Search Suggestion System Using Entity Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face inconvenience when searching for information related to previously viewed web pages, as they must retype or copy and paste content, especially if it is in a foreign language or lengthy, which can be cumbersome.
Innovation Solution
A computer-implemented method and system that provides search query suggestions based on previously viewed content by identifying entities and associated actions within the content, allowing users to select suggested terms and actions directly from a search field without manual reentry.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users manually retype or copy and paste content from previously viewed web pages into the search query box, then the search query can be entered, but the process becomes cumbersome and time-consuming
Solution Approach 1:
The system performs preliminary actions by automatically capturing and storing information about previously viewed web pages (URLs, titles, content) in the background. When a user activates the search field, these pre-captured data are immediately processed to generate search suggestions, eliminating the need for users to manually retype or copy content.
Solution Approach 2:
The system serves itself by automatically generating search suggestions from previously viewed content without requiring user intervention. The browser monitors its own activity, stores viewed page information, and autonomously generates relevant search queries based on that data, making the search process self-serve the user.
2Ease of operation
If the search system analyzes previously viewed content to identify entities and generate suggestions, then search convenience is improved, but system complexity increases
Solution Approach 1:
The browser system performs multiple functions: it acts as a web browser, automatically monitors and stores viewed page information, performs entity recognition and classification on the stored content, and generates search suggestions. This multi-functionality consolidates what could be separate complex systems into a single integrated solution.
Solution Approach 2:
The patent introduces an intermediary component that sits between the user and the search engine. This intermediary automatically captures web page information, processes it to identify entities and their types, and formulates search queries. This mediator handles the complexity of content analysis and entity recognition, shielding the user from these complex operations while providing convenient search suggestions.
Data Source
AI summary
Computer-implemented methods for providing suggestions for a search based on previously viewed content are provided. In one aspect, a method includes receiving information on previously viewed content, and receiving a request to enter a query into a search field subsequent to receiving the information on the previously viewed content. The method also includes identifying, based on the content, at least one entity referred to in the content, and providing an identifier of the at least one entity for display with the search field. Systems and machine-readable storage media are also provided.