-
公开(公告)号：US12277387B2
公开(公告)日：2025-04-15
申请号：US18056197
申请日：2022-11-16
Inventor： Ruiqing Zhang , Zhongjun He , Zhi Li , Hua Wu
IPC: G06F40/232 , G06F40/279 , G06F40/53
Abstract: A text processing method is provided. The method includes: a first probability value of each candidate character of a plurality of candidate characters corresponding to a target position is determined based on character feature information corresponding to the target position in a text fragment to be processed, wherein the character feature information is determined based on a context at the target position in the text fragment to be processed; a second probability value of each candidate character of the plurality of candidate characters is determined based on a character string including the candidate character and at least one character in at least one position in the text fragment to be processed adjacent to the target position; and a correction character at the target position is determined based on the first probability value and the second probability value of each candidate character of the plurality of candidate characters.
-
312.发明申请公开(公告)号：US20250117668A1
公开(公告)日：2025-04-10
申请号：US18987988
申请日：2024-12-19
Inventor： Xinran He , Xianwei Xue , Bolei He , Kunbin Chen , Jinchang Luo , Ruigao Li
IPC: G06N3/096 , G06N3/0475
Abstract: A method for model training based on a large model includes: determining a first large model as a teacher model of a language model, and performing distillation learning on the language model based on the first large model; inputting a first prompt text into the language model, and obtaining a plurality of first response texts for the first prompt text output by the language model; determining a reference response text for the first prompt text from the plurality of first response texts; and training the language model based on the reference response text for the first prompt text.
-
公开(公告)号：US12270672B2
公开(公告)日：2025-04-08
申请号：US17712557
申请日：2022-04-04
Inventor： Tingting Zhai , Peng Yang , Hongfei Zhu
IPC: G01C21/36
Abstract: The present disclosure provides a method for generating navigation information, an apparatus for generating navigation information, a device, a medium, and a product. The present disclosure relates to the technical field of computers, and specifically relates to the technical field of artificial intelligence, and the present disclosure may be applied to a map navigation scenario. A specific implementation includes: acquiring intersection feature information; determining a set of a complex intersection based on the intersection feature information; determining intersection type information corresponding to the complex intersection in the set of the complex intersection; and generating navigation information corresponding to the complex intersection in the set of the complex intersection based on the intersection type information.
-
公开(公告)号：US20250103825A1
公开(公告)日：2025-03-27
申请号：US18974450
申请日：2024-12-09
Inventor： Xinchao Xu , Wenquan Wu
IPC: G06F40/35
Abstract: A method for generating a dialogue includes acquiring a current first question statement and historical dialogue information associated with the first question statement; acquiring, from a knowledge base, a first knowledge item associated with the first question statement and a second knowledge item having a question-answer relationship with the first knowledge item; obtaining a first reply statement output by a generative model by inputting the first question statement, the first knowledge item, and the historical dialogue information into the generative model; evaluating the first reply statement based on the first question statement, the first knowledge item, and the second knowledge item; and outputting the first reply statement in response to the first reply statement passing evaluation.
-
公开(公告)号：US12260492B2
公开(公告)日：2025-03-25
申请号：US18099602
申请日：2023-01-20
Inventor： Di Wang , Ruizhi Chen , Chen Zhao , Jingtuo Liu , Errui Ding , Tian Wu , Haifeng Wang
Abstract: A method for training a three-dimensional face reconstruction model includes inputting an acquired sample face image into a three-dimensional face reconstruction model to obtain a coordinate transformation parameter and a face parameter of the sample face image; determining the three-dimensional stylized face image of the sample face image according to the face parameter of the sample face image and the acquired stylized face map of the sample face image; transforming the three-dimensional stylized face image of the sample face image into a camera coordinate system based on the coordinate transformation parameter, and rendering the transformed three-dimensional stylized face image to obtain a rendered map; and training the three-dimensional face reconstruction model according to the rendered map and the stylized face map of the sample face image.
-
Patent Agency Ranking
公开(公告)号：US12260186B2
公开(公告)日：2025-03-25
申请号：US17992436
申请日：2022-11-22
Inventor： Zhe Hu , Jiachen Liu , Xinyan Xiao
Abstract: A method of generating a text, a method of training a text generation model, an electronic device, and a storage medium, which relate to a field of a computer technology, in particular to fields of deep learning and natural language processing technologies. A specific implementation solution includes: determining a reference feature representation of a target semantic information; determining, based on the reference feature representation and at least one predetermined logical character, at least one sentence latent representation respectively corresponding to the at least one predetermined logical character; and generating a target text content based on the at least one sentence latent representation.
-
317.发明申请公开(公告)号：US20250094877A1
公开(公告)日：2025-03-20
申请号：US18969719
申请日：2024-12-05
Inventor： Fan WANG , Hua WU , Yingzhan LIN , Zengfeng ZENG , Yufeng HU , Jianhui DING , Haifeng WANG
IPC: G06N20/00
Abstract: A large model-based method of generating a text, a method of training a text generation model, a device, and a medium are provided, which relate to a field of artificial intelligence technology, specifically to fields of deep learning, natural language processing and large model technologies. The large model-based method of generating a text includes: acquiring a memory state for a text to be processed, where the memory state is generated based on a previous text of the text to be processed; determining an embedding feature of the text to be processed as an initial hidden state, and processing the memory state and the initial hidden state by using a first attention mechanism to obtain an updated hidden state; and generating a subsequent text for the text to be processed based on the updated hidden state.
-
公开(公告)号：US20250094806A1
公开(公告)日：2025-03-20
申请号：US18967167
申请日：2024-12-03
Inventor： Junyuan Shang , Yilong Chen , Zhenyu Zhang , Shuohuan Wang , Yu Sun , Hua Wu
IPC: G06N3/082 , G06N3/0475
Abstract: Provided is a large language model training method, an electronic device and a storage medium, relating to the field of artificial intelligence technologies, and in particular, to the fields of deep learning, natural language processing and large model. The method includes: performing dimension reduction parameter fusion on a two-dimensional parameter matrix on each channel in each network layer in a first large language model, respectively, to obtain a second large language model; performing layer reduction parameter fusion on network layers in the second large language model based on a three-dimensional parameter matrix of each network layer in the second large language model to obtain a third large language model; and training the third large language model to obtain a target large language model under the condition that the target loss function determined based on the first and third large language models meets a preset first function condition.
-
公开(公告)号：US20250094713A1
公开(公告)日：2025-03-20
申请号：US18967529
申请日：2024-12-03
Inventor： Shuohuan WANG , Yekun CHAI , Siyu DING , Junyuan SHANG , Zhenyu ZHANG , Yu SUN , Hao TIAN , Hua WU , Haifeng WANG
IPC: G06F40/284 , G06F16/3329
Abstract: A multimodal data generation method is provided. The method includes: inputting a query data sequence into a multimodal model, to obtain a plurality of tokens in a response data sequence, where a current token is generated through the following operations: inputting the query data sequence and a current response data sequence into the multimodal model, so that the multimodal model generates the current token based on the query data sequence and the current response data sequence, in response to determining that the current token belongs to a first data modality; or inputting the query data sequence and a current response data sequence into the multimodal model, so that the multimodal model denoises an initial token sequence based on the query data sequence and the current response data sequence, to generate a result token sequence, in response to determining that the current token belongs to a second data modality.
-
公开(公告)号：US20250094139A1
公开(公告)日：2025-03-20
申请号：US18965152
申请日：2024-12-02
Inventor： Dianhai YU , Wei ZHOU , Xiang GAO , Tiezhu GAO
Abstract: A method of generating a code based on a large model, an electronic device and a storage medium are provided, which relate to the field of artificial intelligence technology, in particular to the fields of deep learning technology and large model technology. The method includes: acquiring a first descriptive text input by a user, where the first descriptive text is configured to characterize a code requirement; searching for a positive code and a negative code matching the first descriptive text, where each of the positive code and the negative code is determined based on a preference operation of the user for a historical code output by the large model; generating a second descriptive text according to the first descriptive text, the positive code, and the negative code; and inputting the second descriptive text into the large model to output a target code matching the code requirement.
-
-
-
-
-
-
-
-
-
Search Results
1526
records
(took 0.035 seconds)
