Topical Search Engine Query Context Model

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current search engines return a vast amount of irrelevant content due to their broad optimization for result diversity, making it time-consuming for users to find relevant information, especially when queries are ambiguous or topic-related, and existing solutions require extensive manual effort or maintenance of comprehensive URL lists.

Innovation Solution

A topical search system that automatically generates query context models to add contextual keywords to queries, focusing search results on specific topics by employing a topic component that intercepts queries, alters them with context information, and utilizes a query context model to constrain results to a particular domain, thereby enhancing relevance without degrading query performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If search engines return a substantial amount of content to maximize result diversity, then the coverage and versatility of search results is improved, but the relevance to user intent deteriorates and users must spend more time filtering irrelevant content

Engineering Contradiction:

Improveresult diversityVSAvoidresult relevance

Core Design Contradiction:

Adaptability or versatilityVSManufacturing precision

Solution Approach 1:

The system performs preliminary actions by automatically generating query context models and pre-identifying relevant websites and topics before the actual search query is executed. This allows the search engine to pre-filter and pre-rank results based on predicted relevance, reducing the need for users to manually filter content while maintaining diverse results

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces query context models as an intermediary layer between the user query and search results. These models act as mediators that automatically interpret user intent and filter results accordingly, eliminating the need for users to manually filter irrelevant content while preserving result diversity

Inventive Principle:

Principle #24Intermediary (Mediator)

2Manufacturing precision

If users manually specify relevant websites and add fixed keywords to queries to filter results, then the relevance of search results is improved, but the ease of operation and time required deteriorates

Engineering Contradiction:

Improveresult relevanceVSAvoiduser effort

Core Design Contradiction:

Manufacturing precisionVSEase of operation

Solution Approach 1:

The system implements self-service by automatically generating query context models that identify relevant websites and contextual keywords without requiring user input. The system serves itself by autonomously interpreting queries and filtering results, eliminating the need for users to manually specify websites or add keywords

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual process of specifying websites and adding keywords with an automated computational system. Machine learning algorithms and natural language processing substitute for manual user actions, automatically generating context models and filtering results based on inferred user intent

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Manufacturing precision

If custom search engines restrict results to specific sites, then the relevance is improved, but the device complexity and maintenance burden increases

Engineering Contradiction:

Improveresult relevanceVSAvoidsystem complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The query context model system serves multiple functions: it automatically identifies relevant websites, generates contextual keywords, ranks results, and adapts to different user intents. This multi-functional approach eliminates the need for separate custom search engines for different topics, reducing overall system complexity while maintaining high relevance

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9177045B2Topical search engines and query context models

Publication Date: 2015.11.03 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Topical search engines can add contextual keywords to an input query to bias results toward a particular topic or domain. In one instance, query context models can be constructed to facilitate topical search. Upon receipt of one or more topic-relevant sites, a plurality of topical queries can identified automatically. Contextual keywords can be identified with respect to the plurality of topical queries as a function of lexical generality, among other things. Subsequently, a query context model, comprising the identified topical queries and related contextual keywords, can be employed to restrict query results to a particular topic.