知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

20 records (took 0.011 seconds)

    Ranking search results using machine learning based models
    1.
    发明授权
    Ranking search results using machine learning based models 有权

    公开(公告)号：US10606910B2

    公开(公告)日：2020-03-31

    申请号：US15730591

    申请日：2017-10-11

    Applicant: salesforce.com, inc.

    Inventor： Jayesh Govindarajan ,  Nicholas Beng Tek Geh ,  Francisco Borges ,  Ammar Haris

    IPC: G06F17/30 ,  G06F16/9535 ,  H04L29/08 ,  G06N20/00

    Abstract: An online system identifies and ranks records using multiple machine learning models in response to a search query. Therefore, the online system can provide selected records that are of the most relevance to a user of a client device that provided the search query. More specifically, the online system applies a first machine learning model that is of low complexity, such as a regression model. Therefore, the first machine learning model can quickly narrow down the large number of records of the online system to a first set of candidate records. The online system analyzes candidate records in the first set by applying a more complex, second machine learning model that more accurately determines records of interest for the user. In various embodiments, the online system can apply subsequent machine learning models of higher complexity for selecting and ranking records for provision to the client device.

    TRAINING A MACHINE LEARNING MODEL USING STRUCTURED DATA
    2.
    发明申请
    TRAINING A MACHINE LEARNING MODEL USING STRUCTURED DATA 有权

    公开(公告)号：US20220318669A1

    公开(公告)日：2022-10-06

    申请号：US17220567

    申请日：2021-04-01

    Applicant: salesforce.com, inc.

    Inventor： Zachary Alexander ,  Na Cheng ,  Jayesh Govindarajan

    IPC: G06N20/00 ,  G06K9/62

    Abstract: A computing system may receive a corpus of training data including a plurality of data entity schemas. A first data entity of a first set of data entities corresponding to a first data entity schema is associated with a topic characteristic based on a first set of attributes defined by the first data entity schema, and a first attribute of the first set of attributes is associated with a structural characteristic that is common across each of the first set of data entities. The system may identify a respective attribute type identifier for each attribute of the first set, generate an attribute embedding for each attribute using the attribute value and the identifier, generate an entity embedding based on each attribute embedding and parameterize the topic characteristic for each data entity and the structural characteristic for each attribute.

    Re-indexing query-independent document features for processing search queries
    4.
    发明授权
    Re-indexing query-independent document features for processing search queries 有权

    公开(公告)号：US10733241B2

    公开(公告)日：2020-08-04

    申请号：US15730574

    申请日：2017-10-11

    Applicant: salesforce.com, inc.

    Inventor： Jayesh Govindarajan ,  Ammar Haris ,  Nicholas Beng Tek Geh ,  Francisco Borges

    IPC: G06F17/00 ,  G06F16/93 ,  G06F16/248 ,  G06F16/958 ,  G06F16/332

    Abstract: An online system stores documents for access by users. The online system also stores query independent information about the documents. Query independent features include data that can be used to score or rank a document independent of any terms entered as a search query. The online system periodically determines whether the values of query independent features have changed, such as by checking activity logs. The online system updates records of query independent features accordingly, and sends information about the updated records to an enterprise search platform for re-indexing. When a user sends a search query to the online system, the enterprise search platform determines whether documents are relevant to the query based on the document contents and the query independent features associated with the documents.

    Predicting Interest for Items Based on Trend Information
    5.
    发明申请
    Predicting Interest for Items Based on Trend Information 审中-公开
    基于趋势信息预测项目的兴趣

    公开(公告)号：US20160232543A1

    公开(公告)日：2016-08-11

    申请号：US15014863

    申请日：2016-02-03

    Applicant: salesforce.com, Inc.

    Inventor： Jayesh Govindarajan ,  Naren Chittar

    IPC: G06Q30/02 ,  G06N5/04

    CPC classification number: G06Q30/0202

    Abstract: A predictive demand system receives a request from a client device to predict interest for an item. The predictive demand system identifies a description of the item included with the request. The predictive demand system identifies topics included in the description and calculates a topic score for each identified topic. If trend information is available for an identified topic, the topic score is determined based on the trend information of the topic. If trend information is not available for the identified topic, the topic score is determined based on trend information of related topics. The predictive demand system determines a predictive score for the item based on the topic scores of the topics included in the item description. The predictive score indicates predicted interest in the item.

    Abstract translation: 预测需求系统接收来自客户机设备的请求以预测项目的兴趣。 预测需求系统识别包含在请求中的项目的描述。 预测需求系统识别描述中包括的主题，并计算每个识别的主题的主题分数。 如果趋势信息可用于识别的主题，则基于主题的趋势信息来确定主题得分。 如果趋势信息对于识别的主题不可用，则主题得分基于相关主题的趋势信息确定。 预测需求系统基于项目描述中包括的主题的主题分数确定项目的预测分数。 预测分数表示该项目的预期兴趣。

    PREDICTING A TYPE OF A RECORD SEARCHED FOR BY A USER
    7.
    发明申请
    PREDICTING A TYPE OF A RECORD SEARCHED FOR BY A USER 审中-公开

    公开(公告)号：US20200233874A1

    公开(公告)日：2020-07-23

    申请号：US16815958

    申请日：2020-03-11

    Applicant: salesforce.com, inc.

    Inventor： Naren M. Chittar ,  Jayesh Govindarajan ,  Edgar Gerardo Velasco ,  Anuprit Kale ,  Francisco Borges ,  Guillaume Kempf ,  Marc Brette

    IPC: G06F16/2457 ,  G06N20/00 ,  G06N5/00 ,  G06F16/242 ,  G06N20/20

    Abstract: As part of providing the services to users, an online system stores multiple records that are accessible by users of the online system. When a user provides a search query, the online system extracts morphological and dictionary features from the query. The online system provides the extracted features to a machine learning model as an input. The machine learning model outputs a score for each potential entity type that indicates a likelihood that the search query is for a record associated with the entity type. The output from the machine learning model is used by the online system to select one or more entity types that the user is likely searching for. The online system searches the stored records based on the search query but limits the searching to records associated with at least one of the selected entity types.

    PREDICTING A TYPE OF A RECORD SEARCHED FOR BY A USER
    9.
    发明申请
    PREDICTING A TYPE OF A RECORD SEARCHED FOR BY A USER 审中-公开

    公开(公告)号：US20180293241A1

    公开(公告)日：2018-10-11

    申请号：US15481366

    申请日：2017-04-06

    Applicant: salesforce.com, inc.

    Inventor： Naren M. Chittar ,  Jayesh Govindarajan ,  Edgar Gerardo Velasco ,  Anuprit Kale ,  Francisco Borges ,  Guillaume Kempf ,  Marc Brette

    IPC: G06F17/30 ,  G06N99/00 ,  G06N7/00

    Abstract: As part of providing the services to users, an online system stores multiple records that are accessible by users of the online system. When a user provides a search query, the online system extracts morphological and dictionary features from the query. The online system provides the extracted features to a machine learning model as an input. The machine learning model outputs a score for each potential entity type that indicates a likelihood that the search query is for a record associated with the entity type. The output from the machine learning model is used by the online system to select one or more entity types that the user is likely searching for. The online system searches the stored records based on the search query but limits the searching to records associated with at least one of the selected entity types.

Patent Agency Ranking