AUTOMATIC GENERATION OF DOCUMENTATION AND AGGREGATION OF COMMUNITY CONTENT

• US 20200133662A1
• Filed: 10/25/2019
• Published: 04/30/2020
• Est. Priority Date: 10/25/2018
• Status: Active Grant

• Current Assignee: Affirm, Inc. (Affirm Holdings, Inc.)
• Original Assignee: Manhattan Engineering Incorporated
• Inventors: Smith, Adam, Upadhyaya, Tarak, Lozano, Juan, Hung, Daniel
• Granted Patent: US 11,256,502 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 8/73 Program documentation
• CPC Class Codes: G06F 9/54 Interprogram communication
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 20/20 Ensemble learning
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A system and method may provide assistance to programmers related to the creation of documentation. In some aspects, the system may automatically generate documentation-related text in source code. In other aspects, the system may automatically detect the need for the programmer to edit long-from documentation when changes are detected in code. Moreover, the system may provide for the aggregation or creation of documentation content based on one or more data sources, such as by embedding links to those data sources into documentation. In some aspects, some components of the system are based on machine learning methods and are trained on collected data.

Claims

1. A computer-implemented method comprising:

retrieving a portion of source code, the portion of source code including a function;

automatically generating a docstring for the function using a machine learning model;

inserting the generated docstring in the source code.

2. The computer-implemented method of claim 1, further comprising analyzing one or more usages of the function in the source code to infer a return type of the function.

3. The computer-implemented method of claim 1, wherein the machine learning model is a neural network.

4. The computer-implemented method of claim 1, further comprising analyzing one or more usages of the function in the source code to infer a type of at least one parameter of the function.

5. The computer-implemented method of claim 1, further comprising:

detecting entry of a change in the source code to a return value or at least one parameter of the function;

updating the docstring based on the change in the source code to the return value or at least one parameter of the function.

6. The computer-implemented method of claim 1, further comprising:

using documentation or code from referenced entities to generate the docstring.

7. The computer-implemented method of claim 1, further comprising:

identifying an application programming interface (API) call in the function definition;

detecting a change to a parameter or return value of the API call;

updating the docstring based on the detected change to the parameter or return value of the API call.

8. A computer-implemented method comprising:

retrieving a portion of source code;

receiving edits at a cursor location in a code editor from a user;

updating source code at the cursor location in response to the edits received from the user;

detecting changes to one or more code entities in the portion of source code;

identifying documentation corresponding to the changed code entities;

automatically loading the documentation and displaying the documentation to the user;

receiving one or more edits from the user to the documentation;

storing the one or more edits from the user.

9. The computer-implemented method of claim 8, further comprising:

visually highlighting a plurality of portions of the documentation that are associated with the changed code entities.

10. The computer-implemented method of claim 8, wherein identifying documentation corresponding to the changed code entities comprises identifying links to the one or more changed code entities.

11. The computer-implemented method of claim 8, wherein identifying documentation corresponding to the changed code entities comprises performing named entity recognition.

12. The computer-implemented method of claim 8, wherein identifying documentation corresponding to the changed code entities comprises using a machine learning model to identify references to the changed code entities.

13. A computer-implemented method comprising:

retrieving a portion of source code;

receiving edits at a cursor location in a code editor from a user;

updating source code at the cursor location in response to the edits received from the user;

detecting changes to one or more code entities in the portion of source code;

identifying one or more code examples corresponding to the changed code entities;

automatically loading the code examples and displaying the code examples to the user;

receiving one or more edits from the user to the code examples;

storing the one or more edits from the user.

14. The computer-implemented method of claim 13, wherein identifying a code example corresponding to the changed code entities comprises detecting usage of the changed code entities in the code example.

15. A computer-implemented method comprising:

providing documentation for a code entity of a software package;

embedding in a section of the documentation for the code entity a plurality of references to online data sources, the online data sources including content related to the code entity;

displaying the documentation;

during display of the documentation, loading the content from the online data sources based on the plurality of references.

16. The computer-implemented method of claim 15, further comprising:

automatically updating the loaded content from the online data sources;

wherein at least one of the data sources is a set of code examples in a repository.

17. The computer-implemented method of claim 15, further comprising:

automatically updating the loaded content from the online data sources;

wherein the section of the documentation is a reference section.

18. The computer-implemented method of claim 15, wherein the section of the documentation is a list of frequently asked questions.

19. The computer-implemented method of claim 15, wherein the section of the documentation is a long-form documentation section.