{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11461537","patent":{"patent_number":"US-11461537","title":"Systems and methods of data augmentation for pre-trained embeddings","assignee":null,"inventors":[],"filing_date":"2020-03-24T00:00:00.000Z","publication_date":"2022-10-04T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06F","G06F","G06F","G06N","G06N","G06N","G06N","G06V","G06V","G06V","G06V","G06N"],"num_claims":28,"abstract":"Systems and methods are provided for generating textual embeddings by tokenizing text data and generating vectors to be provided to a transformer system, where the textual embeddings are vector representations of semantic meanings of text that is part of the text data. The vectors may be averaged for every token of the generated textual embeddings and concatenating average output activations of two layers of the transformer system. Image embeddings may be generated with a convolutional neural network (CNN) from image data, wherein the image embeddings are vector representations of the images that are part of the image data. The textual embeddings and image embeddings may be combined to form combined embeddings to be provided to the transformer system."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Systems and methods of data augmentation for pre-trained embeddings","description":"Systems and methods are provided for generating textual embeddings by tokenizing text data and generating vectors to be provided to a transformer system, where the textual embeddings are vector repres","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11461537","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11461537","citation_suggestion":"Patentable. \"Systems and methods of data augmentation for pre-trained embeddings\" (US-11461537). https://patentable.app/patents/US-11461537","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11461537","json":"https://patentable.app/api/llm-context/US-11461537","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T17:38:57.879Z"}