Analyzing conversations to automatically identify product features that resonate with customers

• US 10,360,911 B2
• Filed: 03/27/2018
• Issued: 07/23/2019
• Est. Priority Date: 06/01/2015
• Status: Active Grant

• Current Assignee: Zoominfo Converse LLC
• Original Assignee: AffectLayer, Inc. (ZoomInfo Technologies, Inc.)
• Inventors: Raanani, Roy, Levy, Russell, Breakstone, Micha Yochanan, Facher, Dominik
• Primary Examiner(s): Addy, Thjuan K
• Application Number:
  US15/937,494
• Publication Number:
  US 20180218733A1
• Time in Patent Office: 483 Days
• Field of Search: 37926507, 37926505, 37926506, 3792661, 37926503
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04M 2203/401 Performance feedback
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

A product functionality identification system to automatically determine product features that are a favorite of customers by analyzing conversations of representatives with the customers. The product functionality identification system retrieves recordings of various conversations, extracts features of the conversations, and analyzes the features to determine a set of features that is indicative of favorite functionalities of a product for one or more customers. A favorite functionality is one of multiple product features that is determined to be a favorite of one or more customers. The set of features is further analyzed to generate a favorite functionality manifest, which includes information regarding the favorite functionalities (a) as a summary of what is discussed in the conversations or (b) verbatim from the conversations.

Claims

1. A computer-implemented method, comprising:

retrieving multiple recordings of conversations associated with multiple representatives, wherein each of the conversations is between at least one of the representatives and at least one of multiple customers;

extracting multiple features from each of the recordings, wherein the multiple features indicate characteristics of any of (a) a customer of multiple customers in the corresponding conversation, (b) a representative of multiple representatives in the corresponding conversation, (c) the corresponding conversation;

analyzing the multiple features associated with a first conversation of the multiple conversations to determine a first set of features that is indicative of a favorite functionality of a product, the favorite functionality being a product feature that is determined to be a favorite of a first customer of the multiple customers in the first conversation; and

generating, based on the first set of features, information regarding the favorite functionality.

2. The computer-implemented method of claim 1, wherein analyzing the features includes determining the first set of features based on a usage of one or more words or phrases in the first conversation that are indicative of the favorite functionality.

3. The computer-implemented method of claim 2, wherein determining the first set of features includes determining a specified word or a specified phrase in the first conversation which is explicitly indicative of the favorite functionality.

4. The computer-implemented method of claim 2, wherein determining the first set of features includes determining a set of words or phrases in the first conversation based on which the favorite functionality is implicit.

5. The computer-implemented method of claim 4, wherein determining the set of words or phrases based on which the favorite functionality is implicit includes analyzing a portion of the first conversation prior to or after the set of words or phrases to determine the favorite functionality that is implied.

6. The computer-implemented method of claim 1, wherein generating the information regarding the favorite functionality includes generating one or more words or phrases in the first conversation that are indicative of the favorite functionality.

7. The computer-implemented method of claim 1, wherein generating the information regarding the favorite functionality includes generating a summary of the favorite functionality.

8. The computer-implemented method of claim 7, wherein generating the summary of the favorite functionality includes generating the summary by performing a semantic analysis of the first set of features, the first set of features including one or more words or phrases in the first conversation that are indicative of the favorite functionality.

9. The computer-implemented method of claim 7, wherein generating the summary of the favorite functionality includes generating the summary to include a context of the first conversation, the context including identification of the first customer or a first representative of the multiple representatives associated with the first conversation.

10. The computer-implemented method of claim 7, wherein the summary includes any information obtained using metadata associated with the first conversation.

11. The computer-implemented method of claim 7, wherein generating the summary includes generating the summary using any of a rule-based, artificial intelligence, machine-learning, or natural language processing techniques.

12. The computer-implemented method of claim 1, wherein retrieving the multiple recordings include retrieving a data stream associated with a real-time conversation between the first representative and the first customer.

13. The computer-implemented method of claim 12 further comprising:

extracting one or more features from the real-time conversation that are indicative of the favorite functionality associated with the product.

14. The computer-implemented method of claim 12 further comprising:

determining a specified product being discussed in the first conversation;

retrieving one or more product features of the specified product that are determined as favorite functionalities of the specified product for one or more of the customers; and

generating information regarding the favorite functionalities of the specified product on a display device associated with the first representative.

15. The computer-implemented method of claim 1, wherein extracting the features includes:

generating features that include a transcription, vocabulary and a language model of the conversations as a first output.

16. The computer-implemented method of claim 15, wherein extracting the features includes:

generating, using the first output, features that include semantic information from the conversations.

17. The computer-implemented method of claim 1, wherein extracting the features includes extracting a visual feature associated with a conversation of the conversations.

18. The computer-implemented method of claim 1, wherein extracting the features includes extracting the features using any of an artificial intelligence, a machine learning, or natural language processing technique.

19. The computer-implemented method of claim 1, wherein at least one of the recordings includes a recording of a video call between one of the customers and one of the representatives.

20. The computer-implemented method of claim 1, wherein at least one of the recordings includes an online meeting between one of the customers and one of the representatives.

21. The computer-implemented method of claim 1, wherein at least one of the recordings includes a recording of a virtual reality-based conversation between one of the customers and one of the representatives.

22. The computer-implemented method of claim 1, wherein at least one of the recordings includes a recording of an augmented reality-based conversation between one of the customers and one of the representatives.

23. The computer-implemented method of claim 1, wherein at least one of the multiple recordings includes an e-mail conversation between one of the customers and one of the multiple representatives.

24. A non-transitory computer-readable storage medium storing computer-readable instructions, comprising:

instructions for retrieving a recording of a conversation associated with a representative and a customer;

instructions for extracting multiple features from the recording, wherein the multiple features indicate characteristics of any of (a) the customer, (b) the representative, (c) the conversation;

instructions for analyzing features associated with the conversation to determine a first set of features that is indicative of a favorite functionality of a product, the favorite functionality being one of multiple product features that is determined as a favorite of the customer; and

instructions for generating information regarding the favorite functionality, the information including one or more words or phrases in the conversation that are indicative of the favorite functionality.

25. The non-transitory computer-readable storage medium of claim 24, wherein the instructions for generating the information include:

instructions for generating a summary of the favorite functionality, the summary generated based on the one or more words or phrases in the conversation that are indicative of the favorite functionality.

26. The non-transitory computer-readable storage medium of claim 24, wherein the instructions for determining the first set of features include:

instructions for determining a set of words or phrases in the conversation based on which the favorite functionality is implicit.

27. A system, comprising:

a processor;

a first component that is configured to extract multiple features from each of multiple recordings of conversations, wherein each conversation is associated with at least one of multiple customers and at least one of multiple representatives;

a second component that is configured to analyze features associated with a first conversation of the conversations to determine a first set of features that is indicative of a favorite functionality of a product, wherein the favorite functionality is one of multiple product features that is indicated as a favorite of a first customer of the multiple customers in the first conversation; and

a third component that is configured to generate information regarding the favorite functionality based on the first set of features.

28. The system of claim 27, wherein the third component is further configured to generate the information by determining a set of words or phrases in one or more of the conversations that is indicative of the favorite functionality implicitly.