US 10,832,173 B1Granted

Cognitive software development

AssigneeInternational Business Machines Corporation

InventorsMarco Pistoia, Joseph Ligman, Stephen Wood, Shaohan Hu

Life of this patent

Estimating the term…

Loading patent…

Abstract

In an embodiment, a method of estimating the cost of a software project comprising receiving natural language software descriptions and electronic source code files for respective completed software projects; storing, in a computer memory, an input set of functional labels and size data extracted from each of the source code files, the functional labels corresponding to labels in a software development library; training a natural language processing model to output a project set of functional labels for one of the source code files; training a regression analysis model to output a project size for the one of the source code files; predicting, using the natural language understanding model, a proposal set of functional labels; predicting, using the regression analysis model, a proposal size; and using the proposal size to calculate a proposal cost; and preparing a software development proposal that includes a natural language proposed-software description and the proposal cost.

Claims20

Dependent claims

A computer implemented method, the method comprising:

receiving a natural language (NL) software description for a completed software project;
receiving an electronic source code file for the completed software project;
storing, in the computer memory, a first input set of functional labels assembled in a software development library;
storing, in a computer memory, a second input set of functional labels and size data extracted from the electronic source code file of the completed software project, each the second input set of functional labels corresponding to at least one of the labels in the first input set of functional labels, the completed software project having a corresponding NL software description;
training a NL processing model such that the model outputs a project set of functional labels for the source code file using the NL software description as an input sample corresponding to functional labels from the second input set of functional labels;
training a regression analysis model such that the model outputs a project size for the source code file using the project set of functional labels as an input sample corresponding to a project size from the size data;
predicting, using the NL processing model, a proposal set of functional labels;
predicting, using the regression analysis model, a proposal size;
calculating a proposal cost based at least in part on the proposal size;
and
preparing a software development proposal that includes a NL proposed-software description and the proposal cost.

8 more elements

A computer usable program product comprising a computer-readable storage device, and program instructions stored on the storage device, the stored program instructions comprising:

program instructions to receive, by one or more processors, a natural language (NL) software description for a completed software project;
program instructions to receive, by one or more processors, an electronic source code file for the completed software project;
program instructions to store, by one or more processors, in the computer memory, a first input set of functional labels assembled in a software development library;
program instructions to store, by one or more processors, in a computer memory, a second input set of functional labels and size data extracted from the electronic source code file of the completed software project, each the second input set of functional labels corresponding to at least one of the labels in the first input set of functional labels, the completed software project having a corresponding NL software description;
program instructions to train, by one or more processors, a NL processing model such that the model outputs a project set of functional labels for the source code file using the NL software description as an input sample corresponding to functional labels from the second input set of functional labels;
program instructions to train, by one or more processors, a regression analysis model such that the model outputs a project size for the source code file using the project set of functional labels as an input sample corresponding to a project size from the size data;
program instructions to predict, by one or more processors, using the NL processing model, a proposal set of functional labels;
program instructions to predict, by one or more processors, using the regression analysis model, a proposal size;
program instructions to calculate, by one or more processors, a proposal cost based at least in part on the proposal size;
and
program instructions to prepare, by one or more processors, a software development proposal that includes a NL proposed-software description and the proposal cost.

8 more elements

A computer system comprising a processor, a computer-readable memory, and a computer-readable storage device, and program instructions stored on the storage device for execution by the processor via the memory, the stored program instructions comprising:

program instructions to receive, by one or more processors, a natural language (NL) software description for a completed software project;
program instructions to receive, by one or more processors, an electronic source code file for the completed software project;
program instructions to store, by one or more processors, in the computer memory, a first input set of functional labels assembled in a software development library;
program instructions to store, by one or more processors, in a computer memory, a second input set of functional labels and size data extracted from the electronic source code file of the completed software project, each the second input set of functional labels corresponding to at least one of the labels in the first input set of functional labels, the completed software project having a corresponding NL software description;
program instructions to train, by one or more processors, a NL processing model such that the model outputs a project set of functional labels for the source code file using the NL software description as an input sample corresponding to functional labels from the second input set of functional labels;
program instructions to train, by one or more processors, a regression analysis model such that the model outputs a project size for the source code file using the project set of functional labels as an input sample corresponding to a project size from the size data;
program instructions to predict, by one or more processors, using the NL processing model, a proposal set of functional labels;
program instructions to predict, by one or more processors, using the regression analysis model, a proposal size;
program instructions to calculate, by one or more processors, a proposal cost based at least in part on the proposal size;
and
program instructions to prepare, by one or more processors, a software development proposal that includes a NL proposed-software description and the proposal cost.

8 more elements

Dependencies are inferred from the claim text.