-
公开(公告)号：EP4439584A1
公开(公告)日：2024-10-02
申请号：EP22906035.5
申请日：2022-10-12
发明人： WANG, Yimin , ZHANG, Changzheng , TU, Dandan , GAO, Yi , ZHENG, Jinping , CHEN, Xiaoshi
IPC分类号： G16H50/20
摘要： A method and an apparatus for interpreting medical detection data are disclosed. The method includes: obtaining medical detection data to be interpreted, where the medical detection data to be interpreted includes a detection image and indicator data; performing image recognition on the detection image, to obtain image recognition data; and interpreting, by using a rule library, the indicator data and the image recognition data, to obtain an interpretation result, where an interpretation rule in the rule library is obtained by mining and analyzing a plurality of pieces of interpreted data based on a data mining algorithm, and the rule library is dynamically updated with an interpretation process. Because the interpretation rule in the rule library is obtained by mining and analyzing the plurality of pieces of interpreted data based on the data mining algorithm, a potential data law that is difficult to be discovered by human can be mined, and a more accurate interpretation rule can be extracted. In addition, the rule library is dynamically updated with the interpretation process, so that data laws covered by the rule library can be enriched, thereby improving accuracy of automatic interpretation of the medical detection data.
-
2.发明公开
公开(公告)号：EP4231229A1
公开(公告)日：2023-08-23
申请号：EP21890893.7
申请日：2021-10-16
发明人： WANG, Xiudong , JIN, Xin , TU, Dandan
IPC分类号： G06T7/00
摘要： Embodiments of this application relate to the AI field, and disclose an industrial defect recognition method and system, a computing device, and a storage medium. In embodiments of this application, a target region is first extracted from a to-be-recognized image, and then a defect coarse-selection region including an industrial defect is obtained from the target region. Through two times of region extraction, a proportion of a size of the industrial defect to a size of a background is increased, so that a probability of detecting a small-sized industrial defect can be increased. After the defect coarse-selection region including the industrial defect is detected, localization and size estimation are further performed on the industrial defect in the defect coarse-selection region, so that precision of the defect localization and size estimation can be effectively improved. In addition, in embodiments of this application, not only a defect type is recognized, but also localization and size estimation can be performed on the industrial defect, enriching recognition dimensions of the industrial defect.
-
3.发明公开
公开(公告)号：EP4280226A1
公开(公告)日：2023-11-22
申请号：EP21922457.3
申请日：2021-11-15
发明人： GONG, Weimeng , LI, Jun , TU, Dandan
摘要： This application provides a remote reproduction method, applied to a remote reproduction system, where the system includes a first terminal worn by a first user and a second terminal worn by a second user, and the first user and the second user are located in different geographical scenarios. The method includes: The second terminal obtains an action image of the first user, where the action image of the first user includes a sequence of at least one action formed by a pre-constructed human body model of the first user, and then the second terminal reproduces, for the second user, the action image of the first user to a geographical scenario in which the second user is located. According to the method, when the second terminal side reproduces the image of the first user, a multi-angle image does not need to be transmitted in real time, thereby reducing network resource occupation, avoiding frame loss and frame freezing when network quality is poor, and improving interaction experience.
-
公开(公告)号：EP4307217A1
公开(公告)日：2024-01-17
申请号：EP21937741.3
申请日：2021-12-18
发明人： DU, Changde , JIN, Xin , JIANG, Huajie , TU, Dandan
IPC分类号： G06T7/00
摘要： A fault image generation method and apparatus are provided. The fault image generation method includes: obtaining a non-fault image and a first fault image, where the non-fault image records a first object that is not faulty, the first fault image records a second object that is faulty, and a type of the first object is different from a type of the second object; and migrating a fault pattern of the second object in the first fault image to the first object in the non-fault image, to obtain a second fault image, where the second fault image presents the first object in a faulty state. A part of an image of a specific type of object is replaced by using a fault pattern that records another type of object, to obtain a second fault image of the specific type of object. This improves universality and flexibility of obtaining the fault pattern, and increases diversity of fault types in the second fault image.
-
公开(公告)号：EP4276601A1
公开(公告)日：2023-11-15
申请号：EP21922417.7
申请日：2021-10-28
发明人： HE, Jia , PAN, Feiyang , JIN, Xin , TU, Dandan
IPC分类号： G06F8/38
摘要： This application relates to a page layout method and apparatus. The method includes: obtaining page information, element information of at least one page element to be laid out, and a layout rule; obtaining at least one candidate page layout policy based on the page information, the element information of the at least one page element to be laid out, and the layout rule by using a reinforcement learning algorithm; and determining a target page layout policy from the at least one candidate page layout policy by using an imitation learning algorithm.
-
公开(公告)号：EP4177792A1
公开(公告)日：2023-05-10
申请号：EP21851426.3
申请日：2021-07-05
发明人： WU, Shuzhe , JIN, Xin , LI, Xincheng , TU, Dandan
摘要： This application provides a method, an apparatus, and a computing device for updating an AI model, and a storage medium, and belongs to the field of artificial intelligence technologies. The method includes: obtaining an inference data set, where inference data in the inference data set is used to be input into an existing AI model for performing inference; determining that there is a difference between data distribution of the inference data set and data distribution of a training data set, where the training data set is a data set used for training the existing AI model; and updating the existing AI model by using the inference data set to obtain an updated AI model. According to this application, the existing AI model can be updated in a timely manner when it is perceived that there is a difference between data distribution of the inference data set and data distribution of the training data set, instead of updating the existing AI model only when a user finds that precision of the AI model is reduced. Therefore, the AI model can be updated in a timely manner.
-
公开(公告)号：EP3989158A1
公开(公告)日：2022-04-27
申请号：EP19937682.3
申请日：2019-07-18
发明人： LI, Jun , LIU, Haomiao , GONG, Weimeng , TU, Dandan
摘要： This application provides a video similarity detection method, relates to the field of artificial intelligence, and specifically relates to computer vision. The method includes: A detection apparatus receives a first video, and determines a key frame of the first video based on the first video; inputs the key frame to a feature extraction model to obtain a feature of the key frame; determines a similar key frame and a second video based on the feature of the key frame, where the first video is a to-be-detected video, and the second video is a video, in a video library, that is similar to the first video; and further inputs the key frame and the similar key frame to an editing type recognition model to obtain an editing type, where the editing type indicates an editing type used for editing between the first video and the second video. The feature extraction model and the editing type recognition model are separately different based on neural network models. According to this method, the similar video corresponding to the to-be-detected video can be more accurately determined, and the type of editing performed on the to-be-detected video compared with the similar video is further obtained.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.025 秒)
