Automated assistant for customer service representatives

1. A method, comprising:

receiving by a call center a call from a caller, the call comprising utterances from the caller;

routing the call to a customer service representative of the call center, wherein the customer service representative interacts with a computer device during the call, wherein the computer device comprises a display;

processing the utterances with an automated assistant computing device to recognize speech in the utterances, wherein the automated assistant computing device is in communication with the computer device of the customer service representative;

assigning a first score that indicates a degree of accuracy associated with the recognized speech in the utterances;

determining, by the automated assistant computing device, a concept of the utterances based at least in part on the assigned first score;

assigning a second score that indicates a degree of accuracy associated with the determined concept to the recognized speech;

matching the determined concept to information in a knowledge database based at least in part on a predetermined mapping between one or more concepts and one or more informational entities; and

displaying the information from the knowledge database on the display of the computer device of the customer service representative based at least in part on the matching and the assigned second score.

2. The method of claim 1 , wherein the information is a recommendation to the customer service representative.

3. The method of claim 2 , further comprising:

displaying a plurality of recommendations on the display.

4. The method of claim 1 , wherein the information is promotional information.

5. The method of claim 1 , further comprising:

verbally communicating the information on the display of the customer service representative to the caller during the call.

6. The method of claim 1 , wherein the automated assistant comprises an automatic speech recognition component.

7. The method of claim 6 , wherein the automatic speech recognition component comprises an acoustic processor, an acoustic model, and language model.

8. The method of claim 7 , further comprising:

delivering decoded audio from the speech recognition component to an application comprising a knowledge database, a recommendation engine, and a language understanding component.

9. The method of claim 1 , wherein the information comprises a link.

10. The method of claim 1 , further comprising:

removing the information from the display after an expiration of a time period.

11. A system, comprising:

a call center configured to receive a call from a caller and telephonically connect a customer service representative to the caller, wherein the call comprises utterances;

a computer device comprising a display that displays information to the customer service representative, wherein the computer device comprises at least one processor and at least one computer memory device for storing instructions to be executed by the at least one processor; and

an automated assistant computing device in communication with the customer service representative computer device, wherein the automated assistant is programmed to:

process the utterances and recognize speech in the utterances;

convert the recognized speech in the utterances into a string of one or more words;

assign a score that indicates a degree of accuracy associated with the converted string of one or more words with the recognized speech;

determine a first concept associated with the string of one or more words converted from the recognized speech in the utterances based at least in part on the string of one or more words and the assigned score; and

transmit information to the customer service representative computer device based on the determined first concept and the assigned score so that the information is displayed on the customer service representative computer device.

12. The system of claim 11 , wherein the automated assistant computing device comprises a voice recognition system configured to process the utterances.

13. The system of claim 12 , wherein the information comprises a recommendation.

14. The system of claim 12 , further comprising a database configured to store a log that accumulates data regarding the information displayed.

15. A call center system, comprising:

a customer service representative computer device; and

a computer system comprising a voice recognition system, wherein the voice recognition system is configured to:

process one or more utterances to recognize speech in the one or more utterances;

assign a first score that indicates a degree of accuracy associated with the recognized speech in the one or more utterances;

determine a concept of one or more utterances based at least in part on the recognized speech and the first score;

assign a second score that indicates a degree of accuracy associated with the determined concept; and

provide a recommendation to the customer service representative computer device based on the determined concept and the assigned second score.

16. The call center system of claim 15 , wherein the voice recognition system is configured to provide promotional information to the customer service representative computer device.

17. The call center system of claim 15 , wherein the customer service representative computer device comprises a display configured to display the recommendation.

18. The call center system of claim 15 , further comprising a database configured to store a log that accumulates the recommendation provided to the customer service representative, wherein:

the log is available for human analysis, wherein the human analysis includes analyzing the recommendation for usefulness to the caller after the recommendation is provided to the caller; and

the voice recognition system is further configured to determine a concept of a subsequent call based on the human analysis of the log.

19. The system of claim 11 , wherein the automated assistant is further programmed to:

determine a second concept associated with the string of one or more words converted from the recognized speech in the utterances; and

generate an additional recommendation based at least in part on the determined second concept.

20. The method of claim 1 , wherein the predetermined mapping is generated automatically or by a human.

21. The method of claim 1 , wherein the displaying the information is further based at least in part on the assigned score.