Predicting a sales success probability score from a distance vector between speech of a customer and speech of an organization representative

• US 8,914,285 B2
• Filed: 07/17/2012
• Issued: 12/16/2014
• Est. Priority Date: 07/17/2012
• Status: Active Grant

• Current Assignee: Nice Ltd
• Original Assignee: Nice Systems Limited (Nice Ltd)
• Inventors: Wasserblat, Moshe, Eylon, Dan, Pereg, Oren, Daya, Ezra, Ashkenazi, Tzach, Pollak, Ohad, Avlagon, Moshe
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US13/550,626
• Publication Number:
  US 20140025376A1
• Time in Patent Office: 882 Days
• Field of Search: 704/232, 704/235, 704/236, 704/238, 704/251, 704/255, 704/270, 379/265.06, 379/265.07, 705/7.31, 705/7.37, 705/14.1
• US Class Current: 704/238
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: G10L 25/63 for estimating an emotional state

Abstract

A computerized method for sales optimization including receiving at a computer server a digital representation of a portion of an interaction between a customer and an organization representative, the portion of an interaction comprises a speech signal of the customer and a speech signal of the organization representative; analyzing the speech signal of the organization representative; analyzing the speech signal of the customer; determining a distance vector between the speech signal of the organization representative and the speech signal of the customer; and predicting a sale success probability score for the captured speech signal portion.

Claims

1. A computerized method for sales optimization comprising:

receiving at a general purpose computer serving as a computer server a digital representation of a portion of an interaction between a customer and an organization representative, the portion of an interaction comprises a speech signal of the customer and a speech signal of the organization representative;

analyzing the speech signal of the organization representative;

analyzing the speech signal of the customer;

determining by the computer server a distance vector between the speech signal of the organization representative and the speech signal of the customer; and

predicting a sale success probability score for the captured speech signal portion.

2. The method according to claim 1, further comprises applying a statistical model to the distance vector.

3. The method according to claim 2, wherein said statistical model is created from distance vectors generated from features extracted from a group of interactions with a determination if there was a successful sale or not at each portion of each interaction.

4. The method according to claim 1, analyzing, the speech signal of the customer comprises extracting prosodic features of the speech signal of the customer.

5. The method according to claim 1, analyzing the speech signal of the organization representative comprises extracting prosodic features of the speech signal of the organization representative.

6. The method according to claim 1, wherein analyzing the speech signal of the customer comprises performing speech recognition of the speech signal of the customer.

7. The method according to claim 1, wherein analyzing the speech signal of the organization representative comprises performing speech recognition of the speech signal of the organization representative.

8. The method according to claim 1, wherein the method is performed while the interaction is in progress.

9. The method according to claim 1 further comprising:

storing the sale success probability score;

predicting a second sale success probability score for the next portion of the interaction using the stored sale success probability scores.

10. The method according to claim 1, further comprises issuing a sale recommendation signal based on the sale success probability score.

11. The method according to claim 10, wherein the said sale recommendation signal is issued based on the second sale success probability score and/or speech recognition history and/or CRM data.

12. The method according to claim 1, wherein analyzing the speech signal of the customer comprises automatically transcribing, the speech signal of the customer.

13. The method according to claim 1, wherein analyzing the speech signal of the customer comprises automatically detecting keywords in the speech signal of the customer.

14. The method according to claim 1, wherein analyzing the speech signal of the customer comprises automatically detecting emotions in the speech signal of the customer.

15. The method according to claim 1, wherein analyzing the speech signal of the organization representative comprises automatically transcribing the speech signal of the organization representative.

16. The method according to claim 1, wherein analyzing the speech signal of the organization representative comprises automatically detecting keywords in the speech signal of the organization representative.

17. The method according to claim 1, wherein analyzing the speech signal of the organization representative comprises automatically detecting emotions in the speech signal of the organization representative.