Implicit Query Reformulation for Contextual Search Relevance

Solution Overview

Problem

Web search engines face challenges in providing relevant results when receiving queries from new environments and contexts, such as integrated search boxes in operating systems and virtual assistants, due to lack of necessary context, requiring users to perform multiple searches to obtain relevant results.

Innovation Solution

A system that automatically identifies and contextually reformulates implicit device-related queries by generating new queries based on data associated with the electronic device, allowing for relevant search results to be retrieved and provided directly to the user.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If web search engines receive queries from new environments and contexts (integrated search boxes, virtual assistants), then the system can serve more users and contexts, but the search relevance deteriorates due to lack of device context

Engineering Contradiction:

Improveability to serve queries from multiple environmentsVSAvoidsearch result relevance

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary actions by collecting and storing device context data (device type, operating system, installed applications, user settings) before the search query is submitted. This pre-collected context is then automatically associated with the query to enhance relevance without requiring user input.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary context enrichment layer between the query and search engine. This intermediary component automatically adds device-specific context parameters to the query, acting as a mediator that bridges the gap between the user's implicit intent and the search engine's needs for specific search parameters.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If users perform multiple searches with various queries to obtain relevant results, then search relevance can be improved, but the time and number of operations increase

Engineering Contradiction:

Improvesearch result relevanceVSAvoidtime required for multiple searches

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by collecting and storing device context data (device type, operating system, installed applications, user settings) before the search query is submitted. This pre-collected context is then automatically associated with the query to enhance relevance without requiring user input.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system enables self-service by automatically enriching queries with device context without requiring user intervention. The user simply submits their intent, and the system autonomously adds the necessary device-specific parameters to retrieve relevant results in a single search operation.

Inventive Principle:

Principle #25Self-service

3Ease of operation

If web search engines provide general search results, then the system can maintain simplicity, but the results become irrelevant to the specific device and user context

Engineering Contradiction:

Improvesystem simplicityVSAvoidresult relevance to device context

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent introduces an intermediary context enrichment layer between the query and search engine. This intermediary component automatically adds device-specific context parameters to the query, acting as a mediator that bridges the gap between the user's implicit intent and the search engine's needs for specific search parameters.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system enables self-service by automatically enriching queries with device context without requiring user intervention. The user simply submits their intent, and the system autonomously adds the necessary device-specific parameters to retrieve relevant results in a single search operation.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20220327118A1Automatic identification and contextual reformulation of implicit device-related queries

Publication Date: 2022.10.13 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

System and methods for performing automatic identification and contextual reformulation of implicit device-related queries are described. In some examples, a query server may receive a query from an electronic device, receive data associated with the electronic device, determine that the query is related to the electronic device, generate a new query based at least in part on the query and the data associated with the electronic device, retrieve results related to the new query, and send the results related to the new query to the electronic device. In some examples, determining that the query is related to the electronic device includes determining that the query is a semi-implicit device query or a fully implicit device query. The data associated with the electronic device can include a model name of the electronic device, an operating platform for the electronic device, and/or additional data related to the electronic device.