Google llc (20240202795). Search with Machine-Learned Model-generated Queries simplified abstract
Contents
Search with Machine-Learned Model-generated Queries
Organization Name
Inventor(s)
Harshit Kharbanda of Pleasanton CA (US)
Alice Au Quan of San Francisco CA (US)
Belinda Luna Zeng of Cupertino CA (US)
Christopher James Kelley of Orinda CA (US)
Jieming Yu of Jersey City NJ (US)
Minsang Choi of San Francisco CA (US)
Search with Machine-Learned Model-generated Queries - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240202795 titled 'Search with Machine-Learned Model-generated Queries
The abstract of the patent application describes systems and methods for searching using machine-learned model-generated outputs to generate theoretical datasets that can be matched to real-world examples.
- Selecting a plurality of terms to generate a prompt input for a dataset generation model.
- Processing the prompt input to generate a plurality of model-generated datasets.
- Receiving a selection of a particular model-generated database to query a real-world database.
Potential Applications: - Data analysis and research - Information retrieval and matching - Artificial intelligence and machine learning
Problems Solved: - Generating theoretical datasets for comparison - Improving search accuracy and relevance - Streamlining database querying processes
Benefits: - Enhanced data analysis capabilities - Increased efficiency in information retrieval - Improved decision-making based on matched datasets
Commercial Applications: Title: Advanced Data Matching Technology for Enhanced Decision-Making This technology can be used in industries such as finance, healthcare, and e-commerce for data analysis, customer profiling, and targeted marketing strategies.
Questions about the technology: 1. How does this technology improve the accuracy of dataset matching? 2. What are the potential limitations of using machine-learned model-generated outputs for searching?
Original Abstract Submitted
systems and methods for searching using machine-learned model-generated outputs can provide a user with a medium for generating a theoretical dataset that can then be matched to a real world example. the systems and methods can include selecting a plurality of terms, which can be utilized to generate a prompt input that can be processed by a dataset generation model to generate a plurality of model-generated datasets. a selection can then be received that selects a particular model-generated database to utilize to query a database.
