-
公开(公告)号：US20210216805A1
公开(公告)日：2021-07-15
申请号：US17205773
申请日：2021-03-18
Inventor： Xiangxiang LV , En SHI , Yongkang XIE
Abstract: The present application discloses an image recognition method, apparatus, an electronic device and a storage medium, and relates to the field of neural networks and depth learning. An implementation solution may be as follows: loading a first image recognition model; inputting an image to be recognized into a first image recognition model; predicting the image to be recognized by using a first image recognition model to obtain an output result of a network layer of the first image recognition model; and performing post-processing on the output result of the network layer of the first image recognition model, to obtain an image recognition result.
-
232.发明申请公开(公告)号：US20210216783A1
公开(公告)日：2021-07-15
申请号：US17144523
申请日：2021-01-08
Inventor： Xiang LONG , Dongliang HE , Fu LI , Xiang ZHAO , Tianwei LIN , Hao SUN , Shilei WEN , Errui DING
Abstract: A method includes screening, by a video-clip screening module in a video description model, a plurality of video proposal clips acquired from a video to be analyzed, to acquire a plurality of video clips suitable for description. The plural video proposal clips acquired from the video to be analyzed may be screened by the video-clip screening module to acquire the plural video clips suitable for description; and then, each video clip is described by a video-clip describing module, thus avoiding description of all the video proposal clips, only describing the screened video clips which have strong correlation with the video and are suitable for description, removing the interference of the description of the video clips which are not suitable for description in the description of the video, guaranteeing the accuracy of the final descriptions of the video clips, and improving the quality of the descriptions of the video clips.
-
公开(公告)号：US20210216716A1
公开(公告)日：2021-07-15
申请号：US17213927
申请日：2021-03-26
Inventor： Qi Wang , Zhifan Feng , Zhijie Liu , Siqi Wang , Chunguang Chai , Yong Zhu
IPC: G06F40/295 , G06F16/33
Abstract: A method, apparatus, device, and storage medium for entity linking is disclosed. The method includes: acquiring a target text; determining at least one entity mention included in the target text; determining a candidate entity corresponding to each of the entity mention based on a preset knowledge base; determining a reference text of each of the candidate entity and determining additional feature information of each of the candidate entity; and determining an entity linking result based on the target text, each of the reference text, and each piece of the additional feature information.
-
公开(公告)号：US20210216715A1
公开(公告)日：2021-07-15
申请号：US17023915
申请日：2020-09-17
Inventor： Shu WANG , Kexin REN , Xiaohan ZHANG , Zhifan FENG , Yang ZHANG , Yong ZHU
IPC: G06F40/295 , G06F40/253 , G06F16/33 , G06N20/00 , G06N5/04
Abstract: A method for mining an entity focus in a text may include: performing word and phrase feature extraction on an input text; inputting an extracted word and phrase feature into a text coding network for coding, to obtain a coding sequence of the input text; processing the coding sequence of the input text using a core entity labeling network to predict a position of a core entity in the input text; extracting a subsequence corresponding to the core entity in the input text from the coding sequence of the input text, based on the position of the core entity in the input text; and predicting a position of a focus corresponding to the core entity in the input text using a focus labeling network, based on the coding sequence of the input text and the subsequence corresponding to the core entity in the input text.
-
235.发明申请公开(公告)号：US20210216686A1
公开(公告)日：2021-07-15
申请号：US17215932
申请日：2021-03-29
Inventor： Ying LIU , Xin Xie , Ming Xu , Yuezhen Qi , Ruifeng Li , Lu Bai
IPC: G06F30/27
Abstract: Embodiments of the present disclosure disclose a method, apparatus and electronic device for constructing a reinforcement learning model, and a computer readable storage medium, relate to the field of big data and deep learning technology. An implementation of the method can include: establishing a first simulation model between a calciner coal feed amount and a calciner temperature; establishing a second simulation model among a kiln head coal feed amount, a kiln current, a secondary air temperature, and a smoke chamber temperature; establishing a prediction model among: an under-grate pressure; the calciner temperature output by the first simulation model; the kiln current, the secondary air temperature, and the smoke chamber temperature content output by the second simulation model; and a free calcium; and constructing a reinforcement learning model according to a preset reinforcement learning model architecture, using the first simulation model, the second simulation model, and the prediction model.
-
Patent Agency Ranking
公开(公告)号：US20210216594A1
公开(公告)日：2021-07-15
申请号：US17216134
申请日：2021-03-29
Inventor： Lianghuang FAN , Xuefeng LUO , Xiaojun Zhao , Xie HE , Changfu BAI
IPC: G06F16/9032 , G06F40/30 , G06F9/451 , G06F16/9035
Abstract: A method and an apparatus are provided. The method may include: determining a service scenario based on a query sentence; entering the service scenario, and entering a first dialog node tree corresponding to the service scenario; storing, in response to determining that a common scenario needs to be entered based on a verification of a related parameter by the each parameter verification dialog node, the each parameter verification dialog node and jumping to the common scenario, and entering a second dialog node tree; collecting user information using the second dialog node tree, and in response to determining that the user information is collected successfully, determining whether a processing result of the second dialog node tree meets a backtracking condition; and returning to the service scenario based on the stored parameter verification dialog node and continuing to execute other dialog logic processing of the service scenario.
-
公开(公告)号：US20210216077A1
公开(公告)日：2021-07-15
申请号：US17216208
申请日：2021-03-29
Inventor： Teng ZHANG
Abstract: A method for training a trajectory planning model, an apparatus, and computer storage medium are provided. The method may include: obtaining an image of a physical environment in which a vehicle is located via at least one sensor of the vehicle, the image including multiple objects surrounding the vehicle; obtaining a feature chart indicating multiple initial trajectory points of the vehicle in the image from a trajectory planning model based on the image; identifying the image to determine in the image a first area associated with a road object in multiple objects and a second area associated with a non-road object in the multiple objects; determining a planning trajectory point based on positional relationship of the multiple initial trajectory points with respect to the first area and the second area; and training a trajectory planning model based on the planning track point and the actual trajectory point of the vehicle.
-
公开(公告)号：US20210213971A1
公开(公告)日：2021-07-15
申请号：US17215563
申请日：2021-03-29
Inventor： Dayun SHEN
Abstract: Exemplary embodiments of the present disclosure provide a method and apparatus for determining road information data and a computer storage medium, which may be used for autonomous driving, road information prediction, and driving route planning. The method for determining road information data includes: determining, via a precision navigation device of a vehicle, a plurality of locations of the vehicle; acquiring, via a sensor of the vehicle, a plurality of image frames of a physical environment where the vehicle is located; determining, from the plurality of locations, a target location corresponding to at least one image frame among the plurality of image frames; and determining, based on the determined target location and a map related to the physical environment, road information data corresponding to the at least one image frame. According to the solution of the present disclosure, road information annotation data may be accurately and efficiently generated.
-
公开(公告)号：US11064053B2
公开(公告)日：2021-07-13
申请号：US16567930
申请日：2019-09-11
Inventor： Shuangyang Song , Xianhui Niu , Li Li , Linjiang Lian
IPC: G06F16/23 , H04L29/06 , G06F16/22 , H04L29/08 , G06F16/953
Abstract: Embodiments of the present disclosure relate to a method and an apparatus for processing data. The method can include: determining, in response to receiving an access request, a time interval between the access request and a last access request as a first time interval; acquiring a preset complete binary tree from a management server end, a value of a non-leaf node of the complete binary tree being related to a time interval of latest two access requests received by a metadata server, a leaf node being used to represent a virtual node in a distributed system, and the virtual node corresponding to the metadata server; selecting a target path from the complete binary tree according to the first time interval; and sending the access request and the target path to a metadata server corresponding to a leaf node of the target path.
-
公开(公告)号：US20210211832A1
公开(公告)日：2021-07-08
申请号：US17207601
申请日：2021-03-19
Inventor： Yanyan Li , Xinjiang Lu , Jianguo Duan
IPC: H04W4/021
Abstract: A method, device, and medium for recommending a region of interest are provided. The method includes: acquiring access data, the access data including correlation information between any two regions in a region group, in which a correlation between any two regions in the region group is acquired based on a region pair formed by the any two regions in the region group where sample users are located and the number of access times corresponding to the region pair, and in which the region group is acquired based on division of map data, and the map data includes boundary information of an entity in a real world; determining a region where a first user is currently located; and recommending region information of the region of interest for the first user based on the access data and the region where the first user is currently located.
-
-
-
-
-
-
-
-
-
Search Results
1660
records
(took 0.041 seconds)
