{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11983489","patent":{"patent_number":"US-11983489","title":"Extractive summary generation by abstractive trained model","assignee":null,"inventors":[],"filing_date":"2023-06-23T00:00:00.000Z","publication_date":"2024-05-14T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06F","G06N","G06N","G06N","G06N"],"num_claims":24,"abstract":"A method and computer system are provided for generating a text summary. An input text is processed by a model that comprises a set of attention heads. The model is trained to generate abstractive summaries of text documents. A subset of the attention heads are identified. For each attention head in the subset, a portion is identified from the input text that is used to generate the abstractive summary. For each sentence of the input text, a fractional size is calculated for an intersection of the portion and the respective sentence relative to the respective sentence. A subset of the sentences is then determined, where the respective fractional size of each sentence in the subset meets a first threshold. An extractive summary of the input text is then generated from the subset of sentences."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Extractive summary generation by abstractive trained model","description":"A method and computer system are provided for generating a text summary. An input text is processed by a model that comprises a set of attention heads. The model is trained to generate abstractive sum","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11983489","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-11983489","citation_suggestion":"Patentable. \"Extractive summary generation by abstractive trained model\" (US-11983489). https://patentable.app/patents/US-11983489","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11983489","json":"https://patentable.app/api/llm-context/US-11983489","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T04:47:30.707Z"}