25results about How to "Improve final performance" patented technology

The invention discloses a domain-adaptive retrieval enhancement generation method and system, and the method comprises the steps: carrying out the document analysis and semantic partitioning of a document through a semantic understanding model and a document rule, and storing document fragments; on the basis of the large language model and a preset question library, generating a question and disassembling the question; performing correlation evaluation and sorting on the initial retrieval results in combination with a retrieval technology; candidate content most matched with the cue words is screened out through a large language model, and question-retrieval fragments are scored and marked; performing fusion on the initial retrieval result and the scoring and labeling result to construct positive and negative samples, and constructing a supervised data set; and based on a preset loss function, utilizing the supervised data set to carry out supervised training on the knowledge semantic search model, replacing the RAG mixed search module, and carrying out continuous iteration. By means of the technical scheme, new domain knowledge and operation feedback data can be flexibly applied, and domain self-adaptive retrieval enhancement generation is achieved.

The invention relates to a construction method of a cooperative combat decision-making agent for ground unmanned equipment, and aims to solve the problem of space dimension disaster of a complex cooperative combat task. The DRL solution space is effectively compressed, the exploration efficiency is improved, and meanwhile intelligent decision making of tasks with different granularities in the whole combat process is achieved; aiming at the problem of generating a'task layer 'combat command action strategy, a cooperative combat decision-making agent network model is constructed to realize the unified coordination control from the effective representation of complex state input to the combat action; by constructing a distributed training framework, the sampling and training efficiency is improved, and high-throughput asynchronous parallel training of a cooperative combat decision-making agent network model is realized; by establishing a combat decision agent learning algorithm based on deep reinforcement learning and solving the combat decision agent learning algorithm, the learning efficiency and final performance of an agent network model are effectively improved.

The invention discloses a hypersonic flight vehicle adaptive attitude control method based on near-end strategy optimization, and belongs to the technical field of hypersonic flight vehicle control, and the method comprises the steps: building an air-breathing hypersonic flight vehicle longitudinal dynamic model considering power; performing reinforcement learning training on the obtained environment model by using a PPO algorithm to obtain an optimized control strategy; selecting a proper state representation and action space, and designing a strategy network and a value network for the processed model, so that an original complex attitude control problem is converted into a reinforcement learning problem which can be effectively learned; and training the reinforcement learning model by using an improved PPO algorithm to obtain a final control instruction. According to the method, the model is trained by using the PPO algorithm, so that the defects of complex controller design, strict requirement on model precision and the like of a traditional control method can be effectively overcome. A simulation experiment verifies that pitch angle tracking can be effectively realized, and the stability of an execution mechanism is guaranteed.

The invention belongs to the technical field of material science, and discloses a shape optimization method for a high-temperature alloy disc type pre-forged piece. According to the method, finite element numerical simulation, a support vector machine and a genetic algorithm are combined, a GA-SVR prediction model between an input variable and a target function is established, the optimal value of the target function is predicted, and the optimal geometric parameter combination of the pre-forged piece is obtained. Firstly, the shape of a pre-forged piece is preliminarily designed through experience, then a finite element simulation result is extracted to establish a data set, parameters of a support vector machine model serve as a target function of a genetic algorithm by means of the data set, the parameters of the support vector machine model are optimized by means of the genetic algorithm, and an optimal prediction model is obtained. And for the size parameter combination of the pre-forged piece when the best deformation uniformity evaluation index is obtained, the deformation uniformity of finish forging is effectively improved through global optimization of the genetic algorithm, so that the final performance of the forged piece is improved.

The invention discloses a road surface disaster detection method and system, electronic equipment and a storage medium, and relates to the technical field of intelligent traffic management and computer vision, and the method comprises the steps: collecting image data containing a plurality of road surface disaster types, carrying out the data marking in each image data, and carrying out the data marking; a data sample is constructed through each piece of image data subjected to data annotation; training the improved YOLOv10 model by using the data sample until a loss function of the improved model reaches a preset end condition, and determining the improved model of which the loss function reaches the preset end condition as a disaster detection model; acquiring a to-be-detected image of a to-be-detected road surface, and inputting the to-be-detected image into the disaster detection model for processing to obtain a disaster detection result of the to-be-detected road surface, the disaster detection result including a disaster type and a disaster position; by combining the deep learning technology and optimization algorithm design, the problem that the existing method is insufficient in detection precision, robustness and applicability is solved.

The invention discloses a two-stage sparse method based on a small sample rapid sparse large-scale language model, and the method comprises the following steps: S1, mask initialization: based on a plurality of importance indexes for measuring parameters, employing a plurality of mask initialization methods to initialize a mask of a language model; s2, reordering the masks: reordering the masks based on the small sample calibration set and the straight-through estimator; s3, mask adjustment: based on the small sample calibration set and the reordered mask matrix in the step S2, taking an original model as a teacher model, taking a sparse model as a student model, realizing a block-level self-distillation process of the large language model in a time dimension before and after sparsification, and obtaining the sparse model; the method consumes less computing power, uses a smaller data set, occupies less GPU memory while realizing considerable performance, does not influence the reasoning speed of the sparse model, and has remarkable practical value and application prospect.

The present invention relates to the technical field of steel pipe production, and specifically to a heat treatment device for annealing steel pipes, comprising a main body, a heating mechanism and a feeding and discharging mechanism, wherein the heating mechanism is arranged on the top of the main body, and the feeding and discharging mechanism is arranged on the top of the heating mechanism, wherein the heating mechanism comprises a heating chamber, wherein the top of the heating chamber is provided with an opening, wherein a rotating frame is rotatably connected inside the heating mechanism, wherein the circumferential outer surface of the rotating frame is provided with an installation groove, wherein a clamping mechanism is arranged inside the installation groove for clamping and rotating the steel pipe to achieve uniform heating, wherein the feeding and discharging mechanism comprises a limiting shell fixedly installed at the top opening of the heating chamber, wherein cavities are arranged inside the two ends of the limiting shell. The present invention realizes continuous self-rotation heating of the steel pipe by combining the rotating frame with the clamping mechanism, wherein the automatic feeding and discharging of the feeding and discharging mechanism shortens the production cycle, wherein the continuous rotation of the rotating frame supports the simultaneous annealing of multiple pipes, thereby meeting large-scale production and reducing labor intensity.

The invention discloses a blood filtering membrane preparation device and method, and belongs to the technical field of blood filtering membrane preparation. The method comprises the steps that materials are prepared, a membrane material is polyethersulfone, a solvent is a mixed solvent and specifically comprises N-methyl pyrrolidone (NMP) and gamma-butyrolactone, additives comprise a pore-forming agent, an anticoagulant and bioactive molecules, and the bioactive molecules are heparin. A spinning solution is uniformly dispersed through the ultrasonic dispersion instrument and the magnetic stirrer, the agglomeration state of a membrane material and an additive in a solvent is effectively broken through through the strong vibration and cavitation effect of the ultrasonic dispersion instrument, and full contact and mixing of all components are promoted; therefore, the uniformity of a mixed solution before spinning is remarkably improved, a blood filtering film forming structure is more compact, pore distribution is more uniform, the spinning solution is stirred in cooperation with a magnetic stirrer, agglomeration of particles in the spinning solution is reduced, and the uniformity and stability of the spinning solution can be more effectively improved.

The invention discloses a series green and environment-friendly mortar formula suitable for northwest climate, and particularly relates to the technical field of mortar, the series green and environment-friendly mortar formula comprises the following components: 100-250 parts of cement, 20-30 parts of attapulgite powder, 20-30 parts of boric sludge, 150-250 parts of natural sand, 10-20 parts of reinforcement powder, 5-10 parts of polysiloxane elastomer, and 2-4 parts of itaconic acid. The prepared mortar is better in breaking strength, corrosion resistance and water resistance, meanwhile, the mortar can be toughened and enhanced, the shrinkage resistance of the mortar is improved, early-stage shrinkage cracking is reduced, then the prepared mortar can effectively slow down the evaporation speed of water, the wettability of the mortar is kept, and the water resistance of the mortar is improved. The mortar prepared by the invention has better weather resistance, can resist strong sunlight, high temperature, low temperature and other extreme weather conditions in northwest regions, keeps the long-term stability and durability of the mortar, and can prevent the mortar from being frozen and damaged under the severe cold weather condition in winter in northwest regions.

The invention provides a stirring device for chemical raw material production, and belongs to the technical field of chemical raw material production, the stirring device comprises a stirring barrel and a stirring shaft arranged in the stirring barrel, and the bottom of the stirring barrel communicates with a discharge pipe; the stirring shaft is hollow and rotationally connected to the middle of the stirring barrel, a plurality of stirring blades are arranged on the stirring shaft, a plurality of material guiding openings communicated with an inner cavity of the stirring shaft are formed in the bottom of the stirring shaft, a plurality of filtering holes are formed in the top of the stirring shaft in an array mode, and an auger is rotationally connected to the interior of the stirring shaft; an auxiliary stirring blade capable of rotating along with the auger is arranged between the upper surface of the auger and the top wall of the inner cavity of the stirring shaft; a driving unit is arranged at the bottom of the stirring barrel and is used for driving the stirring shaft and the auger to rotate in opposite directions; according to the invention, the influence of solid impurities on stirring work and defoaming work can be reduced.

The invention discloses a gastrointestinal tract image classification method based on an improved Adam optimization algorithm, and belongs to the technical field of medical image processing. The method comprises the following steps: a data preprocessing module for acquiring gastrointestinal tract image data for preprocessing, constructing a data set, and randomly dividing the preprocessed gastrointestinal tract image into a training set and a test set; the feature extraction module is used for extracting key features from the preprocessed image; the image classification module is used for classifying the images subjected to feature extraction by adopting an improved Adam algorithm (AdaWAGC algorithm); the result output module is used for displaying an image classification result; and the evaluation module is used for evaluating the classification result. By adopting the method to classify the gastrointestinal tract image, the accuracy and efficiency of gastrointestinal tract image recognition can be improved.

This invention discloses a method for removing micro-water from polar lubricating oil based on the synergy of electric field polarization and crystal field. The method includes: first, filtering the polar lubricating oil containing trace amounts of water to remove mechanical impurities, then heating it to 25℃~35℃; then introducing it into an electric field polarization unit, where it is polarized using an electric field until the dielectric constant of the lubricating oil increases by 3%~8% relative to its initial value; next, introducing it into a crystal field unit, where it is stirred and mixed to fully contact an inorganic crystalline particle adsorbent with a superhydrophilic surface, using the adsorbent to remove water from the oil; finally, passing it through a fine filtration unit to remove the water-swollen inorganic crystalline particle adsorbent, thus completing the micro-water removal of the polar lubricating oil. This invention achieves efficient and deep dehydration of polar lubricating oil at room temperature, with advantages such as low energy consumption, low cost, no additive loss, and no impact on oil performance.

The invention provides a forming process of a complex special-shaped section launching barrel. The forming process comprises the following steps of production preparation, forming of a functional layer and an inner pipe body, filling of a guide sliding groove and forming of an outer pipe body, overall curing and pre-pipe-hoop forming and aftertreatment. According to the invention, a sharp and complex geometrical shape is converted into a curved surface in smooth transition through the pretreatment procedure of filling wires into the guide chute, so that a perfect base is provided for the subsequent laying of a structural layer, and the hidden danger of overhead is fundamentally eliminated; a vacuum bag technology is combined with hand lay-up forming, and a silicone rubber block is used in a key area for local sealing and flow guiding. According to the combined process, uniform compaction pressure can be applied within the range of the whole structure, interlayer bubbles and redundant resin are efficiently removed, a product with high compactness and low porosity is obtained, and the reliability of consistency of mechanical properties of the product is greatly improved.

The invention discloses an artificial plastic stone design and construction method based on an artificial intelligence technology, the method runs through the whole process of design and construction through an AI technology, and the method comprises the following specific steps: firstly, writing cue words, and generating a large number of concept and intention diagrams of artificial plastic stones by using AI; then, through an image fusion technology, a plurality of design schemes are generated in combination with classical design case optimization, and after an optimal scheme is selected, a corresponding three-dimensional model is generated by utilizing AI; generating a structure model of the supporting steel frame, the modeling reinforcing mesh and the concrete lining mesh through the three-dimensional model; and in the construction stage, reinforcing steel bar machining, concrete pouring and detail carving are conducted according to the model, and finally the accurate plastic stone structure is formed. According to the method, the AI technology is integrated into multiple working processes of the landscape garden, intelligence from conceptual design to the whole construction life cycle is achieved, the design efficiency is greatly improved, the problem that design and construction are disjointed in a traditional method is solved, and the method has the advantages of being efficient, accurate and sustainable.

The application discloses a kind of unsupervised exposure correction methods, method includes: constructing semantic prompt guide's exposure perception module, the exposure level of image is perceived at visual semantic level;Exposure parameter modulation is constructed pseudo-supervision generation module, according to image exposure level adaptive exposure modulation is carried out, and synthesis is used to guide model training pseudo-supervision image;Construct color degradation compensation exposure correction module, by joint execution luminance correction and color compensation, the luminance distortion in abnormal exposure image and color degradation are recovered;Unsupervised exposure correction network is trained using the network optimization mechanism of multiple loss functions;Based on the unsupervised exposure correction network after training, input image is handled, and image luminance level and color fidelity are effectively improved.The application generates pseudo-supervision image according to image exposure level adaptive to guide model training, and compensates the color information of image while luminance correction, to realize the collaborative recovery of luminance and color.

The invention provides a language model training method and device, and the method comprises the steps: obtaining original dialogue type text data, and converting dialogue type data in the original dialogue type text data, so as to obtain a plurality of pieces of text type data; wherein the original dialogue type text data comprises at least two types of text data; performing text data mixing on the multiple pieces of text type data in a preset mixing mode to obtain target training data; wherein the preset mixing mode comprises a title-free mixing mode and / or a multi-title mixing mode; and inputting the target training data into a to-be-trained language model, and training the to-be-trained language model by using the target training data to obtain a target language model. Through the method and the device, the calculation overhead of the model is controlled while the text expression diversity is ensured, so that the training efficiency and the final performance of the language model are remarkably improved.

The invention relates to the technical field of intelligent decision making, can be applied to business system platforms such as financial science and technology, medical health and the like, and discloses a question answer generation method, device, equipment and medium, and the method comprises the steps: collecting a plurality of question answers generated by questions, collecting the question answers generated by each question into a question and answer sample set, calculating a reward model score and a reference model benchmark score of each question and answer sample in the question and answer sample set one by one, fitting into a confidence coefficient curve, and dividing an answer retention interval; screening answers to the questions according to the answer retention interval, and calculating and updating an answer retention proportion in the question and answer sample set; optimizing the question and answer model according to the answer retention proportion, and generating a plurality of candidate answers of the user question by using the optimized question and answer model; and calculating candidate reward scores, retaining candidate answers corresponding to the candidate reward scores in the answer retaining interval, and performing semantic fusion on the answers to generate a final question answer of the user question. The accuracy of question answer generation can be improved.

The invention belongs to the field of named entity recognition of natural language processing, and discloses a tire building machine quality defect named entity recognition method for improving BiLSTM-CRF. Comprising the following steps: step 1, preprocessing unstructured data such as on-site production quality of a forming machine, determining a preset BME label, performing manual labeling by using a labeling tool, and providing a data set for a subsequent process; and step 2, constructing a BiLSTM-CRF training learning model. And step 3, adding a learning rate scheduler to carry out timely dynamic adjustment on model parameters. And 4, testing the trained model by using a test set. Test results of the HMM model, the BiLSTM model, the BiLSTM + CRF model and the improved BiLSTM + CRF model are compared, and the results show that compared with other models, the improved BiLSTM-CRF model can consider context information and can dynamically adjust parameters, so that the model can more accurately judge entity boundaries and categories, and the overall effect is improved compared with other models.

The utility model belongs to the technical field of metal matrix composite material processing equipment, and particularly relates to a metal matrix composite material ultrasonic treatment device which comprises a stirring tank and an ultrasonic tank, a pump body used for conveying materials is arranged between the stirring tank and the ultrasonic tank, a motor is arranged at the top of the stirring tank, and the output end of the motor is connected with a stirring shaft. The stirring shaft is connected with a scraping mechanism; the scraping mechanism comprises a positioning frame, the two sides of the positioning frame are fixedly connected with blocking seats, and the two blocking seats are symmetrical about the center of the positioning frame; pin joint rods are inserted into the side faces of the blocking bases, and scraping plates are rotationally connected to the side faces of the pin joint rods. According to the device disclosed by the utility model, the unique stirring blade and scraper mechanism is designed, so that efficient and uniform stirring in the stirring tank is realized, and the scraper can be separated from the inner wall of the stirring tank when the inner wall of the stirring tank does not need to be cleaned through the innovative design of the stirring shaft, so that the abrasion is reduced; and the maintenance cost of the equipment is reduced through a simplified scraper replacement mechanism.

The invention discloses a multi-parameter collaborative optimization method for an MOSFET (Metal-Oxide-Semiconductor Field Effect Transistor) driving circuit based on deep reinforcement learning. The method comprises the following steps: constructing a parameterized MOSFET driving circuit simulation environment taking SPICE as a core; a decision framework is established based on a simulation environment, and an MOSFET driving circuit parameter optimization problem is converted into a strategy learning process of an intelligent agent: the process is guided by a discrete action space representing MOSFET driving circuit parameter adjustment, a state space containing driving circuit working conditions and PCB layout parameters, and a composite reward function; the intelligent agent obtains a converged strategy model through strategy learning in a parameterized environment; the strategy model can be called as a decision basis for parameter optimization of the MOSFET driving circuit during deployment. According to the MOSFET driving circuit multi-parameter collaborative optimization method based on deep reinforcement learning, automatic global optimization of high-dimensional parameters and intelligent balance among multiple targets are achieved, and the design efficiency, performance and reliability of the MOSFET driving circuit are remarkably improved.

The invention relates to a concentric circle chip taking mode in a chip packaging process, which comprises the following steps of: 1) feeding on a wafer table: putting a prepared wafer into a lifting frame, and automatically loading the wafer to the wafer table; the method comprises the following steps of (1) packaging a chip mounter on a concentric circle path, (2) scanning a bar code, (3) loading a map, (4) positioning and setting the circle center, (5) converting concentric circles, (6) taking concentric circles, and starting concentric circle taking after all the steps are completed. By means of the mode that the chip mounter takes the chips on the concentric circle path, dies with similar performance are packaged on the same module, and the final performance of the module is improved.

This invention discloses a hybrid energy laser-powered UAV communication method and system based on reinforcement learning, belonging to the field of UAV energy management technology in 6G air-to-ground communication. Addressing the problem of rotorcraft UAVs struggling to maintain long-term service in hotspot scenarios due to limited onboard battery capacity, a photovoltaic-grid hybrid power supply laser transmitter is constructed to continuously wirelessly charge the UAV. The UAV uses non-orthogonal multiple access (NOMA) to serve ground users. With the goal of maximizing the total system throughput, under constraints such as UAV battery state of charge and user service quality, the UAV trajectory, laser emission power, and fractional-order power allocation exponent are jointly optimized. This non-convex temporally coupled problem is modeled as a Markov decision process, and an improved dual-delay deep deterministic policy gradient algorithm (I-TD3) integrating priority experience replay and n-step reward is proposed for solving it.

This invention provides a low-carbon, non-fired brick made entirely from solid waste and its preparation method, belonging to the technical field of solid waste resource utilization and low-carbon building materials. The non-fired brick is made from specific weight parts of industrial solid waste raw materials, including 30-45 parts steel slag, 30-45 parts blast furnace slag, 10-40 parts calcium carbide slag, and 20 parts water. The preparation method includes: mixing and stirring the above raw materials into a slurry, pressing it into brick blanks, then placing the brick blanks in a carbonization curing chamber, introducing CO2 industrial waste gas at a pressure of 0.1 MPa for 4-24 hours of carbonization curing, and finally transferring them to a constant temperature and humidity environment for 26-28 days of conventional curing. This method utilizes the calcium carbonate and silica gel generated during the carbonization process to construct an early strength framework, and further optimizes the microstructure through the synergistic hydration reaction of the solid waste components during subsequent curing. The resulting non-fired brick has excellent mechanical properties, good durability, and significant carbon fixation effect, while achieving low-cost production.

The present invention relates to an AI online education intelligent question-answering information processing method, comprising the following steps: S1: collecting teaching materials, preprocessing and annotating, and forming a labeled text data set; S2: constructing a question-answering model based on XLNet; S3: introducing a specific context to optimize the question-answering model for a specific subject or topic, and obtaining an optimized question-answering model; S4: considering the age group hierarchical design based on the labeled text data set, and constructing an auxiliary understanding information knowledge map; S5: the user inputs a query, and obtains the best matching answer based on the optimized question-answering model; then, according to the user age group and the best matching answer, the auxiliary understanding information is obtained from the knowledge map to obtain a complete answer; S6: adjusting the content and difficulty provided through user interaction data, and recommending relevant field knowledge based on user behavior and preference. The present invention not only provides the direct answer required by the user, but also provides supplementary background information to enhance understanding, and presents its needs according to user characteristics.

The application discloses a robot pose estimation method based on deep learning, which solves the contradiction between labor-intensive pose annotation in real-world images and the difference between virtual training domain and real domain. The application proposes an unsupervised learning paradigm, which includes four parts. First, based on rendered robot pose estimation, the rendered image estimated in the current state is updated together with the real image to predict the pose. Then, the robot key point detection is input into the encoder-decoder network structure to predict the confidence map. Then, the projected key points of the pose estimation and the detected key points are converted into a distributed situation to construct a divergence-based objective function. Finally, the divergence objective function is approximated by using the integral based on sampling. The comprehensive design enables the unsupervised learning to stably enhance the network.