{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11257486","patent":{"patent_number":"US-11257486","title":"Machine learning to propose actions in response to natural language questions","assignee":null,"inventors":[],"filing_date":"2020-02-28T00:00:00.000Z","publication_date":"2022-02-22T00:00:00.000Z","cpc_codes":["G06F","G10L","G06N","G06N","G06N","G10L","G10L","G10L","G10L","G06F","G06F","G10L","G10L"],"num_claims":7,"abstract":"A method of training machine learning models (MLMs). An issue vector is generated using an issue MLM to generate a first output including first embedded natural language issue statements. An action vector is generated using an action MLM to generate a second output including related embedded natural language action statements. The issue and action MLMs are of a same type. An inner product of the first and second output is calculated, forming a third output. The third output is processed according to a sigmoid gate process to predict whether a given issue statement and corresponding action statement relate to a same call, resulting in a fourth output. A loss function is calculated from the fourth output by comparing the fourth output to a known result. The issue MLM and the action MLM are modified using the loss function to obtain a trained issue MLM and a trained action MLM."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Machine learning to propose actions in response to natural language questions","description":"A method of training machine learning models (MLMs). An issue vector is generated using an issue MLM to generate a first output including first embedded natural language issue statements. An action ve","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11257486","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-11257486","citation_suggestion":"Patentable. \"Machine learning to propose actions in response to natural language questions\" (US-11257486). https://patentable.app/patents/US-11257486","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11257486","json":"https://patentable.app/api/llm-context/US-11257486","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T07:43:03.855Z"}