Enhancing call center performance
View Patent ↗Some general aspects of the invention relate to systems and methods of processing data, for example, to improve customer interactions. One aspect, in particular, relates to a computer-implemented method that includes accepting user input for analysis of a database having media data and metadata. The media data includes a group of audio recordings and the metadata includes descriptive information of the group of audio recordings. A representation of a set of call series is formed based on user input, and processed to generate an analysis report. A visual representation of the analysis report is formed for presentation to a user.
1. In a system in electronic communication with a database having media data, the media data including audio recordings of calls and metadata associated with the calls, a computer-implemented method comprising:
accepting user input specifying a set of criteria that define a call series indicative of a plurality of content-related audio recordings, the set of criteria including a minimum number of calls sharing a common caller identifier within a defined time interval;
forming a representation of a set of one or more call series based on the user input, including identifying as a call series each of one or more pluralities of content-related audio recordings that satisfies the set of criteria;
processing the representation of the set of one or more call series to generate an analysis report; and
performing a content-based analysis of the media data that includes applying a phonetically based word-spotting technique to search for occurrences of one or more queries in the metadata, the metadata including a searchable phonetic representation of the media data.
2. The computer-implemented method of claim 1 , wherein forming the representation of the set of one or more call series includes performing a content-based analysis of the media data that includes searching the audio recordings for content associated with one or more queries, or with a predetermined combination of queries.
3. The computer-implemented method of claim 1 , wherein the searchable representation of the media data includes an at least partially textual representation of the media data.
4. The computer-implemented method of claim 1 , wherein processing the representation of the set of one or more call series to generate an analysis report includes:
determining a set of one or more common topics among the set of one or more call series.
5. The computer-implemented method of claim 4 , wherein determining the set of one or more common topics includes:
applying a set of one or more structured queries on a phonetic or textual representation of the media data.
6. The computer-implemented method of claim 5 , wherein the structured queries include phrases, Boolean operators, time-based operators, or a combination thereof.
7. The computer-implemented method of claim 1 , wherein processing the representation of the set of one or more call series to generate an analysis report includes:
determining a degree of correlation of the content of a first audio recording in each identified call series with the content of subsequent audio recordings in the identified call series.
8. The computer-implemented method of claim 7 , wherein determining the degree of correlation includes:
for each audio recording in the set of identified call series, determining whether the recording is associated with at least one of a predetermined set of content categories.
9. The computer-implemented method of claim 8 , wherein determining the degree of correlation further includes:
within a subset of call series whose first audio recording is associated with a first content category, computing the ratio of call series each having at least one audio recording associated with the second content category.
10. The computer-implemented method of claim 8 , wherein determining the degree of correlation further includes:
within a subset of call series whose first audio recording is associated with a first content category, computing the ratio of call series each having at least one non-first audio recording associated with the second content category.
11. The computer-implemented method of claim 8 , wherein determining the degree of correlation further includes:
within a subset of call series each of which has at least one audio recording being associated with a first content category, computing the ratio of call series each having at least one audio recording associated with the second content category.
12. The computer-implemented method of claim 8 , wherein determining the degree of correlation further includes:
within a subset of call series each of which has at least one audio recording being associated with a first content category, computing the ratio of call series each having at least one non-first audio recording associated with the second content category.
13. The computer-implemented method of claim 8 , wherein determining the degree of correlation further includes:
determining a linear or non-linear combination of call counts associated with a first and a second content category.
14. The computer-implemented method of claim 1 , wherein the set of criteria includes one or more of the following: a minimum number of calls within a call series, a minimum amount of time allowed between consecutive calls in a call series, a maximum amount of time allowed between consecutive calls in a series, a total duration of a call series, talk-time characteristics and/or non-talk time characteristics in a call series, and an occurrence of a search term.
15. The computer-implemented method of claim 1 , further comprising:
forming a visual representation of the analysis report for presentation to a user.
16. The computer-implemented method of claim 1 , wherein the caller identifier includes a customer ID value, automatic number identification (ANI), and caller ID value.