Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Training a classification model using labeled training data that does not overlap with target classifications for the classification model

Training a classification model using labeled training data that does not overlap with target classifications for the classification model

US Patent 11947632 · Granted Apr 2, 2024

Estimated economic value: $31,786,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Using language model to generate recipe with refined content2025
Machine learning model for click through rate predication using three vector rep2025
Using unsupervised clustering and language model to normalize attribute tuples o2025
Using unsupervised clustering and language model to normalize attribute tuples o2025
Clustering data describing interactions performed after receipt of a query based2025
Non-transitory computer-readable medium, and method for context-based content-sc2025
Machine learned models for search and recommendations2025
Accounting for item attributes when selecting items satisfying a query based on 2025
Training a machine learned model to determine relevance of items to a query usin2025
Picking sequence optimization within a warehouse for an item list2025
Weakly supervised extraction of attributes from unstructured data to generate tr2025
Weakly supervised extraction of attributes from unstructured data to generate tr2025