Neural Network Keyword Generation for Search Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines face challenges in determining the relevance of web pages to user queries due to subjective user interests and the complexity of objectively assessing the importance of web pages, leading to inefficiencies in keyword generation and search result relevance.
Innovation Solution
A neural network system is employed for keyword generation, where neurons are connected to represent words, documents, and concepts, allowing for context-based searching by regulating neuron activity and connections based on user input, thereby identifying relevant keywords and improving search result relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional search engines match search terms to web pages, then search results can be generated quickly, but the relevance and quality of returned pages deteriorates due to subjective user interests and inability to capture document context
Solution Approach 1:
The patent replaces conventional mechanical search term matching with a neural network system that processes document context. The neural network analyzes semantic relationships and generates keywords based on contextual understanding rather than simple string matching, improving relevance while managing complexity through automated learning
Solution Approach 2:
The patent introduces neural networks as an intermediary between search queries and document retrieval. The neural network acts as a mediator that processes user intent and document content, generating contextual keywords that bridge the gap between simple term matching and complex relevance assessment
2Reliability
If search engines attempt to sort hits by relevance score, then the most relevant pages can be positioned at the top, but determining appropriate scores becomes difficult due to subjective user interests and knowledge
Solution Approach 1:
The patent enables the neural network to automatically generate relevance scores and keywords without manual intervention. The system self-adjusts by learning from document contexts and user interactions, eliminating the need for complex manual scoring systems while maintaining accurate ranking
Solution Approach 2:
The patent transforms the scoring problem by changing from static relevance scores to dynamic keyword representations. The neural network generates contextual keywords that inherently encode relevance information, allowing documents to be ranked based on keyword匹配度 rather than complex scoring algorithms
3Quantity of substance
If the amount of information on the web grows rapidly, then more content is available to users, but locating desired information becomes more challenging
Solution Approach 1:
The patent extracts essential contextual information from documents using neural networks. Instead of requiring users to search through vast amounts of information, the system extracts and generates key contextual keywords that represent the essence of each document, making information location easier despite growing content volume
Solution Approach 2:
The patent segments document information into meaningful contextual keywords through neural network processing. By breaking down complex document content into discrete, relevant keywords, the system makes large volumes of information more searchable and manageable for users
Data Source
AI summary
A system for identifying keywords in search results includes a plurality of neurons connected as a neural network, the neurons being associated with words and documents. An activity regulator regulates a minimum and/or maximum number of neurons of the neural network that are excited at any given time. Means for displaying the neurons to a user and identifying the neurons that correspond to keywords can be provided. Means for changing positions of the neurons relative to each other based on input from the user can be provided. The change in position of one neuron changes the keywords. The input from the user can be dragging a neuron on a display device, or changing a relevance of two neurons relative to each other. The neural network can be excited by a query that comprises words selected by a user. The neural network can be a bidirectional network. The user can inhibit neurons of the neural network by indicating irrelevance of a document. The neural network can be excited by a query that identifies a document considered relevant by a user. The neural network can also include neurons that represent groups of words. The neural network can be excited by a query that identifies a plurality of documents considered relevant by a user, and can output keywords associated with the plurality of documents.