Systems and methods to utilize text representations of conversations

• US 10,147,427 B1
• Filed: 09/17/2015
• Issued: 12/04/2018
• Est. Priority Date: 09/17/2014
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Johnson, Zakery L., Neuse, Jonathan E.
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US14/857,539
• Time in Patent Office: 1,174 Days
• CPC Class Codes: G06F 16/36 Creation of semantic tools, e.g. ontology or thesauri
• CPC Class Codes: G06F 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 25/54 for retrieval
• CPC Class Codes: G10L 25/63 for estimating an emotional state

Abstract

A method for electronically utilizing content in a communication between a customer and a customer representative is provided. An audible conversation between a customer and a service representative is captured. At least a portion of the audible conversation is converted into computer searchable data. The computer searchable data is analyzed during the audible conversation to identify relevant meta tags previously stored in a data repository or generated during the audible conversation. Each meta tag is associated with the customer. Each meta tag provides a contextual item determined from at least a portion of one of a current or previous conversation with the customer. A meta tag determined to be relevant to the current conversation between the service representative and the customer is displayed in real time to the service representative currently conversing with the customer.

Claims

1. A method for electronically utilizing content in a communication between a customer and a service representative, the method comprising the steps of:

capturing, by a processor, an audible conversation between a customer and a service representative;

converting, by the processor, the entire audible conversation into computer searchable text data;

storing, by the processor, the entire audible conversation in an audio repository and the searchable text data representative of the entire audio conversation in an text repository;

analyzing iteratively in real time, by a processor, the computer searchable text data during the audible conversation to identify one or more meta tags previously stored in the text repository or generated during the audible conversation determined relevant to a current conversation between the service representative and the customer, wherein each of the one or more meta tags are associated with the customer and wherein each meta tag provides a contextual item determined from at least a portion of one of the current or previous conversation with the customer;

generating one or more recommendations of product offerings tailored to the customer based on the one or more meta tags, wherein the contextual item associated with the meta tag represents one or more topics discussed during one or more communication sessions and each contextual item includes one or more contextual keys;

displaying, to the service representative, a meta tag and the one or more recommendations determined to be relevant to the current conversation between the service representative and the customer; and

determine sentiment toward the contextual item associated with the meta tag by detecting one or more words having a sentiment polarity using a sentiment dictionary containing sentiment related words having a particular polarity whereby once polarity has been determined, a number of positive and negative sentiment words spoken the customer in relation to identified contextual items are countered.

2. The method of claim 1, further comprising:

analyzing, by a processor, the computer searchable data to generate one or more meta tags wherein each meta tag relates to at least a portion of the searchable data and wherein each meta tag is associated with a contextual item; and

storing the computer searchable data and each said meta tag in the data repository in association with said customer.

3. The method of claim 2, wherein the computer searchable data comprises text data converted from at least a portion of the one or more audible conversations.

4. The method of claim 2, wherein storing one or more meta tags in a data repository further comprises storing at least a portion of an audible conversation as a voice data with each said meta tag in the data repository in association with said customer.

5. The method of claim 1, wherein analyzing the computer searchable data comprises analyzing, by a processor, the computer searchable data during the audible conversation to determine likely existing and future needs of the customer.

6. The method of claim 1, wherein analyzing, by a processor, the stored computer searchable data representing previous audible conversations with the customer and simultaneously analyzing the computer searchable data converted from the captured current audible conversation comprises searching combined computer searchable data to identify one or more sentiment-related keywords associated with the contextual item.

7. The method of claim 1, wherein analyzing, by a processor, the stored voice data representing previous audible conversations with the customer and simultaneously analyzing at least a portion of the captured current audible conversation with the customer comprises searching combined voice data to identify customer'"'"'s emotional states associated with the contextual item.

8. The method of claim 5, further comprising selectively presenting to the service representative one or more products adapted to substantially address the determined needs based on the meta tag determined to be relevant to the current conversation.

9. A computer program product for electronically utilizing content in a communication between a customer and a service representative, the computer program product comprising:

one or more non-transitory computer-readable storage devices and a plurality of program instructions stored on at least one of the one or more computer-readable storage devices, the plurality of program instructions comprising;

program instructions to capture an audible conversation between a customer and a service representative;

program instructions to convert the entire audible conversation into computer searchable text data;

program instructions to store the entire audible conversation in an audio repository and the entire searchable text data representative of the entire audio conversation in a text repository;

program instructions to analyze the computer searchable text data during the audible conversation to identify one or more meta tags previously stored in the text repository or generated during the audible conversation determined relevant to a current conversation between the service representative and the customer, wherein each of the one or more meta tags are associated with the customer and wherein each meta tag provides a contextual item determined from at least a portion of one of the current or previous conversation with the customer;

program instructions to generate one or more recommendations of product offerings tailored to the customer based on the one or more meta tags, wherein the contextual item associated with the meta tag represents one or more topics discussed during one or more communication sessions and each contextual item includes one or more contextual keys; and

program instructions to display, to the service representative, a meta tag and the one or more recommendations determined to be relevant to the current conversation between the service representative and the customer; and

program instructions to determine sentiment toward the contextual item associated with the meta tag by detecting one or more words having a sentiment polarity using a sentiment dictionary containing sentiment related words having a particular polarity whereby once polarity has been determined, a number of positive and negative sentiment words spoken the customer in relation to identified contextual items are countered.

10. The computer program product of claim 9, wherein the program instructions to store one or more meta tags in a data repository comprise:

program instructions to analyze the computer searchable data representing previous conversations between the customer and a service representative in order to generate one or more meta tags, wherein each meta tag relates to at least a portion of the searchable data and wherein each meta tag is associated with a contextual item; and

program instructions to store the computer searchable data and each said meta tag in the data repository in association with said customer.

11. The computer program product of claim 10, wherein the computer searchable data comprises text data converted from at least a portion of the one or more audible conversations.

12. The computer program product of claim 10, wherein program instructions to store one or more meta tags further comprise program instructions to store at least a portion of an audible conversation as a voice data with each said meta tag in the data repository in association with said customer.

13. The computer program product of claim 9, wherein program instructions to analyze the computer searchable data comprise program instructions to analyze the computer searchable data during the audible conversation to determine likely existing and future needs of the customer.

14. The computer program product of claim 9, wherein the program instructions to analyze the stored computer searchable data representing previous audible conversations with the customer and to simultaneously analyze the computer searchable data converted from the captured current audible conversation comprise program instructions to search combined computer searchable data to identify one or more sentiment-related keywords associated with the contextual item.

15. The computer program product of claim 9, wherein the program instructions to analyze the stored voice data representing previous audible conversations with the customer and to simultaneously analyze at least a portion of the captured current audible conversation with the customer comprise program instructions to search combined voice data to identify customer'"'"'s emotional states associated with the contextual item.

16. A computer system for electronically utilizing content in a communication between a customer and a service representative, the computer system comprising one or more processors, one or more computer-readable storage devices, and a plurality of program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors, the plurality of program instructions comprising:

program instructions to capture an audible conversation between a customer and a service representative;

program instructions to convert the entire audible conversation into computer searchable text data;

program instructions to store the entire audible conversation in an audio repository and the entire searchable text data representative of the entire audio conversation in a text repository;

program instructions to analyze the computer searchable text data during the audible conversation to identify one or more meta tags previously stored in the text repository or generated during the audible conversation determined relevant to a current conversation between the service representative and the customer, wherein each of the one or more meta tags are associated with the customer and wherein each meta tag provides a contextual item determined from at least a portion of one of the current or previous conversation with the customer;

program instructions to generate one or more recommendations of product offerings tailored to the customer based on the one or more meta tags, wherein the contextual item associated with the meta tag represents one or more topics discussed during one or more communication sessions and each contextual item includes one or more contextual keys;

program instructions to display, to the service representative, a meta tag and the one or more recommendations determined to be relevant to the current conversation between the service representative and the customer; and

program instructions to determine sentiment toward the contextual item associated with the meta tag by detecting one or more words having a sentiment polarity using a sentiment dictionary containing sentiment related words having a particular polarity whereby once polarity has been determined, a number of positive and negative sentiment words spoken the customer in relation to identified contextual items are countered.

17. The computer system of claim 16, wherein the program instructions to store one or more meta tags in a data repository comprise:

program instructions to analyze the computer searchable data representing previous conversations between the customer and a service representative in order to generate one or more meta tags, wherein each meta tag relates to at least a portion of the searchable data and wherein each meta tag is associated with a contextual item; and

program instructions to store the computer searchable data and each said meta tag in the data repository in association with said customer.