Samsung patents AI system to auto-generate chip test scenarios
Samsung describes a method that uses AI models to automatically create test plans for system-on-chip hardware. The system builds a knowledge graph of use cases and constraints, then uses specialized AI agents to retrieve relevant data and optimize test paths. A human-in-the-loop verification agent validates the plan before final test scenarios are generated.
In the filing’s own words
A method and a system for generating test scenarios using artificial intelligence (AI) models are disclosed. The method comprises extracting configurable parameters and operable constraints from system-on-chip (SoC) information; aggregating use case information from a dataflow, the parameters, and the constraints; identifying a hardware-software coordination mechanism; and generating a knowledge graph by creating a use case profile. A retrieval augmented generation agent and a path optimization agent are instantiated to retrieve domain-specific information and determine traversal paths through the knowledge graph, respectively. A test plan is generated based on the use case profile, the domain-specific information, and the traversal paths. The test plan is validated by a human-in-the-loop (HITL) verification agent and iteratively refined based on validation feedback. Finally, a plurality of test scenarios is generated based on the validated and refined test plan.
What exactly they claim (claim 1)
1. A method for generating test scenarios, the method comprising: extracting configurable parameters and operable constraints from system information of a system-on-chip; aggregating use case information from a dataflow, the configurable parameters, and the operable constraints; identifying, based on one or more artificial intelligence (AI) models, a hardware-software coordination mechanism based on the aggregated use case information; generating, based on the one or more AI models, a knowledge graph, wherein generating the knowledge graph comprises creating a use case profile based on the aggregated use case information and the hardware-software coordination mechanism; instantiating at least a retrieval augmented generation agent configured to retrieve domain-specific information from the knowledge graph and a path optimization agent configured to determine traversal paths through the knowledge graph; generating, based on the one or more AI models, a test plan based on the use case profile, the domain-specific information, and the traversal paths associated with the knowledge graph; validating, based on the one or more AI models, the test plan by a human-in-the-loop verification agent; iteratively refining the test plan based on validation feedback from the human-in-the-loop verification agent; and generating, based on the one or more AI models, a plurality of test scenarios based on the validated and refined test plan.
Facts
- Company
- Samsung (SAMSUNG ELECTRONICS CO., LTD.)
- Official title
- METHOD AND SYSTEM FOR GENERATING TEST SCENARIOS USING ARTIFICIAL INTELLIGENCE MODELS
- Publication number
- US20260310589A1
- Application number
- 19638685
- Filed
- Apr 3, 2026
- Published
- Oct 8, 2026
- Inventors
- 6
- Claims
- 20
Classified under
G06F 11/3684 Physics & computingG06N 3/082 Physics & computingG06N 5/02 Physics & computingMore from Samsung in AI & software
- Samsung patents tool to erase objects from photos using AI Sep 24, 2026
- Samsung patents drawing objects into photos with AI Oct 15, 2026
- Samsung patents AI that creates personalized exercise videos Sep 10, 2026
- Samsung patents AI summaries for paused TV shows based on your viewing habits Sep 24, 2026
- Samsung patents turning chat conversations into image prompts Oct 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.