知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

5974 records (took 0.072 seconds)

    Actionable insights for performance of web products in database systems
    251.
    发明授权
    Actionable insights for performance of web products in database systems 有权

    公开(公告)号：US11281563B2

    公开(公告)日：2022-03-22

    申请号：US16773946

    申请日：2020-01-27

    Applicant: salesforce.com, inc.

    Inventor： Billy Ma ,  Jiten Oswal

    IPC: G06F11/36 ,  G06F3/0484 ,  G06F3/04847

    Abstract: In accordance with embodiments, there are provided mechanisms and methods for facilitating actionable insights for performance of web products in database systems according to one embodiment. In one embodiment and by way of example, a method includes dynamically running simulation of modifications to performance factors associated with a web product, and collecting actionable insights associated with the performance factors based on one or more of cost-benefit ratings of the performance factors, one or more delivery platforms, one or more device types. The method may further include recommending, based on the actionable insights, one or more adjustments to one or more of the performance factors to enhance performance of the web product, and facilitating, based on the recommendations, the one or more adjustments to one or more virtual knobs corresponding to the one or more performance factors to facilitate one or more modifications to one or more metrics to enhance the performance of the web product.

    EFFICIENT MONITORING OF NETWORK ACTIVITY IN A CLOUD COMPUTING ENVIRONMENT
    252.
    发明申请
    EFFICIENT MONITORING OF NETWORK ACTIVITY IN A CLOUD COMPUTING ENVIRONMENT 有权

    公开(公告)号：US20220086178A1

    公开(公告)日：2022-03-17

    申请号：US17018355

    申请日：2020-09-11

    Applicant: salesforce.com, inc.

    Inventor： Ajith Jayamohan ,  Wenbiao Xing

    IPC: H04L29/06 ,  H04L12/26 ,  G06F9/455

    Abstract: System and methods are described for efficient monitoring of network traffic in a public cloud computing environment. In one implementation, a method comprises: generating flow log records of network traffic in the public cloud computing environment; identifying a data packet that presents a potential security risk; identifying a captured data packet (PCAP) record corresponding to the identified data packet; and transmitting the PCAP record to a computing device for network traffic analysis.

    Hybrid training of deep networks
    253.
    发明授权
    Hybrid training of deep networks 有权

    公开(公告)号：US11276002B2

    公开(公告)日：2022-03-15

    申请号：US15926768

    申请日：2018-03-20

    Applicant: salesforce.com, inc.

    Inventor： Nitish Shirish Keskar ,  Richard Socher

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Hybrid training of deep networks includes a multi-layer neural network. The training includes setting a current learning algorithm for the multi-layer neural network to a first learning algorithm. The training further includes iteratively applying training data to the neural network, determining a gradient for parameters of the neural network based on the applying of the training data, updating the parameters based on the current learning algorithm, and determining whether the current learning algorithm should be switched to a second learning algorithm based on the updating. The training further includes, in response to the determining that the current learning algorithm should be switched to a second learning algorithm, changing the current learning algorithm to the second learning algorithm and initializing a learning rate of the second learning algorithm based on the gradient and a step used by the first learning algorithm to update the parameters of the neural network.

    SYSTEMS AND METHODS FOR MUTUAL INFORMATION BASED SELF-SUPERVISED LEARNING
    257.
    发明申请
    SYSTEMS AND METHODS FOR MUTUAL INFORMATION BASED SELF-SUPERVISED LEARNING 有权

    公开(公告)号：US20220067534A1

    公开(公告)日：2022-03-03

    申请号：US17006570

    申请日：2020-08-28

    Applicant: salesforce.com, inc.

    Inventor： Junwen Bai ,  Weiran Wang ,  Yingbo Zhou ,  Caiming Xiong

    IPC: G06N3/08 ,  G06K9/62 ,  G06N3/04

    Abstract: Embodiments described herein combine both masked reconstruction and predictive coding. Specifically, unlike contrastive learning, the mutual information between past states and future states are directly estimated. The context information can also be directly captured via shifted masked reconstruction—unlike standard masked reconstruction, the target reconstructed observations are shifted slightly towards the future to incorporate more predictability. The estimated mutual information and shifted masked reconstruction loss can then be combined as the loss function to update the neural model.

    SYSTEMS AND METHODS FOR PARTIALLY SUPERVISED LEARNING WITH MOMENTUM PROTOTYPES
    258.
    发明申请
    SYSTEMS AND METHODS FOR PARTIALLY SUPERVISED LEARNING WITH MOMENTUM PROTOTYPES 有权

    公开(公告)号：US20220067506A1

    公开(公告)日：2022-03-03

    申请号：US17005763

    申请日：2020-08-28

    Applicant: salesforce.com, inc.

    Inventor： Junnan Li ,  Chu Hong Hoi

    IPC: G06N3/08 ,  G06K9/62

    Abstract: A learning mechanism with partially-labeled web images is provided while correcting the noise labels during the learning. Specifically, the mechanism employs a momentum prototype that represents common characteristics of a specific class. One training objective is to minimize the difference between the normalized embedding of a training image sample and the momentum prototype of the corresponding class. Meanwhile, during the training process, the momentum prototype is used to generate a pseudo label for the training image sample, which can then be used to identify and remove out of distribution (OOD) samples to correct the noisy labels from the original partially-labeled training images. The momentum prototype for each class is in turn constantly updated based on the embeddings of new training samples and their pseudo labels.

    Intelligent Training Set Augmentation for Natural Language Processing Tasks
    259.
    发明申请
    Intelligent Training Set Augmentation for Natural Language Processing Tasks 有权

    公开(公告)号：US20220067277A1

    公开(公告)日：2022-03-03

    申请号：US17002562

    申请日：2020-08-25

    Applicant: salesforce.com, inc.

    Inventor： Shiva Kumar Pentyala ,  Mridul Gupta ,  Ankit Chadha ,  Indira Iyer ,  Richard Socher

    IPC: G06F40/253 ,  G06F40/30 ,  G10L15/19

    Abstract: A natural language processing system that trains task models for particular natural language tasks programmatically generates additional utterances for inclusion in the training set, based on the existing utterances in the training set and the existing state of a task model as generated from the original (non-augmented) training set. More specifically, the training augmentation module 220 identifies specific textual units of utterances and generates variants of the utterances based on those identified units. The identification is based on determined importances of the textual units to the output of the task model, as well as on task rules that correspond to the natural language task for which the task model is being generated. The generation of the additional utterances improves the quality of the task model without the expense of manual labeling of utterances for training set inclusion.

    WEB SERVICE TEST AND ANALYSIS PLATFORM
    260.
    发明申请
    WEB SERVICE TEST AND ANALYSIS PLATFORM 有权

    公开(公告)号：US20220066912A1

    公开(公告)日：2022-03-03

    申请号：US17521565

    申请日：2021-11-08

    Applicant: salesforce.com, inc.

    Inventor： Arjun Shetty ,  Sandeep Bansal

    IPC: G06F11/36

    Abstract: A method for testing a web service is disclosed, the method including testing, by a testing application executing on a client computing system, a web service running at least partially on a server computing system. The testing includes directing a web browser of the client computing system to simulate user interaction with the web service to perform a particular operation that includes a particular set of sub-operations. The directing includes issuing one or more requests to perform the particular set of sub-operations. The testing also includes recording test information based on responses received from the web service in response to performing the particular set of sub-operations. The test information includes latency information for at least one of the sub-operations of the particular set. The method also includes presenting, by the client computing system, a user interface having a graphical element depicting an analysis of the recorded test information.

Patent Agency Ranking