Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
CODE COMPLETION METHOD AND APPARATUS, AND RELATED DEVICE
Document Type and Number:
WIPO Patent Application WO/2022/126909
Kind Code:
A1
Abstract:
A code completion method and apparatus, a device, and a computer readable storage medium. The code completion method comprises: obtaining local datasets and an initial model parameter sent by an aggregation server (S101); training local models according to the initial model parameter and the local datasets to obtain local model parameters (S102); encrypting the local model parameters and then sending same to the aggregation server to allow the aggregation server to perform aggregation according to local model parameters sent from multiple participants to obtain global model parameters (S103); obtaining the global model parameters, and updating the local models according to the global model parameters and the local model parameters to obtain a trained code completion model (S104); and obtaining a code input by a user, and inputting the code into the code completion model to obtain a target code (S105). The problem of lack of data privacy protection because the dataset in the traditional code completion process is a public dataset is solved, a personalized code completion service can be provided, and a software development process is accelerated. The code completion method is implemented by means of the code completion apparatus, the device, and the computer readable storage medium.

Inventors:
WANG JIANZONG (CN)
LI ZEYUAN (CN)
HE ANXUN (CN)
Application Number:
PCT/CN2021/083488
Publication Date:
June 23, 2022
Filing Date:
March 29, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
PING AN TECH SHENZHEN CO LTD (CN)
International Classes:
G06F8/33; G06F8/41; G06N3/04; G06N3/08
Domestic Patent References:
WO2019219846A12019-11-21
Foreign References:
CN112527273A2021-03-19
CN110688121A2020-01-14
CN109614103A2019-04-12
CN108388425A2018-08-10
Other References:
KONEČNÝ JAKUB, MCMAHAN H. BRENDAN, YU FELIX X, RICHTÁRIK PETER, SURESH ANANDA THEERTHA, BACON DAVE: "Federated Learning: Strategies for Improving Communication Efficiency", ARXIV, 18 October 2016 (2016-10-18), pages 1 - 5, XP055944394
FANG LIU; GE LI; BOLIN WEI; XIN XIA; MING LI; ZHIYI FU; ZHI JIN: "A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning", ARXIV.ORG, 16 September 2019 (2019-09-16), pages 1 - 12, XP081477702
Attorney, Agent or Firm:
SCIHEAD IP LAW FIRM (CN)
Download PDF: