知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

23 records (took 0.021 seconds)

    DATA SHARDS FOR DISTRIBUTED PROCESSING
    11.
    发明申请
    DATA SHARDS FOR DISTRIBUTED PROCESSING 有权

    公开(公告)号：US20220244988A1

    公开(公告)日：2022-08-04

    申请号：US17163386

    申请日：2021-01-30

    Applicant: salesforce.com, inc.

    Inventor： Yuxi Zhang ,  Kexin Xie

    IPC: G06F9/48 ,  G06K9/62 ,  G06N20/00 ,  G06F9/38 ,  H04L9/06

    Abstract: Systems, devices, and techniques are disclosed for data shards for distributed processing. Data sets of data for users may be received. The data sets may belong to separate groups. User identifiers in the data sets may be hashed to generate hashed identifiers for the data sets. The user identifiers in the data sets may be replaced with the hashed identifiers. The data sets may be split to generate shards. The data sets may be split into the same number of shards. Merged shards may be generated by merging the shards using a separate running process for each of the merged shards. The merged shards may be generated using shards from more than one of the two or more data sets. An operation may be performed on all of the merged shards.

    AUTOMATIC RULE GENERATION FOR NEXT-ACTION RECOMMENDATION ENGINE
    12.
    发明申请
    AUTOMATIC RULE GENERATION FOR NEXT-ACTION RECOMMENDATION ENGINE 有权

    公开(公告)号：US20220198529A1

    公开(公告)日：2022-06-23

    申请号：US17563874

    申请日：2021-12-28

    Applicant: salesforce.com, inc.

    Inventor： Yuxi Zhang ,  Kexin Xie ,  Shrestha Basu Mallick ,  Darrell Grissen

    IPC: G06Q30/02

    Abstract: A system can recommend a next action for a user. A memory can store user data corresponding to the user and can include historic interaction points. A behavior pattern can be identified based on two or more interaction points stored in the user data. An intent of the user based on the behavior pattern can be identified. The intent can be based on a previous behavior pattern of another user. Several probabilities that the user will meet one or more objectives can be determined based on the intent. The probabilities can be scored using and used to assign a policy to the first user. A next action can be recommended based on the policy and executed with respect to the user. The outcome of the recommended next action can be stored to the user data.

    VISUALIZATION OF DYNAMIC EVENTS AND ANOMALY DETECTION
    13.
    发明申请
    VISUALIZATION OF DYNAMIC EVENTS AND ANOMALY DETECTION 有权

    公开(公告)号：US20210287246A1

    公开(公告)日：2021-09-16

    申请号：US16818016

    申请日：2020-03-13

    Applicant: salesforce.com, inc.

    Inventor： Yuxi Zhang ,  Kexin Xie

    IPC: G06Q30/02

    Abstract: Systems, device and techniques are disclosed for asynchronous remote call with undo data structures. A selection of a data point of a time series may be received. The data point may represent a measurement of an overall target metric for events at a point in time. A graph for the data point may be displayed on a display device. The display of the graph for the data point may include nodes for the events displayed with sizes based on an influence scores for the events, and an edge between each of the nodes and a hidden node, with a width that may represent an adjusted change in a measurement of a target metric for the event corresponding to the node, and a color of the edge may represent whether the adjusted change in the measurement of the target metric for the event is positive or negative.

    Automatic rule generation for next-action recommendation engine
    15.
    发明授权
    Automatic rule generation for next-action recommendation engine 有权

    公开(公告)号：US11900424B2

    公开(公告)日：2024-02-13

    申请号：US17563874

    申请日：2021-12-28

    Applicant: salesforce.com, inc.

    Inventor： Yuxi Zhang ,  Kexin Xie ,  Shrestha Basu Mallick ,  Darrell Grissen

    IPC: G06Q30/02 ,  G06Q30/0251 ,  G06Q30/0201

    CPC classification number: G06Q30/0281 ,  G06Q30/0201 ,  G06Q30/0271

    Abstract: A system can recommend a next action for a user. A memory can store user data corresponding to the user and can include historic interaction points. A behavior pattern can be identified based on two or more interaction points stored in the user data. An intent of the user based on the behavior pattern can be identified. The intent can be based on a previous behavior pattern of another user. Several probabilities that the user will meet one or more objectives can be determined based on the intent. The probabilities can be scored using and used to assign a policy to the first user. A next action can be recommended based on the policy and executed with respect to the user. The outcome of the recommended next action can be stored to the user data.

    DETERMINING A HYPERPARAMETER FOR INFLUENCING NON-LOCAL SAMPLES IN MACHINE LEARNING
    16.
    发明申请
    DETERMINING A HYPERPARAMETER FOR INFLUENCING NON-LOCAL SAMPLES IN MACHINE LEARNING 有权

    公开(公告)号：US20230004860A1

    公开(公告)日：2023-01-05

    申请号：US17366249

    申请日：2021-07-02

    Applicant: salesforce.com, inc.

    Inventor： Donglin Hu ,  Yuxi Zhang ,  Kexin Xie

    IPC: G06N20/00 ,  G06N7/00

    Abstract: Methods, computer readable media, and devices for determining a hyperparameter for influencing non-local samples in machine learning are disclosed. One method may include identifying a set of local samples associated with a first entity, identifying a set of non-local samples comprising samples associated with a plurality of entities other than the first entity, assigning a local sample weight to one or more samples of the set of local samples, determining a range of non-local sample weights, determining a range of hyperparameters based on the range of non-local sample weights, determining an optimized hyperparameter based on the range of hyperparameters, assigning an optimized non-local sample weight to one or more samples of the set of non-local samples, and generating a prediction using machine learning.

    Technologies for predicting personalized message send times
    17.
    发明授权
    Technologies for predicting personalized message send times 有权

    公开(公告)号：US11431663B2

    公开(公告)日：2022-08-30

    申请号：US16662718

    申请日：2019-10-24

    Applicant: salesforce.com, inc.

    Inventor： Yuxi Zhang ,  Kexin Xie

    IPC: G06F15/16 ,  H04L51/18 ,  G06F17/16 ,  G06N20/00 ,  H04L51/42

    Abstract: Disclosed embodiments are related to send time optimization technologies for sending messages to users. The send time optimization technologies provide personalized recommendations for sending messages to individual subscribers taking into account the delay and/or lag between the send time and the time when a subscriber engages with a sent message. A machine learning (ML) approach is used to predict the optimal send time to send messages to individual subscribers for improving message engagement. The personalized recommendations are based on unique characteristics of each user's engagement preferences and patterns, and deals with historical feedback that is generally incomplete and skewed towards a small set of send hours. The ML approach automatically discovers hidden factors underneath message and send time engagements. The ML model may be a two-layer non-linear matrix factorization model. Other embodiments may be described and/or claimed.

    Epsilon-closure for frequent pattern analysis
    19.
    发明授权
    Epsilon-closure for frequent pattern analysis 有权

    公开(公告)号：US11366821B2

    公开(公告)日：2022-06-21

    申请号：US16119960

    申请日：2018-08-31

    Applicant: salesforce.com, inc.

    Inventor： Yacov Salomon ,  Kexin Xie

    IPC: G06F16/2458 ,  G06F16/28 ,  G06F16/901

    Abstract: Methods, systems, and devices supporting epsilon (ε)-closure for frequent pattern (FP) analysis are described. Some database systems may analyze data sets to determine FPs. In some cases, the FP set may include a large number of semi-redundant patterns, resulting in significant memory or processing overhead. To reduce the redundancy of these patterns, the database system may implement pre-configured or dynamic threshold occurrence differences (e.g., ε values) to test against related patterns. For example, the database system may calculate the difference between the data objects covered by a sub-pattern and a super-pattern (e.g., where the super-pattern includes all the same data attributes of the sub-pattern, plus one additional attribute). This difference may be compared to a corresponding ε value, and if the difference is less than the ε value, the database system may remove one of the patterns (e.g., the sub-pattern) from the set of valid FPs to limit redundancy.

    Automatic rule generation for next-action recommendation engine
    20.
    发明授权
    Automatic rule generation for next-action recommendation engine 有权

    公开(公告)号：US11210712B2

    公开(公告)日：2021-12-28

    申请号：US16520556

    申请日：2019-07-24

    Applicant: salesforce.com, inc.

    Inventor： Yuxi Zhang ,  Kexin Xie ,  Shrestha Basu Mallick ,  Darrell Grissen

    IPC: G06Q30/02

    Abstract: A system can recommend a next action for a user. A memory can store user data corresponding to the user and can include historic interaction points. A behavior pattern can be identified based on two or more interaction points stored in the user data. An intent of the user based on the behavior pattern can be identified. The intent can be based on a previous behavior pattern of another user. Several probabilities that the user will meet one or more objectives can be determined based on the intent. The probabilities can be scored using and used to assign a policy to the first user. A next action can be recommended based on the policy and executed with respect to the user. The outcome of the recommended next action can be stored to the user data.

Patent Agency Ranking