Skip to main content
SpringerLink
Log in

Human-agent service matching using natural language queries: system test and training

  • Original Article
  • Published:
Personal and Ubiquitous Computing Aims and scope Submit manuscript

Abstract

Smart environments, ambient intelligence and intelligent agents leave the user lost between large amounts of services. Ad-hoc networks, mobile agents and mobile devices make the set of available services dynamic over time and space, increasing the user’s problems to find the service he needs. Earlier, we presented a ServiceMatcher that can find the agent best fitting to the user’s natural language request. This paper presents performance results of the ServiceMatcher. The test queries come from human users in a realistic scenario (see our other paper in this issue). With a short training of the agent vocabularies, over 80% correct service matches are found.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3.
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Smarthome (2003) Welcome to SmartHome.http://www.smarthome.com

  2. Spinellis DD (2003) The information furnace: consolidated home control. Pers Ubiquitous Comput 7(1):53–69

    Article  MathSciNet  Google Scholar 

  3. Philips (2002) Ambient Intelligence in HomeLab. http://www.philips.com/Assets/Downloadablefile/LEAFLET8x-1504.pdf

  4. Smartkom (2004) SmartKom: dialog-based human-technology interaction by coordinated analysis and generation of multiple Modalities.http://www.smartkom.org

  5. Blaylock N (2002) Managing communicative intentions in dialogue using a collaborative problem-solving model. Technical Report 774, University of Rochester, Computer Science Department. http://www.cs.rochester.edu/u/blaylock/Pubs/./Files/tr774.pdf

  6. Kaasainen E (2003) User needs for location-aware mobile services. Pers Ubiquitous Comput 7(1):70–79

    Article  Google Scholar 

  7. Pasman W (2004) Organizing ad hoc agents for human-agent service matching. In: Proceedings of Mobiquitous 2004 (Boston, MA, August 22–25), pp 278–287

  8. Lindenberg J, Pasman W, Kranenborg K, Stegeman J, Neerincx MA (2006) Improving service matching and selection in ubiquitous computing environments: a user study. Pers Ubiquitous Comput (this issue)

  9. Damerau FJ (1964) A technique for computer detection and correction of spelling errors. Commun ACM 7(3):171–176

    Article  Google Scholar 

  10. JADE (2003) Java Agent Development Framework. http://jade.cselt.it

  11. Wang Y, Stroulia E (2003) Semantic structure matching for assessing web service similarity. In: Proceedings of international conference on service oriented computing (Universita Degli Studi Di Trento, December 15–18). http://www.cs.toronto.edu/∼yw

  12. Salton G, Wong A, Yang CS (1975) A vector-space model for information retrieval. J Am Soc Inf Sci 18:613–620

    MATH  Google Scholar 

Download references

Acknowledgements

This work is part of the CACTUS project which was co-funded by the Dutch Ministry of Economic Affairs as part of the policy plan “Concurreren met ICT Competenties”.

Author information

Authors and Affiliations

  1. Delft University of Technology, Mekelweg 4, Delft, Netherlands

    W. Pasman & J. Lindenberg

  2. TNO Human Factors, Kampweg 5, Soesterberg, Netherlands

    J. Lindenberg

Authors
  1. W. Pasman
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. Lindenberg
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to W. Pasman.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Pasman, W., Lindenberg, J. Human-agent service matching using natural language queries: system test and training. Pers Ubiquit Comput 10, 393–399 (2006). https://doi.org/10.1007/s00779-006-0067-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00779-006-0067-6

Keywords

Search

Navigation