WO2024261698 - DYNAMIC RESOURCE PREDICTION USING LARGE CODE LANGUAGE MODELS
National phase entry is expected:
Publication Number
WO/2024/261698
Publication Date
26.12.2024
International Application No.
PCT/IB2024/056053
International Filing Date
21.06.2024
Title **
[English]
DYNAMIC RESOURCE PREDICTION USING LARGE CODE LANGUAGE MODELS
[French]
PRÉDICTION DYNAMIQUE DE RESSOURCES À L'AIDE DE GRANDS MODÈLES DE LANGAGE DE CODE
Applicants **
AURORA LABS LTD.
Ehad Haam 54
6520216 Tel AViv, IL
Inventors
SAHAR, Carmit
c/o Aurora Labs Ltd.
Ehad Haam 54
6520216 Tel AViv, IL
YELLIN, Daniel
c/o Aurora Labs Ltd.
Ehad Haam 54
6520216 Tel AViv, IL
GANCHEV, Stojancho
c/o Aurora Labs Ltd.
Ehad Haam 54
6520216 Tel AViv, IL
FOX, Zohar
c/o Aurora Labs Ltd.
Ehad Haam 54
6520216 Tel AViv, IL
Priority Data
63/509,953
23.06.2023
US
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| * | |
International Searching Authority |
EPO
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Translation |
|
Recalculate
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing | 1861 | |
| EPO | Filing, Examination | 8679 | |
| Japan | Filing | 596 | |
| South Korea | Filing | 575 | |
| USA | Filing, Examination | 3760 |
Total: 15471 USD
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Abstract[English]
Disclosed herein are techniques for dynamically predicting resource usage for code changes. Techniques include identifying an element of programming code; identifying a programming code execution environment; accessing a code language processing model, wherein the code language processing model has been trained to associate programming code execution tasks with amounts of computing resource usage; and predicting, without requiring execution of the element of programming code, an amount of computing resource usage associated with an execution of the element of programming code in the programming code execution environment.[French]
L'invention concerne des techniques de prédiction dynamique d'utilisation de ressources pour des changements de code. Les techniques comprennent l'identification d'un élément de code de programmation; l'identification d'un environnement d'exécution de code de programmation; l'accès à un modèle de traitement de langage de code, le modèle de traitement de langage de code ayant été entraîné pour associer des tâches d'exécution de code de programmation à des quantités d'utilisation de ressources informatiques; et la prédiction, sans nécessiter l'exécution de l'élément de code de programmation, d'une quantité d'utilisation de ressources informatiques associée à une exécution de l'élément de code de programmation dans l'environnement d'exécution de code de programmation.