DEEP REINFORCEMENT LEARNING-BASED MULTI-STEP QUESTION ANSWERING SYSTEMS

    公开(公告)号:US20200175046A1

    公开(公告)日:2020-06-04

    申请号:US16695641

    申请日:2019-11-26

    Inventor: Yu Wang Hongxia Jin

    Abstract: A method includes receiving a user query and performing, using at least one processor, multiple rounds of an answer generation process. Each round of the answer generation process includes selecting one of multiple functions to be performed based on an input state. The input state for each round includes an embedding of the user query in a feature space. The input state for at least one round also includes an embedding of information to be used to identify an answer to the user query in the feature space. Each round of the answer generation process also includes performing the selected function. The multiple functions include (i) an answer generation function that produces the answer to the user query and (ii) at least one additional function that updates the input state for a current round for use during a subsequent round. In addition, the method includes providing the answer to the user.

    MULTI-MODELS THAT UNDERSTAND NATURAL LANGUAGE PHRASES

    公开(公告)号:US20190332668A1

    公开(公告)日:2019-10-31

    申请号:US16390241

    申请日:2019-04-22

    Abstract: A system determines intent values based on an object in a received phrase, and detail values based on the object in the received phrase. The system determines intent state values based on the intent values and the detail values, and detail state values and an intent detail value based on the intent values and the detail values. The system determines other intent values based on the intent values and another object in the received phrase, and other detail values based on the detail values and the other object in the received phrase. The system determines a general intent value based on the other intent values, the other detail values, and the intent state values, and another intent detail value based on the other intent values, the other detail values, and the detail state values.

    SYSTEM AND METHOD FOR ACTIVE MACHINE LEARNING

    公开(公告)号:US20190318261A1

    公开(公告)日:2019-10-17

    申请号:US16370542

    申请日:2019-03-29

    Abstract: An electronic device for active learning includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to select one or more entries from a data set including unlabeled data based on a similarity between the one or more entries and labeled data. The at least one processor is further configured to cause the one or more entries to be labeled.

    METHOD TO LEARN PERSONALIZED INTENTS
    14.
    发明申请

    公开(公告)号:US20190266237A1

    公开(公告)日:2019-08-29

    申请号:US15904203

    申请日:2018-02-23

    Abstract: A method includes retrieving, at an electronic device, a first natural language (NL) input. An intent of the first NL input is undetermined by both a generic parser and a personal parser. A paraphrase of the first NL input is retrieved at the electronic device. An intent of the paraphrase of the first NL input is determined using at least one of: the generic parser, the personal parser, or a combination thereof. A new personal intent for the first NL input is generated based on the determined intent. The personal parser is trained using existing personal intents and the new personal intent.

    METHOD FOR AUTOMATING ACTIONS FOR AN ELECTRONIC DEVICE

    公开(公告)号:US20190065993A1

    公开(公告)日:2019-02-28

    申请号:US15967327

    申请日:2018-04-30

    Abstract: A method for action automation includes determining, using an electronic device, an action based on domain information. Activity patterns associated with the action are retrieved. For each activity pattern, a candidate action rule is determined. Each candidate action rule specifies one or more pre-conditions when the action occurs. One or more preferred candidate action rules are determined from multiple candidate action rules for automation of the action.

    SYSTEM AND METHOD TO ENABLE PRIVACY-PRESERVING REAL TIME SERVICES AGAINST INFERENCE ATTACKS

    公开(公告)号:US20170220817A1

    公开(公告)日:2017-08-03

    申请号:US15011368

    申请日:2016-01-29

    Abstract: One embodiment provides a method comprising receiving general private data identifying at least one type of privacy-sensitive data to protect, collecting at least one type of real-time data, and determining an inference privacy risk level associated with transmitting the at least one type of real-time data to a second device. The inference privacy risk level indicates a degree of risk of inferring the general private data from transmitting the at least one type of real-time data. The method further comprises distorting at least a portion of the at least one type of real-time data based on the inference privacy risk level before transmitting the at least one type of real-time data to the second device.

    Vectorial private equality testing
    18.
    发明授权
    Vectorial private equality testing 有权
    矢量私人平等测试

    公开(公告)号:US09390271B2

    公开(公告)日:2016-07-12

    申请号:US13907783

    申请日:2013-05-31

    CPC classification number: G06F21/60 G06F21/6254 H04L9/008

    Abstract: A system for equality testing, the system comprising a first client device including a first private data unit, a second client device including a second private data unit, and a server. The server receives a first obfuscated data unit corresponding to the first private data unit from the first client device, and a second obfuscated data unit corresponding to the second private data unit from the second client device. The server performs a vector calculation based on the first and second obfuscated data units to generate a combination of the first and second obfuscated data units. The server sends the combination to the first client device. The first client device is configured to determine whether the first private data unit is equal to the second private data unit based on the combination.

    Abstract translation: 一种用于相等测试的系统,所述系统包括包括第一专用数据单元的第一客户端设备,包括第二专用数据单元的第二客户端设备和服务器。 服务器从第一客户端设备接收对应于第一专用数据单元的第一混淆数据单元,以及与第二客户端设备对应的第二私有数据单元的第二混淆数据单元。 服务器基于第一和第二混淆数据单元执行向量计算,以产生第一和第二混淆数据单元的组合。 服务器将组合发送到第一个客户端设备。 第一客户端设备被配置为基于该组合来确定第一专用数据单元是否等于第二专用数据单元。

    ELECTRONIC SYSTEM WITH RISK PRESENTATION MECHANISM AND METHOD OF OPERATION THEREOF
    19.
    发明申请
    ELECTRONIC SYSTEM WITH RISK PRESENTATION MECHANISM AND METHOD OF OPERATION THEREOF 有权
    具有风险呈现机制的电子系统及其操作方法

    公开(公告)号:US20160188883A1

    公开(公告)日:2016-06-30

    申请号:US14586723

    申请日:2014-12-30

    CPC classification number: G06F21/577 G06F2221/033

    Abstract: An electronic system includes: a control unit configured to: calculating a risk score based on a permission requested by an application, generating a summary presentation based on the risk score for presenting a risk visualization of a privacy risk posed by an application, generating a subcategory presentation based on the risk score for presenting the risk visualization of the privacy risk posed to a device feature by the application, and a user interface, coupled to the control unit, configure to present a risk presentation including the summary presentation, the subcategory presentation, or a combination thereof for displaying on a device.

    Abstract translation: 电子系统包括:控制单元,被配置为:基于应用所请求的许可来计算风险分数,基于用于呈现由应用构成的隐私风险的风险可视化的风险分数生成概要呈现,生成子类别 基于用于呈现由应用对设备特征构成的隐私风险的风险可视化的风险评分的呈现,以及耦合到所述控制单元的用户界面,配置为呈现包括所述概要呈现,所述子类别呈现, 或其组合以在设备上显示。

    Computing system with privacy mechanism and method of operation thereof
    20.
    发明授权
    Computing system with privacy mechanism and method of operation thereof 有权
    具有隐私机制的计算系统及其操作方法

    公开(公告)号:US09355272B2

    公开(公告)日:2016-05-31

    申请号:US14010331

    申请日:2013-08-26

    Inventor: Hongxia Jin

    CPC classification number: G06F21/6245 G06Q10/00

    Abstract: A computing system includes a context module configured to determine a sharing context; an option module, coupled to the context module, configured to generate a sharing option for the sharing context based on a default set for the sharing context, a user's past sharing selection for the sharing context, and a personalization degree for the sharing context; and a privacy preference module, coupled to the option module, configured to estimate a user's privacy preference based on the sharing option.

    Abstract translation: 计算系统包括被配置为确定共享上下文的上下文模块; 耦合到上下文模块的选项模块被配置为基于用于共享上下文的默认集合,用于共享上下文的用户过去共享选择以及用于共享上下文的个性化度量来为共享上下文生成共享选项; 以及耦合到所述选项模块的被配置为基于所述共享选项来估计用户的隐私偏好的隐私偏好模块。

Patent Agency Ranking