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;
performing, by a communication programming interface:
directing a network interface to answer the call to participate in an on-line discussion;
starting an instance of a dialog manager; and
directing the dialog manager to load an application and a knowledge domain of a called party associated with the answered call;
outputting, from an automatic speech recognition module, a response based upon a language model and grammars and a best match to the dialog manager using words and phrasings the called party historically uses based on a called party's knowledge domain;
updating, by the dialog manager via a web application server, a dialog context;
asking on-line questions, via the personal representative device, with the device based on the dialog context and on the knowledge domain of the called party;
answering on-line questions, via the personal representative device, with the device based on the dialog context and on the knowledge domain of the called party;
answering SMS messages, via the personal representative device, with a caller device based on the dialog context and on the knowledge domain of the called party, wherein the personal representative device directs a personal representative cloud service to send the SMS messages; and
answering on-line chat requests, via the personal representative device, with the caller device based on the dialog context and on the knowledge domain of the called party, wherein the personal representative device directs the personal representative cloud service to send the on-line chat messages.
2. The method of claim 1 , wherein when the call is unanswerable the personal representative device performs one of at least answer the call, screen a caller and transfer the call.
3. The method of claim 1 , wherein when the call is unanswerable the personal representative device performs at least one of making appointments and cancelling appointments.
4. The method of claim 1 , wherein when the call is unanswerable the personal representative device responds to user commands.
5. The method of claim 1 , wherein when the call is unanswerable the communication programming interface authenticates a user voice.
6. The method of claim 1 , wherein when the call is unanswerable the communication programming interface accesses a user calendar.
7. The method of claim 1 , wherein when the call is unanswerable the communication programming interface accesses contact information.
8. The method of claim 1 , wherein when the call is unanswerable the communication programming interface presents caller history.
9. The method of claim 1 , wherein when the call is unanswerable the communication programming interface presents usage statistics.
10. The method of claim 1 , wherein when the call is unanswerable the communication programming interface adds a caller to a conference call.
11. The method of claim 1 , further comprising:
forwarding, to the communication programming interface, a language model and grammars to be installed with an automatic speech recognition module;
forwarding, to a natural language processing module, the called party's knowledge domain associated with on-line communication; and
outputting, from the natural language processing module, a list of intents having entities and confidence scores associated with the list of intents.
12. 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;
performing, by a communication programming interface:
directing a network interface to answer the call to participate in an on-line discussion;
starting an instance of a dialog manager; and
directing the dialog manager to load an application and a knowledge domain of a called party associated with the answered call;
outputting, from an automatic speech recognition module, a response based upon a language model and grammars and a best match to the dialog manager using words and phrasings the called party historically uses based on a called party's knowledge domain;
updating, by the dialog manager via a web application server, a dialog context;
asking on-line questions, via the personal representative device, with the device based on the dialog context and on the knowledge domain of the called party; and
answering on-line questions, via the personal representative device, with the device based on the dialog context and on the knowledge domain of the called party;
answering SMS messages, via the personal representative device, with a caller device based on the dialog context and on the knowledge domain of the called party, wherein the personal representative device directs a personal representative cloud service to send the SMS messages; and
answering on-line chat requests, via the personal representative device, with the caller device based on the dialog context and on the knowledge domain of the called party, wherein the personal representative device directs the personal representative cloud service to send the on-line chat messages.
13. The non-transitory computer readable medium of claim 12 , wherein when the call is unanswerable the personal representative device performs one of at least answer the call, screen a caller and transfer the call.
14. The non-transitory computer readable medium of claim 12 , wherein when the call is unanswerable the personal representative device performs at least one of making appointments and cancelling appointments.
15. The non-transitory computer readable medium of claim 12 , wherein when the call is unanswerable the personal representative device responds to user queries.
16. The non-transitory computer readable medium of claim 12 , wherein when the call is unanswerable the personal representative device responds to user commands.
17. The non-transitory computer readable medium of claim 12 , wherein when the call is unanswerable the communication programming interface authenticates a user voice.
18. The non-transitory computer readable medium of claim 12 , wherein when 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.
19. The non-transitory computer readable medium of claim 12 , further comprising:
forwarding, to the communication programming interface, a language model and grammars to be installed with an automatic speech recognition module;
forwarding, to a natural language processing module, the called party's knowledge domain associated with on-line communication; and
outputting, from the natural language processing module, a list of intents having entities and confidence scores associated with the intents.
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 communication programming interface configured to:
direct a network interface to answer the call to participate in an on-line discussion;
start an instance of a dialog manager; and
direct the dialog manager to load an application and knowledge domain associated with the answered call;
an automatic speech recognition module outputs a response based upon a language model and grammars and a best match to the dialog manager using words and phrasings a called party historically uses based on a called party's knowledge domain;
update, by the dialog manager via a web application server, a dialog context;
wherein the personal representative device asks on-line questions with the device based on the dialog context and on the knowledge domain of the called party;
wherein the personal representative device answers on-line question with the device based on the dialog context and on the knowledge domain of the called party;
wherein the personal representative device answers SMS messages with a caller device based on the dialog context and on the knowledge domain of the called party and the personal representative device directs a personal representative cloud service to send the SMS messages; and
wherein the personal representative device answers on-line chat requests with the caller device based on the dialog context and on the knowledge domain of the called party and the personal representative device directs the personal representative cloud service to send the on-line chat messages.