-
公开(公告)号：US20220392242A1
公开(公告)日：2022-12-08
申请号：US17819838
申请日：2022-08-15
Abstract: A method for training a text positioning model includes: obtaining a sample image, where the sample image contains a sample text to be positioned and a text marking box for the sample text; inputting the sample image into a text positioning model to be trained to position the sample text, and outputting a prediction text box for the sample image; obtaining a sample prior anchor box corresponding to the sample image; and adjusting model parameters of the text positioning model based on the sample prior anchor box, the text marking box and the prediction text box, and continuing training the adjusted text positioning model based on a next sample image until model training is completed, to generate a target text positioning model.
-
公开(公告)号：US20220391672A1
公开(公告)日：2022-12-08
申请号：US17820972
申请日：2022-08-19
Inventor： Kafeng Wang , Haoyi Xiong , Chengzhong Xu , Dejing Dou
Abstract: The disclosure provides a multi-task deployment method, and an electronic device. The method includes: obtaining N first tasks and K network models, in which N and K are positive integers greater than or equal to 1; allocating the N first tasks to the K network models differently for operation, to obtain at least one candidate combination of tasks and network models, in which each candidate combination includes a mapping relation between the N first tasks and the K network models; selecting a target combination with a maximum combination operation accuracy from the at least one candidate combination; and deploying a target mapping relation comprised in the target combination and the K network models on a prediction machine.
-
公开(公告)号：US20220391182A1
公开(公告)日：2022-12-08
申请号：US17820095
申请日：2022-08-16
Inventor： En Shi , Yongkang Xie , Zihao Pan , Shupeng Li , Xiaoyu Chen , Zhengyu Qian , Jingqiu Li
Abstract: A method for model production includes acquiring a related operation for model production from a user interface layer of a model production system, and determining a software platform of the model production system; acquiring a model service corresponding to the related operation by invoking an application programming interface (API) corresponding to the related operation, wherein the API is located between the user interface layer and other layer in the model production system; performing the model service by invoking local resources of the software platform with a tool of the software platform adapted to the model service, to generate a target model; and applying the target model in a target usage scene.
-
公开(公告)号：US20220390230A1
公开(公告)日：2022-12-08
申请号：US17883395
申请日：2022-08-08
Inventor： Bo PENG , Chao LI , Cong GAO , Zhanjie GAO , Yunfeng LI
Abstract: A method for generating a speech package, an electronic device and a storage medium The method includes: determining a number of texts to be displayed and a speech recording condition based on a type of a recording mode selection control in response to the recording mode selection control being triggered; acquiring speech data with an amount matched with the number based on the speech recording condition; sending the speech data to a server; and acquiring a speech package generated by the server using the speech data.
-
公开(公告)号：US20220382841A1
公开(公告)日：2022-12-01
申请号：US17819258
申请日：2022-08-11
Inventor： Pochang LIAO , Shuhe WANG , Pengfei ZHONG , Jiawei LIAO , Xiaohua REN , Xiaolin HUANG , Huibin ZHAO
Abstract: An information authentication method is provided. The method includes: determining a plurality of first objects in a target image; determining at least one second object in the target image; and executing, for each of the plurality of first objects, a first authentication operation including: determining whether the at least one second object includes a second object associated with the first object; performing first authentication on the second object associated with the first object in response to determining that the at least one second object includes the second object associated with the first object to obtain a first authentication result of the first object; and outputting the first authentication result.
-
Patent Agency Ranking
186.发明申请公开(公告)号：US20220382585A1
公开(公告)日：2022-12-01
申请号：US17884860
申请日：2022-08-10
Inventor： Peng Gao , Shaoqing Guo , Zhensheng Yang , Wei Guo , Pengju Xing , Chaoqian Liuzeng
Abstract: The present disclosure provides a system for processing data. A specific implementation is as follows: a control server acquires, based on a preset scheduling strategy, a second puller from the first puller, and a second task execution manager from the first task execution manager; and controls the second puller and the second task execution manager to perform an operation; a second puller acquires data of a to-be-processed message in a message queue; serializes the data of the to-be-processed message to obtain to-be-stored data; stores the to-be-stored data into a database to obtain stored first data; and adds a data state of the first data to the database; and a second task execution manager acquires second data from the database, and executes a task corresponding to the second data; and updates the data state based on a task execution result of the second data.
-
公开(公告)号：US20220381574A1
公开(公告)日：2022-12-01
申请号：US17818375
申请日：2022-08-09
Inventor： Linpei ZHANG , Li ZHAI
IPC: G01C21/34
Abstract: Embodiments of the present disclosure provide a multipath generation method, an apparatus, a device and a storage medium, and relate to the field of artificial intelligence, in particular to the field of intelligent transportation. A specific implementation solution is: in response to a path generation request, generating M recommended paths from a starting node to a destination node, where the M recommended paths are generated through m path generation processes including: in an i-th path generation process, generating ni recommended paths based on a constructed search tree, and for each recommended path of the ni recommended paths, determining traffic costs of road segments of the recommended path in an (i+1)-th path generation process according to penalty factors, the traffic costs being associated with a recommendation priority of path; where m≥i≥1, M>ni>1.
-
公开(公告)号：US20220375456A1
公开(公告)日：2022-11-24
申请号：US17855438
申请日：2022-06-30
Inventor： Shaoxiong YANG , Chen ZHAO
Abstract: A method for animation synthesis includes: obtaining an audio stream to be processed and a syllable sequence, wherein both the audio stream and the syllable sequence correspond to the same text and each syllable in the syllable sequence is pinyin of each character of the text; obtaining a phoneme information sequence of the audio stream by performing phoneme detection on the audio stream, wherein each piece of phoneme information in the phoneme information sequence comprises a phoneme category and a pronunciation time period; determining a pronunciation time period corresponding to each syllable in the syllable sequence based on the syllable sequence, phoneme categories and pronunciation time periods in the phoneme information sequence; and generating an animation video corresponding to the audio stream based on the pronunciation time period corresponding to each syllable in the syllable sequence and an animation frame sequence corresponding to each syllable.
-
189.发明申请公开(公告)号：US20220374713A1
公开(公告)日：2022-11-24
申请号：US17880070
申请日：2022-08-03
Inventor： Zhihua WU , Dianhai YU , Yulong AO , Weibao GONG
IPC: G06N3/08
Abstract: The present disclosure provides a method and apparatus for performing distributed training on a deep learning model. The method may include: generating a distributed computation view based on data information of a to-be-trained deep learning model; generating a cluster resource view based on property information of a cluster hardware resource corresponding to the to-be-trained deep learning model; determining a target segmentation strategy of a distributed training task based on the distributed computation view and the cluster resource view; and performing distributed training on the to-be-trained deep learning model based on the target segmentation strategy.
-
公开(公告)号：US20220374219A1
公开(公告)日：2022-11-24
申请号：US17881936
申请日：2022-08-05
Inventor： Yiming WEN
Abstract: A method is provided that includes: identifying a plurality of processing modules configured to provide a service, dependency information among the plurality of processing modules, and a plurality of performance parameters corresponding to the plurality of processing modules, respectively, wherein the plurality of processing modules are implemented as computer program instructions stored in one or more computer-readable storage mediums and are configured to be executed by one or more processors; determining thread configuration information based on the plurality of performance parameters, wherein the thread configuration information includes a plurality of thread numbers corresponding to the plurality of processing modules, respectively, wherein each thread number of the plurality of thread numbers is a number of threads included in a thread pool configured to execute the corresponding processing module; and packaging the plurality of processing modules, the dependency information, and the thread configuration information to generate an image for providing the service.
-
-
-
-
-
-
-
-
-
Search Results
1470
records
(took 0.034 seconds)
