Search Result Intent Grouping for Ambiguous Queries

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional search engines face challenges in accurately disambiguating search results due to ambiguous keyword-based queries, often returning thousands of irrelevant results that require users to sift through multiple pages to find relevant content.

Innovation Solution

The system groups search results based on user intents identified through entity recognition, allowing users to modify and refine search results using entity attributes, thereby providing more relevant and organized search engine result pages (SERPs).

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional keyword-based search is used, then search results cover broad topics, but the results are ambiguous and require users to traverse multiple pages to find relevant content

Engineering Contradiction:

Improvesearch result relevanceVSAvoidtime to locate relevant content

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent segments search results into multiple intent-based groups (e.g., informational, navigational, transactional) rather than presenting a single flat list. Each group contains results relevant to a specific user intent, allowing users to quickly locate relevant content without traversing multiple pages of mixed results.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes the parameter of result organization from simple keyword matching to multi-dimensional intent classification. By analyzing query characteristics and result properties, the system transforms the search result structure to reflect different user intents, improving relevance without increasing user effort.

Inventive Principle:

Principle #35Parameter changes

2Quantity of substance

If thousands of search results are returned, then comprehensive coverage is achieved, but users must navigate through numerous irrelevant results

Engineering Contradiction:

Improvenumber of search resultsVSAvoidease of finding relevant content

Core Design Contradiction:

Quantity of substanceVSEase of operation

Solution Approach 1:

Instead of presenting thousands of results as a single list, the patent divides them into organized groups based on intent. This segmentation maintains comprehensive coverage while making the results easier to navigate by allowing users to focus on specific intent groups rather than sifting through all results sequentially.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent adds a new dimension to search results by organizing them according to user intent categories. This transforms the traditional one-dimensional ranked list into a multi-dimensional structure where results are organized both by relevance score and by intent type, providing users with additional navigation pathways.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Speed

If SERP renders only top n results, then page load time is reduced, but users may miss relevant content on subsequent pages

Engineering Contradiction:

ImproveSERP loading speedVSAvoidrelevant content visibility

Core Design Contradiction:

SpeedVSLoss of information

Solution Approach 1:

By segmenting results into intent groups, the system can render multiple focused groups within the top n results rather than a single mixed list. This allows more relevant content to be visible on the first page while maintaining fast loading times, as each group is tightly focused on a specific intent.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary intent classification and grouping before rendering the SERP. This preliminary organization ensures that the most relevant results for each intent are positioned prominently in the top n results, reducing the need for users to navigate to subsequent pages.

Inventive Principle:

Principle #10Preliminary action

4Productivity

If keyword-based matching is used, then simple queries are processed quickly, but ambiguous queries return irrelevant results

Engineering Contradiction:

Improvequery processing speedVSAvoidsearch result accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent introduces intent classification as an intermediary step between keyword matching and result ranking. This intermediary layer analyzes query characteristics and result properties to determine user intent, thereby improving result accuracy without significantly impacting processing speed, as the classification can be performed using pre-computed features.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS9183310B2Disambiguating intents within search engine result pages

Publication Date: 2015.11.10 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Systems, computer-readable media, and methods for generating search engine results pages are provided. A user provides a search engine with one or more query terms. The query terms may be associated with an intent, e.g. product entity, store entity, person entity. The search engine classifies the query and identifies search results that correspond to the query. The search results are grouped based on intents associated with the query. A graphical user interface displays the grouped on search results and allows the user to modify the groupings. The graphical user interface is also updated with entity or entity attributes corresponding to the intents used to group the search results.