Generating templated documents using machine learning techniques

    公开(公告)号:US10691998B2

    公开(公告)日:2020-06-23

    申请号:US15385804

    申请日:2016-12-20

    Applicant: Google Inc.

    Abstract: Systems and methods of predicting documentation associated with an encounter between attendees are provided. For instance, attendee data indicative of one or more previous visit notes associated with a first attendee can be obtained. The attendee data can be inputted into a machine-learned note prediction model that includes a neural network. The neural network can generate one or more context vectors descriptive of the attendee data. Data indicative of a predicted visit note can be received as output of the machine-learned note prediction model based at least in part on the context vectors. The predicted visit note can include a set of predicted information expected to be included in a subsequently generated visit note associated with the first attendee.

    GENERATING TEMPLATED DOCUMENTS USING MACHINE LEARNING TECHNIQUES

    公开(公告)号:US20180174043A1

    公开(公告)日:2018-06-21

    申请号:US15385804

    申请日:2016-12-20

    Applicant: Google Inc.

    Abstract: Systems and methods of predicting documentation associated with an encounter between attendees are provided. For instance, attendee data indicative of one or more previous visit notes associated with a first attendee can be obtained. The attendee data can be inputted into a machine-learned note prediction model that includes a neural network. The neural network can generate one or more context vectors descriptive of the attendee data. Data indicative of a predicted visit note can be received as output of the machine-learned note prediction model based at least in part on the context vectors. The predicted visit note can include a set of predicted information expected to be included in a subsequently generated visit note associated with the first attendee.

    Discovery of Incentive Effectiveness
    3.
    发明申请
    Discovery of Incentive Effectiveness 审中-公开
    发现激励有效性

    公开(公告)号:US20160125747A1

    公开(公告)日:2016-05-05

    申请号:US14531863

    申请日:2014-11-03

    Applicant: Google Inc.

    CPC classification number: G09B5/00 G06Q50/22 G09B19/00 G16H50/70

    Abstract: Some embodiments of the present disclosure provide a method that includes compiling, for each of a plurality of individuals, health-related data in a plurality of categories, determining that a given individual has a particular type of health-related data in a particular set of one or more categories, and based on the determination that the given individual has the particular type of health-related data in the particular set of one or more categories, transmitting from a server device to a client device associated with the given individual, over a communication network, a first instruction configured to cause the client device to present a first incentive designed to cause a change in the given individual's health-related data. The first incentive may make use of a first type of motivational foundation. The method may also include determining whether the first incentive was effective or ineffective.

    Abstract translation: 本公开的一些实施例提供了一种方法,其包括针对多个个体中的每一者编译多个类别中的健康相关数据,确定给定个体在特定组中具有特定类型的健康相关数据 一个或多个类别,并且基于确定给定个体在一个或多个类别的特定集合中具有特定类型的健康相关数据,从服务器设备发送到与给定个体相关联的客户端设备,通过 通信网络,第一指令,其被配置为使得客户端设备呈现旨在引起给定个人健康相关数据的改变的第一激励。 第一种激励可以利用第一种激励基础。 该方法还可以包括确定第一激励是有效还是无效。

Patent Agency Ranking