公开(公告)号：US20240265309A1

公开(公告)日：2024-08-08

申请号：US18638414

申请日：2024-04-17

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Biao LU ,  Jieming ZHU ,  Xiuqiang HE ,  Zhaowei WANG

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: This application relates to the artificial intelligence field, and in particular, to an item recommendation method and apparatus, and a storage medium. The method includes: obtaining historical interaction data of a target object, where the historical interaction data indicates a historical interaction event between the target object and at least one item; obtaining a pre-trained target recommendation model, where the target recommendation model includes a graph neural network model with one convolutional layer, and the convolutional layer indicates an association relationship between a sample object and a sample item; and invoking, based on the historical interaction data, the target recommendation model to output a target item corresponding to the target object. In the embodiments of this application, a framework structure of the target recommendation model is simplified, so that model operation time is greatly reduced.

公开(公告)号：US20240020541A1

公开(公告)日：2024-01-18

申请号：US18476830

申请日：2023-09-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Wei GUO ,  Huifeng GUO ,  Yong GAO ,  Ruiming TANG ,  Wenzhi LIU ,  Xiuqiang HE

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: This application describes a model training method, applied to the field of artificial intelligence. The method includes a computing core of a first processor obtains an embedding used for model training, and writes an updated embedding to a first memory of the first processor instead of transferring the updated embedding to a second processor after model training is completed. In this application, after updating an embedding, the first processor saves the updated embedding to the first memory of the first processor. Without needing to wait for the second processor to complete a process of transferring a second target embedding to a GPU, the first processor may directly obtain the updated embedding and perform model training of a next round based on the updated embedding, provided that the first processor may obtain a latest updated embedding.

公开(公告)号：US20240419634A1

公开(公告)日：2024-12-19

申请号：US18812195

申请日：2024-08-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Bin WU ,  Xiuqiang HE ,  Li QIAN

IPC: G06F16/16 ,  G06F18/22 ,  G06F18/23

Abstract: This application provides an application program (APP) management method, a terminal device, a server, and a system. According to the method, APPs downloaded on a terminal device can be automatically clustered. This saves time of a user and improves user experience. The method is applicable to a terminal device, and the method includes: obtaining a target desktop folder based on type information of an APP downloaded by the terminal device and attribute information of a desktop folder on the terminal device, where the downloaded APP is to be clustered in the target desktop folder; and clustering the downloaded APP into the target desktop folder.

公开(公告)号：US20230129455A1

公开(公告)日：2023-04-27

申请号：US18145635

申请日：2022-12-22

Applicant: Huawei Technologies Co., Ltd.

Inventor： Bin WU ,  Xiuqiang HE ,  Li QIAN

IPC: G06F16/16 ,  G06F18/22 ,  G06F18/23

Abstract: This application provides an application program (APP) management method, a terminal device, a server, and a system. According to the method, APPs downloaded on a terminal device can be automatically clustered. This saves time of a user and improves user experience. The method is applicable to a terminal device, and the method includes: obtaining a target desktop folder based on type information of an APP downloaded by the terminal device and attribute information of a desktop folder on the terminal device, where the downloaded APP is to be clustered in the target desktop folder; and clustering the downloaded APP into the target desktop folder.

公开(公告)号：US20240184837A1

公开(公告)日：2024-06-06

申请号：US18441389

申请日：2024-02-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Jieming ZHU ,  Zhou ZHAO ,  Shengyu ZHANG ,  Xiuqiang HE ,  Li QIAN

IPC: G06F16/9535 ,  G06V10/40

CPC classification number: G06F16/9535 ,  G06V10/40

Abstract: Examples of recommendation methods and apparatus are described. In one example method, a plurality of images are obtained, where each image includes one candidate interface and one type of candidate content presented by using the candidate interface. Image feature data of each image is obtained, and input for a prediction model is determined based on user feature data of a target user and the image feature data. Then, a degree of preference of the target user for each image is predicted by using the prediction model. At least one of a candidate interface or candidate content that are included in the plurality of images is selected based on the degree of preference. Recommendation is then performed to the user based on the selected candidate content or candidate interface.

公开(公告)号：US20230162005A1

公开(公告)日：2023-05-25

申请号：US18157277

申请日：2023-01-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Pengxiang CHENG ,  Zhenhua DONG ,  Xiuqiang HE ,  Xiaolian ZHANG ,  Shi YIN ,  Yuelin HU

IPC: G06N3/045

CPC classification number: G06N3/045

Abstract: This application provides a neural network distillation method and apparatus in the field of artificial intelligence. The method includes: obtaining a sample set, where the sample set includes a biased data set and an unbiased data set, the biased data set includes biased samples, and the unbiased data set includes unbiased samples; determining a first distillation manner based on data features of the sample set, where, in the first distillation manner, a teacher model is trained by using the unbiased data set and a student model is trained by using the biased data set; and training a first neural network based on the biased data set and the unbiased data set in the first distillation manner, to obtain an updated first neural network.

公开(公告)号：US20230153857A1

公开(公告)日：2023-05-18

申请号：US18156512

申请日：2023-01-19

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Jingjie LI ,  Hong ZHU ,  Zhenhua DONG ,  Xiaolian ZHANG ,  Shi YIN ,  Xinhua FENG ,  Xiuqiang HE

IPC: G06Q30/0251 ,  G06Q30/0202

CPC classification number: G06Q30/0251 ,  G06Q30/0202

Abstract: A training method includes: obtaining a first recommendation model, where a model parameter of the first recommendation model is obtained through training based on n first training samples; determining an impact function value of each first training sample with respect to a verification loss of m second training samples in the first recommendation model; determining, based on the impact function value of each first training sample with respect to the verification loss, a weight corresponding to each first training sample; and training the first recommendation model based on the n first training samples and the weights corresponding to the n first training samples, to obtain a target recommendation model.

公开(公告)号：US20230088171A1

公开(公告)日：2023-03-23

申请号：US17989719

申请日：2022-11-18

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Guohao CAI ,  Gang WANG ,  Zhenhua DONG ,  Xiaoguang LI ,  Xiuqiang HE ,  Hong ZHU

IPC: G06F16/9535 ,  G06F16/954

Abstract: A method and an apparatus for training a search recommendation model, and a method and an apparatus for sorting search results are provided. The training method includes: obtaining a training sample set including a sample user behavior group sequence and a masked sample user behavior group sequence; and using the training sample set as input data, and training a search recommendation model, to obtain a trained search recommendation model, where a target of the training is to obtain the object of the response operation of the sample user after the mask processing, the search recommendation model is used to predict a label of a candidate recommendation object in search results corresponding to a query field when a target user inputs the query field, and the label is used to indicate a probability that the target user performs a response operation on the candidate recommendation object.

公开(公告)号：US20210248651A1

公开(公告)日：2021-08-12

申请号：US17242588

申请日：2021-04-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Chih Yao CHANG ,  Hong ZHU ,  Zhenhua DONG ,  Xiuqiang HE ,  Bowen YUAN

IPC: G06Q30/02 ,  G06K9/62 ,  G06N20/00

Abstract: This application provides a recommendation model training method in the artificial intelligence (AI) field. The training method includes: obtaining a first training sample; processing attribute information of a first user and information about a first recommended object based on an interpolation model, to obtain an interpolation prediction label of the first training sample; and performing training by using the attribute information of the first user and the information about the first recommended object as an input to a recommendation model and using the interpolation prediction label of the first training sample as a target output value of the recommendation model, to obtain a trained recommendation model. According to the technical solutions of this application, impact of training data bias on recommendation model training can be alleviated, and recommendation model accuracy can be improved.

公开(公告)号：US20200258006A1

公开(公告)日：2020-08-13

申请号：US16863110

申请日：2020-04-30

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Fei CHEN ,  Zhenhua DONG ,  Zhenguo LI ,  Xiuqiang HE ,  Li QIAN ,  Shuaihua PENG

IPC: G06N20/00 ,  G06N5/02

Abstract: Example prediction methods and apparatus are described. One example includes sending a first model parameter and a second model parameter by a server to a plurality of terminals. The first model parameter and the second model parameter are adapted to a prediction model of the terminal. The server receives a first prediction loss sent by at least one of the plurality of terminals. A first prediction loss sent by each of the at least one terminal is calculated by the terminal based on the prediction model that uses the first model parameter and the second model parameter. The server updates the first model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated first model parameter. The server updates the second model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated second model parameter.