Finding Preferred Query Relaxations in Content-Based Recommenders

Studies in computational intelligencePublished 1 January 2008

Dietmar Jannach

DOI10.1007/978-3-540-77623-9_5

Source URL

Citations48

SJR quartileQ4

SJR score0.19

SNIP0.29

TL;DR

A new technique for determining all maximal succeeding subqueries of a query in an efficient way is presented which allows us to determine optimal or `preferred' solutions within the limited time frames of Interactive recommendation sessions.

Abstract

In many content-based approaches to product recommendation, the set of suitable items is determined by mapping the customer's needs to required product characteristics. A 'failing query' in that context corresponds to a situation in which none of the items in the catalog fulfills all of the customer requirements and in which no proposal can be made. 'Query relaxation' is a common technique to recover from such situations which aims at determining those items that fulfill as many of the constraints as possible. This chapter proposes two new algorithms for query relaxation, which aim at resolving common shortcomings of previous approaches. The first algorithm addresses the problem of response times for computing user-optimal relaxations in interactive recommendation sessions. The proposed algorithm is based on a combination of different techniques like partial evaluation of subqueries, precomputation of query results and compact in-memory data structures. The second algorithm is an improvement of previous approaches to mixed-initiative failure recovery: Instead of computing all minimal 'conflicts' within the user requirements in advance – as suggested in previous algorithms – we propose to determine preferred conflicts 'on demand' and use a recent, general-purpose and fast conflict detection algorithm for this task.1

Keywords

Computer Science

Artificial IntelligenceA theory of diagnosis from first principles

2,897 Citations1987Raymond Reiter

The theory accommodates diagnostic reasoning in a wide variety of practical settings, including digital and analogue circuits, medicine, and database updates, and reveals close connections between diagnostic reasoning and nonmonotonic reasoning.

Elsevier eBooksFoundations of Constraint Satisfaction

1,616 Citations1993

Introduction to the C SP CSP solving - an overview chapter fundamental concepts of the CSP chapter problem reduction chapter basic search strategies for solving CSPs search orders in searching in C SPs exploitation of problem specific features stochastic search methods.

QUICKXPLAIN: preferred explanations and relaxations for over-constrained problems

380 Citations2004Ulrich Junker

This work significantly accelerate the basic method by a divide-and-conquer strategy and thus provides the technological basis for the explanation facility of a principal industrial constraint programming tool, which is, for example, used in numerous configuration applications.

International Journal of Cooperative Information SystemsMinimization in Cooperative Response to Failing Database Queries

113 Citations1997Parke Godfrey

The complexity results and the algorithmic approaches given in this paper should allow for the construction of cooperative facilities which identify MFSs and XSSs for database systems and are relevant to a number of problems outside of databases too, and may find further application.

View PDF

Lecture notes in computer scienceIncremental Relaxation of Unsuccessful Queries

43 Citations2004David McSherry

This work presents a mixed-initiative approach to recovery from the retrieval failures that occur when there is no case that satisfies all the user’s requirements.

ADVISOR SUITE - A knowledge-based sales advisory system

42 Citations2004Dietmar Jannach

The presented system consistently follows a knowledge-based approach where all required development activities - from the definition of the user model and the recommendation rules, up to the personalization of the dialogue flow as well as user interface generation - are based on simple conceptual models and declarative knowledge representation.

Towards Conversational Recommender Systems: A Dialogue Grammar Approach.

41 Citations2002Derek Bridge

This work proposes an approach that uses both a dialogue grammar and a recommendation strategy to achieve global dialogue coherence in systems that support mixed-initiative interaction.

Product Recommendation Systems: A New Direction

32 Citations2001Derek Bridge

An ordered type is one that has a non-trivial partial order of its values that may be useful in product recommendation and a distinction is drawn at this point between ordered types and unordered types.

Lecture notes in computer scienceTechniques for Fast Query Relaxation in Content-Based Recommender Systems

24 Citations2007Dietmar Jannach

New techniques for the fast computation of 'user-optimal' query relaxations are described and a general-purpose conflict detection algorithm can be applied for determining 'preferred' conflicts in interactive relaxation scenarios.

Lecture notes in computer scienceA Knowledge-Based Framework for the Rapid Development of Conversational Recommenders

9 Citations2004Dietmar Jannach, Gerold Kreutler

The Advisor Suite framework for rapid development of conversational recommenders for arbitrary domains is presented, which shows that development times and costs for online sales advisory systems can be significantly reduced when following the described knowledge-based approach.