Method, apparatus and system for capturing and analyzing interaction based content

• US 8,204,884 B2
• Filed: 05/02/2011
• Issued: 06/19/2012
• Est. Priority Date: 07/14/2004
• Status: Active Grant

• Current Assignee: Nice Systems Limited (Nice Ltd)
• Original Assignee: Nice Systems Limited (Nice Ltd)
• Inventors: Freedman, Ilan, Dolev, Yair, Falik, Talia, Pereg, Oren, Wasserblat, Moshe, Aharoni, Gili, Bar, Eytan, Shermister, Shai, Arussy, Lior, Meidav, Yifat
• Primary Examiner(s): Badawi, Sherief
• Application Number:
  US13/098,504
• Publication Number:
  US 20110206198A1
• Time in Patent Office: 414 Days
• Field of Search: 379/265.06, 379/265, 707/703, 707/702, 707/737, 707/749, 709/203
• US Class Current: 707/737
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/51 Centralised call answering arrangements requiring operator intervention , e.g. call or contact centers for telemarketing
• CPC Class Codes: H04M 3/5141 Details of processing calls and other types of contacts in an unified manner unified messaging in packet-switching networks H04L51/56
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements

Abstract

An apparatus and methods for capturing and analyzing customer interactions the apparatus comprising interaction information units, interaction meta-data information units associated with each of the interaction information units, a rule based analysis engine component for receiving the interaction information, an adaptive database, an interaction capture and storage component for capturing interaction information, a multi segment interaction capture device, an initial set up and calibration device and a pre processing and content extraction device.

Claims

1. A method for capturing and analyzing customer interactions with an agent, comprising:

pre-processing at least two interaction information units using audio analysis for at least one of the at least two interaction information units, extracting content data items from the at least two interaction information units;

storing the content data items in a content data item database;

selectively analyzing the at least one of the at least two interaction information units suitable for further analysis by applying content analysis rules on said content data items, including non-text based analysis rules by a rule based content analysis engine;

classifying the content data items from the at least two interaction information units into at least two user-defined categories, by matching at least one of the content data items against the at least two user-defined categories and associating the at least one of the content data items with a suitable category of the at least two user-defined categories, the at least two user-defined categories defined in accordance with at least one word combined with a screen event or with a CRM entry that occurred substantially at the time the at least one word was used;

using the rules to look for pre-defined combinations of specific keywords, emotion levels or talk behavior; and

notifying the agent by providing a coaching statement to a computing device used by the agent when a pre-defined combination is found.

2. A method according to claim 1, further comprising using analysis results in at least one usage selected from the group consisting of:

a quality management application for evaluating agents'"'"' performance, said quality management application employing quality management electronic evaluation forms, an e-learning application, a playback application, and a reporter or statistics application.

3. A method according to claim 1, wherein the pre-processing or analyzing includes at least one item selected form the group consisting of:

a behavioral pattern identification, speaker identification, speaker verification, speaker separation, call flow analysis, excitement analysis, emotion analysis, screen events analysis, video analysis, speech recognition, word spotting, and optical character recognition (OCR).

4. A method according to claim 1, wherein at least one of the content data items is selected from the group consisting of:

extracted text, a word, a phrase, an excitement level, an emotion level of a customer, an emotion level of an agent, an identified screen event, a behavioral pattern, a call flow parameter, a speaker identification, results of speakers separation or results of object analysis for video.

5. A method according to claim 1, wherein the analyzing uses at least one additional information source selected from the group consisting of:

an interaction meta-data, an organization knowledge base, customer Relationship Management (CRM) information, and Computer Telephone Integration (CTI) information.

6. A method for capturing and analyzing customer interactions with an agent, comprising:

pre-processing at least two interaction information units using audio analysis for at least one of the at least two interaction information units, extracting content data items from the at least two interaction information units;

storing the content data items in a content data item database;

selectively analyzing the at least one of the at least two interaction information units suitable for further analysis by applying content analysis rules on said content data items, including non-text based analysis rules by a rule based content analysis engine;

classifying the content data items from the at least two interaction information units into at least two user-defined categories, by matching at least one of the content data items against the at least two user-defined categories and associating the at least one of the content data items with a suitable category of the at least two user-defined categories, the at least two user-defined categories defined in accordance with at least one word combined with a screen event or with a CRM entry that occurred substantially at the time the at least one word was used; and

using the rules to automatically fill in quality management evaluation forms related to the performance of the agent.

7. A method according to claim 6, further comprising using analysis results in at least one usage selected from the group consisting of:

a quality management application for evaluating agents'"'"' performance, said quality management application employing quality management electronic evaluation forms, an e-learning application, a playback application, and a reporter or statistics application.

8. A method according to claim 6, wherein the pre-processing or analyzing includes at least one item selected form the group consisting of:

a behavioral pattern identification, speaker identification, speaker verification, speaker separation, call flow analysis, excitement analysis, emotion analysis, screen events analysis, video analysis, speech recognition, word spotting, and optical character recognition (OCR).

9. A method according to claim 6, wherein at least one of the content data items is selected from the group consisting of:

extracted text, a word, a phrase, an excitement level, an emotion level of a customer, an emotion level of an agent, an identified screen event, a behavioral pattern, a call flow parameter, a speaker identification, results of speakers separation or results of object analysis for video.

10. A method according to claim 6, wherein the analyzing uses at least one additional information source selected from the group consisting of:

an interaction meta-data, an organization knowledge base, customer Relationship Management (CRM) information, and Computer Telephone Integration (CTI) information.

11. A method for capturing and analyzing customer interactions with an agent, comprising:

pre-processing at least two interaction information units using audio analysis for at least one of the at least two interaction information units, extracting content data items from the at least two interaction information units;

storing the content data items in a content data item database;

selectively analyzing the at least one of the at least two interaction information units suitable for further analysis by applying content analysis rules on said content data items, including non-text based analysis rules by a rule based content analysis engine;

classifying the content data items from the at least two interaction information units into at least two user-defined categories, by matching at least one of the content data items against the at least two user-defined categories and associating the at least one of the content data items with a suitable category of the at least two user-defined categories, the at least two user-defined categories defined in accordance with at least one word combined with a screen event or with a CRM entry that occurred substantially at the time the at least one word was used; and

using the rules to automatically update quality management evaluation forms to include particular questions related to the performance of the agent.

12. A method according to claim 11, further comprising using analysis results in at least one usage selected from the group consisting of:

a quality management application for evaluating agents'"'"' performance, said quality management application employing quality management electronic evaluation forms, an e-learning application, a playback application, and a reporter or statistics application.

13. A method according to claim 11, wherein the pre-processing or analyzing includes at least one item selected form the group consisting of:

a behavioral pattern identification, speaker identification, speaker verification, speaker separation, call flow analysis, excitement analysis, emotion analysis, screen events analysis, video analysis, speech recognition, word spotting, and optical character recognition (OCR).

14. A method according to claim 11, wherein at least one of the content data items is selected from the group consisting of:

extracted text, a word, a phrase, an excitement level, an emotion level of a customer, an emotion level of an agent, an identified screen event, a behavioral pattern, a call flow parameter, a speaker identification, results of speakers separation or results of object analysis for video.

15. A method according to claim 11, wherein the analyzing uses at least one additional information source selected from the group consisting of:

an interaction meta-data, an organization knowledge base, customer Relationship Management (CRM) information, and Computer Telephone Integration (CTI) information.