Methods, systems, and computer readable media for network testing and collecting generative artificial intelligence training data
Methods, systems, and computer readable media for networking testing. In some examples, a system includes a test controller and a training data collector. The test controller is configured for receiving a test case including test case definition information defining a network test for a system under test (SUT); determining test system resource information for test system resources configured to execute the test case; and executing the test case on the SUT. The training data collector is configured for collecting at least a portion of the test case definition information; collecting SUT status information or SUT configuration information or both for the SUT; collecting metadata associated with the test case including at least one test context label; and processing collected data to produce artificial intelligence training data.
1 . A network test system for network testing, the network test system comprising:
a test controller implemented using at least one hardware or firmware processor and configured for:
receiving a test case including test case definition information defining a network test for a system under test (SUT);
determining test system resource information for test system resources configured to execute the test case; and
executing the test case on the SUT;
a generative artificial intelligence (GAI) model training data collector implemented as an integrated subsystem of the network test system, the GAI model training data collector being configured for:
collecting at least a portion of the test case definition information;
collecting SUT status information or SUT configuration information or both for the SUT;
collecting metadata associated with the test case including at least one test context label; and
processing the at least a portion of the test case definition information, test system resource information, SUT status information or SUT configuration information, and metadata to produce artificial intelligence (AI) training data for training a generative AI model to drive operation of a test system in testing a network device under test by transmitting packets to the device under test.
2 . The network test system of claim 1 , wherein collecting SUT status information or SUT configuration information or both comprises polling the SUT via an administrative interface.
3 . The network test system of claim 1 , wherein the test case definition information specifies one or more of: test traffic generators, transmit ports, receive ports, load modules, test environment topology details, test traffic types, test protocols, test traffic generation rates, test connection/teardown rates, packet sizes, and timeout settings.
4 . The network test system of claim 1 , wherein processing the at least a portion of the test case definition information, SUT status information or SUT configuration, and metadata to produce artificial intelligence training data comprises correlating and associating one or more natural language labels of the metadata with the portion of the test case definition information.
5 . The network test system of claim 1 , comprising the artificial intelligence training system, wherein the artificial intelligence training system is configured for using the artificial intelligence training data to train an artificial intelligence model configured for producing one or more test cases in response to a natural language query.
6 . The network test system of claim 1 , wherein the training data collector is configured for exporting the artificial intelligence training data to an artificial intelligence training system by exporting the artificial intelligence training data to an external system via an interface and a data communications network.
7 . The network test system of claim 1 , wherein the network test system is configured for training, using a federated learning architecture, an artificial intelligence model configured for producing one or more test cases in response to a natural language query.
8 . A method for network testing, the method comprising:
receiving, by a network test system, a test case including test case definition information defining a network test for a system under test (SUT);
determining, by the network test system, test system resource information for network test system resources configured to execute the test case;
executing, by the network test system, the test case on the SUT;
collecting, by a generative artificial intelligence (GAI) model training data collector implemented as an integrated subsystem of the network test system, at least a portion of the test case definition information;
collecting, by the GAI model training data collector, SUT status information or SUT configuration information or both for the SUT;
collecting, by the GAI model training data collector, metadata associated with the test case including at least one test context label; and
processing, by the GAI model training data collector, the at least a portion of the test case definition information, test system resource information, SUT status information or SUT configuration information, and metadata to produce artificial intelligence training data for training a generative AI model to drive operation of a test system in testing a network device under test by transmitting packets to the device under test.
9 . The method of claim 8 , wherein collecting SUT status information or SUT configuration information or both comprises polling the SUT via an administrative interface.
10 . The method of claim 8 , wherein the test case definition information specifies one or more of: test traffic generators, transmit ports, receive ports, load modules, test environment topology details, test traffic types, test protocols, test traffic generation rates, test connection/teardown rates, packet sizes, and timeout settings.
11 . The method of claim 8 , wherein processing the at least a portion of the test case definition information, SUT status information or SUT configuration, and metadata to produce artificial intelligence training data comprises correlating and associating one or more natural language labels of the metadata with the portion of the test case definition information.
12 . The method of claim 8 , comprising using the artificial intelligence training data to train an artificial intelligence model configured for producing one or more test cases in response to a natural language query.
13 . The method of claim 8 , comprising exporting the artificial intelligence training data to an artificial intelligence training system by exporting the artificial intelligence training data to an external system via an interface and a data communications network.
14 . The method of claim 8 , comprising training, using a federated learning architecture, an artificial intelligence model configured for producing one or more test cases in response to a natural language query.
15 . A non-transitory computer readable medium storing executable instructions that when executed by at least one processor of a computer control the computer to perform operations comprising:
receiving, by a network test system, a test case including test case definition information defining a network test for a system under test (SUT);
determining, by the network test system, test system resource information for test system resources configured to execute the test case;
executing, by the network test system, the test case on the SUT;
collecting, by a generative artificial intelligence (GAI) model training data collector implemented as an integrated subsystem of the network test system, at least a portion of the test case definition information;
collecting, by the GAI model training data collector, SUT status information or SUT configuration information or both for the SUT;
collecting, by the GAI model training data collector, metadata associated with the test case including at least one test context label; and
processing, by the GAI model training data collector, the at least a portion of the test case definition information, test system resource information, SUT status information or SUT configuration information, and metadata to produce artificial intelligence training data for training a generative AI model to drive operation of a test system in testing a network device under test by transmitting packets to the device under test.
16 . The non-transitory computer readable medium of claim 15 , wherein collecting SUT status information or SUT configuration information or both comprises polling the SUT via an administrative interface.
17 . The non-transitory computer readable medium of claim 15 , wherein the test case definition information specifies one or more of: test traffic generators, transmit ports, receive ports, load modules, test environment topology details, test traffic types, test protocols, test traffic generation rates, test connection/teardown rates, packet sizes, and timeout settings.
18 . The non-transitory computer readable medium of claim 15 , wherein processing the at least a portion of the test case definition information, SUT status information or SUT configuration, and metadata to produce artificial intelligence training data comprises correlating and associating one or more natural language labels of the metadata with the portion of the test case definition information.
19 . The non-transitory computer readable medium of claim 15 , comprising using the artificial intelligence training data to train an artificial intelligence model configured for producing one or more test cases in response to a natural language query.
20 . The non-transitory computer readable medium of claim 15 , comprising training, using a federated learning architecture, an artificial intelligence model configured for producing one or more test cases in response to a natural language query.