Huazhong University of Science and Technology

Wuhan Kaidi Engineering Technology Research Institute Co., Ltd.

Changjiang Survey Planning Design and Research Co., Ltd.

Feng Zhao

Hai Jin

Haiqing Zhang

Langjunqing Jin

Hong Li

Fei Yu

Xuming Zhang

Peng Qiu

Qigui Yang

Xin Zhao

Min Li

Xinqiang Niu

Feng Li

Lijun Su

Qin Sun

Mingyue Ding

Xuehong Yang

Tao Xu

Xia Hua

Zhenhua Yao

Lixin Liu

Baixing Liu

Weina Yu

Maohua Li

Fei Zhu

Guanyu Li

Jinxia Ren

Liping Cheng

Jingke Zhang

The present invention relates to a relation-enhancement knowledge graph embedding method and system, wherein the method at least comprises: performing collaborative coordinate-transformation on entities in the knowledge graph; performing relation core enhancement by means of relation-entropy weighting, so as to endow entity vectors with strong relation property; building an interpretability mechanism for a knowledge graph embedding model, and accounting for effectiveness and feasibility of the relation enhancement by proving convergence of the knowledge graph embedding model; and using a dynamic parameter-adjusting strategy to perform learn representation learning of to the vectors in the knowledge graph, and configuring deviation control to ensure accurate embedding. The present invention can measure rationality of facts with improved accuracy, prove through reasoning the modeling ability of the model from the perspective of complex relation pairs, perform vector computing for entities and relations, thereby accomplishes knowledge graph embedding and reasoning.

Relation-enhancement knowledge graph embedding method and system

The present invention relates to method and device for text-enhanced knowledge graph joint representation learning, the method at least comprises: learning a structure vector representation based on entity objects and their relation linking in a knowledge graph and forming structure representation vectors; discriminating credibility of reliable feature information and building an attention mechanism model, aggregating vectors of different sentences and obtain association-discriminated text representation vectors; and building a joint representation learning model, and using a dynamic parameter-generating strategy to perform joint learning for the text representation vectors and the structure representation vectors based on the joint representation learning model. The present invention selective enhances entity/relation vectors based on significance of associated texts, so as to provide improved semantic expressiveness, and uses 2D convolution operations to train joint representation vectors. As compared to traditional translation models, the disclosed model has better performance in tasks like link prediction and triad classification.

Method and device for text-enhanced knowledge graph joint representation learning

The present invention discloses a registration method and system for a non-rigid multi-modal medical image. The registration method comprises: obtaining local descriptors of a reference image according to Zernike moments of order 0 and repetition 0 and Zernike moments of order 1 and repetition 1 of the reference image; obtaining local descriptors of a floating image according to Zernike moments of order 0 and repetition 0 and Zernike moments of order 1 and repetition 1 of the floating image; and finally obtaining a registration image according to the local descriptors of the reference image and the floating image. In the present, by using self-similarity of the multi-modal medical image and adopting the Zernike moment based local descriptor, the non-rigid multi-modal medical image registration is thus converted into the non-rigid mono-modal medical image registration, thereby greatly improving its accuracy and robustness.

Registration method and system for non-rigid multi-modal medical image

A construction layout for caverns of an underground nuclear power plant, including: two primary caverns accommodating nuclear reactor powerhouses, electric powerhouse caverns, safe powerhouse caverns, auxiliary powerhouse caverns, nuclear fuel powerhouse caverns, connecting powerhouse caverns, a first primary traffic tunnel, a third primary traffic tunnel, a second primary traffic tunnel, a fourth primary traffic tunnel, and a primary steam channel. The electric powerhouse caverns, the safe powerhouse caverns, and the nuclear fuel powerhouse caverns are arranged along the longitudinal direction of the mountain. Each of the safe powerhouse caverns and each of the nuclear fuel powerhouse caverns are disposed on two sides of each of the two primary caverns in the longitudinal direction of the mountain, respectively. Each of the electric powerhouse caverns and each of the safe powerhouse caverns are located on a same side of each the two primary caverns.

Construction layout for caverns of underground nuclear power plant

The invention is relates to a method and a system for producing synthetic gas from biomass by high temperature gasification, including: feeding raw material, carbonizing, pulverizing the charcoal, and transporting charcoal powder to the gasification furnace for gasification. A heat source for the carbonizing is achieved by a direct combustion reaction between external combustible gas and external oxygen in a carbonization furnace. The heat emitted from the reaction being directly provided to the necessary heat of biomass pyrolysis, and yielding pyrolysis gas and charcoal from carbonization furnace. The temperature of carbonization furnace is controlled at between 400&#xb0; C. and 600&#xb0; C. by adjusting the amount of oxygen. The temperature of a burner nozzle of the carbonization furnace is controlled at between 1200&#xb0; C. and 1800&#xb0; C. by adjusting the input amount of the external combustible gas at between more than 1 and less than 5 times that required for a complete combustion with the external oxygen. Pulverizing the charcoal includes charcoal cooling, decompression, pulverizing, supercharging, fluidizing, and transported to the gasifier by controlling the amount of pyrolysis gas.

Method and system for producing synthetic gas from biomass by high temperature gasification

A method and a system for producing synthetic gas from biomass by high temperature gasification, including: feeding raw material, carbonizing, pulverizing the charcoal, and transporting charcoal powder to the gasification furnace for gasification. A heat source for the carbonizing is achieved by a direct combustion reaction between external combustible gas and external oxygen in a carbonization furnace. The heat emitted from the reaction being directly provided to the necessary heat of biomass pyrolysis, and yielding pyrolysis gas and charcoal from carbonization furnace.

Growing community of inventors

Wuhan, China

Feng Zhao