-
公开(公告)号：US20250021610A1
公开(公告)日：2025-01-16
申请号：US18901831
申请日：2024-09-30
Inventor： Zeyang LEI , Siqi BAO , Hua WU , Haifeng WANG
IPC: G06F16/9535
Abstract: A human-machine interaction solution which relates to the field of artificial intelligence technologies, such as natural language processing technologies, large language models, deep learning technologies, or the like, is proposed. The solution may include: acquiring a question input by a user during a conversation with a large language model; retrieving memory information in a memory bank, the memory information being historical memory information about the user; and in response to retrieved memory information required for generating answer information corresponding to the question, taking the retrieved memory information as matched memory information, and generating the answer information by the large language model in conjunction with the matched memory information.
-
公开(公告)号：US12198236B2
公开(公告)日：2025-01-14
申请号：US17807132
申请日：2022-06-15
Inventor： Xiaopei Hou , Junjun Zhang , Changjun Sheng , Juntao Tong , Jiajing Fu , Dan Ma , Yingjie Niu , Wenya Liu , Yuke Zhang , Yun Zhao , Youhan Chen , Xiufeng Han , Xiulong Xia , Yang Zhang
Abstract: Provided are a map data processing method and apparatus, and a storage medium, which relate to the field of data processing technology and, in particular, to artificial intelligence technology, for example, computer vision, map technology, and intelligent transportation. A specific implementation solution includes: processing landform coverage data according to a type of surface species coverage and a data processing rule associated with the type of surface species coverage to obtain a surface species coverage effect map; and generating a landform map according to the surface species coverage effect map and a reference map.
-
公开(公告)号：US12195019B2
公开(公告)日：2025-01-14
申请号：US18003017
申请日：2022-11-28
Inventor： Shu Jiang , Hao Liu , Szu-Hao Wu , Fuyang Zhao , Xiaoyi Zhu , Haofeng Kou , Helen K. Pan
Abstract: In one embodiment, a microcontroller unit (MCU) receives an expected state of an autonomous driving vehicle (ADV) from a controller of the ADV, where the controller controls motions of the ADV using a control algorithm. The MCU receives sensor data from one or more sensors of the ADV. The MCU determine an actual state of the ADV based on the sensor data. The MCU determines a performance metric of the control algorithm based on the expected state and the actual state. In response to determining the performance metric has satisfied a predetermined condition, the MCU determines a plurality of weight values for the control algorithm. The MCU sends the plurality of weight values to the control system to tune one or more weight parameters of the control algorithm using the plurality of weight values, where the controller controls the ADV using the tuned control algorithm.
-
公开(公告)号：US20250010870A1
公开(公告)日：2025-01-09
申请号：US18887857
申请日：2024-09-17
Inventor： Haowei ZHAO , Pengfei ZHANG , Yuchen SUN , Yuqing GUO , Kuan ZHANG , Lin MA , Changchun LIU
Abstract: A method for controlling a vehicle, including: simulating and deducing, based on current state information between a target vehicle and a traffic participant, an interaction process between the target vehicle and the traffic participant to obtain an initial part of a cooperative game tree; updating, in response to there being a target leaf node that is capable of being expanded to obtain a target child node in the initial part, respective nodes on a deduction path from the root node to the target child node based on a path parameter of an updated predicted trajectory, to obtain a complete cooperative game tree composed of the initial part and the target child node; and determining a first control instruction of the target vehicle using the complete cooperative game tree, to control the target vehicle using the first control instruction.
-
公开(公告)号：US12192598B2
公开(公告)日：2025-01-07
申请号：US17646122
申请日：2021-12-27
Inventor： Mingyue Zhang
IPC: H04N21/8547 , G06F40/137 , G06F40/40
Abstract: A method of processing audio or video data is provided, which relates to a field of a natural language processing technology, and in particular to a semantic understanding of a natural language. The method includes: extracting a text information from the audio or video data; generating a text outline and a plurality of time periods according to the text information, the text outline includes multi-level outline entries, and the plurality of time periods are associated with the multi-level outline entries; generating a display field for the audio or video data according to the text outline and the plurality of time periods; adding the display field to the audio or video data, so as to obtain updated audio or video data. A device, and a storage medium are further provided.
-
Patent Agency Ranking
公开(公告)号：US12190445B2
公开(公告)日：2025-01-07
申请号：US17974416
申请日：2022-10-26
Inventor： Zhangwei Meng , Hao Li , Gen Li , Jiacheng Ding
Abstract: A high-precision map construction method, apparatus, and electronic device are provided. The method can include: displaying a first color image corresponding to a first track point; according to a first color sub-image and a depth image corresponding to the first track point, obtaining point cloud data corresponding to the first sub-color image, wherein the first sub-color image is a sub-image corresponding to an element to be added in the first color image, and the element to be added is an element to be added in a high-precision map for display; extracting a bounding box corresponding to the point cloud data; and generating a newly-added three-dimensional element according to the bounding box in the high-precision map.
-
37.发明申请公开(公告)号：US20250008168A1
公开(公告)日：2025-01-02
申请号：US18747103
申请日：2024-06-18
Inventor： Chenfei Wang
IPC: H04N21/2187 , H04N21/231 , H04N21/239
Abstract: The disclosure provides a method and an apparatus for scheduling a return-to-origin link, an electronic device and a storage medium, and relates to a field of artificial intelligence technologies, more particularly to a field of cloud computing and cloud storage technologies. The method includes: constructing a custom data frame, the custom data frame including address information of a push stream node; adding the custom data frame to live data to be transmitted, and distributing the live data by a first return-to-origin link to edge nodes which receive a play request of each user; requesting to employ a second return-to-origin link to perform return-to-origin operation in response to detecting that a line traffic corresponding to any edge node in the edge nodes which receive the play request of each user exceeds a preset threshold, the second return-to-origin link being shorter than the first return-to-origin link; and integrating the live data transmitted by the first return-to-origin link and live data transmitted by the second return-to-origin link, and distributing integrated live data to the user. With the disclosure, delay the reduced without introducing other central control system, and the user experience is improved.
-
公开(公告)号：US12183324B2
公开(公告)日：2024-12-31
申请号：US17738651
申请日：2022-05-06
Inventor： Xiaoyin Fu , Zhijie Chen , Mingxin Liang , Mingshun Yang , Lei Jia , Haifeng Wang
IPC: G10L15/02 , G06F16/683 , G10L15/187 , G10L15/26
Abstract: The present disclosure provides speech recognition and codec methods and apparatuses, an electronic device and a storage medium, and relates to the field of artificial intelligence such as intelligent speech, deep learning and natural language processing. The speech recognition method may include: acquiring an audio feature of to-be-recognized speech; encoding the audio feature to obtain an encoding feature; truncating the encoding feature to obtain continuous N feature fragments, N being a positive integer greater than one; and acquiring, for any one of the feature segments, corresponding historical feature abstraction information, encoding the feature segment in combination with the historical feature abstraction information, and decoding an encoding result to obtain a recognition result corresponding to the feature segment, wherein the historical feature abstraction information is information obtained by feature abstraction of recognized historical feature fragments.
-
公开(公告)号：US12174902B2
公开(公告)日：2024-12-24
申请号：US18016754
申请日：2022-07-25
Inventor： Zhou Cheng
IPC: G06F16/9538 , G06N3/0455
Abstract: A method is provided that includes: determining a plurality of recall data associated with data to be searched; determining, for each recall data of the plurality of recall data, a recommendation degree of the recall data based on a similarity between the recall data and each recall data of the plurality of recall data; and ranking the recall data in the plurality of recall data based on the recommendation degree of each recall data of the plurality of recall data.
-
公开(公告)号：US20240420587A1
公开(公告)日：2024-12-19
申请号：US18749421
申请日：2024-06-20
Inventor： Zhenhui SHI , Yuan XIA , Jun CHEN , Haifeng HUANG
IPC: G09B7/02
Abstract: A method includes: performing retrieval in question-answer text in a drug knowledge base based on drug question text, to obtain answer text corresponding to the drug question text; performing retrieval in drug instructions in the drug knowledge base based on the drug question text, to obtain instruction text corresponding to the drug question text; and generating response text corresponding to the drug question text based on the answer text and the instruction text.
-
-
-
-
-
-
-
-
-
Search Results
1526
records
(took 0.042 seconds)
