METHODS, SYSTEMS, ARTICLES OF MANUFACTURE AND APPARATUS TO IDENTIFY CODE SEMANTICS

Patent №

US 11,635,949

Granted

2023-04-25

Filed 2021

Owner

INTEL CORPORATION

Lab

AI components

4

ml · nlp · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

17555051

Methods, apparatus, systems, and articles of manufacture are disclosed to identify code semantics. An example apparatus includes processor circuitry to perform at least one of first, second, or third operations to instantiate validated repository parse circuitry to identify embedding values corresponding to validated code, syntax analysis circuitry to identify syntax information based on statistical recurrence metrics of the embedding values, bidirectional model circuitry to train a forward semantic model and a backward semantic model based on (a) semantic information corresponding to the syntax information and (b) divisional segmentation information corresponding to the syntax information, and target repository mining circuitry to generate target code model input fragments including learned syntactic information, learned semantic information, and learned divisional segmentation information, the target code model input fragments to facilitate inference with the forward semantic model and the backward semantic model.

Machine learningNatural languageKnowledge representationAI hardwareG06F 8/436G06F 11/3604G06F 8/447G06F 8/74G06F 8/75G06F 11/3608G06F 18/2132G06F 40/30+9 more

AI classification

Natural language1.00
Machine learning1.00
AI hardware1.00
Knowledge representation1.00
Vision0.32
Planning0.03
Evolutionary computation0.00
Speech0.00

Ownership

INTEL CORPORATION

assignment · 588770353

Assignors

GOTTSCHLICH, JUSTIN

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC