Systems and methods to improve job posting structure and presentation

    公开(公告)号:US10997560B2

    公开(公告)日:2021-05-04

    申请号:US15389681

    申请日:2016-12-23

    Applicant: Google Inc.

    Abstract: The present disclosure provides systems and methods that improve job posting structure and presentation by, for example, classifying portions of job postings into informative sections. As an example, given a job posting, a computing system implementing aspects of the present disclosure can separate the job posting into multiple portions. After separation into portions, the computing system can classify each portion into the most plausible job-posting-specific section. For example, the computing system can include and implement a machine-learned classification model to classify the portions into the sections. Following classification, the computing system can modify the job posting based on the classification of the portions. In particular, the structure and/or presentation of the job posting can be improved based on the classification of the portions into the sections.

    Action suggestions for user-selected content

    公开(公告)号:US10970646B2

    公开(公告)日:2021-04-06

    申请号:US14872582

    申请日:2015-10-01

    Applicant: GOOGLE INC.

    Abstract: Systems and methods are provided for suggesting actions for selected text based on content displayed on a mobile device. An example method can include converting a selection made via a display device into a query, providing the query to an action suggestion model that is trained to predict an action given a query, each action being associated with a mobile application, receiving one or more predicted actions, and initiating display of the one or more predicted actions on the display device. Another example method can include identifying, from search records, queries where a website is highly ranked, the website being one of a plurality of websites in a mapping of websites to mobile applications. The method can also include generating positive training examples for an action suggestion model from the identified queries, and training the action suggestion model using the positive training examples.

    Applying social interaction-based policies to digital media content

    公开(公告)号:US10956945B1

    公开(公告)日:2021-03-23

    申请号:US14629203

    申请日:2015-02-23

    Applicant: Google Inc.

    Abstract: Social interaction-based policies are provided to a digital content owner and are applied to uploaded content matching digital content owned by the digital content owner. Social interaction-based policies enable the content owner to obtain various benefits to the content owned by the content owner within a video hosting site and outside the video hosting site. The benefits include using content owner's successful digital content to drive traffic or subscriptions to content owner's social interaction platforms and increase engagement with viewers of the digital content within and outside the video hosting site. The social interaction-based policies also enable content uploaders of digital content matching content owned by others to participate in sharing revenue generated from their uploaded videos subject to social interaction-based policies applied to the uploaded videos.

    High-throughput algorithm for multiversion concurrency control with globally synchronized time

    公开(公告)号:US10951706B2

    公开(公告)日:2021-03-16

    申请号:US15374722

    申请日:2016-12-09

    Applicant: Google Inc.

    Abstract: Throughput is preserved in a distributed system while maintaining concurrency by pushing a commit wait period to client commit paths and to future readers. As opposed to servers performing commit waits, the servers assign timestamps, which are used to ensure that causality is preserved. When a server executes a transaction that writes data to a distributed database, the server acquires a user-level lock, and assigns the transaction a timestamp equal to a current time plus an interval corresponding to bounds of uncertainty of clocks in the distributed system. After assigning the timestamp, the server releases the user-level lock. Any client devices, before performing a read of the written data, must wait until the assigned timestamp is in the past.

    Indicators for entities corresponding to search suggestions

    公开(公告)号:US10949468B2

    公开(公告)日:2021-03-16

    申请号:US15416344

    申请日:2017-01-26

    Applicant: GOOGLE INC.

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for dynamically generating indicators of entity locations on an electronic map corresponding, for example, to a suggested search request. In one aspect, a method includes providing an electronic map of a geographic area for display on a user interface, receiving a character string entered into the user interface, the character string representing a partial search query, determining a suggested search request based on the character string, and identifying an entity responsive to the suggested search request and a geographic location for the identified entity. An indicator identifying the geographic location of the entity is provided for display on the electronic map.

    Determining additional features for a task entry based on a user habit

    公开(公告)号:US10949448B1

    公开(公告)日:2021-03-16

    申请号:US15476261

    申请日:2017-03-31

    Applicant: Google Inc.

    Abstract: Methods and apparatus related to determining additional features for a user task entry of a user based on a user habit of the user. For example, one or more aspects of a user task entry of a user may be compared to one or more aspects of a user habit of the user to determine a correlation measure between the task entry and the user habit. If the correlation measure satisfies a threshold, one or more additional features of the user task entry may be determined based on the user habit. For example, the user habit may include one or more trigger indicators that indicate an actual entry or anticipated entry of the user into the user habit, and one or more of the trigger indicators may be utilized to determine task trigger indicators for the user task entry.

    Systems and methods of motion detection using dynamic thresholds and data filtering

    公开(公告)号:US10942196B2

    公开(公告)日:2021-03-09

    申请号:US15676564

    申请日:2017-08-14

    Applicant: Google Inc.

    Abstract: Systems and methods of detecting human movement with a sensor are provided, including generating a motion event signal in response to movement detected by the sensor, and generating a parameterized curve to represent the detected motion. The parameterized curve is fit to a predetermined window of sensor data captured by the sensor to filter the motion event signal. A noise magnitude estimate and a curve fit error is determined based on the fitted parameterized curve to the predetermined window. A detection threshold value is determined based on the curve fit error, a noise source signal estimate of known noise, and zero or more noise magnitudes from other sources. Human motion is determined by correlating a true motion event signal with human motion based on a comparison between a value of a point on the parameterized curve and the detection threshold value.

    Employing entropy information to facilitate determining similarity between content items

    公开(公告)号:US10929464B1

    公开(公告)日:2021-02-23

    申请号:US14613752

    申请日:2015-02-04

    Applicant: Google Inc.

    Inventor: Pawel Zuczek

    Abstract: Systems and techniques for generating and/or configuring a similarity heat map representative of similarities between two data sets are presented. The system can include an input component, a similarity component and a mapping component. The input component receives a first data set associated with a first media item and a second data set associated with a second media item. The similarity component computes similarity between a data value of the first data set and a corresponding data value of the second data set. The mapping component configures a data point of a similarity map to represent a match between the data value and the corresponding data value in response to a determination that information associated with the similarity does not match previously determined information associated with another similarity between another data value of the first data set and another corresponding data value of the second data set.

    Dynamically generating video context

    公开(公告)号:US10924441B1

    公开(公告)日:2021-02-16

    申请号:US14838201

    申请日:2015-08-27

    Applicant: Google Inc.

    Abstract: A computer-implemented method for modifying the presentation of URL included in a comment is provided herein. Implementations of the method include receiving a comment of a user of a first content-sharing platform. The comment is associated with a media item and includes a uniform resource locator (URL). Implementations of the method further include determining a context in which the comment is to be rendered and modifying presentation of the URL based on the determined context and the URL.

Patent Agency Ranking