{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11941373","patent":{"patent_number":"US-11941373","title":"Code generation through reinforcement learning using code-quality rewards","assignee":null,"inventors":[],"filing_date":"2021-12-17T00:00:00.000Z","publication_date":"2024-03-26T00:00:00.000Z","cpc_codes":["G06F","G06N","G06F","G06F","G06F","G06N","G06N","G06N","G06N","G06N","G06N","G06N"],"num_claims":20,"abstract":"A deep learning model trained to learn to predict source code is tuned for a target source code generation task through reinforcement learning using a reward score that considers the quality of the source code predicted during the tuning process. The reward score is adjusted to consider code-quality factors and source code metrics. The code-quality factors account for the predicted source code having syntactic correctness, successful compilation, successful execution, successful invocation, readability, functional correctness, and coverage. The source code metrics generate a score based on how close the predicted source code is to a ground truth code."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Code generation through reinforcement learning using code-quality rewards","description":"A deep learning model trained to learn to predict source code is tuned for a target source code generation task through reinforcement learning using a reward score that considers the quality of the so","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11941373","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-11941373","citation_suggestion":"Patentable. \"Code generation through reinforcement learning using code-quality rewards\" (US-11941373). https://patentable.app/patents/US-11941373","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11941373","json":"https://patentable.app/api/llm-context/US-11941373","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T08:25:29.937Z"}