公开(公告)号：EP3239853A1

公开(公告)日：2017-11-01

申请号：EP15880764.4

申请日：2015-02-06

申请人： Huawei Technologies Co. Ltd.

发明人： HUANG, Guowei ,  YAN, Youliang ,  ZHU, Wangbin

IPC分类号： G06F17/16

CPC分类号： H04L67/1023 ,  G06F9/505 ,  G06F9/5083 ,  G06F17/16 ,  G06F17/30215 ,  G06F17/30539 ,  G06F17/30958 ,  H04L47/823 ,  H04L67/1012 ,  H04L67/1078

摘要： The present invention discloses a data processing system, a computing node, and a data processing method. The data processing system includes a management node and a first class of computing nodes. The management node is configured to allocate first processing tasks to the first class of computing nodes; at least two computing nodes in the first class of computing nodes concurrently process the first processing tasks allocated by the management node; a computing node performs a combine combine2 operation and a reduce reduce2 operation on a data block M x and a data block V 1x , to obtain a first intermediate result; and the management node obtains a processing result for a to-be-processed dataset according to first intermediate results obtained by the first class of computing nodes. According to the data processing system provided by embodiments of the present invention, when a combine operation and a reduce operation are being performed on data blocks, there is no need to perform all combine operations before the reduce operation is performed; instead, the combine operation and the reduce operation are performed alternately, so that memory space occupied by computation can be reduced, and a computation time can be reduced.

摘要翻译： 本发明公开了一种数据处理系统，计算节点和数据处理方法。 数据处理系统包括管理节点和第一类计算节点。 管理节点被配置为将第一处理任务分配给第一类计算节点; 第一类计算节点中的至少两个计算节点同时处理由管理节点分配的第一处理任务; 计算节点对数据块Mx和数据块V1x进行组合combine2操作和reduce reduce2操作，得到第一中间结果; 管理节点根据第一类计算节点获取的第一中间结果获取待处理数据集的处理结果。 根据本发明实施例提供的数据处理系统，当对数据块进行组合操作和缩小操作时，不需要在执行缩小操作之前执行所有的组合操作; 相反，组合操作和缩减操作交替进行，从而可以减少计算占用的存储空间，并且可以减少计算时间。

公开(公告)号：EP4024270A1

公开(公告)日：2022-07-06

申请号：EP20863972.4

申请日：2020-09-10

申请人： HUAWEI TECHNOLOGIES CO., LTD.

发明人： WU, Xiaofei ,  HUANG, Fei ,  XU, Songcen ,  YAN, Youliang

IPC分类号： G06K9/00

摘要： A gesture recognition method, an electronic device, a computer-readable storage medium, and a chip, are provided, and relate to the field of artificial intelligence, and specifically, to a human-computer interaction technology in the field of computer vision. The gesture recognition method includes: obtaining an image stream, and determining, based on a plurality of consecutive frames of hand images in the image stream, whether a user makes a preparatory action; when the user makes the preparatory action, continuing to obtain an image stream, and determining a gesture action of the user based on a plurality of consecutive frames of hand images in the continuously obtained image stream; and next, further responding to the gesture action to implement gesture interaction with the user. In this application, the preparatory action is determined before gesture recognition is performed, so that erroneous recognition occurring in a gesture recognition process can be reduced, thereby improving a gesture recognition effect.

公开(公告)号：EP2940595B1

公开(公告)日：2020-02-12

申请号：EP13869846.9

申请日：2013-08-06

申请人： Huawei Technologies Co., Ltd.

发明人： LAM, Kingtin ,  ZHU, Wangbin ,  YAN, Youliang ,  WANG, Cho-li ,  SHI, Jinghao

IPC分类号： G06F12/1072 ,  G06F12/109 ,  G06F9/50

公开(公告)号：EP2908246B1

公开(公告)日：2018-03-21

申请号：EP13859349.6

申请日：2013-04-25

申请人： Huawei Technologies Co., Ltd.

发明人： LIU, Tanyi ,  YAN, Youliang

IPC分类号： G06F9/54

CPC分类号： G06F9/546 ,  G06F9/467 ,  G06F9/54

摘要： Embodiments of the present invention provide a method, an apparatus, and a system for mutual communication between processes of a many-core processor, and relate to the field of many-core operating systems, so as to increase the speed of reading a message body and enhance user experience. The method is executed by a target kernel Kernal, where the target kernel corresponds to a target processor core. The method includes: acquiring a message header of a message from a quick message channel QMC; executing a CPU pre-fetching command according to the message header, so that a message body that is in the message stored in a shared memory and corresponds to the message header is loaded to a cache cache that corresponds to the target processor core; and switching to a target process, so that the target process acquires the message body from the cache. The embodiments of the present invention apply to a scenario of mutual communication between processes of a many-core processor.

公开(公告)号：EP2672378B1

公开(公告)日：2017-12-20

申请号：EP11777222.8

申请日：2011-05-20

申请人： Huawei Technologies Co., Ltd.

发明人： JIN, Hongbo ,  YAN, Youliang ,  QI, Quan ,  CHEN, Shizhan

IPC分类号： G06F9/44 ,  G06F9/445

CPC分类号： G06F9/541 ,  G06F8/36 ,  G06F9/44521 ,  G06F9/44536

摘要： Embodiments of the present invention provide an open application programming interface selection method and device. The method includes: receiving an invocation request from a user, where the invocation request includes an OpenAPI function parameter; determining an OpenAPI equivalent set according to the OpenAPI function parameter; and selecting a target OpenAPI from multiple OpenAPIs according to a Qos attribute value that corresponds to each OpenAPI in the OpenAPI equivalent set. By adopting the embodiments of the present invention, an OpenAPI with better performance can be selected from numerous OpenAPIs with equivalent functions for a user, thereby improving the quality of service for the user.

公开(公告)号：EP3032413B1

公开(公告)日：2017-07-19

申请号：EP14841750.4

申请日：2014-09-03

申请人： Huawei Technologies Co., Ltd.

发明人： YAN, Youliang ,  ZHENG, Rongfu

IPC分类号： G06F9/45

CPC分类号： G06F8/40 ,  G06F9/445 ,  G06F9/5027 ,  G06F9/5044 ,  G06F11/3604

摘要： Embodiments of the present invention disclose a code generating method, a compiler, a scheduling method, an apparatus and a scheduling system. Code generated in the embodiments of the present invention is executable code applied to a heterogeneous system, and the heterogeneous system includes an accelerated processing unit and a central processing unit. The code generating method in the embodiments of the present invention includes: acquiring, by a compiler, resource information of the accelerated processing unit and resource information of the central processing unit so as to generate an operable platform list; identifying, by the compiler, accelerable code from first user code; embedding, by the compiler, a hook function and an exception handling function before the accelerable code to form second user code; and compiling, by the compiler, the second user code to obtain the executable code. The executable code generated in the embodiments of the present invention can automatically implement proper scheduling of processors during execution.

摘要翻译： 本发明的实施例公开了一种代码生成方法，编译器，调度方法，装置和调度系统。 本发明实施例中生成的代码为应用于异构系统的可执行代码，异构系统包括加速处理单元和中央处理单元。 本发明实施例的代码生成方法，包括：编译器获取加速处理单元的资源信息和中央处理器的资源信息，生成可运行平台列表; 由编译器从第一用户代码识别可加速代码; 由所述编译器在所述可加速代码之前嵌入挂钩函数和异常处理函数以形成第二用户代码; 以及由编译器编译第二用户代码以获得可执行代码。 在本发明的实施例中生成的可执行代码可以在执行期间自动实现处理器的适当调度。

公开(公告)号：EP3079077A1

公开(公告)日：2016-10-12

申请号：EP13900798.3

申请日：2013-12-30

申请人： Huawei Technologies Co., Ltd.

发明人： HUANG, Guowei ,  YAN, Youliang

IPC分类号： G06F17/30

CPC分类号： G06F17/30958 ,  G06F17/30486

摘要： A graph data query method and apparatus are disclosed, where the method includes: acquiring a partition number and a layer number of a query vertex; determining, based on the partition number and the layer number of the query vertex, a partition number and a layer number of a candidate vertex indicated by a query condition, and using them as a candidate partition number and a candidate layer number; foiming a candidate set by using a vertex whose partition number and layer number satisfy any group of a candidate partition number and a candidate layer number; and performing graph data query in the candidate set according to the query condition. By using the solution, graph data query efficiency is improved.

摘要翻译： 本发明公开了一种图数据查询方法和装置，该方法包括：获取查询顶点的分区号和层号; 根据查询顶点的分区号和层号，确定查询条件指示的候选顶点的分区号和层号，并将其用作候选分区号和候选层号; 通过使用其分区号和层号满足候选分区号和候选层号的任意组的顶点来形成候选集; 根据查询条件在候选集合中进行图形数据查询。 通过使用该解决方案，图数据查询效率得到提高。

公开(公告)号：EP2620872A1

公开(公告)日：2013-07-31

申请号：EP11777196.4

申请日：2011-05-17

申请人： Huawei Technologies Co., Ltd.

发明人： QIU, Zhihong ,  YAN, Youliang ,  ZHU, Wangbin ,  JIN, Hongbo ,  ZANG, Wenyang

IPC分类号： G06F9/46

CPC分类号： H04M3/5191 ,  G06F9/54 ,  G06F2209/541 ,  H04L65/1069 ,  H04L65/4061 ,  H04M7/0021

摘要： The present invention discloses a method for callback processing in telecommunication capability opening, a telecommunication capability opening server, a client, and a telecommunication capability opening service system. The method includes: receiving a telecommunication capability application programming interface (API) call request sent by a client, where the telecommunication capability API call request includes a callback information parameter; performing callback processing according to the telecommunication capability API call request, and generating a callback message according to the callback information parameter; and pushing the callback message to the client. The method may also include: initiating a telecommunication capability API call request to a telecommunication capability opening server, where the telecommunication capability API call request includes a callback information parameter; receiving a callback message pushed by the telecommunication capability opening server, and parsing the callback message; and determining, according to a parsing result, a function that callback processing needs, and calling the function.

摘要翻译： 本发明公开了一种电信能力开放中的回叫处理方法，电信能力开放服务器，客户端和电信能力开放服务系统。 该方法包括：接收由客户端发送的电信能力应用编程接口（API）呼叫请求，其中电信能力API呼叫请求包括回叫信息参数; 根据电信能力API呼叫请求执行回叫处理，根据回叫信息参数生成回叫消息; 并将回调消息推送到客户端。 该方法还可以包括：向电信能力开放服务器发起电信能力API呼叫请求，其中电信能力API呼叫请求包括回叫信息参数; 接收由电信能力开启服务器推送的回叫消息，并解析回叫消息; 以及根据解析结果确定回调处理所需的功能，并且调用该功能。

公开(公告)号：EP3980965A1

公开(公告)日：2022-04-13

申请号：EP19756261.4

申请日：2019-06-25

申请人： Huawei Technologies Co., Ltd.

发明人： YAN, Youliang ,  WANG, Tao ,  ZOU, Xueyi ,  SMIRNOV, Viktor Vladimirovich

IPC分类号： G06T1/20 ,  G06T11/00

公开(公告)号：EP3062229A1

公开(公告)日：2016-08-31

申请号：EP13900674.6

申请日：2013-12-31

申请人： Huawei Technologies Co., Ltd.

发明人： LAM, Kingtin ,  HUNG, Chit Ho Dominic ,  WANG, Cho-li ,  YAN, Youliang ,  ZHU, Wangbin

IPC分类号： G06F12/08

CPC分类号： G06F12/08 ,  G06F3/0604 ,  G06F3/0647 ,  G06F3/067 ,  G06F9/5033 ,  G06F9/5083 ,  G06F11/3037 ,  G06F11/3409 ,  G06F12/10 ,  G06F12/1009 ,  G06F2201/81 ,  G06F2212/1024

摘要： In embodiments of the present invention, an on-chip memory in a many-core system is partitioned, and according to a frequency at which a processor core set in each on-chip partition accesses a virtual memory page in virtual memory space that is shared among multiple processes that belong to a same application program, data corresponding to the virtual memory page is moved to an on-chip memory partition in which a processor core set whose access frequency is high is located, so that when the virtual memory page is subsequently accessed, a time delay caused by cross-partition access is reduced.