Patents Assigned to Beijing Baidu Netcom Science and Technology Co., Ltd
  • Publication number: 20230084438
    Abstract: A method of generating a text, a method of training a text generation model, an electronic device, and a storage medium, which relate to a field of a computer technology, in particular to fields of deep learning and natural language processing technologies. A specific implementation solution includes: determining a reference feature representation of a target semantic information; determining, based on the reference feature representation and at least one predetermined logical character, at least one sentence latent representation respectively corresponding to the at least one predetermined logical character; and generating a target text content based on the at least one sentence latent representation.
    Type: Application
    Filed: November 22, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Zhe Hu, Jiachen Liu, Xinyan Xiao
  • Publication number: 20230083116
    Abstract: A federated learning method and system, an electronic device, and a storage medium, which relate to a field of artificial intelligence, in particular to fields of computer vision and deep learning technologies. The method includes: performing a plurality of rounds of training until a training end condition is met, to obtain a trained global model; and publishing the trained global model to a plurality of devices. Each of the plurality of rounds of training includes: transmitting a current global model to at least some devices in the plurality of devices; receiving trained parameters for the current global model from the at least some devices; performing an aggregation on the received parameters to obtain a current aggregation model; and adjusting the current aggregation model based on a globally shared dataset, and updating the adjusted aggregation model as a new current global model for a next round of training.
    Type: Application
    Filed: November 16, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Ji LIU, Hong ZHANG, Juncheng JIA, Jiwen ZHOU, Shengbo PENG, Ruipu ZHOU, Dejing DOU
  • Publication number: 20230081957
    Abstract: A method includes: performing a first diamond search according to an initial point determined from points in a search window, a search step size being incremented by ith power of 2, i being a natural number, 0?i?N; and performing the following first processing: acquiring an updated initial point and an optimization range, the optimization range being less than 2N; performing a second diamond search according to the initial point, wherein, prior to a search with a search step size larger than the optimization range, if it is determined that an ending condition is met, the diamond search is ended and a corresponding second optimal point is determined; and determining a required optimal motion vector according to the second optimal point if the second optimal point meets a predetermined requirement, and otherwise, repeating the first processing.
    Type: Application
    Filed: September 12, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Xu ZHANG, Wenpeng DING
  • Publication number: 20230085458
    Abstract: A method for generating dialog data is provided. An implementation is: obtaining a target dialog data template, where the target dialog data template includes one or more target single-round dialog data templates, each target single-round dialog data template includes one or more keyword slots and related information about each keyword slot, and the related information about each keyword slot includes location information and attribute information; for each keyword slot, determining, from a keyword data set at least based on the attribute information of the keyword slot, one or more target keywords that match the keyword slot; and for each target single-round dialog data template, filling the target single-round dialog data template with the one or more target keywords based on the location information of the one or more keyword slots, to obtain target dialog data.
    Type: Application
    Filed: November 21, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Xin TIAN, Dongfeng HE, Liankai HUANG, Yingzhan LIN, Shiwei HUANG
  • Publication number: 20230083831
    Abstract: The present disclosure provides a method and apparatus for adjusting a virtual face model, an electronic device and a storage medium, so as at least to solve the technical problems of tedious operation steps and poor user experience of conventional solutions for adjusting a virtual image. A specific implementation solution includes: a real human face in a reality scene is identified to obtain a first virtual face model of the real human face in a virtual scene; in response to a face-pinching operation acting on the real human face, the face-pinching operation is identified to determine at least one to-be-adjusted key point in the first virtual face model and an adjustment manner of the at least one to-be-adjusted key point; and the first virtual face model is adjusted to a second virtual face model based on the adjustment manner of the at least one to-be-adjusted key point.
    Type: Application
    Filed: March 3, 2022
    Publication date: March 16, 2023
    Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.
    Inventors: Yiyuan ZHANG, Jiawei LIAO, Yu LIU, Xi HUANG, Xiaohua REN, Xiaolin HUANG, Huibin ZHAO
  • Publication number: 20230078726
    Abstract: Provided are a training method and apparatus for a distributed machine learning model, a device and a medium. The training method includes: acquiring a first homomorphic encryption intermediate parameter and a second homomorphic encryption intermediate parameter; generating a first interference parameter, and forming a first encryption interference parameter by encrypting the first interference parameter by using a second homomorphic public key of a second participant; performing calculation based on the first homomorphic encryption intermediate parameter, the second homomorphic encryption intermediate parameter, the first encryption interference parameter and the homomorphic calculation function of a first submodel to generate a first encryption key parameter.
    Type: Application
    Filed: September 15, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventor: Bo JING
  • Publication number: 20230081696
    Abstract: The present disclosure provides methods for shunting clustered gateways, which relate to the field of computer technologies, and in particular, relate to the technical field of data transmission. A specific implementation solution is: in response to receiving a first packet sent by a target internal network machine, a first hash value is acquired, wherein the first hash value is generated by a shunt of a public network gateway cluster, and the shunt is configured to perform a hash calculation on the first packet based on a pre-configured port dictionary; a target gateway machine is selected from the public network gateway cluster according to the first hash value; and the first packet is sent to the target gateway machine.
    Type: Application
    Filed: April 1, 2022
    Publication date: March 16, 2023
    Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.
    Inventors: Zhifeng HUANG, Wansheng Zhang
  • Publication number: 20230078041
    Abstract: A method of displaying an animation, an electronic device and a storage medium, which relate to a field of a computer technology, in particular to fields of artificial intelligence and augmented reality technologies. The method includes: determining, in response to a scene switching operation for a target scene, a first sampling result corresponding to each vertex of a three-dimensional model according to a first cubic texture object corresponding to the target scene; determining a roaming animation according to a color information of each vertex in a current scene and the first sampling result corresponding to each vertex; and presenting the roaming animation so as to switch the current scene to the target scene.
    Type: Application
    Filed: October 27, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventor: Da QU
  • Publication number: 20230081543
    Abstract: A method for synthetizing a speech includes: obtaining a source speech; suppressing a noise in the source speech based on an amplitude component and/or phase component of the source speech, to obtain a noise-reduced speech; performing a speech recognition process on the noise-reduced speech to obtain corresponding text information; inputting the text information of the noise-reduced speech and a preset tag into a trained acoustic model to obtain a predicted acoustic feature matching the text information; and generating a target speech based on the predicted acoustic feature.
    Type: Application
    Filed: November 21, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Bo Peng, Yongguo Kang, Cong Gao
  • Publication number: 20230077818
    Abstract: The present disclosure discloses a method for establishing a medicine synergism prediction model, a prediction method and corresponding apparatus, and relates to deep learning and artificial intelligence (AI) medical technologies in the field of AI technologies. A specific implementation solution includes: acquiring a relation graph, nodes in the relation graph including medicine nodes and protein nodes, and edges indicating that interaction exists between the nodes; collecting, from the relation graph, a medicine node pair with definite synergism and a label of whether the medicine node pair has synergism as training samples; and training the medicine synergism prediction model by taking the medicine node pair in the training samples as input to the medicine synergism prediction model and taking the label of whether the medicine node pair has synergism as target output; wherein the medicine synergism prediction model is obtained by learning the relation graph based on a graph attention network.
    Type: Application
    Filed: June 20, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Jing HU, Guodong ZHAO
  • Publication number: 20230081015
    Abstract: Disclosed are a method for acquiring information. The method includes: acquiring a file to be processed and an information type; recognizing at least one piece of candidate information related to the information type from the file to be processed; determining a target recognition feature and a semantic feature of each piece of candidate information, the target recognition feature is configured to describe a matching condition between the each piece of candidate information and the information type; and determining target information from the at least one piece of candidate information based on the target recognition feature and the semantic feature.
    Type: Application
    Filed: October 28, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Yushen Chen, Guangyao Han, Lei Su, Zeqing Jiang, Zhiping Li, Hongda Yue, Haijing Xu, Ming Luan
  • Publication number: 20230077816
    Abstract: The present disclosure provides a method for training sound source localization model and a sound source localization method, and relates to the field of artificial intelligence technologies such as voice processing and deep learning. The method for training sound source localization model method includes: obtaining a sample audio according to an audio signal including a wake-up word; extracting an audio feature of at least one audio frame in the sample audio, and marking a direction label and a mask label of the at least one audio frame; and training a neural network model by using the audio feature of the at least one audio frame and the direction label and the mask label of the at least one audio frame, to obtain a sound source localization model.
    Type: Application
    Filed: April 8, 2022
    Publication date: March 16, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Wei Du, Saisai Zou, Tengyu Du
  • Patent number: 11604766
    Abstract: A method, an apparatus, an electronic device, a computer-readable storage a medium and a computer program product for labeling data are provided. The method may include: obtaining a labeling accuracy requirement for to-be-labeled data; determining a process monitoring parameter matching the to-be-labeled data; weighting the process monitoring parameter with a coefficient having a corresponding size to obtain a comprehensive accuracy according to dependent and causal relationships between contents of different to-be-labeled data; and outputting, in response to the comprehensive accuracy satisfying the labeling accuracy requirement, labeled data.
    Type: Grant
    Filed: August 25, 2021
    Date of Patent: March 14, 2023
    Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.
    Inventor: Xue Yang
  • Patent number: 11604774
    Abstract: A method and apparatus of converting a schema in a deep learning framework, an electronic device, and a computer storage medium are provided. The method of converting the schema in the deep learning framework includes: updating a first schema, based on first syntax elements in the first schema and a context relationship between the first syntax elements in the first schema, so as to obtain an updated first schema; generating second syntax elements corresponding to updated first syntax elements in the updated first schema, based on a mapping relationship between the updated first syntax elements in the updated first schema and second syntax elements in a second schema system; and combining the second syntax elements according to a context relationship between the updated first syntax elements, so as to generate a second schema.
    Type: Grant
    Filed: September 21, 2021
    Date of Patent: March 14, 2023
    Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Liujie Zhang, Yamei Li, Huihuang Zheng, Hongyu Liu, Xiang Lan, Dianhai Yu, Yanjun Ma, Tian Wu, Haifeng Wang
  • Publication number: 20230075033
    Abstract: The present disclosure provides a ride-hailing method and apparatus, an electronic device and a readable storage medium, and relates to the field of artificial intelligence technologies such as intelligent transportation and deep learning. The ride-hailing method includes: acquiring a rapid ride-hailing request, the rapid ride-hailing request including a departure position and a destination position of a user; determining a target pick-up point according to the departure position and the destination position; obtaining an arrival time from the departure position to the target pick-up point; and outputting the target pick-up point and path planning information from the departure position to the target pick-up point when a target region where the target pick-up point is located is determined as an easy ride-hailing region according to the arrival time. According to the present disclosure, users' ride-hailing time can be reduced, and the users' ride-hailing efficiency can be improved.
    Type: Application
    Filed: March 25, 2022
    Publication date: March 9, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Hao Zhang, Xi Ma, Bu Mi, Xiufeng Han
  • Publication number: 20230074351
    Abstract: A method of configuring a cloud server resource, an electronic device and a storage medium, which specifically relate to a field of artificial intelligence technology, in particular to a field of cloud computing technology. A method of configuring a cloud server resource includes: obtaining an operation index of a server instance of an object; comparing the obtained operation index with a threshold; and determining whether a configuration of the cloud server resource is to be adjusted, based on a result of the comparing.
    Type: Application
    Filed: November 10, 2022
    Publication date: March 9, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Dong HAN, Minghe QIAO
  • Publication number: 20230072116
    Abstract: A method and an apparatus for recommending a travel mode, an electronic device; and a storage medium are provided. An implementation is: receiving a request from a user for querying a first point of interest; analyzing a travel type of the user based on the request; obtaining an alternative travel mode based on the travel type in combination with user information; calculating a travel cost corresponding to the alternative travel mode; and recommending at least one travel mode for the user according to the travel cost.
    Type: Application
    Filed: October 26, 2022
    Publication date: March 9, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Hao CHEN, Runmei ZHAO, Jizhou HUANG
  • Publication number: 20230076471
    Abstract: A training method, a text translation method, an electronic device, and a storage medium, which relate to a field of artificial intelligence, in particular to fields of natural language processing and deep learning technologies.
    Type: Application
    Filed: November 8, 2022
    Publication date: March 9, 2023
    Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
    Inventors: Xiyang WANG, Ruiqing ZHANG, Zhongjun HE, Zhi LI, Hua WU
  • Patent number: 11599122
    Abstract: A vehicle control method and device are disclosed. An embodiment of the method includes: receiving an assistance driving instruction associated with a vehicle; and sending an assistance control instruction to the vehicle, to cause the vehicle to execute the assistance control instruction to control the vehicle, the assistance control instruction being generated through a simulation driving operation performed by an assistance driving user based on travelling environment information of the vehicle presented to the assistance driving user.
    Type: Grant
    Filed: December 9, 2020
    Date of Patent: March 7, 2023
    Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
    Inventor: Jinyang Gu
  • Patent number: 11599825
    Abstract: Embodiments of the present disclosure relate to a method for training a trajectory classification model. The method includes: acquiring trajectory data; computing a trajectory feature of the trajectory data based on a temporal feature and a spatial feature of the trajectory data, the trajectory feature comprising at least one of a curvature or a rotation angle; and training the trajectory feature to obtain the trajectory classification model. Embodiments of the present disclosure further provide an apparatus for training a trajectory classification model, an electronic device, and a computer readable medium.
    Type: Grant
    Filed: December 11, 2019
    Date of Patent: March 7, 2023
    Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.
    Inventors: Enyang Bai, Kedi Chen, Miao Zhou, Quan Meng, Wei Wang