Automatic detection, summarization and reporting of business intelligence highlights from automated dialog systems
View Patent ↗A method and system for reporting data from a spoken dialog service is disclosed. The method comprises extracting data regarding user dialogs using a dialog logging module in the spoken dialog service, analyzing the data to identify trends and reporting the trends. The data may be presented in a visual form for easier consumption. The method may also relate to identifying data within the control or outside the control of a service provider that is used to adjust the spoken dialog service to maximize customer retention.
1. A method of reporting data from an automated spoken dialog service, the method comprising:
extracting data regarding user dialogs with the automated spoken dialog service, and not with a human agent, using a dialog logging module within the automated spoken dialog service;
analyzing the data to identify trends for at least one geographic area to yield identified trends;
comparing the identified trends for the at least one geographic area with an average in a wider geographical area containing the at least one geographic area;
modifying the automated spoken dialog service on a geographic basis according to the identified trends and comparison;
based on the analysis of the data and the comparison of the identified trends, generating top natural language headlines, each of which describes at least one identified trend; and
displaying the generated top headlines to a user.
2. The method of claim 1 , further comprising presenting a visual representation of the data.
3. The method of claim 1 , wherein analyzing the data further comprises analyzing a time-sequence associated with the data.
4. The method of claim 1 , wherein extracting the data further comprises extracting the data according to a specified set of features.
5. The method of claim 2 , wherein displaying the generated top headlines further comprises presenting a summary of the identified trends.
6. The method of claim 1 , wherein the identified trends relate to user patterns over time.
7. The method of claim 2 , wherein displaying the generated top headlines further comprises generating an XML-based report.
8. The method of claim 2 , wherein displaying the generated top headlines further comprises generating a web-based report.
9. The method of claim 2 , wherein displaying the generated top headlines further comprises:
presenting a user with the option to drill down into the analyzed data.
10. The method of claim 9 , wherein presenting the user with the option to drill down into the analyzed data further comprises presenting the user with the option to hear user dialogs.
11. A system for reporting data generated from an automated spoken dialog service, the system comprising:
means for extracting from a dialog logging module data regarding user dialogs with the automated spoken dialog service and not with a human agent;
means for analyzing the data to identify trends for at least one geographic area to yield identified trends;
means for comparing the identified trends for the at least one geographical area with an average in a wider geographical area containing the at least one geographic area;
means for modifying the automated spoken dialog service on a geographic basis according to the identified trends and comparison;
means, based on the analysis of the data and the comparison of the identified trends, for generating top natural language headlines, each of which describes at least one identified trend; and
means for displaying the generated top headlines to a user.
12. The system of claim 11 , further comprising means for reporting trends and enabling a user to drill down into the analyzed data, wherein the user can choose to view the analyzed data and hear user dialogs.
13. A non-transitory computer-readable storage medium storing executable instructions for controlling a computing device to report data generated from an automated spoken dialog service, wherein under the control of the instructions, the computing device performs the following steps:
extracting from a dialog logging module data regarding user dialogs with the automated spoken dialog service and not with a human agent;
analyzing the data to identify trends for a geographic area to yield identified trends;
comparing the identified trends for the geographical area with an average in a wider geographical area containing the geographic area;
modifying the automated spoken dialog service on a geographic basis according to the identified trends and comparison;
based on the analysis of the data and the comparison of the identified trends, generating top natural language headlines, each of which describes at least one identified trend; and
displaying the generated top headlines to a user.