公开(公告)号：US10332013B2

公开(公告)日：2019-06-25

申请号：US14977991

申请日：2015-12-22

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhenhua Dong ,  Xiuqiang He ,  Gong Zhang ,  Guoxiang Cao

IPC: G06N5/04 ,  H04W4/50 ,  G06N20/00 ,  G06F16/2457 ,  G06F16/9535

Abstract: An application program recommending method may include acquiring current context information of the terminal, acquiring an amount of context information generated when the terminal runs a first application program, where the first application program refers to an application program stored in the terminal, determining a to-be-used recommending mechanism according to the amount of the context information generated when the terminal runs the first application program, and determining, according to the to-be-used recommending mechanism, a second application program corresponding to the current context information, where the second application program refers to a to-be-recommended application program; and displaying the second application program. In this way, accuracy of predicting an application program to be used by a user is improved. Moreover, when historical information of using an application program by the user is insufficient, a to-be-recommended application program can also be accurately determined.

公开(公告)号：US20160034968A1

公开(公告)日：2016-02-04

申请号：US14856230

申请日：2015-09-16

Applicant: Huawei Technologies Co., Ltd.

Inventor： Wenyuan Dai ,  Xiuqiang He ,  Guoxiang Cao

IPC: G06Q30/02 ,  G06F17/30

CPC classification number: G06Q30/0269 ,  G06F16/9535

Abstract: A method for determining a target user, includes: for any target service, acquiring historical data of multiple behavior objects that belong to a same service type as the target service; establishing a correspondence between user identifiers of different users and behavior object identifiers of different behavior objects of the same type; based on multiple established correspondences, constructing a data model that includes a user identifier and a behavior object identifier; using a value update rule to obtain, by means of calculation, a value of a probability that a user corresponding to each user identifier becomes a target user of the target service; and further using the value of the probability to select a target user of the target service, which can not only determine a target user group in a relatively open manner, but also effectively improve accuracy of and efficiency in determining a target user.

Abstract translation: 一种用于确定目标用户的方法，包括：对于任何目标服务，获取属于与目标服务相同的服务类型的多个行为对象的历史数据; 建立不同用户的用户标识符和相同类型的不同行为对象的行为对象标识符之间的对应关系; 基于多个建立的对应关系，构建包括用户标识符和行为对象标识符的数据模型; 使用值更新规则，通过计算获得与每个用户标识符对应的用户成为目标服务的目标用户的概率的值; 并且进一步使用概率的值来选择目标服务的目标用户，其不仅可以以相对开放的方式确定目标用户组，而且还有效地提高确定目标用户的准确性和效率。

公开(公告)号：US11830033B2

公开(公告)日：2023-11-28

申请号：US16198704

申请日：2018-11-21

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhirong Liu ,  Ruiming Tang ,  Zhenhua Dong ,  Xiuqiang He ,  Guoxiang Cao

IPC: G06Q30/02 ,  G06Q30/06 ,  G06F16/28 ,  G06Q30/0251 ,  G06Q30/0601

CPC classification number: G06Q30/0255 ,  G06F16/285 ,  G06Q30/0251 ,  G06Q30/0631

Abstract: The method includes: collecting historical operations of sample users for M items, and predicting a preference value of a target user for each of the M items according to historical operations of the sample users for each of the M items, collecting classification data of N to-be-recommended items, and classifying the N to-be-recommended items according to the classification data of the N to-be-recommended items, to obtain X themes, where each of the X themes includes at least one of the N to-be-recommended items, and the N to-be-recommended items are some or all of the M items; calculating a preference value of the target user for each of the X themes according to a preference value of the target user for a to-be-recommended item included in each of the X themes; and pushing a target theme to the target user.

公开(公告)号：US11734716B2

公开(公告)日：2023-08-22

申请号：US16198704

申请日：2018-11-21

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhirong Liu ,  Ruiming Tang ,  Zhenhua Dong ,  Xiuqiang He ,  Guoxiang Cao

IPC: G06Q30/02 ,  G06Q30/06 ,  G06F16/28 ,  G06Q30/0251 ,  G06Q30/0601

CPC classification number: G06Q30/0255 ,  G06F16/285 ,  G06Q30/0251 ,  G06Q30/0631

Abstract: The method includes: collecting historical operations of sample users for M items, and predicting a preference value of a target user for each of the M items according to historical operations of the sample users for each of the M items, collecting classification data of N to-be-recommended items, and classifying the N to-be-recommended items according to the classification data of the N to-be-recommended items, to obtain X themes, where each of the X themes includes at least one of the N to-be-recommended items, and the N to-be-recommended items are some or all of the M items; calculating a preference value of the target user for each of the X themes according to a preference value of the target user for a to-be-recommended item included in each of the X themes; and pushing a target theme to the target user.

公开(公告)号：US09819564B2

公开(公告)日：2017-11-14

申请号：US14249035

申请日：2014-04-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Gong Zhang ,  Guoxiang Cao

IPC: G06F1/00 ,  H04L12/26 ,  G06F11/30 ,  G06Q10/10 ,  H04W52/02

CPC classification number: H04L43/0876 ,  G06F11/3096 ,  G06Q10/1091 ,  H04M2250/10 ,  H04M2250/12 ,  H04W52/0274 ,  Y02D70/142 ,  Y02D70/164

Abstract: The present invention provide a terminal device, including: at least one sensor, a data processing unit, a memory, a CPU, and a storage, where the sensor is configured to sense a corresponding measured object and generate corresponding sensing data; and the data processing unit is configured to collect the sensing data jointly with the CPU in a mutually complementary manner, store the collected sensing data in the memory, perform feature extraction on the sensing data stored in the memory, and store extracted feature data in the storage, where the mutually complementary manner refers to that, when one of the data processing unit and the CPU is in a working state, the other is in a dormant state. The terminal device provided by the embodiments of the present invention can improve a utilization rate of the CPU.

公开(公告)号：US20160110649A1

公开(公告)日：2016-04-21

申请号：US14977991

申请日：2015-12-22

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhenhua Dong ,  Xiuqiang He ,  Gong Zhang ,  Guoxiang Cao

IPC: G06N5/04 ,  G06N99/00 ,  G06F17/30

CPC classification number: G06N5/046 ,  G06F16/24575 ,  G06F16/9535 ,  G06N20/00 ,  H04W4/50

Abstract: An application program recommending method may include acquiring current context information of the terminal, acquiring an amount of context information generated when the terminal runs a first application program, where the first application program refers to an application program stored in the terminal, determining a to-be-used recommending mechanism according to the amount of the context information generated when the terminal runs the first application program, and determining, according to the to-be-used recommending mechanism, a second application program corresponding to the current context information, where the second application program refers to a to-be-recommended application program; and displaying the second application program. In this way, accuracy of predicting an application program to be used by a user is improved. Moreover, when historical information of using an application program by the user is insufficient, a to-be-recommended application program can also be accurately determined.

Abstract translation: 应用程序推荐方法可以包括获取终端的当前上下文信息，获取当终端运行第一应用程序时产生的上下文信息的量，其中第一应用程序参考存储在终端中的应用程序， 根据当终端运行第一应用程序时生成的上下文信息的量，根据所使用的推荐机制确定与当前上下文信息相对应的第二应用程序，其中， 第二个应用程序是指一个要推荐的应用程序; 并显示第二应用程序。 以这种方式，提高了用户使用的预测应用程序的精度。 此外，当使用用户的应用程序的历史信息不足时，还可以准确地确定要推荐的应用程序。