US 12,645,554 B2Granted

System and method for planning and executing test of electronic device

AssigneeKeysight Technologies, Inc.

InventorMaxim Pletner

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method for planning and executing a test of a DUT includes receiving a test description from a user via a GUI, where the test description identifies the DUT and an objective of the test; composing a prompt for querying a large language model (LLM) based on the test description, where LLM includes a trained machine learning algorithm; sending the prompt to the LLM via an API; determining, using the LLM, a test plan for executing the test to be performed in response to the prompt to achieve the objective of the test based on the test description and general testing information, where the test plan identifies a type of test, test instruments for performing the test, a test procedure using the instrument, and parameters of the DUT to be measured according to the test procedure; providing, via the GUI, the test plan to the user for testing the DUT.

Claims20

Dependent claims

A method for planning and executing a test of a device under test (DUT), the method comprising:

receiving a test description of the test from a user via a graphical user interface (GUI), wherein the test description identifies the DUT to be tested and an objective of the test;
composing a prompt for querying a large language model (LLM) based on the test description, wherein LLM comprises at least one previously trained machine learning algorithm, wherein composing the prompt comprises translating the test description into a preformatted prompt template that is compatible with the LLM;
sending the prompt to the LLM via an application programming interface (API);
determining, using the LLM, a test plan for executing the test to be performed on the DUT in response to the prompt to achieve the objective of the test based at least in part on the test description and general testing information, wherein the test plan identifies a type of test, a test configuration including identifying at least one test instrument for performing the test, and a test procedure for measuring at least one parameter of the DUT using the test configuration;
providing, via the GUI, the test plan to the user to be implemented for testing the DUT;
receiving, via at least one of the GUI or an interface with the at least one test instrument, at least one measurement of the at least one parameter of the DUT made during the test of the DUT according to the test plan;
composing a results prompt for the LLM based on the at least one measurement of the at least one parameter of the DUT including a measurement value of the at least one measurement;
sending the results prompt to the LLM via the API;
performing an analysis of the at least one measurement, using the LLM, in response to the prompt based at least in part on the general testing information;
generating, using the LLM, a test report providing the at least one measurement and the analysis of the at least one measurement, and suggesting additional testing of the DUT;
and
providing, via the GUI, the test report to the user.

9 more elements

A system for planning and executing a test of a device under test (DUT), the system comprising:

a graphical user interface (GUI) provided by a display, wherein the GUI is configured to receive a test description of the test including an identification of the DUT to be tested and an objective of the test;
at least one server configured to execute a large language model (LLM) comprising at least one previously trained machine learning algorithm;
and
at least one processor in communication with the GUI and the at least one server, wherein the at least one processor is configured to compose a prompt for the LLM based on the test description received from the GUI, wherein composing the prompt comprises translating the test description into a preformatted prompt template that is compatible with the LLM, and to send the prompt to the at least one server via an application programming interface (API),
wherein the LLM is trained to determine a test plan for executing the test to be performed on the DUT in response to the prompt to achieve the objective of the test based at least in part on the test description and general testing information, wherein the test plan identifies a type of test, a test configuration including identifying at least one test instrument for performing the test, and a test procedure for measuring at least one parameter of the DUT using the test configuration,
wherein the at least one processor receives the test plan from the LLM via the API, and provides the test plan to the user via the GUI to be implemented for testing the DUT,
wherein the at least one processor receives at least one measurement of the at least one parameter of the DUT made during the test of the DUT according to the test plan via at least one of the GUI or an interface with the at least one test instrument,
wherein the at least one processor composes a results prompt for the LLM based on the at least one measurement of the at least one parameter of the DUT including a measurement value of the at least one measurement, and sends the results prompt to the LLM via the API,
wherein the LLM performs an analysis of the at least one measurement in response to the results prompt based at least in part on the general testing information, and generates a test report providing the at least one measurement and the analysis of the at least one measurement, and suggesting additional testing of the DUT, and
wherein the at least one processor receives the test report from the LLM via the API, and provides the test report to the user via the GUI.

7 more elements

A non-transitory computer readable medium storing instructions for planning and executing a test of a device under test (DUT) that, when executed by at least one processor, cause the at least one processor to:

receive a test description of the test of the DUT from a graphical user interface (GUI), the test description including an identification of the DUT to be tested and an objective of the test;
compose a prompt for a large language model (LLM), comprising at least one previously trained machine learning algorithm, based on the test description, wherein composing the prompt comprises translating the test description into a preformatted prompt template that is compatible with the LLM;
provide the prompt to the LLM via an application programming interface (API);
determine a test plan for executing the test to be performed on the DUT using the LLM in response to the prompt to achieve the objective of the test based at least in part on the test description and general testing information, wherein the test plan identifies a type of test, a test configuration including identifying at least one test instrument for performing the test, and a test procedure for measuring at least one parameter of the DUT using the test configuration;
receive the test plan from the LLM via the API, and provide the test plan to the user via the GUI to be implemented for testing the DUT;
receive at least one measurement of the at least one parameter of the DUT made during the test of the DUT according to the test plan via at least one of the GUI or an interface with the at least one test instrument;
compose a results prompt for the LLM based on the at least one measurement of the at least one parameter of the DUT including a measurement value of the at least one measurement;
provide the results prompt to the LLM via the API;
perform an analysis of the at least one measurement using the LLM in response to the results prompt based at least in part on the general testing information;
generate a test report using the LLM providing the at least one measurement and the analysis of the at least one measurement, and suggesting additional testing of the DUT;
and
receive the test report from the LLM via the API, and provide the test report to the user via the GUI.

9 more elements

Dependencies are inferred from the claim text.