Large language model analysis and grouping of software requirements to generate test cases for software testing

A method, comprising:

• receiving unstructured text requirements written in natural language, the unstructured text requirements describing software requirements for a software program, wherein the software requirements are interdependent and sequential, such that data produced by a first software requirement is an input to a second software requirement;
• identifying relationships between a plurality of different software requirements of the software requirements at least in part by:
• generating, using at least one large language model, structured text requirements from the unstructured text requirements;
• analyzing how data flows between the plurality of different software requirements by comparing inputs and outputs of the structured text requirements;
• analyzing how the plurality of different software requirements influence path and decision points to achieve functionality identified by the software requirements;
• and
• identifying dependencies between the plurality of different software requirements by comparing the inputs and the outputs of the structured text requirements;
• establishing a sequence for the plurality of different software requirements based on the relationships identified between the plurality of different software requirements of the software requirements;
• grouping the plurality of different software requirements together into at least one logical group of software requirements based on the sequence for the plurality of different software requirements of the software requirements and the relationships between the plurality of different software requirements;
• generating test cases based on the at least one logical group of software requirements for the sequence of the plurality of different software requirements;
• executing the software program using the test cases;
• and
• analyzing results of execution of the software program using the test cases to identify any defects in the software program.

A non-transitory computer-readable medium including a set of instructions that, when executed by at least one processor, cause the at least one processor to:

• receive unstructured text requirements written in natural language, the unstructured text requirements describing software requirements for a software program, wherein the software requirements are interdependent and sequential, such that data produced by a first software requirement is an input to a second software requirement;
• identify relationships between a plurality of different software requirements of the software requirements at least in part by:
• generating, using at least one large language model, structured text requirements from the unstructured text requirements;
• analyzing how data flows between the plurality of different software requirements by comparing inputs and outputs of the structured text requirements;
• analyzing how the plurality of different software requirements influence path and decision points to achieve functionality identified by the software requirements;
• and
• identifying dependencies between the plurality of different software requirements by comparing the inputs and the outputs of the structured text requirements;
• establish a sequence for the plurality of different software requirements based on the relationships identified between the plurality of different software requirements of the software requirements;
• group the plurality of different software requirements together into at least one logical group of software requirements based on the sequence for the plurality of different software requirements of the software requirements and the relationships between the plurality of different software requirements;
• generate test cases based on the at least one logical group of software requirements for the sequence for the plurality of different software requirements;
• execute the software program using the test cases;
• and
• analyze results of execution of the software program using the test cases to identify any defects in the software program.