Identifying unreported issues through customer service interactions and website analytics

• US 10,341,491 B1
• Filed: 11/26/2018
• Issued: 07/02/2019
• Est. Priority Date: 11/26/2018
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Inventors: Edwards, Joshua, Mossoba, Michael, Benkreira, Abdelkader M'Hamed
• Primary Examiner(s): Baker, Matthew H
• Application Number:
  US16/200,101
• Time in Patent Office: 218 Days
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5191 interacting with the Internet

Abstract

Identifying unreported issues in computing applications based on customer service interactions and website analytics. A computing system may receive communication data between a CSP and a user. The system may analyze the communication data using an NLP algorithm to identify a plurality of concepts in the communication data. The system may identify, based on the concepts, a target application associated with the communications between the CSP and the user. The system may receive analytics data from a web server hosting the target application and identify a feature of the target application that is not functioning. The system may then assign a priority to the feature of the target application that is not functioning based on a type of the feature and the received analytics data and generate a service issue record for the feature of the target application that is not functioning and the assigned priority.

Claims

1. An apparatus, comprising:

a processor circuit; and

a memory storing instructions which when executed by the processor circuit, cause the processor circuit to;

receive communication data comprising recordings of communications between a customer service professional (CSP) and a user;

analyze the communication data using a natural language processing (NLP) algorithm to identify a plurality of concepts in the communication data;

identify, based at least in part on the plurality of concepts, a target application associated with the communications between the CSP and the user;

receive analytics data from a web server hosting the target application;

identify, based at least in part on the plurality of concepts and the received analytics data, a feature of the target application hosted by the web server that is not functioning;

determine a number of instances of the target application where the feature is not functioning based on the received analytics data;

assign a priority to the feature of the target application that is not functioning based at least in part on a type of the feature, the determined number of instances of the target application where the feature is not functioning, and the received analytics data, wherein the priority is a first priority value of a plurality of priority values; and

generate a service issue record specifying the feature of the target application that is not functioning and the assigned priority, the service issue record to facilitate an analysis of a source code of the target application.

2. The apparatus of claim 1, the memory storing instructions which when executed by the processor circuit, cause the processor circuit to:

receive a report from the CSP indicating at least one operation used to resolve an issue for the user, the issue related to the feature of the target application that is not functioning; and

identify that the feature of the target application is not functioning based on the report from the CSP indicating the at least one operation used to resolve the issue for the user.

3. The apparatus of claim 2, the memory storing instructions which when executed by the processor circuit, cause the processor circuit to:

generate, in the service issue record, an indication of the at least one operation used to cause the feature to function to facilitate the analysis of the source code of the target application; and

determine a location of the feature in the source code of the target application based on the received analytics data.

4. The apparatus of claim 1, the memory storing instructions which when executed by the processor circuit, cause the processor circuit to:

determine, based on the assigned priority, a time deadline to modify the source code of the target application to cause the feature to function correctly; and

generate, in the service issue record, an indication of the time deadline to modify the source code of the target application to cause the feature to function correctly, wherein the service issue record is outputted for display.

5. The apparatus of claim 1, wherein the communication data comprises an audio/video log comprising speech data, the memory storing instructions which when executed by the processor circuit, cause the processor circuit to:

convert the speech data to text data using a speech-to-text algorithm, wherein the text data is analyzed using the NLP algorithm to identify the plurality of concepts.

6. The apparatus of claim 5, the memory storing instructions which when executed by the processor circuit, cause the processor circuit to:

identify, by the NLP algorithm, a semantic meaning of each of the plurality of concepts; and

identify the feature of the target application that is not functioning based on the semantic meaning of each of the plurality of concepts.

7. The apparatus of claim 1, the memory storing instructions which when executed by the processor circuit, cause the processor circuit to:

receive communication data comprising a text chat log between the CSP and a second user;

analyze the text chat log using the NLP algorithm to identify a plurality of concepts in the text chat log; and

identify the feature of the target application that is not functioning based on the analysis of the text chat log and the identified plurality of concepts in the text chat log.

8. A non-transitory computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by a processor circuit to cause the processor circuit to:

receive communication data comprising recordings of communications between a customer service professional (CSP) and a user;

analyze the communication data using a natural language processing (NLP) algorithm to identify a plurality of concepts in the communication data;

identify, based at least in part on the plurality of concepts, a target application associated with the communications between the CSP and the user;

receive analytics data from a web server hosting the target application, the analytics data generated based at least in part on analytics data of the web server;

identify a feature of the target application hosted by the web server that is not functioning based at least in part on;

(i) the plurality of concepts and the received analytics data, (ii) a number of requests to use the feature of the target application specified in the analytics data, and (iii) a number of errors in the analytics data of the web server;

assign a priority to the feature of the target application that is not functioning based at least in part on a type of the feature and the received analytics data; and

generate a service issue record specifying the feature of the target application that is not functioning and the assigned priority, the service issue record to facilitate an analysis of a source code of the target application.

9. The non-transitory computer-readable storage medium of claim 8, further comprising computer-readable program code executable by the processor circuit to cause the processor circuit to:

receive a report from the CSP indicating at least one operation used to resolve an issue for the user, the issue related to the feature of the target application that is not functioning; and

identify that the feature of the target application is not functioning based on the report from the CSP indicating the at least one operation used to resolve the issue for the user.

10. The non-transitory computer-readable storage medium of claim 9, further comprising computer-readable program code executable by the processor circuit to cause the processor circuit to:

determine a number of instances of the target application where the feature is not functioning based on the received analytics data; and

assign the priority based on the determined number of instances of the target application where the feature is not functioning, wherein the priority is a first priority value of a plurality of priority values.

11. The non-transitory computer-readable storage medium of claim 8, further comprising computer-readable program code executable by the processor circuit to cause the processor circuit to:

determine, based on the assigned priority, a time threshold for modifying the source code of the target application to cause the feature to function correctly; and

generate, in the service issue record, an indication of the time threshold for modifying the source code of the target application to cause the feature to function correctly, wherein the service issue record is outputted for display.

12. The non-transitory computer-readable storage medium of claim 8, wherein the communication data comprises an audio/video log comprising speech data, further comprising computer-readable program code executable by the processor circuit to cause the processor circuit to:

convert the speech data to text data using a speech-to-text algorithm, wherein the text data is analyzed using the NLP algorithm to identify the plurality of concepts;

identify, by the NLP algorithm, a semantic meaning of each of the plurality of concepts; and

identify the feature of the target application that is not functioning based on the semantic meaning of each of the plurality of concepts.

13. The non-transitory computer-readable storage medium of claim 8, further comprising computer-readable program code executable by the processor circuit to cause the processor circuit to:

receive communication data comprising a text chat log between the CSP and a second user;

analyze the text chat log using the NLP algorithm to identify a plurality of concepts in the text chat log; and

identify the feature of the target application that is not functioning based on the analysis of the text chat log and the identified plurality of concepts in the text chat log.

14. A method, comprising:

receiving communication data comprising recordings of communications between a customer service professional (CSP) and a user;

analyzing the communication data using a natural language processing (NLP) algorithm executing on a computer processor to identify a plurality of concepts in the communication data;

identifying, based at least in part on the plurality of concepts, a target application associated with the communications between the CSP and the user;

receiving analytics data from a web server hosting the target application;

identifying, based at least in part on the plurality of concepts and the received analytics data, a feature of the target application hosted by the web server that is not functioning;

assigning a priority to the feature of the target application that is not functioning based at least in part on a type of the feature and the received analytics data;

generating a service issue record specifying the feature of the target application that is not functioning and the assigned priority, the service issue record to facilitate an analysis of a source code of the target application;

determining, based on the assigned priority, a time threshold for modifying the source code of the target application to cause the feature to function correctly; and

generating, in the service issue record, an indication of the time threshold for modifying the source code of the target application to cause the feature to function correctly, wherein the service issue record is outputted for display.

15. The method of claim 14, further comprising:

receiving a report from the CSP indicating at least one operation used to resolve an issue for the user, the issue related to the feature of the target application that is not functioning; and

identifying that the feature of the target application is not functioning based on the report from the CSP indicating the at least one operation used to resolve the issue for the user.

16. The method of claim 15, further comprising:

generating, in the service issue record, an indication of the at least one operation used to cause the feature to function to facilitate the analysis of the source code of the target application;

determining a location of the feature in the source code of the target application based on the received analytics data; and

outputting an indication of the identified location in the source code of the target application for display.

17. The method of claim 14, further comprising:

receiving communication data comprising a text chat log between the CSP and a second user;

analyzing the text chat log using the NLP algorithm to identify a plurality of concepts in the text chat log; and

identifying the feature of the target application that is not functioning based on the analysis of the text chat log and the identified plurality of concepts in the text chat log.

18. The method of claim 14, wherein the communication data comprises an audio/video log comprising speech data, the method further comprising:

converting the speech data to text data using a speech-to-text algorithm, wherein the text data is analyzed using the NLP algorithm to identify the plurality of concepts;

identifying, by the NLP algorithm, a semantic meaning of each of the plurality of concepts; and

identifying the feature of the target application that is not functioning based on the semantic meaning of each of the plurality of concepts.