Juan Lozano

US Patent:

20200125482, Apr 23, 2020

Filed:

Oct 18, 2019

Appl. No.:

16/657880

Inventors:

- San Francisco CA, US
Tarak Upadhyaya - San Francisco CA, US
Juan Lozano - San Francisco CA, US
Daniel Hung - San Francisco CA, US

International Classification:

G06F 11/36
G06N 3/04
G06F 8/36
G06F 8/33
G06F 8/41

Abstract:

A system and method may provide for identifying and executing code examples in displayed documents. In embodiments disclosed herein, a portion of executable code on a displayed page may be identified, modified, and executed. In one embodiment, a code example may be identified on a web page by a web browser extension, and a code example editing interface displayed to enable editing of the code example in the web browser. An execution environment for the code example may be generated, and the code example executed in a similar context as it was displayed in. For example, a code example may be executed in a web browser. Some embodiments disclosed relate to identifying parameters of a code execution environment, executing code examples remotely, and sharing code examples.

US Patent:

20200117446, Apr 16, 2020

Filed:

Oct 14, 2019

Appl. No.:

16/601402

Inventors:

- San Francisco CA, US
Tarak Upadhyaya - San Francisco CA, US
Juan Lozano - San Francisco CA, US
Daniel Hung - San Francisco CA, US

International Classification:

G06F 8/75
G06F 17/27
G06N 3/08
G06K 9/62
G06F 16/903

Abstract:

A system and method may provide assistance to programmers during programming to reduce the number of routine tasks that must be performed. In some aspects, the system may provide for searching a corpus of source code based on keyword or natural language search input. Search results including code entities and snippets of code that are described by the search input are then provided as search results. Some embodiments relate to using a neural network encoder to generate tensor embeddings of source code and related text in a joint tensor space. Relatedness between embeddings in this joint tensor space for text and associated source code is used in some embodiments to facilitate code search.

US Patent:

20200097261, Mar 26, 2020

Filed:

Sep 23, 2019

Appl. No.:

16/579750

Inventors:

- San Francisco CA, US
Tarak Upadhyaya - San Francisco CA, US
Juan Lozano - San Francisco CA, US
Daniel Hung - San Francisco CA, US

International Classification:

G06F 8/33
G06F 8/34
G06N 3/04
G06F 17/27

Abstract:

A system and method may provide assistance to programmers during programming to reduce the number of routine tasks that must be performed. In some aspects, the system may suggest one or more code snippets that comprise code completions. The code snippets may be single or multi-token. In some aspects, the system may provide predictive editing or predictive navigation, where the system may predict edits or navigation actions based on a programmer's actions. In some aspects, the system is based on machine learning methods and is trained on past actions of programmers in a code editor.

US Patent:

20200097389, Mar 26, 2020

Filed:

Sep 23, 2019

Appl. No.:

16/579753

Inventors:

- San Francisco CA, US
Tarak Upadhyaya - San Francisco CA, US
Juan Lozano - San Francisco CA, US
Daniel Hung - San Francisco CA, US

International Classification:

G06F 11/36
G06F 11/07
G06K 9/62
G06N 3/04

Abstract:

A system and method may provide assistance to programmer during programming to detect and predict the existence of errors in code and, in some aspects, predict fixes for erroneous code. In some aspects, the system and method may use artificial intelligence to learn based on edits made by programmers, by observing code changes that cause errors and code changes that fix errors, or based on other data.