Voice Search Refinement Detection via Pseudo-Search Weighting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Voice-based search interfaces face challenges in determining whether a user's subsequent voice command is a refinement of a previous search query or a new query, leading to inefficiencies in search result processing and user interaction.

Innovation Solution

A method and system that process voice commands by performing pseudo searches on combinations of search queries, determining relative weights of search results using ranking algorithms, and transmitting triggers to update search results and widgets on user devices, allowing for refinement of search queries and improved user interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice-based search interfaces process each voice command as a completely new search query, then the system maintains simplicity in query processing, but the search result relevance deteriorates when users provide refinement commands

Engineering Contradiction:

Improvesimplicity in query processingVSAvoidsearch result relevance

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs preliminary analysis by executing pseudo-searches on both the original query and the new voice command before final processing. This preliminary action allows the system to predict whether the new command is a refinement without fully committing to complex processing immediately, thus maintaining operational simplicity while improving result relevance through predictive analysis.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts its processing approach based on the relationship between queries. By determining whether a new voice command is a refinement of a previous query or a completely new search, the system adapts its processing depth and methodology, optimizing both operational efficiency and result relevance based on the specific interaction context.

Inventive Principle:

Principle #15Dynamics

2Measurement precision

If the system performs complex analysis to determine whether a voice command is a refinement or new query, then the search result relevance improves, but the processing time increases

Engineering Contradiction:

Improvesearch result relevanceVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs partial analysis through pseudo-searches that evaluate query relationships without executing full search processing. This partial action provides sufficient information to determine refinement status and guide subsequent processing, achieving high result relevance while avoiding the time cost of complete analysis for every voice command.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

By performing preliminary pseudo-searches to assess query relationships before final search execution, the system prepares ahead of time with minimal processing overhead. This preliminary action enables the system to make informed decisions about processing depth, reducing overall processing time while maintaining high result relevance.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If the system executes multiple pseudo searches to determine query refinement status, then the accuracy of refinement detection improves, but the computational resources consumed increase

Engineering Contradiction:

Improverefinement detection accuracyVSAvoidcomputational resources

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system executes partial pseudo-searches that provide sufficient information for refinement detection without performing complete search operations. This partial action achieves high detection accuracy by evaluating key query characteristics while consuming fewer computational resources than full search executions would require.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The pseudo-searches function as lightweight, temporary computational objects that are created, evaluated, and discarded to determine query relationships. These disposable pseudo-search operations provide necessary analytical power for accurate refinement detection while minimizing sustained computational resource consumption, as they are not permanent or persistent operations.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

Data Source

PatentUS10255240B2Method and system for processing a voice-based user-input

Publication Date: 2019.04.09 Y E HUB ARMENIA LLC

AI summary

There is disclosed a method of processing a search query, the method executable at a server. The method comprises receiving, via a communication network from an electronic device associated with the user, a first voice command from the user, the first voice command comprising an indication of a first search query; receiving, via the communication network from the electronic device associated with the user, a second voice command from the user, the second voice command comprising an indication of a second search query; determining if the second search query is a refinement of the first search query, said determining comprising; performing a first pseudo search based on a combination of the first search query and the second search query; performing a second pseudo search including the second search query; determining relative weight of the first pseudo search results and the second pseudo search results; deducing that the second search query is a refinement of the first search query responsive to the relative weight of the first pseudo search results being higher than that of the second pseudo search results.