Method and system for automatically formulating an optimization problem using machine learning

A system for processing a natural language text description of an optimization problem, the system comprising one or more processors and one or more memories storing software instructions that, when executed by the one or more processors, cause the system to:

• receive the natural language text description of an optimization problem as a sequence of computer readable text entities, the sequence of computer readable text entities representative of a natural language speech that is spoken by a user or a natural language text inputted by the user via an input device;
• generate, based on the natural language text description, a text markup language intermediate representation (IR) of the optimization problem, the text markup language IR including an IR objective declaration that defines an objective for the optimization problem and a first IR constraint declaration that indicates a first constraint for the optimization problem, wherein the text markup language IR is generated by:
• generating, based on the natural language text description, an objective declaration prompt that includes information about the objective for the optimization problem and a first constraint declaration prompt that includes information about the first constraint for the optimization problem;
• providing the objective declaration prompt and the natural language text description to a transformer to generate the IR objective declaration;
• and
• providing the first constraint declaration prompt and the natural language text description to the transformer to generate the first IR constraint declaration;
• and
• generate, based on the text markup language IR, an algebraic modelling language (AML) formulation of the optimization problem, the AML formulation including an AML objective declaration that defines the objective for the optimization problem and a first AML constraint declaration that indicates the first constraint for the optimization problem.

A non-transitory computer readable medium storing instructions which, when executed by the one or more processors, cause the one or more processors to:

• receive a natural language text description of an optimization problem as a sequence of computer readable text entities, the sequence of computer readable text entities representative of a natural language speech that is spoken by a user or a natural language text inputted by the user via an input device;
• generate, based on the natural language text description, a text markup language intermediate representation (IR) of the optimization problem, the text markup language IR including an IR objective declaration that defines an objective for the optimization problem and a first IR constraint declaration that indicates a first constraint for the optimization problem, wherein the text markup language IR is generated by:
• generating, based on the natural language text description, an objective declaration prompt that includes information about the objective for the optimization problem and a first constraint declaration prompt that includes information about the first constraint for the optimization problem;
• providing the objective declaration prompt and the natural language text description to a transformer to generate the IR objective declaration;
• and
• providing the first constraint declaration prompt and the natural language text description to the transformer to generate the first IR constraint declaration;
• and
• generate, based on the text markup language IR, an algebraic modelling language (AML) formulation of the optimization problem, the AML formulation including an AML objective declaration that defines the objective for the optimization problem and a first AML constraint declaration that indicates the first constraint for the optimization problem.