{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-9727637","patent":{"patent_number":"US-9727637","title":"Retrieving text from a corpus of documents in an information handling system","assignee":null,"inventors":[],"filing_date":"2014-08-19T00:00:00.000Z","publication_date":"2017-08-08T00:00:00.000Z","cpc_codes":["G06F","G06F","G06N","G06N","G06N"],"num_claims":20,"abstract":"A mechanism is provided for retrieving candidate answers from a corpus of documents. The mechanism receives an input question for which an answer is sought. The mechanism extracts features of the input question based on a natural language processing. The mechanism executes a first search of the corpus of documents based on a first subset of the extracted features of the input question and an initial evaluation of a utility of the first subset of extracted features to generate a subset of documents. The mechanism executes a second search of a set of passages extracted from the subset of documents based on a second subset of the extracted features of the input question and a reevaluation of the utility of the second subset of extracted features thereby forming a subset of passages. The mechanism generates query results from the subset of passages matching from which candidate answers are identified."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Retrieving text from a corpus of documents in an information handling system","description":"A mechanism is provided for retrieving candidate answers from a corpus of documents. The mechanism receives an input question for which an answer is sought. The mechanism extracts features of the inpu","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-9727637","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-9727637","citation_suggestion":"Patentable. \"Retrieving text from a corpus of documents in an information handling system\" (US-9727637). https://patentable.app/patents/US-9727637","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-9727637","json":"https://patentable.app/api/llm-context/US-9727637","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-06-06T05:15:34.752Z"}