-
公开(公告)号：US20210374542A1
公开(公告)日：2021-12-02
申请号：US17444687
申请日：2021-08-09
Inventor： Wenhui ZHANG , Dianhai YU , Zhihua WU
Abstract: The invention discloses a method and an apparatus for updating parameters of a multi-task model. The method includes: obtaining a training sample set, in which the training sample set comprises a plurality of samples and a task to which each sample belongs; putting each sample into a corresponding sample queue sequentially according to the task to which each sample belongs; training a shared network layer in the multi-task model and a target sub-network layer of tasks associated with the sample queue with samples in the sample queue in case that the number of the samples in the sample queue reaches a training data requirement, so as to generate a model parameter update gradient corresponding to the tasks associated with the sample queue; and updating parameters of the shared network layer and the target sub-network layer in a parameter server according to the model parameter update gradient.
-
公开(公告)号：US20210374397A1
公开(公告)日：2021-12-02
申请号：US17129531
申请日：2020-12-21
Abstract: The disclosure may provide a method for obtaining a document layout, an electronic device, and a storage medium. The method may include: obtaining a plurality of characters and character information of each of the plurality of characters in a target document; generating a character fully-connected graph based on the plurality of characters and the character information of each of the plurality of characters; obtaining a spatial semantic feature of each of the plurality of characters; generating types of character vertices based on the character information of each of the plurality of characters; generating types of edges based on the spatial semantic feature of each of the plurality of characters, and the character information of each of the plurality of characters; and obtaining a document layout of the target document based on the types of the character vertices and the types of the edges.
-
公开(公告)号：US20210374349A1
公开(公告)日：2021-12-02
申请号：US17444693
申请日：2021-08-09
Inventor： Jiachen LIU , Xinyan XIAO , Hua WU , Haifeng WANG
IPC: G06F40/295 , G06N20/00 , G06N5/02
Abstract: A method for text generation, relates to a field of natural language processing, including: obtaining corpus data; labeling the corpus data to obtain a first constraint element; obtaining a first generation target; and generating a first text matching the first generation target by inputting the corpus data and the first constraint element into a generation model.
-
554.发明申请公开(公告)号：US20210374344A1
公开(公告)日：2021-12-02
申请号：US17094943
申请日：2020-11-11
Inventor： Shuohuan WANG , Chao PANG , Yu SUN
IPC: G06F40/284 , G06N20/00 , G06F16/23 , G06F7/08
Abstract: A method for resource sorting, a method for training a sorting model and corresponding apparatuses which relate to the technical field of natural language processing under artificial intelligence are disclosed. The method according to some embodiments includes: forming an input sequence in order with an item to be matched and information of candidate resources; performing Embedding processing on each Token in the input sequence, the Embedding processing including: word Embedding, position Embedding and statement Embedding; and inputting result of the Embedding processing in a sorting model to obtain sorting scores of the sorting model for the candidate resources, the sorting model is obtained by pre-training of a Transformer model.
-
公开(公告)号：US20210374334A1
公开(公告)日：2021-12-02
申请号：US17117211
申请日：2020-12-10
Abstract: A method for training a language model, an electronic device and a readable storage medium, which relate to the field of natural language processing technologies in artificial intelligence, are disclosed. The method may include pre-training the language model using preset text language materials in a corpus; replacing at least one word in a sample text language material with a word mask respectively to obtain a sample text language material including at least one word mask; inputting the sample text language material including the at least one word mask into the language model, and outputting a context vector of each of the at least one word mask via the language model; determining a word vector corresponding to each word mask based on the context vector of the word mask and a word vector parameter matrix; and training the language model based on the word vector corresponding to each word mask.
-
Patent Agency Ranking
公开(公告)号：US20210373952A1
公开(公告)日：2021-12-02
申请号：US17142770
申请日：2021-01-06
Inventor： Zexiang WANG , Ziang JIA
IPC: G06F9/50 , G06F1/3206
Abstract: A resource scheduling method and apparatus, an electronic device, and a storage medium are provided, which are related to the technical field of system resource scheduling. The resource scheduling method comprises: monitoring whether a current system can bear a load of a target application which has triggered and entered a high-computational-power scenario, subjecting the system to resource scheduling if the system is monitored to be unable to bear the load of the target application, and running the target application in the high-computational-power scenario based on scheduled system resources.
-
公开(公告)号：US11188443B2
公开(公告)日：2021-11-30
申请号：US16505284
申请日：2019-07-08
Inventor： Miao Zhang
IPC: G06F15/173 , G06F11/34
Abstract: Embodiments of the present disclosure disclose a method, apparatus and system for processing log data. A specific embodiment of the method includes: acquiring multiple pieces of to-be-processed log data generated based on a log within a preset time period, the to-be-processed log data including multiple attributes and preset indicators; determining multiple attribute value groups; determining, for an attribute value group, based on indicator values of preset indicators respectively indicated by multiple pieces of to-be-processed log data having each attribute value in the attribute value group, an indicator statistic value of the preset indicators of a log having each attribute value in the attribute value group; and generating a log data aggregation table based on indicator statistic values of preset indicators respectively corresponding to the multiple attribute value groups.
-
公开(公告)号：US20210366155A1
公开(公告)日：2021-11-25
申请号：US17117422
申请日：2020-12-10
Inventor： Jinrang Jia
Abstract: The present disclosure discloses a method and apparatus for detecting an obstacle, and relates to the technical field of intelligent transportation. A specific implementation plan is: acquiring a current image acquired by a camera; inputting the current image into a pre-trained detection model to obtain a position of a detection frame of an obstacle and determine a first pixel coordinate of a grounding point in the current image; determining an offset between the current image and a template image; converting the first pixel coordinate into a world coordinate of the grounding point based on the offset; and outputting the world coordinate of the grounding point as a position of the obstacle in a world coordinate system. This embodiment solves the problem of camera jitter from an image perspective, greatly improves the robustness of the roadside perception system, and saves computing resources.
-
公开(公告)号：US20210365713A1
公开(公告)日：2021-11-25
申请号：US17397497
申请日：2021-08-09
Inventor： Lu GAN , Yan FU , Yangjie ZHOU , Lianghui CHEN , Shunnan XU
Abstract: The disclosure provides an image clustering method and an image clustering apparatus. The method includes: obtaining new images, and clustering the new images to obtain a first cluster; determining a historical cluster similar to the first cluster as a second cluster from existing historical clusters; obtaining a distance between the first cluster and the second cluster; and generating a target cluster by fusing the first cluster and the second cluster based on the distance. In the image clustering method, with the image clustering apparatus of the disclosure, secondary clustering processing performed on the existing historical clusters based on newly added images is not required, new and old clusters are directly fused.
-
公开(公告)号：US20210365698A1
公开(公告)日：2021-11-25
申请号：US17128051
申请日：2020-12-19
Inventor： Jie ZHOU , Ming ZHAO , Liancheng ZHANG , Hao LI , Hang WU , Qiang GUO , Sunjie ZHOU , Fangfang DONG , Jiming MAO , Bo LI
Abstract: Embodiments of the present disclosure generally relate to a method for controlling a simulation vehicle, an electronic device, and a computer readable storage medium. According to the method, a simulation vehicle determines a first region corresponding to a first simulation position where the simulation vehicle is located at a first time point; obtains first environment information about the first region and second environment information about a second region adjacent to the first region; sends the first environment information and the second environment information to a control device of the simulation vehicle; and determines a first action performed by the simulation vehicle at a second time point after the first time point based on a control signal in response to receiving the control signal from the control device, the control signal being determined by the control device based on the first environment information and the second environment information.
-
-
-
-
-
-
-
-
-
Search Results
1986
records
(took 0.033 seconds)
