RATE-LIMITING BASED ON CARDINALITY COMPUTATION

    公开(公告)号:US20210075702A1

    公开(公告)日:2021-03-11

    申请号:US16562769

    申请日:2019-09-06

    Applicant: eBay Inc.

    Abstract: A cloud-based service records time-series data of a plurality of metrics from a plurality of tenants. The time-series data comprises a series of measures of a metric at sequential points in time. The time-series data is recorded in database tables in a manner that consumes more resources when the cardinality of the time-series data is high. When the cardinality of the data for the tenant is too high, the tenant is blacklisted and further data for the tenant is not stored. In addition to identifying incoming time-series data by the tenant that produced it, the data may also identify its type. In this case, the cardinality of each type of data may be determined and the types of data may be individually allowed or blacklisted for the tenant.

    Autonomous Item Generation
    322.
    发明申请

    公开(公告)号:US20210073833A1

    公开(公告)日:2021-03-11

    申请号:US17015822

    申请日:2020-09-09

    Applicant: eBay Inc.

    Abstract: An autonomous item generation system implements a trained machine learning model configured to output fabrication instructions for generating an item and metadata describing the item, automatically and independent of user input. Fabrication instructions output by the machine learning model are transmitted to a fabrication device for generating the item. The autonomous item generation system generates a listing for the item based on the metadata output by the machine learning model and publishes the listing to a virtual marketplace. Analytics data describing feedback for the item listing is used to generate training data for the machine learning model. The training data is input to the machine learning model, which causes the machine learning model to refine at least one control parameter according to a loss function that penalizes negative differences between predicted and observed feedback data for the item. The machine learning model with the refined parameter(s) is then used by the autonomous item generation system to generate fabrication instructions and metadata for an additional item.

    ANOMALY DETECTION BY CORRELATED METRICS

    公开(公告)号:US20210073658A1

    公开(公告)日:2021-03-11

    申请号:US16745822

    申请日:2020-01-17

    Applicant: eBay Inc.

    Abstract: A system is configured to detect a small, but meaningful, anomaly within one or more metrics associated with a platform being monitored. The system displays visuals of the metrics so that a user monitoring the platform can effectively notice a problem associated with the anomaly and take appropriate action to remediate the problem. Moreover, the system uses an ensemble of machine learning algorithms, with a multi-agent voting system, to detect the anomaly. Therefore, via the display of the visuals and the implementation of the machine learning algorithms, the techniques described herein provide an improved way of representing a large number of metrics (e.g., hundreds, thousands, etc.) being monitored for a platform. Moreover, the techniques are configured to expose actionable and useful information associated with the platform in a manner that can be effectively interpreted by a user.

    SYSTEMS AND METHODS TO SUPPLEMENT SEARCH RESULTS RETURNED TO A BUYER OF PARTS

    公开(公告)号:US20210065264A1

    公开(公告)日:2021-03-04

    申请号:US17082172

    申请日:2020-10-28

    Applicant: eBay Inc.

    Abstract: Methods and systems to supplement search results returned to a buyer of parts are described. The system receives a first query from a buyer. The first query includes keywords. The system identifies at least one compatibility keyword included in the keywords. The system further infers that the other keywords in the query are item information that describes a part that is sought for on a network-based marketplace. The system further infers the part has a compatibility based on the compatibility keywords. Next, the system searches a data storage device based on the item information and the compatibility keywords to identify a first listing as matched. Finally, the system presents the first listing describing the matched part. The matched part is indicated as compatible by supplementing the presentation of the first listing with the compatibility keywords from the first query.

    Enhanced search query suggestions
    325.
    发明授权

    公开(公告)号:US10936632B2

    公开(公告)日:2021-03-02

    申请号:US14818034

    申请日:2015-08-04

    Applicant: eBay Inc.

    Abstract: In various example embodiments, a system and method for enhancing autocomplete search suggestions are presented. The system receives a query portion with a token portion from a client device and generates a first search query suggestion set having a first order based on the token portion. The system accesses a token pool associated with the client device and generates a second search query suggestion set having a second order based on the token portion and the token pool. The system selects a first subset of search query suggestions and a second subset of search query suggestions. The system merges the first subset of search query suggestions and the second subset of search query suggestions into a third search query suggestion set, organizes the third search query suggestion set into a third order distinct from the first and second orders, and causes presentation of the third search query suggestion set.

    EFFICIENT GEO-FENCE DATA TRANSFER AND NOTIFICATIONS USING A TIME TO REACH VALUE

    公开(公告)号:US20210044922A1

    公开(公告)日:2021-02-11

    申请号:US17078399

    申请日:2020-10-23

    Applicant: eBay Inc.

    Abstract: A system and method for using time to reach determinations to improve the usability of geo-fences is disclosed. A computer system accesses a current location of a client system and identifies one or more nearby geo-fences. The computer system then calculates the time to reach each of these geo-fences. If the calculated time to reach value for a particular geo-fence is within the notification range associated with that geo-fence, then the computer system generates a notification to display to a user.

    AUTOMATIC TUNING OF MACHINE LEARNING PARAMETERS FOR NON-STATIONARY E-COMMERCE DATA

    公开(公告)号:US20210042811A1

    公开(公告)日:2021-02-11

    申请号:US16659092

    申请日:2019-10-21

    Applicant: eBay Inc.

    Abstract: Techniques are disclosed for automatically adjusting machine learning parameters in an e-commerce system. Hyperparameters of a machine learning component are tuned using a gradient estimator and a first training set representative of an e-commerce context. The machine learning component is trained using the tuned hyperparameters and the first training set. The hyperparameters are automatically re-tuned using the gradient estimator and a second training set representative of a changed e-commerce context. The machine learning component is re-trained using the re-tuned hyperparameters and the second training set.

    Systems and methods for transient local commerce search

    公开(公告)号:US10915944B2

    公开(公告)日:2021-02-09

    申请号:US16159938

    申请日:2018-10-15

    Applicant: eBay Inc.

    Abstract: A system, computer-readable storage medium storing at least one program, and computer-implemented method for a transient local commerce search service is provided. A search query including a user specified location and a user specified time period is received. One or more transient merchants temporarily located within the user specified location at least during the user specified time period are identified. A user interface displaying a map and an indicator of temporary location of the one or more transient merchants is displayed.

    Proactive re-routing of vehicles to control traffic flow

    公开(公告)号:US10914598B2

    公开(公告)日:2021-02-09

    申请号:US15965630

    申请日:2018-04-27

    Applicant: eBay Inc.

    Abstract: Aspects of the present disclosure include a navigation system and computer-implemented methods for proactively re-routing vehicles to control traffic flow. Consistent with some embodiments, the navigation system seeks to reduce traffic flow along primary navigation routes (e.g., routes with relatively short travel times) by re-routing vehicles to alternative navigation routes (e.g., routes with relatively longer travel times) using incentives. As an example, upon detecting a vehicle traveling along an alternative route instead of a primary route, the navigation system updates a data structure that represents a user account of a vehicle occupant to reflect an increased account balance. Consistent with some embodiments, the amount of value provided to an occupant of a vehicle traveling along an alternative routes may be obtained from user accounts of occupants of other vehicles that are traveling along a primary route.

    Detecting Selection of Disabled Inner Links Within Nested Content

    公开(公告)号:US20210034691A1

    公开(公告)日:2021-02-04

    申请号:US17076577

    申请日:2020-10-21

    Applicant: eBay Inc.

    Abstract: Detecting selection of disabled inner links within nested content techniques are described herein. In one or more implementations, a document comprising nested content is displayed on a display of a computing device. The nested content is obtained from a third-party source and includes one or more disabled inner links to respective target portions within the nested content. A disabled link service monitors an address associated with the third-party source of the nested content to detect an address change corresponding to a user selection of one of the disabled inner links within the nested content. Responsive to detecting the address change, a respective target portion of the nested content associated with the selected inner link is located by scanning the nested content. The document is then scrolled to cause display of the target portion of the nested content on the display of the computing device.

Patent Agency Ranking