-
公开(公告)号：US20240412115A1
公开(公告)日：2024-12-12
申请号：US18814332
申请日：2024-08-23
Inventor： Yukun MA , Yingtong BU
IPC: G06N20/00
Abstract: A method, apparatus, device and medium for verifying output data of a processing model are provided. In the method, in response to receiving input data for the processing model, output data corresponding to the input data is determined from the processing model. A verification result associated with the input data and the output data is acquired from a verification model corresponding to the processing model, the verification result indicating a matching degree between the output data and the input data. A final result corresponding to the input data is provided based on the verification result and the output data.
-
公开(公告)号：US20240412049A1
公开(公告)日：2024-12-12
申请号：US18814317
申请日：2024-08-23
Applicant: Beijing Youzhuju Network Technology Co., Ltd. , Lemon Inc.
Inventor： Yukun MA , Arinze OFFOR
IPC: G06N3/0475
Abstract: In embodiments of the present disclosure, a solution for model evaluation is provided. The method comprises: providing inputs in an input set to a first generative model, to obtain a first output set output by a first generative model, wherein the first output set comprises a plurality of outputs corresponding to the plurality of inputs; obtaining first labelling information corresponding to a plurality of outputs in the first output set, the first labelling information indicating a quality level of each output marked in a plurality of quality levels divided in each quality evaluation dimension in the plurality of quality evaluation dimensions; and determining a first overall quality score of the first generative model at least based on the first labelling information of the outputs and respective quality scores corresponding to the plurality of quality levels divided in the plurality of quality evaluation dimensions.
-
公开(公告)号：US12164920B2
公开(公告)日：2024-12-10
申请号：US17984191
申请日：2022-11-09
Applicant: Lemon Inc. , Beijing Youzhuju Network Technology Co. Ltd.
Inventor： Viacheslav Dubeyko , Jian Wang
Abstract: The present disclosure describes techniques for offloading data processing and knowledge synthesis. A set of flags may indicate information about the memory pages in a first memory and may be manageable by at least one central processing unit (CPU). A memory page may be flushed to a second memory if the memory page is associated with a first flag. The first flag may indicate that the memory page is ready to be flushed to the second memory. The second memory may be configured to store a sequence of states of each of the memory pages. Data patterns and relations among the data patterns may be determined by data processing units (DPUs) based on the sequence of states of each of the memory pages. A knowledge base may be built in a third memory based on the data patterns and the relations among the data patterns.
-
公开(公告)号：US12160643B2
公开(公告)日：2024-12-03
申请号：US18393567
申请日：2023-12-21
Inventor： Wen Zhou , Fan Zhang , Ya Li , Chen Du , Rongchang Xie
IPC: H04N21/81 , G06V40/20 , H04N21/234
Abstract: The present disclosure provides a video generation method and apparatus, a device, and a medium and a product, and relates to the technical field of computers. The method includes: acquiring description information of a target video to be generated; according to the description information of the target video, acquiring, from a video material library, a target clip corresponding to the description information; splicing the target clip with each candidate clip of a plurality of candidate clips in the video material library respectively to obtain a plurality of candidate videos; evaluating a score of each candidate video of the plurality of candidate videos; and generating the target video according to the score of each candidate video of the plurality of candidate videos.
-
25.发明授权公开(公告)号：US12153789B2
公开(公告)日：2024-11-26
申请号：US18090323
申请日：2022-12-28
Applicant: Beijing Zitiao Network Technology Co., Ltd. , Beijing Youzhuju Network Technology Co. Ltd.
Inventor： Ye Yuan , Pengfei Ji , Yuchen Wang , Zhaoyiding Mai , Jiayi Shi , Ting Nie , Jingyu Zhang
IPC: G06F3/0486 , G06F3/0483 , G06F9/451 , G06F3/01 , G06F3/16
Abstract: Video-based interaction and video processing methods, an apparatus, a device, and a storage medium are provided. The video-based interaction method includes: in response to a target video being played back to a target image frame, displaying a mask comprising an interactive control on a video playback interface corresponding to the target image frame, the position of the display area of the interactive control on the mask having a correspondence with the display area of a target element on the target image frame, and the display image on the interactive control having a correspondence with the target element. When a trigger operation for the interactive control is received, a target page is displayed.
-
Patent Agency Ranking
公开(公告)号：US20240386683A1
公开(公告)日：2024-11-21
申请号：US18792547
申请日：2024-08-01
Inventor： Zhe LI , Hao LIU , Kequan FAN , Longfei MU , Peng XIANG , Haiyang CAO
Abstract: The embodiments of the present disclosure provide an interaction method and apparatus, device and medium, wherein the interaction method includes: in response to a trigger operation on a target interaction anchor on a video page, obtaining an image to be processed and a material of a target item associated with the target interaction anchor; and generating a target image based on the material of the target item and the image to be processed.
-
27.发明授权公开(公告)号：US12142036B2
公开(公告)日：2024-11-12
申请号：US18531426
申请日：2023-12-06
Inventor： Yan Zeng , Xinsong Zhang , Hang Li
IPC: G06V10/96 , G06F40/40 , G06V10/75 , G06V10/774 , G06V10/82
Abstract: Provided in the present application are a method and apparatus for training a visual language pre-training model, and a device and a medium. The method includes: acquiring pairing groups respectively corresponding to N images, wherein the pairing group of a first image includes: a first pairing group which is composed of the first image and description text of the first image, and a second pairing group which is composed of a local image of the first image and description text of the local image, N is an integer greater than 1, and the first image is any one of the N images; and training a visual language pre-training model according to the pairing groups respectively corresponding to the N images.
-
公开(公告)号：US20240347142A1
公开(公告)日：2024-10-17
申请号：US18632639
申请日：2024-04-11
Applicant: Lemon Inc. , Beijing Youzhuju Network Technology Co., Ltd.
Inventor： Yuwei YANG , Xiangxin ZHOU , Yu BAO , Jiaqi GUAN
Abstract: Embodiments of the present disclosure relate to a method and an electronic device for ligand generation. The method comprises: obtaining a trained ligand generation model, wherein the trained ligand generation model is generated based on decomposition of a ligand by modeling of atom positions, atom types, and chemical bonds; and obtaining, based on a target protein, a target ligand molecule corresponding to the target protein by using the trained ligand generation model. According to the method, the ligand generation model in the embodiments of the present disclosure considers the decomposition of the ligand and also models the chemical bonds, so that it can generate the target ligand molecule with higher affinity.
-
公开(公告)号：US20240346799A1
公开(公告)日：2024-10-17
申请号：US18634560
申请日：2024-04-12
Inventor： Quan Cui , Muyang Yi , Hao Wu , Cheng Yang
IPC: G06V10/26 , G06T3/40 , G06V10/50 , G06V10/764 , G06V10/774 , G06V20/70
CPC classification number: G06V10/26 , G06T3/40 , G06V10/50 , G06V10/764 , G06V20/70 , G06V10/7753
Abstract: Embodiments of the disclosure provides technologies for image segmentation. The method includes: extracting an image feature representation of a target image using a trained image encoder; for each of a plurality of classes, generating, using a trained text encoder, a text feature representation corresponding to a name of the class, and determining a candidate segmentation map for the target image and a class confidence of the class based on the image feature representation and the text feature representation; selecting, from the plurality of classes, at least one class related to the target image based on a plurality of class confidences determined respectively for the plurality of classes; and determining a target segmentation map for the target image based on the at least one candidate segmentation map and the at least one class confidence determined for the at least one selected class.
-
公开(公告)号：US20240345806A1
公开(公告)日：2024-10-17
申请号：US18630753
申请日：2024-04-09
Applicant: Beijing Youzhuju Network Technology Co., Ltd. , Lemon Inc.
Inventor： Zhitao Yang , Qi Chen , Jian Lai , Yimin Chen , Shan Lu , Jian Wang
CPC classification number: G06F7/5443 , G06F7/4876
Abstract: A computing apparatus and method, an electronic device and a storage medium are provided. The computing apparatus includes: a preprocessing module configured to receive N pairs of input parameters, and perform format conversion on each pair of input parameters according to the precision type of the N pairs of input parameters, and obtain N pairs of processed input parameters; and a calculation module configured to respectively compute a product of exponents and mantissas of each pair of processed input parameters, and obtain an output result based on the product of exponents and mantissas of each pair of processed input parameters. The computing apparatus supports multiply-accumulate computation of a plurality of floating-point types. The computing apparatus can multiplex the multiplication computation of the mantissa and make the computing apparatus support multiply-accumulate computations in a plurality of precision formats at the cost of lower area and power consumption.
-
-
-
-
-
-
-
-
-
Search Results
294
records
(took 0.027 seconds)
