Assisted Search for Non-Document Items Using Selected Content
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search methods for non-document items in databases, such as browser extensions and mobile applications, require manual keyword entry and repetitive scrolling, leading to inefficiencies and mismatches between user intent and search indexing.
Innovation Solution
An assisted search system that analyzes selected content to identify objects and submits parallel queries to a database, using machine learning to generate smart queries and present top-ranking results grouped by query confidence and saliency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual keyword entry and scrolling is used for searching non-document items, then the search process requires user effort and time, but the system complexity remains low
Solution Approach 1:
The system automatically analyzes selected content to generate search queries without requiring manual keyword entry. The search system serves itself by extracting objects from content and formulating queries autonomously, eliminating the need for user intervention in query formulation while maintaining relatively simple system architecture.
Solution Approach 2:
The patent introduces an intermediary component that bridges the gap between content selection and database searching. This intermediary analyzes the selected content, identifies relevant objects, and translates them into search queries, thereby improving search efficiency without significantly increasing overall system complexity.
2Speed
If multiple search queries are submitted in parallel, then the search speed increases, but the system complexity and resource usage increase
Solution Approach 1:
The system performs preliminary analysis of the selected content to identify multiple relevant objects before submitting queries. By preparing the queries in advance based on content analysis, the system can submit multiple queries in parallel, achieving faster search speeds while managing complexity through structured preprocessing.
Solution Approach 2:
The patent segments the search process into distinct phases: content analysis, object identification, query formulation, and parallel execution. This segmentation allows multiple queries to be processed in parallel while maintaining clear system boundaries and manageable complexity through modular architecture.
3Measurement precision
If the system analyzes content to identify objects and generates smart queries, then the search accuracy improves, but the processing time and computational resources increase
Solution Approach 1:
The system performs partial content analysis by focusing on identifying key objects rather than comprehensive text processing. By applying object detection selectively to the most relevant parts of the selected content, the system achieves improved search accuracy while minimizing additional processing time and computational overhead.
Data Source
AI summary
Disclosed implementations provide a streamlined, assisted search process for surfacing items from a database that enables guided exploratory searching. For example, a system may receive selected content from a client device and determine a first object and a second object for the selected content using a search converter. The system may generate first results by performing a first search of items in a database using the first object as a query, and generate second results by performing a second search of the items in the database using the second object as a query. The system may select a first set of the first results based on relevance of the first object to the selected content and a second set of the second results based on relevance of the second object to the selected content. The system may provide a combined search result including the first set and the second set.