6results about How to "Excellent efficiency" patented technology

The application discloses a point pair registration method and system based on feature guidance and double constraints, and belongs to the technical field of computer vision and robot grabbing. The method aims to solve the problems of recognition failure and insufficient estimation accuracy of traditional methods when parts are blocked and stacked, and point cloud features are not obvious. The scheme adopts a two-stage optimization strategy. Firstly, in the coarse registration stage, an adaptive sampling PPF algorithm guided by geometric features is proposed. By preferentially sampling points in the edge, curvature and other feature obvious areas, the robustness and efficiency of matching are improved. Secondly, in the fine registration stage, an ICP algorithm with multi-constraint optimization is proposed. The pose result obtained by coarse registration is used as the initial value. Through rotation and angle constraint, a multi-objective optimization function is constructed to guide the fine registration process to converge in the correct direction and avoid falling into local optimum, thereby ensuring the accuracy and physical feasibility of the final pose estimation. The application significantly improves the accuracy of industrial part pose recognition.

The application discloses a pathological feature recognition and negative exclusion method based on microscopic imaging, comprising the following steps: S1, collecting pathological section images and digitally generating original microscopic image data; S2, preprocessing the original microscopic image; S3, constructing a pathological image recognition network that fuses a transformation coder and a gated dynamic receptive field mechanism, and outputting a pathological feature vector; S4, modeling the context through attention guidance and category perception decoder, and outputting an image classification result; S5, constructing a discriminant boundary separation model based on positive and negative sample embedding, and judging the negative exclusion; S6, combining uncertainty and boundary distance for confidence weighted evaluation, setting a dynamic threshold, and screening out low-confidence samples; S7, encoding the classification result and the negative label into structured data, and sending to a diagnosis assistance system. The application fuses multi-scale modeling and negative screening mechanism, realizes intelligent recognition of pathological images and reliable diagnosis output.

This invention discloses an anonymous dynamic authentication and key negotiation method based on certificateless signatures. This method is based on a system model operating in an edge intelligent IoT environment, consisting of four entities: intelligent nodes, a key generation center, edge nodes, and a trusted authority. The method comprises five stages: system initialization performed by the key generation center; pseudo-identities assigned to system entities and public-private key pairs generated through entity registration involving intelligent nodes, edge nodes, and the trusted authority; mutual authentication and key negotiation between intelligent nodes and edge nodes; batch authentication; and encryption transmission of intelligent IoT data using a symmetric encryption algorithm based on the negotiated session key. This invention, based on a certificateless signature mechanism, avoids the complexity of certificate management and key escrow, while eliminating high-overhead operations such as bilinear pairing and exponential operations, effectively reducing the computational burden on resource-constrained terminals.

According to etiology and pathogenesis characteristics of smoking harm, 29 traditional Chinese medicines including adenophora tetraphylla, blueberries, mulberry leaves, mint and the like are prepared into preparations of different formulas through the steps of cutting, decocting and the like. The compound substitutional tea drink for oral administration and the plaster externally applied to the Tiantu acupoint, the Danzhong acupoint and the Shuangfeishu acupoint form an integrated combined system preparation for overall conditioning and prevention, and the purposes of relieving the developed symptoms and preventing injuries are achieved through comprehensive overall regulation and intervention by means of the self overall regulation and control mechanism of the five-internal-organ integrated system of the human body. The invention further discloses a preparation method of the compound substitutional tea drink for oral administration and the plaster externally applied to the Tiantu acupoint, the Danzhong acupoint and the Shuangfeishu acupoint. The combined system preparation has the effects of clearing lung and promoting salivation, relieving sore throat and detoxifying, moistening dryness and reducing phlegm, relieving cough and asthma, reinforcing qi and nourishing yin, and promoting blood circulation to remove meridian obstruction, and is used for preventing and treating smoking harm.

The application discloses a programmable drug release anti-infection and bone formation promoting multifunctional orthopedic internal implant device and a preparation method thereof. The implant is prepared according to the following steps: 1) introducing a titanium nanotube (TNT) structure on the surface of a titanium alloy base by using an anodic oxidation method; 2) sequentially loading an anti-infection component, a bone formation promoting factor and a blood vessel formation promoting factor into the TNT tube by using a vacuum sequential loading process; and 3) finally, coating a poly-tannic acid (PTA) coating on the surface of the material base by using a tannic acid (TA) in-situ self-polymerization technology. The multifunctional bone implant device can sequentially release the anti-infection drug, the blood vessel formation promoting factor and the bone formation promoting factor in the order of the vacuum drug loading, and the modified surface of the device has good drug release and oxidation resistance, so that the bone infection can be efficiently prevented and treated, and the bone repair efficiency is improved.

The invention discloses a bulldozer distance-based building air-conditioning system energy management method based on simulation reinforcement learning and a storage medium, and relates to the technical field of building energy systems, and the method comprises the steps: constructing a day-ahead optimization scheduling strategy based on a building air-conditioning system ash bin model; establishing a simulation reinforcement learning method based on the bulldozer distance; and the imitation reinforcement learning energy management method for the building air conditioning system is constructed. Compared with a traditional strengthening algorithm, the method has the advantages that higher convergence speed and sample efficiency are shown in the training process; and meanwhile, dependence on expert actions can be overcome through autonomous exploration: when errors exist in weather and personnel prediction, compared with an optimized scheduling strategy, the energy system operation cost can be further reduced, and compared with common GAILs (generative adversarial learning), the energy system operation cost can be further reduced. The introduced PWIL has the beneficial effects that the stability is superior in a framework, and the hyper-parameter adjustment burden can be reduced.