising a computing device having a memory that stores computer-executable instructions and a processor that executes the computer-executable instructions to:
establish a chat-based communication session between a virtual assistant application of the computing device and a remote computing device;
create a primary dialogue between the virtual assistant application and the remote computing device, including (i) requesting from a first natural language processing (NLP) service an intent associated with one or more user messages received from the remote computing device and (ii) waiting for a corresponding response that includes the requested intent from the first NLP service;
create a secondary dialogue between the virtual assistant application and the remote computing device that is synchronized to a state of the primary dialogue, including connecting to a second NLP service;
when the response from the first NLP service succeeds, generate one or more primary virtual assistant messages based upon the intent requested from the first NLP service and transmit the one or more primary virtual assistant messages to the remote computing device in the primary dialogue; and
when the response from the first NLP service fails, request an intent from the second NLP service, generate one or more secondary virtual assistant messages based upon the intent requested from the second NLP service, and transmit the one or more secondary virtual assistant messages to the remote computing device in the secondary dialogue.
2. The system of claim 1 , wherein the response from the first NLP service fails when the response is not received from the first NLP service within a predetermined time limit or when the first NLP service returns an error.
3. The system of claim 2 , wherein the computing device captures a first timestamp associated with transmission of the request to the first NLP service and periodically determines an elapsed time based upon the first timestamp.
4. The system of claim 3 , wherein the computing device determines that the response from the first NLP service fails when the elapsed time exceeds the predetermined time limit.
5. The system of claim 2 , wherein when the response from the first NLP service fails, the virtual assistant application transitions from the primary dialogue to the secondary dialogue in the chat-based communication session before transmitting the one or more secondary virtual assistant messages to the remote computing device.
6. The system of claim 5 , wherein after the transition has occurred, the computing device determines that the first NLP service is responsive and the virtual assistant application transitions from the secondary dialogue to the primary dialogue in the chat-based communication session prior to transmitting one or more subsequent virtual assistant messages to the remote computing device.
7. The system of claim 6 , wherein the computing device determines that the first NLP service is responsive through a periodic connectivity check.
8. The system of claim 5 , wherein the transition from the primary dialogue to the secondary dialogue occurs without providing an indication of the transition to the remote computing device.
9. The system of claim 1 , wherein the first dialogue and the second dialogue each comprises a conversation flow between the virtual assistant application and a user of the remote computing device.
10. A computerized method of intelligent dialogue recovery in virtual assistant communication sessions, the method comprising:
establishing, by a computing device, a chat-based communication session between a virtual assistant application of the computing device and a remote computing device;
creating, by the computing device, a primary dialogue between the virtual assistant application and the remote computing device, including (i) requesting from a first natural language processing (NLP) service an intent associated with one or more user messages received from the remote computing device and (ii) waiting for a corresponding response that includes the requested intent from the first NLP service;
creating, by the computing device, a secondary dialogue between the virtual assistant application and the remote computing device that is synchronized to a state of the primary dialogue, including connecting to a second NLP service;
when the response from the first NLP service succeeds, generating, by the computing device, one or more primary virtual assistant messages based upon the intent requested from the first NLP service and transmitting the one or more primary virtual assistant messages to the remote computing device in the primary dialogue; and
when the response from the first NLP service fails, requesting, by the computing device, an intent from the second NLP service, generating one or more secondary virtual assistant messages based upon the intent requested from the second NLP service, and transmitting the one or more secondary virtual assistant messages to the remote computing device in the secondary dialogue.
11. The method of claim 10 , wherein the response from the first NLP service fails when the response is not received from the first NLP service within a predetermined time limit or when the first NLP service returns an error.
12. The method of claim 11 , further comprising capturing, by the computing device, a first timestamp associated with transmission of the request to the first NLP service and periodically determining an elapsed time based upon the first timestamp.
13. The method of claim 12 , further comprising determining, by the computing device, that the response from the first NLP service fails when the elapsed time exceeds the predetermined time limit.
14. The method of claim 11 , wherein when the response from the first NLP service fails, the virtual assistant application transitions from the primary dialogue to the secondary dialogue in the chat-based communication session before transmitting the one or more secondary virtual assistant messages to the remote computing device.
15. The method of claim 14 , wherein after the transition has occurred, the computing device determines that the first NLP service is responsive and the virtual assistant application transitions from the secondary dialogue to the primary dialogue in the chat-based communication session prior to transmitting one or more subsequent virtual assistant messages to the remote computing device.
16. The method of claim 15 , further comprising determining, by the computing device, that the first NLP service is responsive through a periodic connectivity check.
17. The method of claim 14 , wherein the transition from the primary dialogue to the secondary dialogue occurs without providing an indication of the transition to the remote computing device.
18. The method of claim 10 , wherein the first dialogue and the second dialogue each comprises a conversation flow between the virtual assistant application and a user of the remote computing device.