System and method to evaluate agent call logging in a contact center

1. A computerized method for evaluating agent-call-logging, in a contact center, said computerized method comprising:

in a computerized system comprising a processor, a database of recorded interactions; and a database of call loggings, a memory to store the plurality of databases, said processor is configured to operate an evaluating agent-call-logging module, said operating of an evaluating agent-call-logging module comprising:

receiving a recorded interaction between an agent and a customer, stored in the database of recorded interactions and a corresponding agent-call-logging, having ‘n’ sentences, stored in the database of call loggings;

operating a speech-to-text algorithm on the received recorded interaction to yield a summarized text thereof,

wherein said yielded summarized text is comprised of sentences expressed by the customer; and

operating a semantic comparison unit, to compare each sentence in the yielded summarized text with a corresponding sentence in the agent-call-logging, to yield a Sentence Similarity Score (SSS) for each sentence of the agent-call-logging,

wherein said processor is further configured to compare the yielded SSS of each sentence to a preconfigured match threshold, and to indicate an inefficient call logging to a user by sending a corrective sentence mismatch-alert thereto, when the SSS is below the preconfigured match threshold.

2. The computerized method according to claim 1 , wherein the user is any entity that is preconfigured to be associated with the recorded interaction.

3. The computerized method according to claim 1 , wherein the evaluating agent-call-logging module is further comprising calculating a Logging Effectiveness Score (LES) of the agent-call-logging.

4. The computerized method according to claim 3 , wherein the evaluating agent-call-logging module is calculating the LES of the agent-call-logging by adding SSS of each sentence of the ‘n’ sentences to yield a total score and dividing the total score by ‘n’.

5. The computerized method according to claim 3 , wherein the LES of the agent-call-logging is forwarded to associated systems.

6. The computerized method according to claim 5 , wherein the associated systems are selected from at least one of: Quality Management (QM) system, Workforce Management (WFM) system and supervisor dashboard system.

7. The computerized method according to claim 1 , wherein the operating of the semantic comparison unit is performed based on an implementation of a word embedding method on each sentence in the yielded summarized text to generate a first feature vector and an implementation of a word embedding method on each sentence in the agent-call-logging to generate a second feature vector.

8. The computerized method according to claim 7 , wherein the word embedding method is selected from at least one of: Term Frequency-Inverse Document Frequency (TF-IDF), Word2Vec and Smooth Inverse Frequency (SIF) methods.

9. A computerized system for evaluating agent call logging in a contact center, said computerized system comprising:

a database of recorded interactions;

a database of call loggings;

a memory to store the plurality of databases; and

a processor, said processor is configured to operate an evaluating agent-call-logging module, said operating of evaluating agent-call-logging module comprising:

(i) receiving a recorded interaction between an agent and a customer, stored in the database of recorded interactions and a corresponding agent-call-logging, having ‘n’ sentences, stored in the database of call loggings;

(ii) operating a speech-to-text algorithm on the received recorded interaction to yield a summarized text thereof, wherein said yielded summarized text is comprised of sentences expressed by the customer; and

(iii) operating a semantic comparison unit, to compare each sentence in the yielded summarized text with a corresponding sentence in the agent-call-logging, to yield a Sentence Similarity Score (SSS) for each sentence of the agent-call-logging,

wherein said processor is further configured to compare the yielded SSS of each sentence to a preconfigured match threshold, and to indicate an inefficient call logging to a user by sending a corrective sentence mismatch-alert thereto, when the SSS is below the preconfigured match threshold.

10. The computerized system according to claim 9 , wherein the user is any entity that is preconfigured to be associated with the recorded interaction.

11. The computerized method according to claim 9 , wherein the evaluating agent-call-logging module is further comprising calculating a Logging Effectiveness Score (LES) of the agent-call-logging.

12. The computerized system according to claim 11 , wherein the evaluating agent-call-logging module is calculating the LES of the agent-call-logging by adding SSS of each sentence in the ‘n’ sentences to yield a total score and dividing the total score by ‘n’.

13. The computerized method according to claim 11 , wherein the LES of the agent-call-logging is forwarded to associated systems.

14. The computerized system according to claim 13 , wherein the associated systems are selected from at least one of: Quality Management (QM) system, Workforce Management (WFM) system and supervisor dashboard system.

15. The computerized system according to claim 9 , wherein the operating of the semantic comparison unit is performed based on an implementation of a word embedding method on each sentence in the yielded summarized text to generate a first feature vector and an implementation of a word embedding method on each sentence in the agent-call-logging to generate a second feature vector.

16. The computerized system according to claim 15 , wherein the word embedding method is selected from at least one of: Term Frequency-Inverse Document Frequency (TF-IDF), Word2Vec and Smooth Inverse Frequency (SIF) methods.