-
公开(公告)号：US10542519B2
公开(公告)日：2020-01-21
申请号：US16136827
申请日：2018-09-20
Applicant: Huawei Technologies Co., Ltd.
Inventor： Mingxuan Yuan , Jia Zeng , Xialiang Tong
Abstract: A terminal positioning method and a network device, where the network device obtains radio signal sampling information of a first terminal at a current moment. The first terminal is any terminal in a target region, and the target region is a preset geographic region. The network device obtains position information of the first terminal at the current moment by prediction based on the radio signal sampling information of the first terminal at the current moment and a predictive model of the target region. The predictive model is obtained by extensive data training in the target region, has relatively strong error tolerance and error-correction capabilities, and can accurately reflect a relationship between radio signal sampling information and position information of a terminal. Terminal positioning accuracy is effectively improved.
-
公开(公告)号：US12223398B2
公开(公告)日：2025-02-11
申请号：US17038635
申请日：2020-09-30
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xinjie Chen , Jia Zeng , Di Chen , Fangzhou Zhu
IPC: G06N20/00 , G06F18/21 , G06F18/213 , G06F18/22 , G06F18/23213 , G06F18/2431 , G06F18/25
Abstract: A data sequence prediction method includes calculating, based on historical data sequences of N objects, a similarity distance between every two objects of the N objects, to obtain a similarity distance set, where the similarity distance is used to represent a similarity degree of two objects, the historical data sequence includes a plurality of pieces of data arranged according to a preset rule, and N is a positive integer greater than 1, dividing the N objects into K prediction object classes based on the similarity distance set using a clustering algorithm, where K is a positive integer, and K≤N, and predicting a future data sequence of an object included in at least one prediction object class of the K prediction object classes.
-
公开(公告)号：US20240135065A1
公开(公告)日：2024-04-25
申请号：US18542754
申请日：2023-12-17
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Xijun Li , Xiaotian Hao , Mingxuan Yuan , Jianye Hao , Jia Zeng
IPC: G06F30/20
CPC classification number: G06F30/20
Abstract: A service data processing method is provided, including: obtaining a target function and a constraint condition, where the constraint condition includes a constraint relationship between a plurality of variables, and the target function includes at least one variable of the plurality of variables; selecting an initial variable from the plurality of variables for a base variable group; sorting optimized values of variables in a non-base variable group to obtain a maximum heap structure, where each node in the maximum heap structure stores an identifier of a variable and an optimized value corresponding to the variable; updating the non-base variable group and the base variable group based on a first target variable; and obtaining a solving target of a service problem based on a variable in an updated base variable group and the constraint condition.
-
公开(公告)号：US20210012152A1
公开(公告)日：2021-01-14
申请号：US17038635
申请日：2020-09-30
Applicant: Huawei Technologies Co., Ltd.
Inventor： Xinjie Chen , Jia Zeng , Di Chen , Fangzhou Zhu
Abstract: A data sequence prediction method includes calculating, based on historical data sequences of N objects, a similarity distance between every two objects of the N objects, to obtain a similarity distance set, where the similarity distance is used to represent a similarity degree of two objects, the historical data sequence includes a plurality of pieces of data arranged according to a preset rule, and N is a positive integer greater than 1, dividing the N objects into K prediction object classes based on the similarity distance set using a clustering algorithm, where K is a positive integer, and K≤N, and predicting a future data sequence of an object included in at least one prediction object class of the K prediction object classes.
-
公开(公告)号：US09811777B2
公开(公告)日：2017-11-07
申请号：US14552052
申请日：2014-11-24
Applicant: Huawei Technologies Co., Ltd.
Inventor： Zhi Guo , Fuqiang Wu , Jia Zeng , Deepak Mansharamani , John Cortes , Lingyan Sun , Dan Tian
CPC classification number: G06N5/027 , G06F2221/2101 , H04L43/028 , H04L69/12
Abstract: The present invention discloses a rule matching method including: receiving a packet; detecting feature information in content of the packet, and determining whether the detected feature information in the packet conforms to a classification characteristic of one rule group among a plurality of preset rule groups; if yes, determining a state machine corresponding to the one rule group as a first state machine; and determining whether the first state machine is stored in an on-chip memory, and if yes, using the first state machine to match the packet to obtain a matching result; and if no, when an off-chip memory stores the first state machine, loading the first state machine from the off-chip memory into the on-chip memory, and using the first state machine to match the packet to obtain a matching result. Embodiments of the present invention enable a product to achieve better performance.
-
Patent Agency Ranking
公开(公告)号：US20170185895A1
公开(公告)日：2017-06-29
申请号：US15455259
申请日：2017-03-10
Applicant: Huawei Technologies Co., Ltd.
CPC classification number: G06N3/08 , G06N3/0454 , G06N3/084 , G06N5/04
Abstract: A system and a method for training a parameter set in a neural network includes a main-control-node set, used for controlling a training process and storing a data set and a parameter set that are used for training, where the main-control-node set includes M main control nodes, every two of the M main control nodes are in a communication connection, and at least one main control node of the M main control nodes is configured to back up the parameter set. The system also includes N training-node sets, where the training-node set includes multiple training nodes, and the training node is configured to perform training according to a data set and a parameter set that are delivered by the main-control-node set, and send a training result to a corresponding main control node.
-
公开(公告)号：US11290975B2
公开(公告)日：2022-03-29
申请号：US16791795
申请日：2020-02-14
Applicant: Huawei Technologies Co., Ltd.
Inventor： Fangzhou Zhu , Mingxuan Yuan , Jia Zeng , Weixiong Rao
Abstract: A method for obtaining an emission probability includes obtaining a plurality of measurement reports (MRs) of a terminal in a target region and an engineering parameter of at least one base station in the target region, obtaining, based on parameter information in each of the plurality of MRs and the engineering parameter of the at least one base station, a feature vector corresponding to each of the plurality of MRs, processing, using a regression model, location information in each of the plurality of MRs and the feature vector corresponding to each of the plurality of MRs, to obtain a single-point positioning model, calculating, based on the single-point positioning model, the location information in each of the plurality of MRs, and the feature vector corresponding to each of the plurality of MRs, an emission probability of the feature vector corresponding to each of the plurality of MRs.
-
公开(公告)号：US20170097962A1
公开(公告)日：2017-04-06
申请号：US15383606
申请日：2016-12-19
Applicant: Huawei Technologies Co., Ltd.
Inventor： Jia Zeng , Mingxuan Yuan , Shiming Zhang
CPC classification number: G06F16/2465 , G06F16/2237 , G06F16/93 , G06F17/16 , G06F17/2785 , G06N7/005 , G06N20/00
Abstract: A topic mining method and apparatus are disclosed. When an iterative process is executed each time, an object message vector is determined from a message vector according to a residual of the message vector, so that a current document-topic matrix and a current term-topic matrix are updated according to only the object message vector, and then calculation is performed, according to the current document-topic matrix and the current term-topic matrix, on only an object element that is in the term-document matrix and that corresponds to the object message vector, thereby avoiding that in each iterative process, calculation needs to be performed on all non-zero elements in the term-document matrix, and avoiding that the current document-topic matrix and the current term-topic matrix are updated according to all message vectors, which greatly reduces an operation amount, increases a speed of topic mining, and increases efficiency of topic mining.
-
公开(公告)号：US20160364366A1
公开(公告)日：2016-12-15
申请号：US15245795
申请日：2016-08-24
Applicant: Huawei Technologies Co., Ltd.
Inventor： Liang Lan , Mingxuan Yuan , Jia Zeng
CPC classification number: G06F17/16 , G06F17/11 , G06K9/6201
Abstract: An entity matching method and apparatus, where the method includes, calculating kernel matrices K and L after reading a first data source and a second data source with inconsistent entity quantities, respectively, solving a first optimization objective function to obtain a matrix M of a correspondence between an entity on the first data source and an entity on the second data source, and outputting the obtained matrix M. Hence, according to the entity matching method and apparatus provided in the present disclosure, entity matching when entity quantities of data sources are inconsistent may be performed such that accuracy of data mining may be effectively improved, and data value may be effectively presented.
Abstract translation: 一种实体匹配方法和装置，其中所述方法包括：分别在读取第一数据源和具有不一致实体数量的第二数据源之后分别计算核矩阵K和L，求解第一优化目标函数以获得对应的矩阵M 在第一数据源上的实体与第二数据源上的实体之间，并输出所获得的矩阵M.因此，根据本公开中提供的实体匹配方法和装置，当数据源的实体数量不一致时的实体匹配 可以进行数据挖掘的精度有效地提高，并且可以有效地呈现数据值。
-
公开(公告)号：US12047902B2
公开(公告)日：2024-07-23
申请号：US17688087
申请日：2022-03-07
Applicant: Huawei Technologies Co., Ltd.
Inventor： Fangzhou Zhu , Mingxuan Yuan , Jia Zeng , Weixiong Rao
IPC: H04W64/00 , G06N20/00 , H04W24/10 , H04W72/0446 , H04W76/11
CPC classification number: H04W64/003 , G06N20/00 , H04W24/10 , H04W72/0446 , H04W76/11
Abstract: A method for obtaining an emission probability includes obtaining a plurality of measurement reports (MRs) of a terminal in a target region and an engineering parameter of at least one base station in the target region, obtaining, based on parameter information in each of the plurality of MRs and the engineering parameter of the at least one base station, a feature vector corresponding to each of the plurality of MRs, processing, using a regression model, location information in each of the plurality of MRs and the feature vector corresponding to each of the plurality of MRs, to obtain a single-point positioning model, calculating, based on the single-point positioning model, the location information in each of the plurality of MRs, and the feature vector corresponding to each of the plurality of MRs, an emission probability of the feature vector corresponding to each of the plurality of MRs.
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.019 seconds)
