Automated intelligent personal representative
A virtual assistant application, system, and service that interacts with a caller over a telephone, cellular, or VoIP network as the called party's representative when the called party is unavailable, providing answers to queries and performing commands that were provisioned by the called party. The application includes a telephony interface, speech recognition and synthesis, a dialog manager, and knowledge domain. The application can also be configured to interact with a sender of SMS, MMS, or IM messages.
1. A method, comprising:
receiving a call at a device;
when the call is unanswerable, forwarding, by the device, the call to a personal representative device;
detecting, by a telephony network interface of the personal representative device, ringing;
performing, by a communication programming interface:
directing the network interface to answer the call;
starting an instance of a dialog manager; and
directing the dialog manager to load an application and knowledge domain associated with the answered call;
forwarding, to the communication programming interface, a language model and grammars to be installed with an automatic speech recognition module;
outputting, from the automatic speech recognition module, a list of matches with a corresponding confidence score;
providing a best match to the dialog manager;
updating, by the dialog manager, a dialog context;
engaging in a dialog, by the personal representative device, with a caller device based on the dialog context; and
recognizing, by the personal representative device, an emergency and providing the caller with emergency information available in the application.
2. The method of claim 1 , wherein the call is unanswerable when at least one of the device or a user of the device is at least one of busy or not available.
3. The method of claim 1 , wherein the application and the knowledge domain is provided to the dialog manager by at least one of: an application server and a database server.
4. The method of claim 1 , wherein when the call is unanswerable, the dialog manager plays an initial prompt for a caller of the call.
5. The method of claim 4 , wherein the prompt is provided to the communication programming interface to be played by a text-to-speech module.
6. The method of claim 5 , wherein the automatic speech recognition module receives input from the caller and processes the input against at least one of the grammars and semantic analysis.
7. The method of claim 1 , wherein the list is given to the communication programming interface and forwarded to a grammar matching module.
8. The method of claim 7 , wherein at least one of the grammar matching module and a semantic analysis analyzes each match for accuracy against a conversation context maintained by the context manager and selects the best one.
9. The method of claim 1 , comprising identifying the caller and providing, by the personal representative device, the caller with caller-specific information available in the application.
10. The method of claim 1 , comprising providing secure access to calendar and contact information of the user of the device, the information stored in a cloud-based storage environment.
11. The method of claim 1 , wherein the dialog between the caller and the personal representative device continues until at least one of the following occurs:
the call is terminated;
the call is transferred; and
the call is added to another call.
12. The method of claim 9 , wherein, after one of the following occurs, the dialog manager requests the application server to unload the application.
13. A non-transitory computer readable medium comprising instructions that, when read by a processor, cause the processor to perform:
receiving a call at a device;
when the call is unanswerable, forwarding, by the device, the call to a personal representative device;
detecting, by a telephony network interface of the personal representative, ringing;
performing, by a communication programming interface:
directing the network interface to answer the call;
starting an instance of a dialog manager; and
directing the dialog manager to load an application and knowledge domain associated with the answered call;
forwarding, to the communication programming interface, a language model and grammars to be installed with an automatic speech recognition module;
outputting, from the automatic speech recognition module, a list of matches with a corresponding confidence score;
providing a best match to the dialog manager;
updating, by the dialog manager, a dialog context;
engaging in a dialog, by the personal representative device, with a caller device based on the dialog context; and
recognizing, by the personal representative device, an emergency and providing the caller with emergency information available in the application.
14. The non-transitory computer readable medium of claim 13 , wherein the call is unanswerable when at least one of the device or a user of the device is at least one of busy or not available.
15. The non-transitory computer readable medium of claim 13 , wherein the application and the knowledge domain is provided to the dialog manager by at least one of: an application server and a database server.
16. The non-transitory computer readable medium of claim 13 , wherein when the call is unanswerable, the dialog manager plays an initial prompt for a caller of the call.
17. The non-transitory computer readable medium of claim 16 , wherein the prompt is provided to the communication programming interface to be played by a text-to-speech module.
18. The non-transitory computer readable medium of claim 17 , wherein the automatic speech recognition module receives input from the caller and processes the input against at least one of the grammars and semantic analysis.
19. The non-transitory computer readable medium of claim 13 , wherein the list is given to the communication programming interface and forwarded to a grammar matching module.
20. A system, comprising:
a device configured to receive a call;
when the call is unanswerable, the device is configured to forward the call to a personal representative device;
a telephony network interface of the personal representative device configured to detect ringing;
a communication programming interface configured to:
direct the network interface to answer the call;
start an instance of a dialog manager; and
direct the dialog manager to load an application and knowledge domain associated with the answered call;
wherein a language model and grammars to be installed with an automatic speech recognition module are forwarded to the communication programming interface;
wherein a list of matches with a corresponding confidence score are output from the automatic speech recognition module;
wherein a best match is provided to the dialog manager;
wherein the dialog manager updates a dialog context;
wherein the personal representative device engages in a dialog with a caller device based on the dialog context; and
wherein the personal representative device recognizes an emergency and provides the caller with emergency information available in the application.