中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

29 records (took 0.032 seconds)

    HYBRID INFERENCE SYSTEM FOR COGS REDUCTION
    1.
    发明申请
    HYBRID INFERENCE SYSTEM FOR COGS REDUCTION 有权

    公开(公告)号：US20240385814A1

    公开(公告)日：2024-11-21

    申请号：US18241244

    申请日：2023-09-01

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

    Inventor： SHENGYU FU ,  JIN WOO JANG ,  NEELAKANTAN SUNDARESAN ,  ALEXEY SVYATKOVSKIY

    IPC: G06F8/35 ,  G06F11/36

    Abstract: A hybrid inference system for a coding assistant utilizes a routing model to predict whether output generated by a large language model for a given prompt would be accepted by a user of the coding assistant. The routing model routes the prompt when the routing model indicates that the output generated by the large language model is likely to be accepted. The routing model routes the prompt to a local model when the output generated by the large language model is not likely to be accepted. The routing model is trained on the historical output generated by the large language model for various prompts and the acceptance or rejection of the output by users of the coding assistant.

    CODE COMPLETION WITH MACHINE LEARNING
    2.
    发明申请
    CODE COMPLETION WITH MACHINE LEARNING 有权

    公开(公告)号：US20210357193A9

    公开(公告)日：2021-11-18

    申请号：US16866433

    申请日：2020-05-04

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

    Inventor： SHENGYU FU ,  XIAOYU LIU ,  NEELAKANTAN SUNDARESAN

    IPC: G06F8/41 ,  G06N20/00 ,  G06K9/62

    Abstract: A code completion tool uses machine learning models to more precisely predict the likelihood of a method invocation completing a code fragment that follows one or more method invocations of different classes in a same document during program development. In one aspect, the machine learning model is a n-order Markov chain model that is trained on features that represent characteristics of the context of method invocations found in commonly-used programs from a sampled population. The machine learning model is implemented as a hash table contained a ranked order of hash values in descending order of probability of completing a partially-formed method invocation.

    CODE COMPLETION FOR OVERLOADED METHODS
    3.
    发明申请
    CODE COMPLETION FOR OVERLOADED METHODS 审中-公开

    公开(公告)号：US20190303109A1

    公开(公告)日：2019-10-03

    申请号：US16360008

    申请日：2019-03-21

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

    Inventor： SHENGYU FU ,  NEELAKANTAN SUNDARESAN ,  YING ZHAO

    IPC: G06F8/33 ,  G06N20/00 ,  G06K9/62 ,  G06F8/41 ,  G06F17/18

    Abstract: A code completion tool uses machine learning models to more precisely predict the likelihood of an invocation of a particular overloaded method completing a code fragment that follows one or more method invocations of a same class in a same document during program development. In one aspect, the machine learning model is a n-order Markov chain model that is trained on features that represent the method signatures of overloaded methods in order to generate ordered sequences of method signatures of overloaded method invocations.

    CODE REVIEW COMMENT GENERATION VIA RETRIEVAL-AUGMENTED TRANSFORMER WITH CHUNK CROSS- ATTENTION
    4.
    发明申请
    CODE REVIEW COMMENT GENERATION VIA RETRIEVAL-AUGMENTED TRANSFORMER WITH CHUNK CROSS- ATTENTION 有权

    公开(公告)号：US20250068419A1

    公开(公告)日：2025-02-27

    申请号：US18947617

    申请日：2024-11-14

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

    Inventor： SHENGYU FU ,  XIAOYU LIU ,  NEELAKANTAN SUNDARESAN ,  ALEXEY SVYATKOVSKIY

    IPC: G06F8/77 ,  G06F8/33

    Abstract: A retrieval-augmented neural transformer model with chunk cross-attention predicts a code review given a proposed source code change, represented as a code diff hunk, and a set of historical code review comments. The code diff hunk represents proposed edits to a source code snippet with its surrounding context that has not been changed. The historical code review comments are associated with code edits that are semantically similar to the proposed source code changes. The code diff hunk is partitioned into chunks which are used to find semantically similar historical code review comments. The set of historical code review comments is aggregated and used to guide the model in makings its predictions.

    CODE ADAPTATION THROUGH DEEP LEARNING
    6.
    发明公开
    CODE ADAPTATION THROUGH DEEP LEARNING 审中-公开

    公开(公告)号：US20230305824A1

    公开(公告)日：2023-09-28

    申请号：US17703169

    申请日：2022-03-24

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

    Inventor： MILTIADIS ALLAMANIS ,  SHENGYU FU ,  XIAOYU LIU ,  NEELAKANTAN SUNDARESAN ,  ALEXEY SVYATKOVSKIY

    IPC: G06F8/51 ,  G06N3/08

    CPC classification number: G06F8/51 ,  G06N3/08

    Abstract: A code adaptation mechanism automatically integrates the variable names of a pasted source code snippet into variable names defined in a pre-existing partial source code program. The variable names from the pasted source code snippet are replaced with anonymized values. A deep learning model predicts the most likely variable name from the pre-existing partial source code program to replace each anonymized value. The deep learning model is trained on numerous variable usage patterns from various source code programs to learn to predict the most likely mapping of an undefined variable name from the pasted source code snippet to a variable name in the pre-existing partial source code program thereby generating a syntactically and semantically correct program.

Patent Agency Ranking