System and method for automatically generating adaptive interaction logs from customer interaction text

1. A method for a computer apparatus for automatically generating a customer interaction log for an interaction between a customer and an agent, the method comprising:

automatically analyzing received input corresponding to an interaction in the form of a call transcript between the customer and the agent to generate a customer interaction log using at least one model;

displaying the customer interaction log for review by the agent at a graphical user interface of an agent computer;

enabling the agent to provide feedback associated with the displayed generated customer interaction log by way of the graphical user interface; and

automatically updating, based on the agent feedback, at least the customer interaction log.

2. The method of claim 1 wherein the received input comprises at least one of:

received text of speech from a speech recognition system;

received text entered on a Web form;

received text of instant messaging; and

received text of emails.

3. The method of claim 2 further comprising normalizing the received input by performing at least one of:

removing disfluencies from the received input;

normalizing vocabulary in the received input;

normalizing alphanumeric characters in the received input;

correcting misspellings or incorrectly recognized words in the received input;

detecting sentence boundaries in the received input;

capitalizing letters in sentences in the received input; and

detecting call segment boundaries in the received input.

4. The method of claim 1 wherein automatically analyzing the received input to generate the customer interaction log further comprises at least one of:

scoring utterances in the received input based on at least one model;

identifying selected utterances to be used in the customer interaction log; and

correcting words in the selected utterances.

5. The method of claim 1 further comprising initially creating the at least one model by at least one of:

enabling manual rule creation; and

performing machine learning rule creation.

6. The method of claim 1 further comprising performing an analysis of the agent feedback and updating the at least one model based upon the analysis.

7. The method of claim 6 wherein updating the at least one model includes comparing an edited customer interaction log edited by the agent to the automatically generated customer interaction log.

8. The method of claim 1 wherein automatically updating the at least one model further comprises at least one of:

decreasing salience of a rule that generated a deleted sentence;

increasing salience of a rule that generated an inserted sentence;

finding a most similar sentence in the received input to a newly created sentence; and

increasing salience of a rule that generated the most similar sentence.

9. The method of claim 1 further comprising storing the customer interaction log, the agent feedback, or both.

10. The method of claim 9 wherein the agent feedback is stored for a plurality of interactions between customers and agents, and further comprising performing an analysis of the stored agent feedback and determining updating of a global model based on the analysis.

11. The method of claim 1 further comprising generating the customer interaction log with reference to a realtime model automatically generated for the interaction.

12. The method of claim 11 wherein generating the realtime model is performed automatically from a global model.

13. The method of claim 1 , further comprising automatically updating, based on the agent feedback, at least one of: the customer interaction log and the at least one model.

14. A system for automatically generating a customer interaction log for an interaction between a customer and agent, the system comprising:

at least one processing unit configured to execute components;

an analysis component configured to automatically analyze received input corresponding to an interaction in the form of a call transcript between the customer and the agent to generate the customer interaction log using at least one model;

a display generation component configured to generate a display of the customer interaction log for agent review at a graphical user interface of an agent computer;

a feedback collection component configured to enable the agent to provide agent feedback associated with the displayed generated customer interaction log by way of the graphical user interface; and

at least one learning component configured to analyze the agent feedback to determine updating of at least the customer interaction log based on the agent feedback.

15. The system of claim 14 further comprising a text normalizing component configured to transform the received input comprising at least one of:

a disfluency component configured to remove disfluencies from received text;

a vocabulary normalizing component configured to normalize vocabulary in the received text;

a character normalizing component configured to normalize alphanumeric characters in the received text;

a word correction component configured to correct misspellings or incorrectly recognized words in the received text;

a sentence detection component configured to detect sentence boundaries in the received text;

a sentence capitalization component configured to capitalize letters in sentences in the received text; and

a call segment component configured to detect call segment boundaries in the received text.

16. The system of claim 14 wherein the analysis component comprises at least one subcomponent for performing at least one of:

scoring utterances in received input based on at least one model; and

identifying selected utterances to be used in the customer interaction log.

17. The system of claim 14 further comprising at least one storage component configured to store at least one of the at least one models, the customer interaction log, and the agent feedback.

18. The system of claim 14 wherein the analysis component additionally includes at least one of:

an utterance scoring component for scoring utterances in the call transcript based on at least one of a global model and a realtime model; and

an utterance selection component configured to identify selected utterances to be used in the interaction log.

19. The system of claim 17 wherein the agent feedback is stored for a plurality of interactions between customers and agents and wherein the at least one learning component performs an analysis of the stored agent feedback and determines updating of a global model based on the analysis.

20. The system of claim 14 , wherein the feedback collection component additionally is configured to provide feedback to the agent in the form of a warning.

21. The system of claim 14 , wherein the at least one learning component is further configured to analyze the agent feedback to determine updating, based on the agent feedback, of at least one of: the customer interaction log and the at least one model.

22. A non-transitory computer readable medium having stored thereon a sequence of instructions which, when loaded and executed by a processor coupled to an apparatus, causes the apparatus to:

automatically analyze received input corresponding to an interaction in the form of a call transcript between a customer and an agent to generate a customer interaction log using at least one model;

display the customer interaction log for agent review at a graphical user interface of an agent computer;

enable the agent to provide feedback associated with the displayed generated customer interaction log by way of the graphical user interface; and

automatically update, based on the agent feedback, at least the customer interaction log.