Data processing: database and file management or data structures – Database design – Data structure types
Reexamination Certificate
1998-06-25
2001-07-03
Black, Thomas (Department: 2171)
Data processing: database and file management or data structures
Database design
Data structure types
C707S793000, C707S793000, C707S793000, C705S014270, C705S014270
Reexamination Certificate
active
06256633
ABSTRACT:
FIELD OF THE INVENTION
The invention relates to a method and system for enabling retrieval of an information item from an information base in an electronic network.
BACKGROUND ART
Rapidly expanding information archives provide access to terabytes of electronic data, e.g., electronic museums, electronic newspapers, musical archives, digital libraries, software archives, mailing lists, up-to-date weather information and geographic data. Consequently, current advances in information technology are driven by the need to increase the effectiveness of information access and retrieval.
Traditionally, information providers try to overcome the inadequacies of information retrieval by providing fast and powerful search engines, see, for example, U.S. Pat. No. 5,293,552 (PHN 13,666) herewith incorporated by reference. Retrieval mechanisms based on keywords typically return a large set of documents, but are not very precise in their return. Examples of searching systems are commonly available search engines, databases and library lookup systems. The user interacts with the system by providing a query with sufficient information and gets back a set of documents that more or less match the query.
Traditional approaches have devised mechanisms to map a user's query to a document based on overlapping terms or concept words between the query and the document terms.
One known approach is known from “Experiments on Using Semantic Distances Between Words in Image Caption Retrieval”, Alan F. Smeaton and Ian Quigley, Proceedings of the 19th Annual International A CM SIGIR Conference on Research and Development in Information Retrieval, August 1996, Zürich, Switzerland. This approach uses a quantitative measure of semantic similarity between index terms for queries and documents.
Another recent method is described in “A Deductive Data Model for Query Expansion”, Kalervo Jarvelin, Jaana Kristensen, Timo Niemi, Eero Sormunen and Heikki Keskustalo, Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, August 1996, Zürich, Switzerland. This method introduces concept-based query expansion, where each concept is expanded to a disjunctive set of concepts on the basis of conceptual relationships pointed out by the user.
Yet another known idea is proposed in “Incremental Relevance Feedback for Information Filtering”, James Allan, Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. August 1996, Zürich, Switzerland. This idea relates to relevance feedback techniques that process shifts in user interest patterns over a period of time. The user feeds back notions of which query results he/she believes are relevant to the current query.
OBJECT OF THE INVENTION
A key to effective information retrieval lies in mechanisms that increase the precision values for documents retrieved. One problem with existing search systems is that if the query is not very precise, the user is left with the task of scanning through a large of amount of result data to identify documents of interest, because a large percentage of the information retrieved is not relevant to the user. Another drawback is that the known retrieval methods supply a set of results that is restricted to the literal search criteria entered at that moment and not much else. That is, the electronic information retrieval does not have the advantages of real-life browsing at a bookstore where an interesting book cover may catch a person's eye and divert his/her attention or awaken his/her interest. Consequently, the information provider is unable to guide the user to other, yet related, works that could be of interest to this particular user.
It is therefore an object of the invention is to provide a method for retrieving information that improves the quality of the result data.
SUMMARY OF THE INVENTION
To this end, the invention provides a method of enabling a user to navigate through an electronic document base. The invention provides a method of enabling a user to query an electronic document base. The user supplies at least one query object, e.g., a word, a geometrical shape or pattern, a tune or rhythm representing one or more bars of a piece music, etc. The method comprises determining a topical context for the query by means of extracting from an access history, e.g., at least one preceding query, of the user to the document base at least one concept object associated with the current query. The concept object is used to create at least part of a user profile. Then one or more documents are identified in the document base under control of the user profile. The profile is updated based on the content of the identified document.
The invention increases the effectiveness of browsing wide-area information by means of focusing primarily on the user's interest as given by the user's access history in terms of the results of previous queries. Taking these results into account for next queries creates a context that enables interpreting the current query object in view of what currently is likely to be of interest to this specific user. The context for the current query is used to update the user's profile. The profile itself is used as a recommendation for mapping relevant information form the information provider's topic space, also referred to as document base, onto the user's search space.
The profile gets updated dynamically in response to the user's interactions with the document base. Accordingly, the dynamic part reflects the path taken within the provider's information space in the course of the user's search. Preferably, the profile has also a static part that reflects the user's long-term interests. The term “static’ is used to indicate a time scale substantially slower than that of the dynamic part. The static part is determined by, for example, letting the user provide topical information about his/her fields of attention the first time that the user interacts with the document base. Such entries can be changed manually in due course. Alternatively or subsidiarily, statistical analysis of a statistically relevant number of results over time enables finding themes that stay substantially constant.
The preferred embodiment of the invention allows the user to retain a constant theme in his/her profile (static part) as well as to influence the profile by new issues (dynamic part) generated while browsing the provider's information space. This latter aspect of the invention gives a mechanism to information-providers to attract the user's interest while the latter is browsing at their sites.
Preferably, the user is allowed to disable and enable the static and/or dynamic part of his/her profile so as to be able to choose whether or not to use the profiling in retrieving information.
Thus, the invention enables clustering and re-clustering of the information space in a manner effective for highly personalized browsing. The invention can be regarded as an automatic version of the “refine” button as provided by various search engines found on the Internet.
For the example with the music data base mentioned above, see U.S. patent application Ser. No. 08/840,356, filed Apr. 28, 1997 (PHA 23,241), herein incorporated by reference.
REFERENCES:
patent: 5293552 (1994-03-01), Aalbersberg
patent: 5664063 (1997-09-01), Johnson et al.
patent: 5694594 (1997-12-01), Chang
patent: 5761662 (1998-06-01), Dasan
patent: 5771381 (1998-06-01), Jones et al.
patent: 5973683 (1999-10-01), Cragun et al.
patent: 5978799 (1999-11-01), Hirsch
patent: 5995597 (1999-11-01), Woltz et al.
patent: 6009410 (1999-12-01), LeMole et al.
patent: 6021403 (2000-02-01), Horvitz et al.
“Incremental Relevance Feedback for Information Filtering”, by J. Allan, Center for Intelligent Information Retrieval Dept. of Computer Science, Univ. of Mass., Amherst, Mass.
“A Deductive Data Model for Query Expansion”, by K. Jarvelin et al., Dept. of Information Studies, Dept. of Computer Science, Univ. of Tampere, Finl
Black Thomas
Coby Frantz
U.S. Philips Corporation
Verdonk Peter
LandOfFree
Context-based and user-profile driven information retrieval does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Context-based and user-profile driven information retrieval, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Context-based and user-profile driven information retrieval will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2529823