Page-based prediction of user intent
This Google patent describes a system that predicts a user’s intent based on the specific webpage they are currently visiting and the navigational path they took to get there. Once read more
Refined search with machine learning
This Google patent describes a system that improves computer-based searches by allowing users to select which search criteria from a previous search they want to prioritize, then delivering a refined read more
Configuring a large language model to convert natural language queries to structured queries
This Microsoft patent describes a system that uses large language models (LLMs) to automatically convert plain, everyday language search queries into structured, filter-based search queries. It does so by first read more
Reranking documents based on graph representations of the documents
This patent by Google describes a method for improving how a search or question-answering system ranks retrieved documents. When a user submits a query, the system retrieves a set of read more
Controlling Output Rankings in Generative Engines for LLM-based Search
This paper introduces CORE (Controlling Output Rankings in Generative Engines), a method designed to manipulate how large language models (LLMs) with search capabilities rank products and other items in their read more
Methods, systems, and media for modifying search results based on search query risk
This Google patent describes a system developed by Google for automatically demoting (lowering the ranking of) search results that are deemed low-quality or abusive. It works by calculating a “goodness read more
Identifying entity attribute relations
This Google patent describes a method and system developed by Google for identifying entity-attribute relationships within large text corpora. The system uses a classification model that combines multiple types of read more
Document entity extraction using machine-learned models
This Google patent describes a system for extracting specific information from documents and organizing it into a predefined format or “schema.” By using machine-learned models, the system takes a document read more
Methods and systems for extracting information from text
This Google patent describes methods and systems for extracting structured information from unstructured text. The core idea involves parsing text into a tree-like structure based on the grammatical roles of read more
Landing Page Optimization Using Machine-Learning Techniques
This Google patent describes a system where search engines use generative artificial intelligence to help users find specific information within a website without having to browse it manually. When a read more