公开(公告)号：US20230401221A1

公开(公告)日：2023-12-14

申请号：US18063509

申请日：2022-12-08

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Lu GAN ,  Zenghui XU ,  Zhiqun XIA ,  Jianbing ZHANG ,  Lianghui CHEN ,  Jian GONG ,  Ke SUN

IPC: G06F16/2458 ,  G06F16/242 ,  G06F16/2453

CPC classification number: G06F16/2458 ,  G06F16/2433 ,  G06F16/24542

Abstract: Provided are a cross-tables search method, an electronic device and a storage medium, relating to a field of artificial intelligence, and in particular, to natural language processing, big data, knowledge graph technology, which may be applied in scenarios of smart cloud, smart city, and smart government affairs. The cross-tables search method includes: parsing a query to obtain an entity, attribute and relationship required to be searched; determining a cross-tables search strategy according to the entity, the attribute and the relationship; and performing a cross-tables search operation according to the cross-tables search strategy.

公开(公告)号：US20230316709A1

公开(公告)日：2023-10-05

申请号：US17902323

申请日：2022-09-02

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Siqi XU ,  Ke SUN ,  Jian GONG ,  Xu PAN ,  Zhiqun XIA ,  Zhe YANG ,  Zecheng ZHUO

IPC: G06V10/762 ,  G06V10/764 ,  G06V10/74 ,  G06F16/28

CPC classification number: G06V10/762 ,  G06V10/764 ,  G06V10/761 ,  G06F16/285

Abstract: Provided is a data labeling method based on artificial intelligence, an apparatus, and a storage medium relating to the field of artificial intelligence, particularly data labeling, image recognition, and natural language processing. The method includes: determining a plurality of samples involved in clustering; performing a plurality of following operations circularly to realize iterative processing, until a convergence condition is satisfied or a quantity of iterations reaches a number threshold, comprising: pre-clustering the plurality of samples according to a vector representation of the respective samples to obtain a plurality of class clusters, each class cluster containing at least one sample; receiving labeling information for the respective class clusters and re-determining the plurality of samples according to the labeling information; and determining a clustering result according to the labeling information for the respective class clusters.

公开(公告)号：US20230086429A1

公开(公告)日：2023-03-23

申请号：US17992884

申请日：2022-11-22

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Siqi XU ,  Xu PAN ,  Chenhui LIU ,  Jian GONG ,  Zecheng ZHUO

IPC: G06F40/295

Abstract: A method of recognizing an address, an electronic device, and a storage medium, which relate to fields of artificial intelligence and computer technologies, fields of knowledge graph, deep learning and cloud computing. The method includes: performing a location entity recognition on a content to be recognized, so as to obtain a target location entity, the target location entity including at least one of a standardized location entity, an alias location entity, or a landmark location entity; determining a standardized address corresponding to each type of the location entity in the target location entity according to an address graph to obtain at least one standardized address, the address graph including a standardized location entity, an alias location entity, a landmark location entity, and a corresponding relationship between location entities; and determining, from the at least one standardized address, a first target standardized address corresponding to the content to be recognized.

公开(公告)号：US20220414095A1

公开(公告)日：2022-12-29

申请号：US17823224

申请日：2022-08-30

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Zhe YANG ,  Zecheng ZHUO ,  Jian GONG ,  Qiang HUANG ,  Xu PAN ,  Saiding HONG ,  Wenjun ZHANG ,  Siqi XU ,  Sicong LIN ,  Chenhui LIU

IPC: G06F16/2458 ,  G06F16/2455 ,  G06F16/28 ,  G06F40/30

Abstract: A method of processing event data, a device, and a medium are provided, which relate to fields of deep learning, natural language processing, cloud services, etc. The method of processing event data includes: determining target feature data corresponding to target event data, in response to receiving a query request containing the target event data; selecting correlated feature data from candidate feature data based on the target feature data, wherein a similarity between the correlated feature data and the target feature data meets a preset similarity condition; determining operation data associated with the correlated feature data, wherein the operation data represents a level of attention to correlated event data corresponding to the correlated feature data; and determining a level of attention to the target event data based on the operation data.

公开(公告)号：US20220318503A1

公开(公告)日：2022-10-06

申请号：US17849369

申请日：2022-06-24

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Wenjun ZHANG ,  Zecheng ZHUO ,  Jian GONG ,  Qiang HUANG ,  Guoan YOU ,  Xu PAN

IPC: G06F40/279 ,  G06F3/16

Abstract: A method and an apparatus for identifying an instruction, and a screen for voice interaction are provided. The method includes: acquiring a text vector and at least one word importance corresponding to a to-be-identified instruction; selecting a target number of quasi-matching instructions from a preset instruction library based on the text vector and the at least one word importance, where the instruction library includes a correspondence between an instruction and a text vector of the instruction, and the instruction in the instruction library includes an instruction type and an instruction-targeting keyword; and generating, based on the instruction type and the instruction-targeting keyword in the target number of quasi-matching instructions, an instruction type and an instruction-targeting keyword matching the to-be-identified instruction.

公开(公告)号：US20230386237A1

公开(公告)日：2023-11-30

申请号：US18157377

申请日：2023-01-20

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Chenhui LIU ,  Jian GONG ,  Ke SUN ,  Xu PAN ,  Siqi XU ,  Zecheng ZHUO

IPC: G06V30/19

CPC classification number: G06V30/19173 ,  G06V30/19093 ,  G06V30/1912

Abstract: Provided are a classification method and apparatus, an electronic device and a storage medium, which relate to the field of artificial intelligence and in particular, to the fields of natural language processing and deep learning. The classification method comprises: performing coding processing on to-be-classified data to obtain a to-be-classified coding feature; determining reference coding features of reference classification data similar to the to-be-classified data according to the to-be-classified coding feature; and determining a target category of the to-be-classified data according to the reference coding features and reference categories of the reference classification data.

公开(公告)号：US20220198153A1

公开(公告)日：2022-06-23

申请号：US17694034

申请日：2022-03-14

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Jian GONG ,  Yu SUN ,  Hao TIAN ,  Hua WU ,  Haifeng WANG ,  Qiaoqiao SHE

IPC: G06F40/40 ,  G06F40/284 ,  G06F40/205

Abstract: A model training method, a model training platform, an electronic device and a storage medium are provided, which can be used in the field of artificial intelligence, particularly the fields of natural language processing and deep learning. The model training method includes: receiving an input; determining, based on the input, a user-oriented prefabricated function; determining, based on the input, a model training function; determining, based on the input, a pre-trained model; determining, based on the input, a network structure associated with the pre-trained model so as to support use of the pre-trained model; training, based on the input, the model by using the prefabricated function, the model training function, and the pre-trained model; and providing an output associated with a trained model.