Intent-Based Search for Application Discovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search techniques require users to input specific names of applications, documents, or web pages, which can be challenging when users are unaware of the exact name or have difficulty recalling it, leading to incorrect or non-preferred results.
Innovation Solution
Implementing a system that allows users to search for applications or data by describing the intended action, using a comparison with prior user intents and selections to identify relevant applications, and providing output to enable the desired action, such as receiving a description of an action (e.g., "I want to send an email") and identifying suitable applications based on usage percentages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users search for applications by exact name, then search precision is improved, but ease of operation deteriorates when users do not know the exact name
Solution Approach 1:
The patent introduces an intermediary system that translates natural language descriptions of intended actions into application identifiers. Instead of requiring direct name matching, the system acts as a mediator that interprets user intent (e.g., 'send email') and maps it to appropriate applications (e.g., 'Outlook'), thereby resolving the contradiction between precision and ease of operation.
Solution Approach 2:
The patent replaces the mechanical keyword-matching search system with an intent-based interpretation system. Rather than relying on exact name matching mechanics, the new system uses natural language processing and machine learning to understand user intent and identify relevant applications, thus improving ease of operation while maintaining or enhancing search precision.
2Measurement precision
If search requires specific application names, then search accuracy is improved, but loss of information increases when users cannot recall exact names
Solution Approach 1:
The patent performs preliminary action by pre-processing and storing intent-action mappings in advance. The system learns from historical data which applications are associated with which user intents, so when a user searches by description rather than name, the system can accurately retrieve the intended application without requiring the user to have complete information beforehand.
3Device complexity
If traditional search techniques are used, then device complexity is reduced, but productivity decreases when users cannot locate correct results
Solution Approach 1:
The patent changes the search parameter from exact application names to natural language descriptions of intended actions. This parameter transformation allows the system to leverage existing search infrastructure while dramatically improving productivity, as users can search using whatever information they have (even if incomplete) rather than requiring precise names.
Data Source
AI summary
Methods, apparatuses, and systems for intention based search techniques are described herein. An example method comprises receiving data indicative of an intent of a user to perform an action via at least one application, the data comprising a description of the action that is input via a client device application on a client device, identifying, by the computing device, the at least one application based on a comparison of the description of the action and one or more records, the one or more records being indicative of prior intents of one or more users to perform actions and indicative of at least one selection by the one or more users to perform the actions with a selected application, and providing, by the computing device, output to the client device to enable performance of the action via the at least one application.