公开(公告)号：US20250148202A1

公开(公告)日：2025-05-08

申请号：US19016233

申请日：2025-01-10

Applicant: LEMON INC.

Inventor： Hongyu XIONG ,  Han WANG ,  Rui LI ,  Yiqi FENG ,  Yuan GAO ,  Xiangyu ZENG ,  Qingyi LU ,  Bin LIU

IPC: G06F40/211 ,  G06F16/334 ,  G06F40/14 ,  G06F40/30

Abstract: Embodiments of the present disclosure relate to semantic parsing for short text. According to embodiments of the present disclosure, a method is proposed. The method comprises: obtaining a set of sentences associated with a short text, each of the set of sentences containing all of words in the short text; determining a set of syntactic features associated with the set of sentences, each of the set of syntactic features indicating at least one of a constituency relation and a dependency relation of the corresponding sentence; and determining a semantic structure of the short text based on the set of syntactic features.

公开(公告)号：US20250148108A1

公开(公告)日：2025-05-08

申请号：US18502673

申请日：2023-11-06

Applicant: Lemon Inc.

Inventor： Bo Jiang ,  Jian Du ,  Sagar Sharma ,  Qiang Yan

IPC: G06F21/62 ,  G06F21/60

Abstract: Differential privacy composition determination in a secure communication is provided. A method for determining differential privacy composition includes determining a differential privacy configuration including a first privacy parameter and a second privacy parameter, determining a privacy loss distribution, and performing a partial convolution operation of the privacy loss distribution by transforming the privacy loss distribution based on a predetermined parameter, determining an integral range based on the first privacy parameter and the privacy loss distribution, transforming the privacy loss distribution based on the integral range, and performing the partial convolution operation based on the integral range. The method also includes determining the second privacy parameter based on a result of the partial convolution operation, and controlling a dataset based on the differential privacy configuration to limit access to the dataset.

公开(公告)号：US12271612B2

公开(公告)日：2025-04-08

申请号：US18108351

申请日：2023-02-10

Applicant: Lemon Inc.

Inventor： Chul Lee ,  Ping Zhou ,  Hui Frankie Zhang ,  Fei Liu

IPC: G06F12/00 ,  G06F3/06

Abstract: A method for accessing blocks of a solid state drive is described. A starting position is received, where the starting position identifies a first block of a contiguous block region within a namespace of the solid state drive. The contiguous block region is to be accessed according to a single input/output operation and the namespace comprises two dimensions of logical address space with respective indices for indexing blocks within a corresponding dimension of the logical address space. A first dimensional identifier that identifies a size of the contiguous block region in a first dimension of the namespace is received. A second dimensional identifier that identifies a size of the contiguous block region in a second dimension of the namespace is received. Blocks of the contiguous block region are accessed in response to the single input/output operation according to the starting position, the first dimensional identifier, and the second dimensional identifier.

公开(公告)号：US20250113005A1

公开(公告)日：2025-04-03

申请号：US18832768

申请日：2023-01-11

Applicant: Lemon Inc.

Inventor： Runjia Tian ,  Peilin Li ,  Siyao Yang ,  Weikai Lii

IPC: H04N5/222 ,  H04N5/262

Abstract: Provided in the embodiments of the present disclosure are a method and apparatus for processing an effect video and an electronic device, and a storage medium. The method comprises: obtaining current position information of a target touch point in response to an effect triggering operation; determining, according to the current position information and a drawing parameter, a two-dimensional trajectory effect consistent with a motion trajectory of the target touch point; and displaying, in response to detecting that a three-dimensional display condition is satisfied, a three-dimensional trajectory effect that corresponds to the two-dimensional trajectory effect from a plurality of angles, and stopping displaying the three-dimensional trajectory effect upon the detection of an instruction to stop playing the effect video being satisfied.

公开(公告)号：US20250102717A1

公开(公告)日：2025-03-27

申请号：US18894792

申请日：2024-09-24

Applicant: Beijing Zitiao Network Technology Co., Ltd. ,  Lemon Inc.

Inventor： Shaopeng ZHU ,  Ziyang ZHANG ,  Jian CHEN ,  Ling FU ,  Wenbin BAI

IPC: G02B5/30 ,  G02B17/08

Abstract: An optical structure, a manufacturing method thereof and a display device. The optical structure has a light incident side and a light-exiting side, the optical structure includes a first lens, a transflective film, a phase retardation layer, and a polarizing reflective film. The first lens includes a first surface and a second surface, the phase retardation layer is located on a side of the second surface away from the first surface, the phase retardation layer includes an alignment layer and a liquid crystal layer, the manufacturing method includes: coating the alignment layer on the second surface of the first lens; using an alignment light source to optically align the alignment layer from the light incident side; coating the liquid crystal layer on a side of the alignment layer away from the second surface.

公开(公告)号：US20250094111A1

公开(公告)日：2025-03-20

申请号：US18968932

申请日：2024-12-04

Applicant: Lemon Inc.

Inventor： Koken Ishii

IPC: G06F3/14 ,  G06F3/01 ,  G06F3/04815 ,  G06F3/0486

Abstract: A connection may be established between an extended reality (XR) platform and a non-XR platform. User input may be received via one of XR and non-XR devices comprised in the XR and non-XR platforms. Position information associated with the user input may be converted to be executable by an other one of the XR and non-XR devices. Controls may be implemented across the XR and non-XR platforms without switching the input mechanism associated with the one of the XR and non-XR devices to an input mechanism associated with the other one of the XR and non-XR devices.

公开(公告)号：US12254631B2

公开(公告)日：2025-03-18

申请号：US17585301

申请日：2022-01-26

Applicant: Lemon Inc.

Inventor： Peng Wang ,  Xueqing Deng ,  Xiaochen Lian

IPC: G06T7/11 ,  G06T3/40

Abstract: The techniques for dual-level semantic segmentation are provided. Data may be input to a first segmentation network. The input data comprises an image and label information associated with the image. The image may be captured at nighttime and may comprise a plurality of regions. At least one region among the plurality of regions may be determined based at least in part on output of the first segmentation network. The at least one region of the image may be cropped. The cropped at least one region may be input to a second segmentation network. A final output may be produced based on the output of the first segmentation network and output of the second segmentation network.

公开(公告)号：US20250086758A1

公开(公告)日：2025-03-13

申请号：US18728042

申请日：2023-01-13

Applicant: Lemon Inc.

Inventor： Yichun SHI ,  Xiao YANG ,  Xiaohui SHEN

IPC: G06T5/60 ,  G06T5/50

Abstract: The present disclosure provides an image processing method and device. The image processing method includes: performing, by an encoder and a first model, multiple iterations on an initial image to obtain a target image feature corresponding to the initial image; and performing, by a second model, image reconstruction based on the target image feature to obtain a reconstructed image of the initial image, both of the first model and the second model being neural networks for image reconstruction, wherein in the multiple iterations, an image feature extracted by the first model in the image reconstruction and an output image of the first model are feedback information for the encoder to assist the encoder in encoding the initial image.

公开(公告)号：US20250086257A1

公开(公告)日：2025-03-13

申请号：US18957333

申请日：2024-11-22

Applicant: Beijing Youzhuju Network Technology Co., Ltd. ,  Lemon Inc.

Inventor： Xiaojun Xu ,  Jinghan Jia ,  Hang Li ,  Yuanshun Yao

IPC: G06F21/16 ,  G06F40/289

Abstract: Embodiments of the present disclosure provide a solution for watermark processing. A method includes: dividing at least one portion of a n original text for watermark embedding into a plurality of original text segments; determining, for an original text segment of the plurality of original text segments, a target symbol from a symbol sequence in watermark information; converting, based on respective target symbols determined for the plurality of original text segments, the plurality of original text segments into a plurality of watermarked text segments by using a set of language models for watermark embedding, the set of language models corresponding to a set of symbol values respectively; and generating a watermarked text for the original text based on the plurality of watermarked text segments.

公开(公告)号：US20250078857A1

公开(公告)日：2025-03-06

申请号：US18241138

申请日：2023-08-31

Applicant: Lemon Inc.

Inventor： Wei Tsung LU ,  Ju-Chiang WANG

IPC: G10L21/0308 ,  G10L25/18 ,  G10L25/30

Abstract: The present disclosure describes techniques for implementing improved audio source separation. A complex spectrum X is split into a plurality of K bands along a frequency axis by applying band-split operations on the complex spectrum X. The complex spectrum is a time-frequency representation of audio signals. Each of the plurality of K bands is denoted as Xk, k=1, . . . , K. Each band Xk comprises one or more frequency bins. Each individual multilayer perceptron is applied to each band Xk to extract latent representations and obtain outputs Hk0. A time-domain transformer and a frequency-domain transformer are applied on a stacked representation H0. Time-domain and frequency-domain transformers are repeatedly applying in an interleaved manner for L times to obtain HL output from the transformer blocks. The HL is input into a multi-band mask estimation sub-model. A complex ideal ratio mask is generated based on outputs from the multi-band mask estimation sub-model.