Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

207results about How to "Fast learning" patented technology

High-altitude operation lifeline early warning method

The invention discloses an aerial work lifeline early warning method, and belongs to the field of image data processing. The aerial work lifeline early warning method comprises the steps that image data including an operator image and a building construction area image are acquired; extracting a lifeline region by adopting an image segmentation algorithm; extracting timestamps and position information of the image data as metadata, and constructing a spatio-temporal index; constructing a safety belt wearing recognition model based on a convolutional neural network, and setting a space attention mechanism and a channel attention mechanism; constructing a small sample data set; combining the small sample data set with the corresponding metadata; carrying out Few-shot Learning and meta-learning training on the model by utilizing a small sample data set with a space-time label, and identifying a wearing state of the safety belt; and obtaining position coordinates of the image data according to the spatio-temporal index, and performing risk assessment through a decision tree in combination with the identified safety belt wearing state. In the prior art, the aerial work environment is complex and changeable, and the safety belt wearing supervision efficiency of an operator is low, the supervision efficiency is improved.
Owner:SHENZHEN JIANAN GRP

Large-model multi-agent-based financial management recommendation system and method

The invention relates to a large-model multi-agent-based financial management recommendation system and method, and the method comprises the following steps: S1, collecting customer information, product information and historical dialogue data, and constructing elements required by a financial management recommendation scene according to the collected data; s2, based on actual business operation, analyzing financial management gold brand verbal skill and historical customer dialogue data, and summarizing business reaching paths and marketing stages to set a plurality of marketing tasks; s3, establishing a plurality of agent roles according to a marketing task, selecting a proper agent role by adopting a multi-model fusion sub-module, and finishing product recommendation by adopting a large and small model collaboration sub-module; s4, optimizing each agent role by adopting an optimization WEAM algorithm; and S5, carrying out safety verification on the final output of the intelligent agent role, and transmitting information to a digital person for broadcasting and displaying through text-to-voice service. According to the invention, the customer experience is improved, the burden of manual customer service is reduced, and the business operation efficiency is optimized.
Owner:BANK OF SHANGHAI

Action type model optimization method based on reward feedback

The invention relates to the technical field of optimization methods, in particular to an action type model optimization method based on reward feedback, which comprises the following steps of: SI, constructing a multi-level reward function; s2, starting and initializing; s3, observing a current web environment state; s4, executing the action; s5, environment feedback; s6, constructing a Reward model reward signal processing module; s7, reward signal processing; s8, constructing an action evaluation network; s9, action evaluation; s10, updating the strategy; s11, judging whether the task is completed or a termination condition is reached; according to the method, a more comprehensive action feedback mechanism is established, the final reward is considered, the effect of the intermediate action is fully utilized, the action of the intelligent agent is evaluated and fed back more meticulously, the intelligent agent is guided to explore and utilize the environment more reasonably, and the user experience is improved. And an action feedback mechanism encourages the intelligent agent to try more actions which may contribute to realizing the target, and meanwhile, invalid or harmful actions are avoided, so that the exploration of the intelligent agent in the web environment is more efficient.
Owner:YANSHENGXING (BEIJING) TECHNOLOGY CO LTD

Test data management and analysis system

ActiveCN119091967AEnhance dynamic analysis capabilitiesincrease flexibilityBiostatisticsBiological modelsData setEngineering
The invention relates to the technical field of database management, in particular to a test data management and analysis system, which comprises a data self-adaptive analysis module for receiving an RNA (Ribonucleic Acid) sequencing data set, analyzing connectivity of node features and edges in the data set, adjusting weights of nodes and edges, and updating a node feature processing mode and edge weight configuration. According to the method, the genetic map is updated in real time, and the weight configuration of the nodes and the edges is adjusted, so that the dynamic analysis capability of the data is enhanced, the data analysis is more in line with the complexity of biological change, the structural features in the data are allowed to be deeply identified by constructing and comparing the multi-scale topological fingerprints, and the analysis comprehensiveness and the prediction accuracy are improved; according to the method, time sequence data matching and parameter setting are optimized, it is ensured that an analysis result is close to real data, analysis quality and efficiency are improved, spatial and geometric topological features in biological data are extracted, the method is applied to training a neural network model, the learning speed is increased, and prediction accuracy and applicability of the model are improved.
Owner:LUZHOU PEOPLES HOSPITAL

Autonomous robot path planning method based on deep reinforcement learning

The invention belongs to the technical field of robot path planning, discloses an autonomous robot path planning method based on deep reinforcement learning, and aims at the problem that an agent is difficult to fully sense the environment in a complex dynamic environment, the State space of SAC is expanded and adjusted to enhance comprehensive sensing of an unknown environment and more flexible omnibearing obstacle avoidance. A heuristic reward function is designed, dynamic adjustment of reward values is achieved, and therefore the learning process of the robot is optimized. In order to solve the problems that the calculation complexity of an algorithm is increased and the convergence speed is reduced in a complex environment, the sample utilization rate is optimized in combination with a prior experience playback (PER) technology and a SumTree data structure. The weight of a high-value sample is increased through the PER technology, so that an intelligent agent can learn an effective strategy more quickly in the training process; and a SumTree data structure is introduced, so that the PER efficiency is further improved.
Owner:WUHAN UNIV OF SCI & TECH

Recommendation strategy generation method based on big language model enhancement and related equipment

The invention provides a recommendation strategy generation method based on big language model enhancement and related equipment. The method comprises the steps of obtaining a recommendation task; inputting the recommendation task into an intelligent agent, and obtaining a recommendation strategy output by the intelligent agent; wherein the intelligent agent is obtained by training based on a sample recommendation task and a large language model, and the large language model is used for predicting user behaviors based on the sample recommendation task. According to the method, the big language model is combined with the reinforcement learning agent, so that the problem that an accurate recommendation strategy is difficult to quickly provide by a traditional method is effectively solved, and the efficiency and the adaptability of a recommendation system are improved while the accuracy and the individuation degree of the recommendation strategy are improved.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI

Mobile robot path planning method based on SAC algorithm

PendingCN119289981AImprove strategy qualityEfficiently avoidNavigational calculation instrumentsAlgorithmSimulation
A mobile robot path planning method based on an SAC algorithm belongs to the technical field of deep reinforcement learning and mobile robot navigation, integrates the thought of hierarchical reinforcement learning skill combination into the SAC algorithm, and uses a time sequence abstraction method to integrate low-level fine-grained actions, so as to improve the precision of the SAC algorithm. A higher-level coarse-grained action with definite semantics can be learned; in reinforcement learning training, a distributed soft strategy iteration method is used, maximum entropy reinforcement learning is expanded into a distributed learning version, and variance and overestimation of a Q value are reasonably controlled through a learning state-action return distribution function, so that the overall strategy quality of robot path planning is improved. According to the method, training and testing are carried out in a simulation environment Image-Env, and the performance of the algorithm is verified on Turtlebot2. The method can efficiently avoid obstacles, is short in path, and has a good obstacle avoidance effect in a complex dynamic environment.
Owner:ZHEJIANG RUNCHEN TECH CO LTD

Improved PPO scheduling method, system, medium and equipment in AGV composite operation mode of electronic component workshop

The invention relates to the field of electronic component workshop AGV logistics scheduling, and discloses an improved PPO scheduling method and system in an electronic component workshop AGV composite operation mode, a medium and equipment, and the method comprises the steps: carrying out the rasterization of a workshop environment map through grid modeling, enabling the AGV to carry out an A * search algorithm in a grid map through a plurality of task orders, obtaining batch sample data, and carrying out the calculation of the A * search algorithm in the grid map; pre-training is completed according to model parameters of the sample pre-training strategy network; according to the new task order, the AGV interacts with the environment, an observation state, an action space and a reward value are obtained, after matrix processing is carried out on the observation state, the observation state serves as input data of a PPO algorithm, a strategy network loss value and a value network loss value of the PPO algorithm are calculated, network model parameters are updated through a gradient descent method, and PPO training is completed; and generating a real-time task order on line, and guiding the AGV to complete path planning and scheduling tasks through the decision network models trained in the first two stages. According to the method, the electronic component workshop AGV scheduling strategy can be obtained through rapid learning, the learning efficiency is remarkably improved, and stability is achieved.
Owner:BEIJING INFORMATION SCI & TECH UNIV

Non-cooperative spacecraft active tracking method based on deep reinforcement learning

The invention discloses a non-cooperative spacecraft active tracking method based on deep reinforcement learning, and relates to a non-cooperative spacecraft active tracking method. The invention belongs to the field of space flight and aviation. The objective of the invention is to solve the defects that an existing algorithm cannot fuse a spacecraft dynamics model and satellite orbit dynamics, cannot effectively improve the robustness of the algorithm on the basis of guaranteeing the tracking precision, cannot effectively extract time sequence related information about a target from a training sample, and the like. The method comprises the following steps: 1, obtaining the position and speed of a chasing spacecraft; 2, constructing an actor network, a commentator network and a loss function; 3, constructing a reward function, and obtaining a trained actor network and a reviewer network; and 4, obtaining the difference between the position between the target spacecraft and the chasing spacecraft and the expected position, and the speed difference between the target spacecraft and the chasing spacecraft, inputting the difference into the trained actor network, and outputting the action of the current time step by the trained actor network.
Owner:HARBIN INST OF TECH

Continuous casting blank defect classification method, system and equipment based on meta-learning

The invention provides a meta-learning-based continuous casting blank defect classification method, system and equipment. The meta-learning-based continuous casting blank defect classification method comprises the steps of 1, preprocessing an obtained public image classification data set and an obtained continuous casting blank image containing defects; 2, randomly forming a meta-task through meta-learning task allocation on the preprocessed public image classification data set, and inputting the meta-task to a preset image meta-learning classification model to obtain a trained image meta-learning classification model; step 3, performing meta-learning task allocation on the preprocessed continuous casting blank image containing defects to form a meta-task, and performing fine adjustment on the trained image meta-learning classification model by using the obtained meta-task; 4, classifying the defects of the continuous casting blank to be processed by utilizing the final image element learning classification model; according to the method, the problem of dependence on a large amount of labeled data in a traditional defect detection method can be effectively solved, and the classification capability of the model under the condition of few samples can be improved.
Owner:XI AN JIAOTONG UNIV

Multi-mode intelligent security method and system driven by brain-like edge calculation

The invention discloses a brain-like edge calculation-driven multi-mode intelligent security method and system, and aims to improve the security capability in a complex dynamic scene. According to the method, multi-modal data of videos, audios, sensors and the like are collected, preprocessing is carried out by utilizing a brain-like edge computing gateway, dynamic behavior characteristics are extracted, secondary confirmation is carried out through a lightweight visual large model, and then formal early warning is generated. And the system executes intelligent linkage operation according to the early warning information risk level, and records false alarm information for model optimization. According to the invention, brain-like calculation and multi-modal fusion are adopted to improve the recognition precision, edge calculation reduces delay, an intelligent closed loop realizes differentiated treatment, a low-power design and a modular architecture reduce the cost, and the system has a self-learning capability. The defects of an existing security and protection system in the aspects of dynamic behavior recognition, response speed, disposal intelligence, cost control and the like are effectively overcome. The system is suitable for scenes such as a campus and a community, and provides an accurate, efficient and intelligent security solution.
Owner:NINGBO ZHIFENG IOT CO LTD

Large model connection context dialogue method based on LSTM (Long Short-Term Memory) model

The invention provides a large model connection context dialogue method based on an LSTM (Long Short-Term Memory) model, which belongs to the field of intelligent deep learning and comprises the steps of data preprocessing, input sequence coding, hidden state and memory cell initialization, decoding response generation, output sequence decoding, training and optimization, evaluation and adjustment. The method has high accuracy and response speed when processing a complex dialogue scene, and can be widely applied to the fields of intelligent customer service, intelligent assistants and the like.
Owner:SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Payment processing method and device, equipment and medium

The embodiment of the invention discloses a payment processing method and device, equipment and a medium. The scheme comprises the steps of obtaining a payment processing request; the payment processing request is triggered by a first device of a payer and a second device of a payee based on a near field communication mode; before a transaction resource corresponding to the payment processing request is transferred to a collection account of the payee, sending a first payment result page to a first device of the payer; the first payment result page is used for representing that a communication step based on near field communication is completed in an online transaction process; after the transaction resource is transferred to a collection account of the payee, sending a second payment result page to a first device of the payer; the second payment result page is used for indicating that the resource transfer step is completed.
Owner:ALIPAY (HANGZHOU) INFORMATION TECH CO LTD

Excavator control method and system oriented to non-structural working conditions

The invention provides an excavator control method and system oriented to non-structural working conditions. According to the excavator control method and system oriented to the non-structural working condition, on one hand, according to the dynamic remodeling characteristic of earthwork in the excavation process, the excavation action track is planned through the earthwork state obtaining model and the excavation action planning model, the excavator control method and system can adapt to the non-structural working condition, and it is ensured that the operation effect is stable; on the second aspect, through real-time sensing and data feedback, the excavation action track can be adjusted in real time in the operation process, optimization is conducted according to the earthwork state, and the operation flexibility and effect can be improved; thirdly, by autonomously planning an excavation action track, the dependence on a manual operator can be reduced, the requirement of manual intervention is reduced, and the autonomous operation capability is improved; and fourthly, the mining action track is optimized through the mining action planning model, so that the energy consumption in the mining process can be reduced, the operation efficiency can be improved, and the operation cost can be reduced.
Owner:ZHEJIANG UNIV

Internet of Things equipment power consumption self-adaptive optimization method and system based on edge computing

The invention relates to the technical field of internet of things equipment power consumption optimization methods, in particular to an internet of things equipment power consumption self-adaptive optimization method and system based on edge computing, and the method comprises the following steps: firstly, collecting historical operation data of different edge computing equipment, including but not limited to resource utilization rate, power consumption and network bandwidth; then, learning the historical operation data by using an improved multi-target deep reinforcement learning algorithm to obtain an equipment model; thirdly, predicting the optimal power value of the equipment through the equipment model; then, comparing the optimal power value with the actual operation power value of the current equipment, and when the optimal power value is inconsistent with the actual operation power value, sending an optimization instruction to the edge computing equipment; and finally, adjusting the parameter value of the edge computing device according to the optimization instruction to realize self-adaptive optimization of the power consumption of the device, so that the power consumption can be obviously reduced under various load conditions, and the task completion rate and the system response speed can be improved at the same time.
Owner:WUXI INSTITUTE OF TECHNOLOGY

Method for creating item matching condition control model generation result based on large model

The invention provides a method for creating an item matching condition control model generation result based on a large model. The method comprises an item capturing module, an item splitting module, a condition expansion module, a model synchronization module, a reasoning control module, a result output module, a timing updating module and a reasoning monitoring module. A full-privatized operation ecology is created, user demand statements are analyzed through an artificial intelligence technology, a model is accurately matched, then completed items are pointed to corresponding item sources, real contents and intentions conveyed by the statements are accurately grasped, and convenience is brought to affair handling of the user; standard files are automatically collected through the RPA robot and added into the knowledge base, and therefore the knowledge base content of the government affair question-answering system is continuously maintained and enriched; according to the method, service items are collected, a service item list is formed, conditional expansion is carried out on the service items, conditional nature and description are carried out on the items, and therefore accurate matching and efficient management of service item conditions are achieved.
Owner:JIANGSU ZHONGWEI TECH SOFTWARE SYST

Modeling method and device of power system, computer program product and modeling system

The invention provides a modeling method and device of a power system, a computer program product and a modeling system. The method comprises the following steps: acquiring related information of a power system; constructing an intelligent generation model; inputting the related information into the intelligent generation model to obtain virtual model data corresponding to the related information; modeling is carried out according to the virtual model data corresponding to the related information, a virtual model is obtained, and the virtual model is a virtual model of the power system. According to the scheme, the problem that the accuracy of the constructed model of the power system in the prior art is relatively poor is solved.
Owner:ELECTRIC POWER RES INST CHINA SOUTHERN POWER GRID CO LTD +1

Medical image classification method based on GAShuffleNet network

The invention discloses a medical image classification method based on a GAShuffleNet network. The medical image classification method based on the GAShuffleNet network comprises the steps of preprocessing a data set, constructing the GAShuffleNet network, training the GAShuffleNet network, storing a training model of the GAShuffleNet network, verifying the GAShuffleNet network and testing the GAShuffleNet network. The GAShuffleNet adopts a channel shuffling self-attention sub-network, a channel shuffling self-attention sub-network, a channel shuffling self-attention sub-network and a channel shuffling self-attention sub-network, wherein the channel shuffling self-attention sub-network adopts a feature shuffling module. In the training step, the mobility of feature intercommunication is enhanced, and meanwhile, the attention mechanism enables the network to enhance important feature weights in training learning by paying attention to effective information in the images, so that the precision of medical image classification is improved, and the complexity of calculation is reduced. Compared with the prior art, the method has the advantages of high classification accuracy, high robustness, high adaptability, high learning speed and the like, can be used for medical image classification and can also be used for other image classification.
Owner:SHAANXI NORMAL UNIV

Bird trajectory prediction system based on bird detection radar and big data model analysis

The invention relates to the technical field of bird trajectory prediction, in particular to a bird trajectory prediction system based on bird detection radar and big data model analysis, which comprises a data acquisition module, a prediction model establishment module and a prediction model updating module, and is characterized in that the data acquisition module acquires the speed, acceleration, trajectory and time point data of a bird; the prediction model establishing module sets a trajectory prediction model by using the data, predicts the bird trajectory of the next time point according to the data of the preorder time point, calculates a prediction error, optimizes the error through a training strategy in the model so as to update prediction parameters, and records the time required for prediction; the prediction model updating module calculates an influence coefficient according to the error and the prediction time so as to adjust and update a training strategy of the model; according to the process, the problem that a traditional system is difficult to dynamically adapt to bird movement changes is solved, the prediction accuracy and efficiency are improved through a self-adaptive training strategy, and a more stable and reliable bird trajectory prediction effect is achieved.
Owner:ZHONGAN RUIDA (BEIJING) ELECTRONIC TECH CO LTD

CSI feedback method and system based on deep learning

The invention discloses a CSI (Channel State Information) feedback method and system based on deep learning, belongs to the technical field of communication, and aims to solve the technical problems of low recovery precision, reduced frequency efficiency and huge uplink bandwidth consumption of CSI feedback in a large-scale MIMO (Multiple Input Multiple Output) system. Comprising the following steps that a channel state information feedback model TCMRNet is constructed and trained, the TCMRNet comprises an encoder and a decoder, LSTM network units and convolution layers with different convolution kernel sizes are introduced into the encoder and the decoder, the output end of each convolution layer is connected with a batch normalization layer, and the output end of each convolution layer is connected with an LSTM network unit; the encoder is used for carrying out multi-resolution feature extraction and time correlation analysis on input channel state information and compressing extracted features into feature vectors to be output, and the decoder takes the feature vectors as input and is used for decompressing the feature vectors, recovering the channel state information and outputting reconstructed channel state information; and performing time domain transformation on the reconstructed channel state information.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)

Leukocyte detection method based on FBDM-YOLOv8s

The invention aims to provide a white blood cell detection method based on FBDM-YOLOv8s, which comprises the following steps: A, constructing an improved YOLOv8s neural network model, and the improved YOLOv8s neural network model comprises a Backbond network, a Neck network and a Head network; the Backbond network takes a plurality of groups of Fasnet modules as a main framework, and finally, a group of BRA modules is arranged; b, the improved YOLOv8s neural network model is trained, and a trained improved YOLOv8s neural network model is obtained; and C, introducing a to-be-detected leukocyte image into the trained improved YOLOv8s neural network model, and sequentially processing the to-be-detected leukocyte image through a Backbond network, a Neck network and a Head network to obtain a detected image. According to the method, the edge detection precision can be improved while model parameters are optimized, the calculation speed is increased, and the problems that image cells are incomplete and two cells are mutually overlapped are better solved.
Owner:GUANGXI UNIVERSITY OF TECHNOLOGY

Framework model based on neural network learning and application method thereof

The invention relates to the technical field of medical science, in particular to a framework model based on neural network learning and an application method of the framework model. According to the model, a graph convolutional network (GCN, Transform architecture and long short-term memory network (LSTM) are fused, a multi-level analysis process is constructed, the spatial structure and sequence dynamics of drug molecules are deeply explored, and the model comprises the following specific steps: model training: performing model training by adopting data sets collected by people such as Cui, Q.Cui2020Improved and the like; the model test selects three independent test sets to comprehensively evaluate the performance of the model; according to the data preprocessing, an RDKit library is used, SMILES character strings are converted into molecular objects, a feature tensor is constructed and used for storing core features of each molecule in detail, data splitting is carried out, and the data splitting adopts versions, such as Ahmad, divided by people based on a Cui2020 data set to carry out training and testing of a machine learning model.
Owner:王晨旭

Power marketing data query method and system of JointBERT model based on knowledge graph

The invention is suitable for the technical field of data query, and provides a power marketing data query method and system based on a JointBERT model of a knowledge graph, and the method comprises the steps: obtaining field background knowledge related to the power industry, and constructing the knowledge graph; a JointBERT model is constructed and trained, and the model comprises an input layer used for processing input text data; the coding layer is used for carrying out fusion coding on rich general semantic knowledge in a corpus and domain knowledge in the knowledge graph; the decoding layer is used for generating field and intention corresponding to the input text and slot labels corresponding to words; compressing and optimizing the model by adopting an early leaving mechanism and a knowledge distillation method to obtain a target model; and the power demand problem of the user, which is received in real time, is used as the input parameter and is input into the target model for data query and analysis, so that the enterprise information query efficiency of related workers is improved.
Owner:GUANGXI POWER GRID CORP

Immersive sleep-aiding music synthesis method and immersive sleep-aiding music synthesis system fusing environment sound

The invention discloses an immersive sleep-aiding music synthesis method and system fusing environment sound. The method comprises the following steps: acquiring an environment audio signal and a multi-mode environment parameter; based on the environment audio signals and the multi-modal environment parameters, a fusion feature is generated through a multi-modal information fusion module; performing dynamic attention time-frequency analysis on the fusion features to obtain key time-frequency features; performing personalized feature learning based on the key time-frequency features to obtain personalized features; performing self-correction cycle processing on the personalized features to obtain corrected features; extracting beneficial environment elements from the corrected features; synthesizing and mixing music based on the beneficial environment elements; optimizing the mixed music according to user feedback; through multi-modal information fusion and a dynamic attention mechanism, the system can sense and adapt to a complex sound environment in real time and effectively process various interference noises; the method can quickly learn and adapt to the personal preference of the user, and provides customized sleep-aiding experience.
Owner:DONGGUAN JIAXIN TECH CO LTD

Performance prediction method and system for water-based resin polymer modified emulsified asphalt

The invention discloses a method and system for predicting the performance of water-based resin polymer modified emulsified asphalt, and the method comprises the steps: calculating the performance of the water-based resin polymer modified emulsified asphalt according to the effective components and the performance of the water-based resin polymer modified emulsified asphalt, the mass fraction of a water-based resin polymer modifier, and the type and the performance of the water-based resin polymer modifier; constructing a characteristic performance database of the water-based resin polymer modified emulsified asphalt material; determining performance influence factors of the water-based resin polymer modified emulsified asphalt; taking the characteristic performance data and influence factors of the water-based resin polymer modified emulsified asphalt as a data set; a BP neural network model is constructed, the BP neural network model is subjected to iterative training by adopting the data set and combining particle swarm optimization (PSO) optimization, a trained PSO-BP neural network model is obtained, and then the performance of the water-based resin polymer modified emulsified asphalt is predicted; according to the method, the composition of the water-based resin polymer modified emulsified asphalt and the performance of the water-based resin polymer can be tested in combination with the requirements in different scenes, and training of a PSO-BP model and performance prediction of the water-based resin polymer modified emulsified asphalt are carried out by taking the test result as a sample.
Owner:太行城乡建设集团有限公司 +1

End-to-end calculation method for real-time prediction of explosion damage effect of RC component

The invention discloses an end-to-end calculation method for real-time prediction of an RC component explosion damage effect, and the method comprises the following steps: building an RC component explosion damage effect numerical value solving method, and obtaining RC component explosion damage effect numerical value simulation data; associating the numerical simulation data of the explosion damage effect of the RC component with the explosion working condition and the geometrical shape, the size and the material characteristics of the RC component, and obtaining an RC component explosion damage effect database comprising a training data set and a verification data set; training and optimizing the constructed neural network by using the training data set and the verification data set to obtain an end-to-end calculation model of the explosion damage effect of the RC component; and completing real-time prediction of the explosion damage effect of the target RC component by using the end-to-end calculation model of the explosion damage effect of the RC component. The method for predicting the explosion damage effect of the RC component is simple in process, high in speed and good in seaworthiness.
Owner:NANJING UNIV OF SCI & TECH

Shoe tree glue spraying path automatic generation method based on point cloud data processing

The invention provides a shoe tree glue spraying path automatic generation method based on point cloud data processing, and the method comprises the steps: carrying out the point cloud data preprocessing on the basis of scanning a shoe tree to obtain point cloud data, and obtaining a spatial motion track point mark and data; an approximate glue spraying attachment space track on the shoe tree is obtained through polynomial interpolation; then, orthogonal coordinate system NOA vectors corresponding to the glue spraying attachment space track points on all the shoe trees are sequentially solved, a mechanical arm tail end glue spraying space track obtained after the shoe tree glue spraying track NOA vector directions are offset by a certain distance is solved, and a mechanical arm tail end pose matrix is obtained through solving according to the orthogonal coordinate system NOA vectors and the mechanical arm tail end glue spraying space track; and finally, establishing an inverse kinematics mathematical model according to the D-H parameters of the robot, and substituting the inverse kinematics mathematical model into the tail end pose matrix of the mechanical arm for solving to obtain a shoe tree glue spraying movement track.
Owner:FUZHOU UNIV

Multi-round dialogue intention recognition method, device and equipment based on small sample learning

The invention relates to a multi-round dialogue intention recognition method and device based on small sample learning, computer equipment, a computer readable storage medium and a computer program product, and can be applied to the technical field of computers. The method comprises the following steps: performing intention labeling processing on historical dialogue data in the insurance field to obtain a labeled data set; selecting a training data set for model training from the annotated data set according to the data volume of each intention category in the annotated data set; according to preset data sampling information, sampling from the training data set to obtain a support sample set and a query sample set; according to the support sample set and the query sample set, performing iterative training on a to-be-trained small sample intention recognition model to obtain a trained small sample intention recognition model; and according to a preset model framework, performing model conversion processing on the trained small sample intention recognition model to obtain a target small sample intention recognition model. By adopting the method, the intention recognition efficiency can be improved.
Owner:CHINA LIFE INSURANCE CO LTD

Sample generation method and device, electronic equipment and computer readable medium

PendingCN118964971ASolve the sparse problemimprove accuracyCommerceEngineeringFinancial transaction
The embodiment of the invention discloses a sample generation method and device, electronic equipment and a computer readable medium. The method comprises the following steps: acquiring shallow behavior data of a target user in a target application, wherein the shallow behavior data is behavior data which is generated within a preset duration after the target user downloads the target application and has a behavior occurrence probability greater than a first threshold value; inputting the shallow behavior data into a pre-trained user value prediction model to obtain a user value of the target user, the user value being a transaction value of the target user in the target application within a preset number of days; and under the condition that the user value is greater than a second threshold value, constructing a virtual transaction event, and generating a training sample based on the virtual transaction event and the value, sample data being used for retraining a pre-trained promotion information delivery model. According to the embodiment, the sample size of training the promotion information delivery model is improved, so that the accuracy and effectiveness of the promotion information delivery model are improved.
Owner:BEIJING QIYI CENTURY SCI & TECH CO LTD