Dialogue- and machine learning-facilitated code development

Patent metadata

Field	Value
Publication number	US-12197895-B2
Application number	US-202117552592-A
Country	US
Kind code	B2
Filing date	Dec 16, 2021
Priority date	Dec 16, 2021
Publication date	Jan 14, 2025
Grant date	Jan 14, 2025

Abstract

One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to facilitating code development by predicting one or more code attributes and/or code portions for use in a project code to be written. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a dialogue component that generates a query based on a natural language request comprising a code-related attribute, and a prediction component that predicts another attribute or a code portion to satisfy the request. In an embodiment, an input dataset employed to support the influence mapping can comprise time-stamped tuple data comprising a state, an action and a reward. The code-related attribute can at least partially define a project code, of code to be written.

First claim

What is claimed is:

1. A system, comprising:
a memory that stores computer executable components; and
a processor that executes at least one of the computer executable components that:
provides, using a machine learning model and an interactive dialogue with a user developing a program, source code to the user to perform a functionality of a portion of the program, wherein the providing comprises iteratively, until the source code satisfying the functionality is provided:
receiving, from the user, a natural language (NL) input comprising one or more code-related attributes associated with the functionality;
generating, using the machine learning model, a query based on the natural language (NL) input;
receiving results from execution of the query;
identifying, using the machine learning model, whether the results comprise a code portion that satisfies the functionality;
in response to identifying that the results do not comprise any code portions that satisfy the functionality, presenting a clarification query to the user to elicit additional code-related attributes associated with the functionality; and
in response to identifying that the results comprise the code portion that satisfies the functionality, providing the code portion to the user.

2. The system of claim 1 , wherein the identifying that the results comprise the code portion that satisfies the functionality comprises:
identifying, using the machine learning model, a result of the results that comprises candidate source code that can be modified into the code portion that satisfies the functionality.

3. The system of claim 2 , wherein the identifying that the results comprise the code portion that satisfies the functionality further comprises:
modifying, using the machine learning model, based upon the one or more code-related attributes, the candidate source code into the code portion that satisfies the functionality.

4. The system of claim 1 , wherein the identifying that the results comprise the code portion that satisfies the functionality comprises:
identifying, using the machine learning model, the code portion based on metadata associated with one or more labels of the code portion.

5. The system of claim 1 , wherein the presenting the clarification query to the user comprises:
generating, using the machine learning model, the clarification query based on the one or more code-related attributes and the results from the execution of the query.

6. The system of claim 1 , wherein the presenting the clarification query to the user comprises:
generating, using the machine learning model, a dialogue plan comprising clarification queries for eliciting the additional code-related attributes associated with the functionality.

7. The system of claim 1 , wherein the at least one of the computer executable components further:
trains the machine learning model on one or more code languages.

8. A computer-implemented method, comprising:
providing, by a system operatively coupled to a processor, using a machine learning model and an interactive dialogue with a user developing a program, source code to the user to perform a functionality of a portion of the program, wherein the providing comprises iteratively, until the source code satisfying the functionality is provided:
receiving, from the user, a natural language (NL) input comprising one or more code-related attributes associated with the functionality;
generating, using the machine learning model, a query based on the natural language (NL) input;
receiving results from execution of the query;
identifying, using the machine learning model, whether the results comprise a code portion that satisfies the functionality;
in response to identifying that the results do not comprise any code portions that satisfy the functionality, presenting a clarification query to the user to elicit additional code-related attributes associated with the functionality; and
in response to identifying that the results comprise the code portion that satisfies the functionality, providing the code portion to the user.

9. The computer-implemented method of claim 8 , wherein the identifying that the results comprise the code portion that satisfies the functionality comprises:
identifying, using the machine learning model, a result of the results that comprises candidate source code that can be modified into the code portion that satisfies the functionality.

10. The computer-implemented method of claim 9 , wherein the identifying that the results comprise the code portion that satisfies the functionality further comprises:
modifying, using the machine learning model, based upon the one or more code-related attributes, the candidate source code into the code portion that satisfies the functionality.

11. The computer-implemented method of claim 8 , wherein the identifying that the results comprise the code portion that satisfies the functionality comprises:
identifying, using the machine learning model, the code portion based on metadata associated with one or more labels of the code portion.

12. The computer-implemented method of claim 8 , wherein the presenting the clarification query to the user comprises:
generating, using the machine learning model, a dialogue plan comprising clarification queries for eliciting the additional code-related attributes associated with the functionality.

13. The computer-implemented method of claim 8 , wherein the presenting the clarification query to the user comprises:
generating, using the machine learning model, the clarification query based on the one or more code-related attributes and the results from the execution of the query.

14. A computer program product facilitating a process to facilitate code development, the computer program product comprising a non-transitory computer readable medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
provide, using a machine learning model and an interactive dialogue with a user developing a program, source code to the user to perform a functionality of a portion of the program, wherein the providing comprises iteratively, until the source code satisfying the functionality is provided:
receiving, from the user, a natural language (NL) input comprising one or more code-related attributes associated with the functionality;
generating, using the machine learning model, a query based on the natural language (NL) input;
receiving results from execution of the query;
identifying, using the machine learning model, whether the results comprise a code portion that satisfies the functionality;
in response to identifying that the results do not comprise any code portions that satisfy the functionality, presenting a clarification query to the user to elicit additional code-related attributes associated with the functionality; and
in response to identifying that the results comprise the code portion that satisfies the functionality, providing the code portion to the user.

15. The computer program product of claim 14 , wherein the identifying that the results comprise the code portion that satisfies the functionality comprises:
identifying, using the machine learning model, a result of the results that comprises candidate source code that can be modified into the code portion that satisfies the functionality.

16. The computer program product of claim 15 , wherein the identifying that the results comprise the code portion that satisfies the functionality comprises:
modifying, using the machine learning model, based upon

Assignees

• IBM

Inventors

• Buesser Beat
• Hou Yufang
• Kishimoto Akihiro
• Marinescu Radu

Classifications

• G06F16/243 Primary

  Natural language query formulation · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F8/33 Primary

  Intelligent editors · CPC title

• G06F8/30

  Creation or generation of source code · CPC title