Entity-Based App Suggestions for On-Device Search Queries

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users often face challenges in accessing desired entities on client devices due to the need for accurate identification of applications, leading to repeated queries and resource consumption when using automated assistants or on-device search engines.

Innovation Solution

An on-device system uses historical queries to associate entities with applications, generating probabilistic models to suggest applications for accessing entities, reducing the need for multiple inputs by automatically identifying the correct application based on entity associations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If users explicitly identify and launch the correct application to access a desired entity, then the entity can be accessed successfully, but the user must make multiple inputs and the system consumes more computing and battery resources due to repeated query attempts

Engineering Contradiction:

Improvesuccess rate of entity accessVSAvoidnumber of user inputs required

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system pre-processes historical query data to build an entity-application association model before users need to access entities. By analyzing past queries in advance, the system creates a mapping between entities and their corresponding applications, enabling rapid suggestion generation when users query for entities without specifying applications.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system utilizes historical query feedback from multiple users to continuously improve entity-application associations. By analyzing patterns in past queries where users successfully accessed entities, the system refines its suggestions to better predict which application a user intends to use, increasing accuracy with each iteration.

Inventive Principle:

Principle #23Feedback

2Speed

If users provide incomplete queries that specify entities but not applications, then the query processing speed increases, but the automated assistant cannot respond effectively without accurate application identification

Engineering Contradiction:

Improvequery processing speedVSAvoidresponsiveness of automated assistant

Core Design Contradiction:

SpeedVSReliability

Solution Approach 1:

The system introduces an intermediary entity-application association model that bridges the gap between incomplete user queries and the required application execution. When users provide queries without application specifications, the intermediary model automatically retrieves the correct application based on entity associations from historical data, enabling the automated assistant to respond effectively without requiring complete user input.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If the system requires accurate application identification for each entity access, then the correct application can be triggered, but computing and battery resources are consumed through repeated query attempts

Engineering Contradiction:

Improveaccuracy of application identificationVSAvoidbattery resource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary processing of historical query data to pre-establish entity-application associations before they are needed for actual entity access. By building and storing these associations in advance, the system avoids the need for repeated complex analysis during user interactions, thereby reducing real-time computing requirements and battery consumption.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates a simplified copy or representation of the entity-application relationship structure from historical data. Instead of analyzing raw historical queries each time a user needs to access an entity, the system uses pre-extracted association patterns that replicate the essential information, significantly reducing processing overhead and energy usage during actual operations.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20260064707A1Rendering suggestion for searching entity within application in response to determining the entity is associated with the application

Publication Date: 2026.03.05 GOOGLE LLC

AI summary

Implementations include recognizing entities in a user query received from a client device and determining whether any of the recognized entities is a personal entity using an entity database storing personal entities donated by applications installed at the client device. Application(s) or application action(s) can be determined based on entity information of the recognized entities, and suggestions can be generated to suggest the determined application(s) (or the determined application action(s)). For an application (or application action) determined based on a recognized entity that is determined as a personal entity, a suggestion for the application (or application action) can be boosted for display to a user of the client device.