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

86results about How to "Adapt to dynamic changes" patented technology

Intelligent supply chain scheduling optimization method and system based on autonomous controllable large model

The invention discloses an intelligent supply chain scheduling optimization method and system based on an autonomous controllable large model, and the method comprises the steps: employing a demand prediction agent to predict a future market demand condition according to product sales data; according to supplier supply product data, adopting a supplier management agent to select an optimal supplier as a target supplier; according to the predicted future market demand condition and inventory data, an inventory optimization agent is adopted to generate an optimal inventory replenishment plan; according to the inventory level after the optimal inventory replenishment plan and the logistics transportation data, adopting a logistics scheduling agent to calculate and obtain an optimal transportation path; feedback data of all the agents are collected, performance indexes of all the agents are calculated through the information feedback agents according to the feedback data, and agent parameters are adjusted according to the performance indexes of all the agents; and the strategy output of each agent is integrated into the scheduling strategy of the supply chain. The scheduling strategy can be dynamically scheduled and updated in real time.
Owner:ZHONGKE NANJING SOFTWARE TECH RES INST

Service channel time slot allocation method

The invention relates to the technical field of communication networks, and discloses a service channel time slot allocation method, which comprises the following steps of: 1, acquiring network data in real time from network equipment, the network data comprising bandwidth utilization rate, delay, packet loss rate and service flow type; 2, predicting future network flow fluctuation through a long-short-term memory network model based on historical flow data and real-time network data; and step 3, dynamically adjusting the allocation of time slot resources according to the network flow fluctuation prediction result, and preferentially allocating the time slot resources for high-priority services. According to the method, the dynamic adjustment of the time slot resources is realized by combining the flow prediction of the LSTM model and the Q-learning reinforcement learning algorithm, so that the system can flexibly allocate the resources according to the actual network load condition, the resource waste is reduced, the utilization efficiency of the bandwidth is improved, and the utilization rate of the overall network resources is remarkably improved especially under the condition of high network load.
Owner:国网西藏电力有限公司 +1

Cranial nerve two-way stimulation intelligent regulation and control method and system for Parkinson's disease

The invention discloses a cranial nerve double-path stimulation intelligent regulation and control method and system for Parkinson's disease, and relates to the technical field of medical treatment and neural engineering, and the method comprises the steps: obtaining an electroneurographic signal of a target patient based on a stimulation electrode, and determining neural activity features according to the electroneurographic signal; the stimulating electrodes comprise a first stimulating electrode and a second stimulating electrode; determining a nerve evaluation value according to the nerve activity characteristics, and generating a co-stimulation parameter based on the nerve evaluation value; initial stimulation parameters of the stimulation electrode are adjusted based on the co-stimulation parameters, the target patient is stimulated through the stimulation electrode, and cranial nerve two-way stimulation intelligent regulation and control for the Parkinson's disease are completed. According to the invention, by introducing the abnormal oscillation mode and evaluating the synchronism characteristics of the neural network in real time, the neural activities of the deep brain and the vagus nerve area are comprehensively quantified, and the accuracy of nerve regulation and control is improved; by generating collaborative stimulation parameters and comprehensively considering the mutual influence of the two stimulation pathways, intelligent collaborative regulation and control are realized.
Owner:ZHUJIANG HOSPITAL OF SOUTHERN MEDICAL UNIVERSITY

Defect simulation system and test method for medium-and-low-voltage real-type power distribution network

The invention discloses a medium and low voltage real type power distribution network defect simulation system and a test method thereof, and relates to the technical field of power system fault diagnosis and recovery, and the method comprises the steps: deploying a sensor to collect power distribution network operation data, carrying out the preprocessing, integrating a power distribution network data set, extracting a power distribution network fault feature vector from the power distribution network data set through FFT conversion, and carrying out the fault diagnosis and recovery; the method comprises the following steps: constructing a fault diagnosis model by using a support vector machine (SVM) based on a power distribution network fault feature vector, establishing a simulation model of a medium and low voltage power distribution network by using power system simulation software PSCAD, simulating a power distribution network fault in the simulation model, diagnosing the fault in the simulation model by using the fault diagnosis model, and formulating and implementing a recovery strategy according to a diagnosis result. Evaluating the effect of the recovery strategy, adjusting the recovery strategy according to the evaluation result, repeatedly testing in the simulation environment until the optimal recovery strategy is found, applying the optimal recovery strategy to the actual power distribution network, and continuously monitoring and improving the performance of the actual power distribution network.
Owner:ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY

Indoor unmanned aerial vehicle flight path planning processing method and system

The invention discloses an indoor unmanned aerial vehicle flight path planning processing method and system, and the method comprises the steps: scanning an indoor environment through a laser radar, and obtaining real-time obstacle information; the indoor environment is scanned through laser radar equipment, so that point cloud information and obstacle position information of a plurality of obstacles in the environment can be obtained; dividing the grid map into a plurality of levels of subareas according to the density of the obstacles in the grids and the probability value of the occupied area; generating an initial flight path by adopting an improved fast expansion random tree algorithm based on the partition regions of the multiple levels; smoothing the initial flight path to obtain an optimized flight path; an improved fast expansion random tree algorithm is adopted to generate an initial path, and compared with a traditional algorithm, the algorithm has higher calculation speed and better path quality.
Owner:CONTINENTAL UNIION CHAOLU TECH BEIJING CO LTD

Full-automatic online PAT continuous crystallization control method, medium and system

The invention provides a full-automatic online PAT continuous crystallization control method, a medium and a system, and belongs to the technical field of PAT continuous crystallization, and the method comprises the following steps: firstly, carrying out time sequence analysis and Bayesian network correlation analysis on collected crystallization process parameters and effect data to obtain a change optimization curve and a frequency spectrum characteristic of each parameter; and then, establishing a multi-branch neural network model by using the frequency spectrum characteristics as input, and realizing online prediction of the current crystallization process effect. And then, through genetic algorithm optimization, finding out an optimal crystallization process parameter combination, converting the optimal crystallization process parameter combination into actual production equipment control parameters, and automatically adjusting production equipment. According to the method, the online effect evaluation model based on the neural network is established by collecting and analyzing the historical data of the PAT continuous crystallization process, and the technical problems that in the prior art, self-adaptive online optimization is difficult to achieve, and dynamic changes in production are difficult to respond are solved.
Owner:PHARMAVISION QINGDAO INTELLIGENT TECH LTD

Method for predicting stability of large-span roof of mine cave experience pavilion

The invention relates to artificial intelligence and data processing technologies, and discloses a mine cave experience pavilion large-span roof stability prediction method, which comprises the following steps: collecting data through sensor data collection, visual information collection and real-time environment data collection, and carrying out data fusion and cleaning; inputting sensor data, visual data and environmental disturbance data and outputting an instability risk level based on a multi-modal data prediction model; constructing a risk grade division standard according to the predicted instability risk grade; and dynamically updating the instability probability by using a Bayesian method in combination with historical data and real-time data. The large-span roof safety risk prediction method can accurately predict the safety risk of a large-span roof, so that potential safety risks and hidden dangers can be found in time, hidden dangers can be eliminated in time or personnel and property are transferred, and personnel and property safety is guaranteed.
Owner:贵州轻工职业大学

Natural resource element change detection method based on deep learning

The invention discloses a natural resource element change detection method based on deep learning, and belongs to the field of natural resource element detection, and the method comprises the following steps: S1, collecting and preprocessing multi-source heterogeneous data; s2, extracting multi-source heterogeneous data features by using a deep learning model, and training the deep learning model to identify and classify natural resource elements; s3, constructing a knowledge graph containing natural resource elements, attributes and relationships based on an identification result in the step S2, and providing extra semantic information for the deep learning model; s4, the knowledge in the knowledge graph obtained in the step S3 is embedded into the deep learning model in the step S2 to serve as a constraint condition, and the deep learning model embedded with the knowledge graph is obtained; and S5, collecting multi-source heterogeneous data of a to-be-detected area, pre-processing the multi-source heterogeneous data, inputting the pre-processed multi-source heterogeneous data into the deep learning model embedded into the knowledge graph in the step S4, and outputting a detection result. According to the natural resource element change detection method based on deep learning, the accuracy and the understanding depth of natural resource change detection are improved through structured knowledge representation and strong mode recognition capability, and the limitation of a single technology is overcome.
Owner:INST OF GEOGRAPHICAL SCI & NATURAL RESOURCE RES CAS +1

Construction safety early warning method and system based on mixed reality

The invention belongs to the technical field of building construction safety management, and provides a construction safety early warning method and system based on mixed reality, and the method comprises the steps: converting the longitude and latitude of geographic coordinate system data into plane coordinates, and converting the plane coordinates into a local coordinate system of a spatial mapping grid formed by simultaneous positioning and a map construction technology; through coordinate transformation, geographic coordinate system data can be accurately mapped into a model space coordinate system of the mixed reality equipment, the limitation that external high-precision positioning data are difficult to integrate in a traditional mixed reality technology is broken through, and high-precision equipment positioning is realized; meanwhile, an initial weight value is distributed to each grid unit in the space mapping grid, the weight is dynamically adjusted to change the size of the grid, dynamic management of space mapping grid data is achieved, detailed real space mapping grid data can be reserved after initial alignment is carried out through the space mapping capacity of mixed reality equipment, and the space mapping capacity of the mixed reality equipment is improved. And a data basis is provided for subsequent dynamic collision detection.
Owner:SHANDONG ELECTRIC POWER ENG CONSULTING INST CORP

River micropollutant dynamic monitoring method and system based on artificial intelligence

The invention discloses a river micropollutant dynamic monitoring method and system based on artificial intelligence, and relates to the technical field of environment monitoring, and the method comprises the steps: building a micropollutant concentration prediction model according to the feature data and a particulate matter analysis module; adjusting model parameters of the micropollutant concentration prediction model according to climate change and use change of drainage basin land; and obtaining a concentration result of the micropollutants through the micropollutant concentration prediction model after the model parameters are adjusted, and performing graded early warning according to the concentration result and an early warning threshold value. Through continuous data acquisition and real-time analysis, the change of the concentration of the micropollutants can be found and responded in time, instant early warning information can be provided, and meanwhile, model parameters and early warning threshold values can be dynamically adjusted according to climate change and land use change, so that the system can adapt to the dynamic change of the environment.
Owner:JIANGXI PROVINCIAL ECOLOGICAL CIVILIZATION RES INST (JIANGXI PROVINCIAL MOUNTAIN RIVER & LAKE DEV & MANAGEMENT COMMITTEE OFFICE)

Cache management method, electronic device, storage medium and program product

The invention discloses a cache management method, electronic equipment, a storage medium and a program product, and relates to the technical field of data storage, and the method comprises the following steps: obtaining current operation data of a storage system in a current period, determining current access popularity corresponding to a plurality of data blocks according to the current operation data, and storing the data blocks according to the current access popularity. The resource allocation of the target cache is dynamically adjusted, the problem that the data access efficiency of a storage system in the related technology is low is solved, and the technical effect of improving the data access efficiency of the storage system is achieved.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

IP address resource allocation method and system based on machine learning

The invention discloses an IP address resource allocation method and system based on machine learning, and relates to the technical field of network resource allocation, and the method comprises the steps: receiving an IP address allocation request message sent by a to-be-allocated device; in response to the IP address allocation request message, acquiring an IP address field belonging to the gateway group from the IP address resource pool, dividing the IP address field belonging to the gateway group into a plurality of subdivision address intervals, and storing the plurality of subdivision address intervals after division into an address interval state set; predicting the IP address demand of the to-be-allocated device to obtain an IP address demand prediction result; inputting the resource occupation state of each subdivided address interval in the address interval state set and an IP address demand prediction result into the resource allocation model after training optimization is completed, and outputting an IP address allocation strategy; and allocating IP address resources to the to-be-allocated equipment according to the output IP address allocation strategy. According to the invention, dynamic and intelligent IP address allocation is realized.
Owner:WUXI SHANGHANG DATA CO LTD

Method and equipment for distributing resource data in game

The invention provides a method and equipment for distributing resource data in a game, and the method comprises the steps: collecting high-dimensional data and game state data in the game, and extracting feature data in the high-dimensional data through an attention mechanism; jointly constructing a behavior prediction model based on the user side and the server side, inputting the feature data into the behavior prediction model, and obtaining behavior data of the player; based on the game state data and the behavior data, utilizing a reward function to calculate a reward value of the player; dynamically adjusting an allocation strategy of resources in the game according to the reward value; and monitoring an effect of resource allocation in the game in real time, and performing iterative optimization on the behavior prediction model according to a monitoring result. According to the method, the reward value is innovatively introduced as a distribution basis, and accurate putting of resources in the game is realized through sorting and priority setting. According to the strategy, the use efficiency of resources is improved, the enthusiasm and participation degree of players are stimulated, and the satisfaction degree of the players is improved.
Owner:CHONGQING YOUNI BETTER NETWORK TECHNOLOGY CO LTD

Business process processing method and system based on large language model

The invention provides a business process processing method and system based on a large language model, relates to the technical field of artificial intelligence, and can accurately capture a power grid business session event and a dependency relationship thereof by constructing a multivariate relationship network of power grid business description content, thereby providing a comprehensive data basis for analysis of complex power grid business. Furthermore, the business event, the linkage event and the session knowledge tag are converted into vector representation of a high-dimensional space through an embedded representation and vector fusion technology, so that multi-dimensional information is effectively integrated, and the understanding ability of the model to a power grid business scene is enhanced. According to the method, the initial large language model is subjected to linkage parameter adaptation optimization and parameter learning by using the sample network member vector, and the finally generated target large language model is not only high in accuracy, but also can better adapt to the dynamic change of the power grid business, so that the precision, high efficiency and intelligentization of the business process processing are realized.
Owner:CHENGDU POWER SUPPLY COMPANY OF STATE GRID SICHUAN ELECTRIC POWER

Optimal locating and sizing planning method for energy storage system and distributed power generation

The invention discloses an optimal locating and sizing planning method for an energy storage system and distributed power generation. The method comprises the following steps: representing the condition of installing an energy storage and distributed power supply in each node in a topological graph of a power system through a decision vector; establishing an admittance matrix according to the topological graph of the power system, and then performing conversion to obtain an impedance matrix of the nodes; and by taking the lowest operation cost as an objective function and combining constraint conditions, optimizing decision vectors by combining sensitivity analysis of an impedance matrix and a simulated annealing algorithm to obtain an optimal locating and sizing scheme of the energy storage system and distributed power generation. According to the method, the overall operation environment of a power grid and physical limitations of equipment are more considered, including consideration of the capacity of a transformer, and it is ensured that the safe operation range of the transformer is not exceeded while BESS and DG are increased; greater flexibility is provided, and the number and scale of energy storage and power generation facilities are allowed to be dynamically adjusted.
Owner:STATE GRID HUNAN ELECTRIC POWER COMPANY LIMITED +2

Unmanned aerial vehicle path implementation planning method based on rolling EKF

The invention provides an unmanned aerial vehicle path implementation planning method based on rolling EKF, and the method provides a new path planning strategy for the UAV in an urban space. Firstly, environment information is sensed and acquired; secondly, performing state estimation and trajectory prediction by using an EKF (Extended Kalman Filter); and finally, the model predicts and controls the rolling optimization trajectory. According to the invention, state estimation and trajectory prediction are carried out by using extended Kalman filtering (EKF), so that noise in a trajectory observed by a sensor is reduced, and the predicted trajectory is close to an actual flight trajectory as much as possible; a time axis is introduced, on the basis of rolling optimization of model prediction control, the flight time of the unmanned aerial vehicle is divided into small time intervals, and a dynamic map is constructed based on the time intervals; and searching a feasible path by using a breadth-first search method, and obtaining an optimal path through an A * algorithm. Simulation results show that the provided obstacle avoidance method can effectively avoid static buildings and dynamic obstacles, and a safe flight path is planned for the unmanned aerial vehicle in the urban space.
Owner:AIR FORCE UNIV PLA

Lithium battery multi-threshold active and passive equalization control method and system

The invention belongs to the field of battery health state monitoring, and discloses a lithium battery multi-threshold active and passive equalization control method and system.According to the method, by collecting current, voltage and SOC data of a lithium battery in real time and combining a multi-threshold judgment mechanism, the dynamic change of a battery pack can be reflected more accurately, equalization operation is triggered in time, and the equalization efficiency is improved. The problem of over-equalization or under-equalization possibly caused by a single-threshold strategy is effectively avoided; meanwhile, the intelligent screening of the active equalization strategy and the passive equalization strategy further improves the equalization efficiency and effect, and ensures that the voltage difference and the SOC difference between the single batteries in the battery pack are kept in a reasonable range, thereby prolonging the service life of the battery pack, improving the overall performance, and reducing the potential safety hazard. The method can provide powerful guarantee for stable operation of the energy storage system.
Owner:STATE GRID BEIJING ELECTRIC POWER CO

Energy-saving routing method and system of wireless sensor network

The invention discloses an energy-saving routing method and system for a wireless sensor network, and belongs to the field of wireless networks, and the method comprises the steps: firstly constructing a total energy consumption model of the network, considering the periodic change of a network flow load, adopting different network topologies in different time periods, and reducing the energy consumption; and then, designing and implementing a solution algorithm to find out a routing path with minimum energy consumption. According to the algorithm, an improved greedy strategy is adopted, an evaluation function is introduced, information of current node energy consumption and a minimum energy consumption path is considered, dynamic adjustment is carried out, and a random selection and backtracking mechanism is added. And finally, optimizing the obtained routing path, and further reducing the energy consumption by repeatedly checking and updating nodes on the path. The method provides an effective solution for saving the energy of the wireless sensor network.
Owner:YIBIN VOCATIONAL & TECH COLLEGE

Power generation scheduling method and system for water-light complementary joint optimization

The invention relates to the technical field of power generation dispatching, and particularly discloses a water-light complementary joint optimized power generation dispatching system and method, which are used for solving the problem of how to improve on the basis of a fixed voltage method and a conductance increment method, combine the advantages of the two methods and improve the defects of the two methods. The system comprises a monitoring module, a feedback module, an adjusting module, a control module, an energy storage module and a communication module, an improved fixed voltage method and an incremental conductance method are provided, the fixed voltage method is improved by dynamically adjusting a coefficient, and the power generation scheduling problem of water-light complementation combination in a distributed energy system and a micro-grid is solved. Fourier transform and inverse Fourier transform are combined with a frequency response function to optimize an incremental conductance method; photovoltaic and hydroelectric power generation data and system load requirements are monitored in real time, power generation output is adjusted in real time by adopting an improved fixed voltage method and an improved conductance increment method, performance is optimized through a frequency response function, dynamic changes of a micro-grid are adapted, and power output is smoothed through an energy storage management function.
Owner:GUIZHOU POWER GRID CO LTD

Data resource integration system based on cloud computing

The invention discloses a data resource integration system based on cloud computing, and relates to the technical field of data resource processing, cloud platform data resources are preprocessed through a sequence generation module, timestamps are extracted, standardized time sequences are generated, and t-SNE is used for dimension reduction; the network construction module constructs a similarity complex network according to the sequence after dimension reduction, calculates the similarity of data points and constructs a simplified complex; the persistent calculation module calculates topological features of the simplified complex at different scales through a persistent coherence algorithm to generate a persistent coherence graph; the drift identification module compares the persistent homology graphs in different time periods, calculates a Wasserstein distance and identifies data drift; and the resource integration module classifies and screens data resources according to the drifting result, retains valid data, eliminates invalid data and realizes dynamic integration. And comparing and analyzing the persistent homograph, intelligently classifying and screening data resources based on a drift identification result, automatically eliminating invalid or noise data, and retaining data resources valuable for analysis.
Owner:SHANGHAI YUNSAI SHUHAI TECH CO LTD

AGC frequency modulation control method, system and device based on lithium battery energy storage system and medium

The invention relates to the technical field of power grid frequency modulation, in particular to an AGC frequency modulation control method, system and device based on a lithium battery energy storage system and a medium, and the method comprises the steps: collecting the operation data of a thermal power generating unit and a lithium battery energy storage device in real time, determining an AGC instruction according to the operation data, and obtaining the frequency of a power grid; determining a control signal for power adjustment of the thermal power generating unit according to a power target value and actual generator power in the AGC instruction; adjusting the output power of a generator in the thermal power generating unit by adopting a set control strategy according to the control signal; and according to the power grid frequency deviation, the AGC instruction and the operation states of the unit and the lithium battery energy storage equipment, dynamically adjusting the power distribution proportion of the lithium battery energy storage and the thermal power unit until the power grid frequency modulation requirement is met. The method can maximize the regulation capability of the energy storage system.
Owner:HUANENG TAICANG POWER GENERATION CO LTD +1

Active power distribution network cluster dynamic division method and system based on deep reinforcement learning

The invention discloses an active power distribution network cluster dynamic division method and system based on deep reinforcement learning. The method comprises the following steps: step 1, constructing a power distribution network cluster dynamic division-oriented CMDP model; step 2, converting the CMDP model constructed in the step 1 into an unconstrained problem by using a Lagrange relaxation method, and constructing a solving framework based on AC-DRL for solving the CMDP model; step 3, training the solving framework based on AC-DRL constructed in the step 2 to obtain a deployable CMDP model; and 4, deploying the deployable CMDP model obtained in the step 3 to a power distribution network dispatching cloud platform, and providing a cluster division result according to the real-time observation state of the power distribution network. Compared with a traditional cluster division method, the method has the advantages that in actual application, the calculation complexity is greatly reduced, and an extremely fast decision can be made even for a large system scale, so that the method is more capable of responding to the fluctuation of the state of the power distribution network in real time.
Owner:RES INST OF ECONOMICS & TECH STATE GRID SHANDONG ELECTRIC POWER +1

Multi-agent self-discipline collaborative optimization method and system for multi-region reactive voltage control

The invention relates to the technical field of voltage optimization control of a power system, in particular to a multi-agent self-discipline collaborative optimization method and system for multi-region reactive voltage control, and provides an optimal reactive voltage optimization decision method for establishing a data interaction model, setting a data interaction mode and researching a power distribution network. By optimizing distribution of reactive power, the active loss of the power distribution network is reduced, the economical efficiency of the power system is improved, and the service life of equipment is prolonged; by using a deep reinforcement learning algorithm, effective adjustment of voltage is realized, and node voltage is stabilized; a deep reinforcement learning method is adopted, so that the influence of model errors is reduced, the calculation speed and the real-time response capability are improved, and the calculation cost is reduced; through continuous interaction with actual power grid data, the intelligent agent can cope with the uncertainty of distributed new energy, energy storage and flexible load power generation and power utilization, and the stability and reliability of the system under various complex conditions are improved.
Owner:YUNNAN POWER GRID CO LTD KUNMING POWER SUPPLY BUREAU

Network link security management method based on artificial intelligence

The invention discloses a network link security management method based on artificial intelligence, which relates to the technical field of network security management, and comprises the following steps: when a network receiving link receives a data file of a sending end, obtaining first parameter data of the sending end to generate a sending feature and a fingerprint mark, and performing security verification on the fingerprint mark; and after verification, the data file and the fingerprint mark are packaged to generate a to-be-transmitted file. And when the to-be-transmitted file passes through an intermediate node of the network transmission link, recording second parameter data of the intermediate node, gradually generating a dynamic path mark and inputting the dynamic path mark. And when the file is transmitted to a receiving end, obtaining a complete dynamic path mark, carrying out anomaly analysis on the path mark according to a preset anomaly analysis algorithm, and if an anomaly is detected, generating an anomaly signal and giving an alarm. By sending the fingerprint mark in combination with the dynamic path mark and real-time monitoring, the adaptability of the network environment is improved, and the abnormality in the transmission path is accurately detected.
Owner:JIANGXI SHUNXINGXING TECH CO LTD

Predictive maintenance model management method for communication information system

The invention provides a predictive maintenance model management method for a communication information system, belongs to the field of artificial intelligence, and realizes predictive maintenance of equipment and network nodes by utilizing real-time data in a communication network and combining a PPO algorithm. The method is suitable for a dynamic environment of a large-scale communication network, integrates multi-source data through a data sharing platform, and optimizes the learning and prediction capabilities of the model. Comprising distributed data acquisition, dynamic model updating, maintenance strategy generation, model optimization and real-time data synchronization. The problem that traditional centralized model management cannot adapt to communication network complexity and dynamic change is solved. Through distributed data processing and adaptive optimization of the PPO algorithm, the prediction precision and response speed of the system are improved, and the operation efficiency and maintenance capability of the communication information system are significantly improved.
Owner:INSPUR TIANYUAN COMM INFORMATION SYST CO LTD

Vulnerability detection model training method, script vulnerability detection method and related device

The invention provides a vulnerability detection model training method, a script vulnerability detection method and a related device, and relates to the field of machine learning. The method comprises the following steps: the electronic equipment obtains vulnerability prediction loss of a sample script set according to vulnerability prediction information of the sample script set by a current first to-be-trained model; the variation degree of the sample script set is obtained, the loss is predicted according to the variation degree and the vulnerability, the current first to-be-trained model is updated, and the variation degree represents the complexity of the sample script set. And iterating the above steps until an iteration stop condition of the vulnerability detection model is satisfied. Thus, in the training process of the first to-be-trained model, the parameters of the network are automatically adjusted according to the complexity of the sample script set, so that the trained vulnerability detection model has good generalization ability and can adapt to the dynamic change and complexity of scripts.
Owner:GUANGZHOU ZHONO ELECTRONICS TECH CO LTD

Wafer extraction path optimization method based on adaptive heuristic and hierarchical search

The invention is suitable for the technical field of automation equipment control and path planning, and provides a wafer extraction path optimization method based on adaptive heuristic and hierarchical search, comprising the following steps: Step 1, initialization; step 2, heuristic value calculation: calculating an adaptive heuristic function value according to the current node to guide search; step 3, judging whether an end point is reached or not; step 4, path cost calculation is carried out; step 5, judging node expansion: judging whether to expand a current node according to a self-adaptive expansion condition, and preferentially expanding a node which is most likely to approach an end point; step 6, layered search of paths: layered search is carried out gradually from the outer layer to the inner layer, independent path planning is carried out on each layer, and the search range is reduced; step 7, path backtracking is carried out; step 8, updating a search area; step 9, continuing or terminating the search; and step 10, outputting a result. On the premise of ensuring the shortest path, the start-stop frequency of the motor is reduced, the operation efficiency of automatic equipment is improved, the service life of the equipment is prolonged, and the energy consumption is reduced.
Owner:SUZHOU HUANXU SEMICON TECH CO LTD

Multi-model collaborative knowledge distillation optimization method based on edge calculation

The invention discloses a multi-model collaborative knowledge distillation optimization method based on edge computing. The method comprises the following steps that a plurality of edge devices construct local models respectively and train the local models through collected local data, and the edge devices upload the trained models to a server; real-time performance evaluation is carried out on local models on the edge devices, whether the performance evaluation result meets preset conditions or not is judged, if not, the local models are updated, and the model updating comprises the following steps that 1, a multi-model collaborative distillation strategy is adopted, and knowledge exchange is carried out on the local models on the different edge devices; 2) carrying out data heterogeneity and imbalance processing; 3) carrying out resource adaptive scheduling; (4) the server carries out local model aggregation and issues model updating content in the iteration process to the edge device; if yes, the local model does not need to be updated in the iteration. According to the invention, the performance of multiple models on the edge device can be improved, the communication overhead is reduced, and the data privacy is ensured.
Owner:HAINAN INTELLIGENT SPACE-TIME TECHNOLOGY PARTNERSHIP (LLP) +1

Unmanned mine car path tracking control method based on preview curvature

The invention belongs to the technical field of automatic driving, and provides an unmanned mine car path tracking control method based on preview curvature. According to the tracking control method, the concept of the preview curvature is introduced, complex optimization calculation is reduced, the real-time performance of the control method is improved, the current state of the vehicle and the geometrical characteristics of the future path are considered based on the preview curvature, smoother and more accurate path tracking can be achieved, and the tracking control method is especially superior under the complex conditions of S-shaped bending, sharp turning and the like. Through PID control, different control states can be transited smoothly, frequent control input changes are reduced, and the stability and robustness of path tracking control are improved.
Owner:TAGE IDRIVER TECHNOLOGY CO LTD

Electric meter intelligent communication detection method and system based on power line carrier

The invention discloses an electric meter intelligent communication detection method and system based on a power line carrier, and relates to the technical field of electric meter communication detection, and the method comprises the steps: collecting the communication data of an electric meter at different time periods, inputting an electric meter communication state dynamic sensing model, analyzing features, and obtaining an initial evaluation result; channel characteristic parameters are calculated by using a carrier channel characteristic dynamic estimation algorithm based on the result, and the channel characteristic parameters are input into a power carrier signal demodulation optimization algorithm to generate an optimized demodulation scheme; signals are demodulated and data are verified according to the scheme, related results are uploaded to an electricity meter communication performance optimization management platform, and the platform evaluates performance and generates optimization suggestions and fault early warning. The system comprises a data acquisition unit, a state analysis unit, a channel calculation unit, a demodulation optimization unit, a data processing unit and a performance management unit which operate cooperatively. The communication state can be dynamically sensed, the channel characteristics can be accurately estimated, the demodulation process can be optimized, the integrated management of the communication performance can be realized, and the accuracy and reliability of the electric meter communication can be improved.
Owner:SHENZHEN XUNZHI WULIAN TECH CO LTD