5results about How to "Prove superiority" patented technology

The invention discloses an emergency evacuation planning method based on improved ant colony algorithm and genetic fusion, and belongs to the technical field of emergency management and public safety. The method comprises the following steps: constructing a multi-objective optimization model taking minimization of total evacuation time T, total road section risk R and total personnel panic index P as objectives, and solving the multi-objective optimization model based on fusion of an improved ant colony algorithm and a genetic algorithm to obtain an optimal evacuation path scheme. The evacuation efficiency, safety and personnel psychological factors are comprehensively considered, the state transition probability and the pheromone updating strategy of the ant colony algorithm are improved, the global search mechanism of the genetic algorithm is introduced for deep fusion, and finally, the evacuation efficiency can be improved in a complex evacuation scene. And a global optimal evacuation path giving consideration to timeliness, safety and personnel psychological factors is quickly planned, and the evacuation efficiency is effectively improved.

The composite film is formed by laminating and compounding at least two layers of polymer porous films with anisotropic microporous structures, and the adjacent film layers are stacked after rotating by 45-135 degrees around the axis perpendicular to the film surface, the micropore channels of the upper and lower film layers form a non-through structure in a three-dimensional space, and decoupling of a heat flow transmission direction and a gas diffusion direction is realized. The interlayer dislocation degree is controlled by regulating and controlling the rotation angle, an efficient thermal resistance barrier is formed in the thickness direction, and meanwhile a gas diffusion channel is kept in the plane direction. The composite film has excellent heat insulation performance and air permeability, the heat conductivity coefficient can be as low as 0.028 W / (m.K), the water vapor transmission rate is kept at 980 g / (m.24 h) or above, the preparation process is simple and controllable, and the composite film can be widely applied to the fields of automobile interiors, building heat preservation, garment materials and the like.

This invention belongs to the field of smart grid and load monitoring technology, and provides a multi-task non-intrusive load decomposition method system. The method includes: acquiring the total load data sequence at the input port of the power consumption unit, and inputting the total load data sequence in parallel to a power decomposition branch and a state identification branch; the power decomposition branch processes the total load data sequence to generate a power prediction value for the target appliance; the state identification branch processes the total load data sequence to generate an operating state probability for the target appliance; and the power prediction value and the operating state probability are fused to generate the final decomposed power of the target appliance. This invention, through a dual-branch multi-task architecture and output fusion mechanism, collaboratively optimizes the power prediction and state identification tasks, effectively solving problems such as insufficient long-term dependency modeling, inaccurate capture of diverse features, and power false alarms caused by inconsistent prediction results in existing technologies, significantly improving the accuracy and reliability of load decomposition.

The invention belongs to the technical field of intelligent traffic and artificial intelligence, and discloses an IVCPS quantitative evaluation method based on big language model enabling weight matching, which comprises the following steps: firstly, identifying key test cases, and screening out a key case library by using LLM through component decomposition and a key quantitative matrix; secondly, constructing an initial quantitative evaluation method, and constructing a complete initial quantitative evaluation index system by LLM based on multi-source knowledge; thirdly, performing evaluation weight adaptive generation based on LLM and multi-source knowledge, injecting domain knowledge through an RAG technology, and outputting a weight scheme attached with a reasoning basis by the LLM acting as an expert group; and finally, closed-loop verification and optimization based on empirical indexes are carried out, and continuous iterative optimization of the evaluation model is realized. According to the method, the complete technical scheme of IVCPS evaluation system construction from subjective weight determination to objective weight determination and from static evaluation to dynamic self-adaption is realized, and the scientificity of an evaluation result and the guidance value for actual services are ensured.

This invention discloses a data augmentation method for low-resource news event extraction based on a large language model and generative adversarial networks. The method acquires original news events and extracts a training dataset from them. This dataset undergoes parsing, separation, generator, and discriminator processing, and is then combined with a Sentence-BERT model to obtain a high-quality augmented training dataset. This invention, through a generative paradigm, significantly improves the accuracy scores of both trigger word classification and argument classification in the event extraction subtask, achieving a dramatic performance leap. After generating augmented training data using this invention, the model is trained, ultimately achieving higher accuracy than other methods in the event extraction task, demonstrating the superiority of this data augmentation method.