18157185. Correcting Misspelled User Queries of in-Application Searches simplified abstract (Adobe Inc.)
Contents
Correcting Misspelled User Queries of in-Application Searches
Organization Name
Inventor(s)
Sanat Sharma of Austin TX (US)
Tracy Holloway King of Mountain View CA (US)
Ravindra Sadaphule of Cupertino CA (US)
Josep Valls Vargas of Santa Cruz CA (US)
Francois Guerin of San Francisco CA (US)
Chirag Arora of Union City CA (US)
Arpita Agrawal of San Jose CA (US)
Correcting Misspelled User Queries of in-Application Searches - A simplified explanation of the abstract
This abstract first appeared for US patent application 18157185 titled 'Correcting Misspelled User Queries of in-Application Searches
Simplified Explanation: The patent application describes techniques for correcting misspelled user queries in in-application searches using machine learning.
Key Features and Innovation:
- User query processing system corrects misspelled tokens in user queries.
- Candidate tokens are identified and ranked for replacement.
- Machine learning is used to generate rankings of candidate tokens.
- Selected token is output as the corrected query.
Potential Applications: This technology can be applied in various applications such as search engines, e-commerce platforms, and customer support systems.
Problems Solved:
- Improves user experience by correcting misspelled queries.
- Enhances search accuracy and efficiency.
- Reduces user frustration with search results.
Benefits:
- Increases user satisfaction with search functionality.
- Saves time by providing accurate search results.
- Enhances overall user experience within applications.
Commercial Applications: Potential commercial applications include search engine optimization tools, customer service chatbots, and e-commerce platforms.
Prior Art: Researchers can explore prior art related to machine learning in search query processing and natural language processing techniques.
Frequently Updated Research: Stay updated on advancements in machine learning algorithms for query processing and natural language understanding.
Questions about Misspelled User Queries: 1. How does machine learning improve the accuracy of correcting misspelled user queries? 2. What are the potential limitations of using machine learning for query correction?
Original Abstract Submitted
Techniques for correcting misspelled user queries of in-application searches are described as implemented by a user query processing system, which is configured to receive a user query entered via a search feature of an application, and identify a misspelled token in the user query. Candidate tokens to replace the misspelled token are identified from a collection of tokens, and a ranking of the candidate tokens is generated using machine learning. A token is selected from the candidate tokens based on the ranking, and the selected token is output by the user query processing system.
