Advanced New Technologies Co., Ltd.

Siemens Healthcare Diagnostics Gmbh

Alibaba Group Holding Limited

Siemens Healthcare Gmbh

Microsoft Technology Licensing, LLC

Beijing Sankuai Online Technology Co., Ltd

Siemens Healthineers Ag

Juan Xu

Haitao Zhang

Xin Guo

Jinlong Hou

Danni Cheng

Jian Wang

XiaoFan Zhang

Yue Hu

Bokun Wu

Yanqing Chen

Tian Shen

Puneet Sharma

Yuan Cheng

Zhi Zhang

Jian Jun Wang

Rui Hu

Kan Zhang

Fan Zhou

Xin-Jing Wang

Jiang Tian

Gong Zhang

Xiao Kong

Peixu Hou

Zhian Yu

Biao Tang

Rao Fu

Feiyi Wang

Yanqing Cheng

Zhi Yuan Zhang

Embodiments of the present specification disclose a system and method for generating a vehicle damage image on the basis of a GAN model. During operation, the system obtains a real vehicle image, generates an intermediate image based on the real vehicle image by labeling a target box on the real vehicle image and removing a portion of the real vehicle image within the target box, and generates the vehicle damage image based on the intermediate image by inputting the intermediate image into a machine-learning model, which outputs the vehicle damage image by filling a local image indicating vehicle damage into the target box of the intermediate image.

Method and apparatus for generating vehicle damage image on the basis of GAN network

An embodiment provides a system and method for sample labeling. During operation, the system obtains a plurality of historical loss assessment images and obtains a plurality of candidate samples from the plurality of loss assessment images. A respective candidate sample comprises an image of a candidate damage area detected in a corresponding historical loss assessment image. The system clusters the plurality of candidate samples into a plurality of class clusters. For a respective class cluster, the system determines a center candidate sample set corresponding to a class cluster center of the respective class cluster, receives a manual labeling result associated with candidate samples in the determined center candidate sample set, and performs, according to the manual labeling result, damage classification labeling on other unlabeled candidate samples in the respective class cluster to obtain a plurality of labeled samples.

Method and apparatus for sample labeling, and method and apparatus for identifying damage classification

A system is provided for identifying damages of a vehicle. During operation, the system can obtain a set of digital images associated with a set of tagged digital images as training data. Each tagged digital image in the set of tagged digital images may include at least one damage object. Based on the training data, the system can train a damage identification model by reducing noise associated with the damage object; generating a set of feature vectors for the training data; and using the set of feature vectors to optimize a set of parameters associated with the damage identification model to obtain a trained damage identification model. The system can then apply the trained damage identification model to obtain a damage category prediction result and determine a repair solution based on the damage category prediction result.

System and method for training a damage identification model

The inventive concepts herein relate to performing block retrieval on a block to be processed of a urine sediment image. The method comprises: using a plurality of decision trees to perform block retrieval on the block to be processed, wherein each of the plurality of decision trees comprises a judgment node and a leaf node, and the judgment node judges the block to be processed to make it reach the leaf node by using a block retrieval feature in a block retrieval feature set to form a block retrieval result at the leaf node, and at least two decision trees in the plurality of decision trees are different in structures thereof and/or judgments performed by the judgment nodes thereof by using the block retrieval feature; and integrating the block retrieval results of the plurality of decision trees so as to form a final block retrieval result.

Method and apparatus for performing block retrieval on block to be processed of urine sediment image

A natural language sentence is generated for a radiology report. One or more words are obtained where the one or more words were produced based on image processing of a radiology image. A computer implemented text analysis process is used to analyse the one or more words to generate a natural language sentence representing the radiology image. The natural language sentence is output. The computer implemented text analysis process includes: determining, for each of the one or more words, and using word modified embeddings, a vector representing the word; and determining, based on the determined one or more vectors, and using a text generator model, the natural language sentence.

Natural language sentence generation for radiology

An article generation method and device, and a computer storage medium. According to an example of the method, after a content source is mined based on requirement information inputted by a user, at least one topic dimension vector may be extracted from the mined content source by using a particular topic generation model. Then, for each extracted topic dimension vector, topic sentence mining is performed on the content source according to the topic dimension vector, to obtain topic sentences corresponding to the topic dimension vector. Finally, the topic sentences corresponding to the at least one topic dimension vector are spliced and synthesized, to generate an article conforming to the requirement information.

Article generation

Embodiments of the application provide a method, apparatus, server, and terminal device for obtaining a vehicle loss assessment image. A computer-implemented method for obtaining a vehicle loss assessment image comprises: receiving video data of a damaged vehicle; detecting one or more video images in the video data to identify a damaged portion in the one or more video images; classifying the one or more video images into one or more candidate image classification sets of the damaged portion based on the identified damaged portion; and selecting a vehicle loss assessment image from the one or more candidate image classification sets according to a screening condition.

Method and apparatus for obtaining vehicle loss assessment image, server and terminal device

A system is provided for identifying damages of a vehicle. During operation, the system can obtain a set of digital images associated with a set of tagged digital images as training data. Each tagged digital image in the set of tagged digital images may include at least one damage object. The system can train a damage identification model based on the training data. When training the damage identification model, the system may identify at least a damage object in the training data based on a target detection technique. The system may also generate a set of feature vectors for the training data. The system can use the set of feature vectors to optimize a set of parameters associated with the damage identification model to obtain a trained damage identification model. The system can then apply the trained damage identification model to obtain a damage category prediction result.

One embodiment provides a system and method for vehicle damage identification. During operation, the system obtains, a vehicle image and generates, based on a damage identification model and the obtained vehicle image, an initial damage identification result, which indicates a location of identified vehicle damage. The system displays the initial damage identification result, receives a modification to the initial damage identification result, and generates an updated damage identification result by inputting the damage identification result, image feature information extracted from the vehicle image, and the received modification to a long short-term memory (LSTM) model.

Damage identification result optimization method and apparatus

Embodiments described herein provide a system for facilitating image sampling for training a target detector. During operation, the system obtains a first image depicting a first target. Here, the continuous part of the first target in the first image is labeled and enclosed in a target bounding box. The system then generates a set of positive image samples from an area of the first image enclosed by the target bounding box. A respective positive image sample includes at least a part of the first target. The system can train the target detector with the set of positive image samples to detect a second target from a second image. The target detector can be an artificial intelligence (AI) model capable of detecting an object.

System and method for facilitating efficient damage assessments

Methods, systems, and computer-readable storage media for generation of a vehicle repair plan. Implementations include actions of receiving vehicle damage data including an image of a damaged vehicle. The vehicle damage data is processed to determine a component region. The component region is processed to determine a damaged area and a damage type of a portion of the damaged vehicle. A maintenance plan is generated for the damaged vehicle based on the damaged area and the damage type. The maintenance plan is initiated for the damaged vehicle.

Picture-based vehicle loss assessment

Embodiments of the present specification provide a method and system for improving the quality of a vehicle damage image on the basis of a GAN network. During operation, the system obtains a first vehicle damage image and inputs the first vehicle damage image to a machine-learning model to obtain a second vehicle damage image. The machine-learning model is trained using a plurality of labeled samples of vehicle damage images, and the second vehicle damage image has a better quality than the first vehicle damage image.

Method and apparatus for enhancing vehicle damage image on the basis of a generative adversarial network

One embodiment provides a method and system for performing segmentation on vehicle damage images. During operation, the system obtains a plurality of labeled segmentation and target detection samples. A labeled segmentation sample includes an image of a target object, a classification of the target object, and an outline of the target object; and a labeled target detection sample includes an image of a target object and a classification of the target object. The system trains a segmentation model, which comprises determining, based on labeled segmentation samples, mapping between a target detection parameter associated with target objects of a classification and a target segmentation parameter associated with outlines of the target objects; determining a target detection parameter for each classification; and obtaining a target segmentation parameter for each classification based on the corresponding target detection parameter and mapping, thereby determining the segmentation model for performing segmentation on vehicle damage images.

Method and apparatus for performing damage segmentation on vehicle damage image

One embodiment can provide a system for detecting optimizing a damage detection result. During operation, the system can obtain a digital image of a damaged vehicle, identify a set of candidate damaged areas from the digital image as the damage detection result. The system can then extract a set of feature vectors corresponding to the set of candidate damaged areas For each candidate damaged area, the system can calculate a set of similarity features between the candidate damaged area and other candidate damaged areas in the set of candidate damaged areas based on the set of feature vectors. The system can input the set of similarity features to a damage prediction module. The system can then determine whether the candidate damaged area is an exceptional area based on an output of the damage prediction module to optimize the damage detection result.

System and method for optimizing damage detection results

Structured report data is generated from a medical text report. A medical text report including one or more natural language statements is acquired. A computer implemented text analysis process analyses the medical text report to determine, for each natural language statement, one or more labels for the natural language statement. Structured report data including the determined one or more labels each in association with natural language data from the natural language statement to which the label corresponds is generated. The computer implemented text analysis process includes, for each natural language statement: determining, for each of the one or more words of the natural language statement, and, using word embeddings, a vector representing the word; and determining, based on the determined one or more vectors, and using a text classification model, the one or more labels associated with the natural language statement.

Growing community of inventors

Beijing, China

Juan Xu