Helping satisfy multiple objectives during a service desk conversation

ABSTRACT

Agents manning a service desk have the unenviable task of satisfying multiple conflicting objectives. Specifically, businesses require the agents to meet pre-specified customer satisfaction levels while keeping the cost of operations low or meeting sales targets, objectives that end up being complementary. Additional complexity is introduced by the fact that the objectives are often inter-dependent and have to be met in real-time. Moreover, business might change the objectives from time to time e.g. from reducing cost of operation to increasing sales of slow moving product. In this paper, we describe CallAssist - a speech enabled real-time dialog management system that dynamically helps agents in building a conversation that meets the various business objectives while satisfying customer requirements. An added benefit of our solution is the ability to adapt to changing business needs without incurring agent re-training costs. We provide evaluation results displaying the efficiency and effectiveness of our system.

REFERENCES

• 1: E. Agichtein and V. Ganti. Mining reference tables for automatic text segmentation. SIGKDD, 2004.
• 2: R. Baeza-Yates and B. Ribiero-Neto. Modern Information Retrieval. Addison Wesley Longman Publishing, 1999.
• 3: J. E. Baker. Reducing Bias and Inefficiency in the Selection Algorithm. In ICGA2, 1987.
• 4: A. Borthwick, J. Sterling, E. Agichtein, and R. Grishman. Exploiting diverse sources via maximum entropy in named entity recognition. Sixth Workshop on Very Large Corpora, 1998.
• 5: D. Carmel, M. Shtalhaim, and A. Soffer. eResponder: Electronic Question Responder. 7th International Conference on Cooperative Information Systems, London, UK, 2000.
• 6: V. Chakaravarthy, H. Gupta, P. Roy, and M. Mohania. Efficiently Linking Text Documents With Relevant Structured Information. In VLDB, September 2006.
• 7: V. Chakaravarthy, H. Gupta, P. Roy, and M. Mohania. Efficiently Linking Text Documents With Relevant Structured Information. In VLDB, September 2006.
• 8: S. Chaudhuri, V. Ganti, and R. Motwani. Robust identification of fuzzy duplicates. ICDE, 2005.
• 9: P. Chen. The entity-relationship model: Toward a unified view of data. ACM Transactions on Database Systems, 1(1):9--36, 1976.
• 10: H. Chevalier, C. Ingold, C. Kunz, C. Moore, C. Roven, J. Yamron, B. Baker, P. Bamberg, S. Bridle, T. Bruce, and A. Weader. Large-vocabulary speech recognition in specialized domains. ICASSP-95, May 9-12, 1995, Detroit, MI, USA.
• 11: J. Chu-Carroll and B. Carpenter. Vector-based natural language call routing. Comput. Linguist., 25(3):361--388, 1999.
• 12: W. Cohen and S. Sarawagi. Exploiting dictionaries in named entity extraction: Combining semi-markov extraction processes and data integration methods. SIGKDD, 2004.
• 13: G. Das, V. Hristidis, N. Kapoor, and S. Sudarshan. Ordering the Attributes of Query Results. SIGMOD, 2006.
• 14: D. Ferrucci and A. Lally. UIMA: an architectural approach to unstructured information processing in the corporate research environment. Natural Language Engineering, 10(3):4769--489, 2004.
• 15: A. Kohlmaier, S. Schmitt, and R. Bergmann. A Similarity-based Approach to Attribute Selection in User-Adaptive Sales Dialogs. 4th International Conference on Case-Based Reasoning: Case-Based Reasoning Research and Development, 2001.
• 16: X. Li, P. Morie, and D. Roth. Semantic Integration in Text: From Ambiguous Names to Identifiable Entities. AI Magazine: Special Issue on Semantic Integration, 2005.
• 17: I. Mansuri and S. Sarawagi. Integrating unstructured data into relational databases. ICDE, 2006.
• 18: T. Mitchell. Machine Learning. McGraw Hill, 1997.
• 19: M. Padmanabhan, G. Saon, J. Huang, B. Kingsbury, and L. Mangu. Automatic Speech Recognition Performance on a Voicemail Transcription Task. IEEE Trans. on Speech and Audio Processing, 10(7):433--442, 2002.
• 20: G. Riccardi, A. Gorin, A. Ljolje, and M. Riley. A spoken language system for automated call routing. ICASSP '97, Germany, 1997.
• 21: H. Soltau, B. Kingsbury, L. Mangu, D. Povey, G. Saon, and G. Zweig. The IBM 2004 Coversational Telephony System for Rich Transcription. IEEE ICASSP, March 2005.
• 22: U. Nambiar, H. Gupta and M. Mohania. CallAssist: helping call center agents in preference elicitation. In proc. of VLDB?07, 1338--1341, Vienna, Austria, September 2007.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.4 Systems
          Subjects: Relational databases

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.4 Systems
          Subjects: Query processing

  J. Computer Applications
  J.7 COMPUTERS IN OTHER SYSTEMS
      Subjects: Real time

General Terms:
Algorithms, Design, Management, Performance

Keywords:
dialog systems, preference elicitation, real-time entity analytics