24 results about "Average path length" patented technology

The invention relates to the technical field of path planning, in particular to a path planning method based on an improved ant colony algorithm, which comprises the following steps: establishing a grid map, and initializing parameters of the ant colony algorithm; determining an initial value of pheromone concentration according to the distance between the nodes in the grid map and the initial node and the distance between the nodes in the grid map and the target node; ants are placed at the initial node for multiple times, each ant starts from the initial node, the next node where the ant moves is selected according to the pheromone concentration and heuristic information, and the taboo table and the current pheromone concentration are updated; emptying the taboo table after the tracking of all ants is completed, and recording the paths of all ants; updating a pheromone volatilization factor based on a proportional relation between the average path length and the minimum path length; after the maximum number of iterations is reached, a final planned path is obtained according to the recorded path through which the ants walk; the convergence speed and reliability of the ant colony algorithm can be improved.

The invention provides an abnormal transaction early warning method, device and equipment, a medium and a program product, which can be applied to the field of big data and the field of financial science and technology. The method comprises the steps of calculating an average path length of transaction data to be detected based on a transaction feature isolation forest model, and determining a first class score according to the average path length; wherein the transaction feature isolation forest model is constructed by analyzing a first type of historical transaction data through an isolation forest algorithm; on the basis of transaction discrimination features, a second class score of the transaction data to be tested is calculated through a random forest algorithm, and the transaction discrimination features are obtained by analyzing second class historical transaction data through the random forest algorithm; analyzing the first class score and the second class score, and determining an abnormal level of the to-be-tested transaction data; and based on the abnormal level, early warning the abnormal risk of the to-be-tested transaction data in real time.

The invention provides a key bearer link determination method and device, equipment and a storage medium, and relates to the technical field of satellite communication, and the method comprises the steps: constructing a network topology of a satellite Internet at a current moment; for each node pair, based on nodes and edges in the network topology, determining a first non-coincident average path length when a source node and a destination node in the node pair are accessed to a satellite moving in the same direction at the current moment, and a second non-coincident average path length when the source node and the destination node are accessed to a satellite moving in the opposite direction at the current moment; determining a path length difference value based on the first non-coincident average path length and the second non-coincident average path length; based on the path length difference value corresponding to each node pair, a target key bearing link in the satellite internet is determined, and the target key bearing link is a satellite-ground link which is most influenced by the satellite motion direction. According to the invention, the accuracy of the determined key bearer link can be improved.

This invention discloses a method and system for three-dimensional optimization of pedestrian networks with the goal of improving traffic efficiency. The method includes: acquiring image data of the road system; preprocessing and simplifying the image data to construct a road network dataset containing multiple road nodes; establishing an optimization objective function based on the average path length of the three-dimensional pedestrian passage and the number of turns in the underpass; performing simulation optimization on the objective function according to preset constraints and the road network dataset to obtain the optimal solution composed of road nodes; optimizing the pedestrian network based on the optimal solution, calculating the optimized traffic efficiency index, and optimizing the simulation optimization process based on the traffic efficiency index. This invention not only improves the accuracy and flexibility of three-dimensional pedestrian network optimization but also enhances user comfort and satisfaction, providing a more scientific and flexible solution for urban planning and construction.

The present application belongs to the technical field of flow monitoring, and particularly relates to a coal mine industrial control network abnormal flow monitoring method and system, which comprises the following steps: constructing a two-dimensional feature space from the load byte entropy value and the time stamp interval, clustering and dividing mutually intersecting flow clusters; determining an initial subsampling number, compensating sparse clusters to a basic share; apportioning and deducting excess samples in inverse proportion to Mahalanobis distance variance, maintaining the sampling scale unchanged; constructing an isolation tree for each subsampling set, setting a non-uniform division probability according to the feature variance, determining the maximum depth of the tree through the trace of the covariance matrix and an S-shaped function; calculating a single-tree score according to the average path length of the sample, and obtaining a comprehensive abnormal score through weighted geometric mean according to the cluster weight; adjusting the quantile threshold value by real-time calculation of the cluster weight information entropy, triggering an abnormal alarm if the score exceeds the limit, and realizing the identification of coal mine industrial control network flow anomalies. The present application can compensate sparse clusters, adaptively isolate trees, dynamically adjust threshold values and improve detection accuracy.

The embodiment of the invention provides a social network feature-based team communication complexity analysis method and system, and the method comprises the steps: constructing a command and control social network model, carrying out the fuzzy evaluation of a task unit, determining the overall fuzziness of a task, carrying out the multi-dimensional evaluation of a communication medium, determining a comprehensive value of the richness of the medium, and carrying out the analysis of the richness of the medium. Constructing a task fuzziness-communication medium matching matrix, coupling the task overall fuzziness with a medium richness comprehensive value, determining a medium communication efficiency parameter, and performing complexity analysis on a command and control social network model according to the medium communication efficiency parameter to obtain a command and control social network model; the average path length complexity feature, the network diameter complexity feature and the network density complexity feature of the network are obtained, weighted optimization is carried out on the network edge according to the network complexity feature, an optimized command and control social network model is obtained, and the efficiency of team communication and task execution can be improved.

The invention provides an intelligent identification method and system for abnormal auditing data of a hospital. The intelligent identification method comprises the steps of obtaining a multi-dimensional data set of the hospital, calculating a local outlier factor LOF of each data record, distributing a differential privacy budget and generating a privacy data set; constructing a weighted K nearest neighbor graph based on the privacy data set and the LOF value, and performing community division on the graph; calculating weighted intermediary centrality, community connection strength and average path length of each node, fusing the weighted intermediary centrality, the community connection strength and the average path length into a structural anomaly score, and screening data records of which the scores are higher than a first threshold value as first-level candidate anomaly data; for each piece of first-level candidate abnormal data, mapping the data structure abnormal score into a time window, extracting a time sequence track, and calculating an average time sequence track of the community as a prototype track; outputting a time sequence similarity distance; constructing a confirmation threshold value, wherein the threshold value is adjusted based on community structure characteristics, data differential privacy budget and a structure anomaly score; and when the time sequence similarity distance is greater than the threshold value, identifying the data as abnormal data.

This invention belongs to the field of machine tool cutting state monitoring and intelligent control technology, specifically relating to a method for controlling the cutting state of a tool during the boring process of a space frame member. The method includes: real-time acquisition and preprocessing of multi-dimensional cutting data during the boring process to obtain a basic feature sequence; calculation of the ratio of the average effective cutting power of the sliding window to the instantaneous material removal rate, and obtaining a steady-state cutting energy index after deducting the initial cutting energy benchmark; calculation of the time-dependent decay weight of historical samples using an exponential decay function, and then obtaining the drift compensation boundary probability through root mean square fusion to dynamically correct the isolation forest model's decision boundary; further fusion of the average path length and normalization constant, and obtaining an anti-baseline drift correction anomaly score through the product of the exponential term and the logarithmic suppression term; setting a safety threshold, and performing anti-chipping closed-loop control based on the comparison result between the anomaly score and the threshold. This invention improves the accuracy of tool control during the boring process of space frame members.

The invention discloses a deep reinforcement learning path planning method based on local environment driving, belongs to the technical field of mobile robots, and is used for autonomous navigation and obstacle avoidance of a mobile robot in a complex environment. The method comprises the following steps: firstly, constructing an obstacle contour model according to obstacle point information in a local environment; then constructing a local environment graph structure between the obstacle and the robot by adopting an undirected graph, and extracting spatial feature and deep feature information in a local environment by utilizing a graph attention network; acquiring an optimal local target point by using a local target driving mechanism; and finally, fusing deep reinforcement learning to train an optimal path planning strategy. According to the method, key features in a local environment are learned through local target point guidance and graph attention network reinforcement, the local environment perception ability of the robot is improved, the path planning ability of the robot in a complex environment is enhanced, the average path length can be remarkably shortened while the navigation success rate is improved, and the track smoothness is enhanced.

The invention belongs to the technical field of anomaly detection, and particularly relates to an anomaly detection method and device based on a deep isolation forest. The method comprises the following steps: inputting a to-be-detected data set into a neural network model for data mapping and nonlinear division to obtain a divided data representation set, and constructing an isolation forest by using the divided data representation set; calculating the average path length of the data points in the whole isolation forest and the deviation density measurement of each data point, wherein the deviation density measurement is obtained based on the local density and the deviation calculation of the node characteristic value and the splitting threshold value; the abnormal score of each data point is calculated based on the average path length and the deviation density measurement, the abnormal score is compared with the set threshold value, the abnormal data points are screened out, and the accuracy and robustness of identifying abnormal data under different data types and data scales are improved.

The invention discloses a payment abnormity detection method and device, electronic equipment, a medium and a program product, and relates to the technical field of computers.The method comprises the steps that a graph structure is constructed based on preprocessed user payment information, the graph structure comprises at least two nodes and at least one edge, one node corresponds to one user payment account, and one edge corresponds to one user payment account; the edge is used for representing an association relationship between any two nodes in the at least two nodes; extracting at least one subset from the graph structure, and constructing at least one isolated tree corresponding to the at least one subset based on an isolated forest algorithm; putting a target node into the at least one isolated tree for traversal, and obtaining a first average path length of the target node; and based on the first average path length, determining an abnormal score of the first target node, the abnormal score being used for representing an abnormal degree of the first target node. The method can adapt to complex and changeable payment scenes, and improves the detection precision.

The application discloses a battery cabin fire automatic early warning method and system, electronic equipment and storage medium, which are used for realizing early and accurate early warning of battery cabin thermal runaway. The method first collects voltage time series of the battery monomer charging and discharging process, reconstructs the phase space through mutual information method and false nearest neighbor point method, constructs a recurrence plot matrix and extracts five-dimensional chaotic features such as recurrence rate and determination rate. Relying on the battery electrical connection and space thermal coupling topology, a graph convolution network is built to calculate the abnormal score of the battery monomer. Through the sliding window combined with the first and second derivative analysis, the real abnormal monomer is accurately identified. A local anomaly propagation network is built around the abnormal monomer, the average path length and clustering coefficient of the network are calculated, and the fault diffusion trend is quantified. Finally, according to the change rate threshold of the two topological parameters, the abnormal spread degree is judged, and the fire warning signal is triggered. The method can capture early implicit voltage anomalies of the battery, and effectively identify the fault deterioration and propagation situation.

The invention provides a method for detecting abnormal data of a wind direction sensor. The method comprises the steps of obtaining Gray code data of the wind direction sensor; selecting one numerical value, dividing the numerical values into data units with the same data according to a time sequence, counting the number of data in each data unit as data points, and storing the data points into a to-be-detected data set; generating sub-samples without replacement sampling to construct a plurality of isolation trees until all data points are extracted, and calculating the skewness of the sub-samples; generating a segmentation point according to the skewness, and carrying out recursive segmentation on the data of the sub-sample into two subsets until a stop condition is met; calculating the average path length of each data point in the isolation tree to judge whether the data point is an abnormal data point; and repeating the above steps until each numerical value of the Gray code data is selected, dynamically adjusting the segmentation strategy by using the skewness, enabling the segmentation points to be closer to the abnormal data dense region, and improving the speed and accuracy of removing the abnormal data.

The application relates to the technical field of distributed computing, and discloses an information collaborative processing method and system in a distributed environment, which comprises the following steps: acquiring node connection relations to form a global connection dataset, calculating node connection degrees, average path lengths and comprehensive load scores; screening high-stability nodes as candidate backbones, and selecting a minimum backbone set to cover all non-backbones; periodically collecting local state characteristic vectors of the non-backbones, collecting global state information, and redundantly storing the global state information in the non-backbones after encoding by using a Vandermonde matrix; monitoring backbone abnormalities to trigger reconstruction, and acquiring encoded blocks from the non-backbones by a new backbone node to recover the global state information through error correction code decoding; and publishing an updated task list and routing instruction according to the recovered information to complete collaborative relationship reconstruction. The method can realize reliable storage and rapid recovery of global state information, and significantly improves the self-adaptability, fault tolerance and collaborative efficiency of a distributed system.

The application discloses a kind of local environment driving-based deep reinforcement learning path planning method, belong to mobile robot technical field, for the autonomous navigation and obstacle avoidance of mobile robot in complex environment.The method first constructs obstacle profile model according to the obstacle point information in local environment;Then local environment graph structure between obstacle and robot is constructed using undirected graph, spatial features and deep feature information in local environment are extracted using graph attention network;Then the optimal local target point is obtained using local target driving mechanism;Finally, the optimal path planning strategy is trained by fusing deep reinforcement learning.The application guides local target point and enhances the key features in local environment by graph attention network reinforcement learning, improves the local environment perception ability of robot, enhances the path planning ability of robot in complex environment, can significantly shorten the average path length while improving the navigation success rate, enhances trajectory smoothness.

The application provides a land planning method based on data analysis, comprising: obtaining an initial distance matrix between each plot in a set of farmland plots around a town, respectively calculating the direct connectivity of each plot with other plots based on a distance threshold, and constructing an initial farmland ecological network topology structure diagram; calculating the overall network connectivity, node centrality and average path length of the initial farmland ecological network topology structure diagram through a graph theory algorithm, thereby evaluating the structural integrity of the ecological network to obtain initial values of ecological network structure evaluation indexes; recalculating the connectivity between each plot according to an adjusted distance matrix between plots, reconstructing the farmland ecological network topology structure, and calculating various indexes of network structure integrity to evaluate the ecological network structure; and combining the plot connectivity with the land use efficiency to evaluate the feasibility and cost-effectiveness of the tillage layer stripping and reuse, and determining an optimal adjustment scheme.

The invention provides an employee abnormal behavior detection method and device and a computer readable storage medium. In the scheme, a plurality of employee behavior sample data sets are acquired, an isolation forest model is established by using the employee behavior sample data sets, the isolation forest model comprises a plurality of isolation trees, and the employee behavior sample data sets are in one-to-one correspondence with the isolation trees; calculating an abnormal score of each data point in the employee behavior sample data set based on an isolation forest model, wherein the abnormal score is calculated based on an average path length of each data point in all isolation trees in the isolation forest model; screening the data points for multiple times based on the value of the abnormal score, and deleting a part of isolation trees in the isolation forest model according to the screened data points to obtain an updated isolation forest model; and performing abnormal behavior detection on the to-be-detected employee behavior data by using the updated isolation forest model to obtain an abnormal behavior detection result. According to the scheme, the problem that the detection precision of the employee abnormal behaviors is low is solved.

An improved path planning algorithm LADP-MADDPG based on a multi-agent depth deterministic policy gradient algorithm belongs to the technical field of artificial intelligence, and the algorithm captures time sequence information for agents by introducing a long short-term memory network, and enhances the flexibility and cooperation ability of agent decision making; designing a reward function based on the idea of an artificial potential field method, and guiding the intelligent agent to better complete path planning while solving the problem of reward sparseness; a multi-dimensional dynamic priority calculation method is provided in combination with a priority experience playback mechanism, local optimum is avoided by improving sample diversity and sample utilization rate, and convergence speed is improved. Experimental results show that compared with an original MADDPG algorithm, the LADP-MADDPG algorithm has remarkable advantages in the aspects of convergence speed, success rate and average path length in environments with different numbers of agents and different obstacle complexity, and the adaptability and robustness of the LADP-MADDPG algorithm in different environments are verified.

The invention discloses a steel production modeling method based on a complex network, and relates to the technical field of industrial production process modeling. The method comprises the following steps: deconstructing the whole process of a steel production system, and abstracting three types of units including production processing, energy / medium conversion and storage and material input / output / buffer into network nodes; extracting a device physical connection and production flow transmission relation, and defining a directed edge; a directed complex network model is constructed and visualized; and calculating degree distribution, a global average path length, an improved average path length and a clustering coefficient, and verifying scale-free and small-world characteristics. According to the method, through a'basic theory layer-engineering application layer 'double-layer index system, steel production whole-process global topological representation and system characteristic quantification are achieved, model support is provided for whole-process optimization, academic preciseness and engineering practicability are achieved, and the method can be popularized to cement, thermal power and other process industrial systems.

The invention provides a multi-AGV path planning algorithm based on dynamic adaptive exploration and course learning, and relates to the technical field of automation and intelligent logistics. According to the method, although a traditional deep reinforcement learning method is preliminarily applied to multi-AGV system path planning, the limitations of low efficiency, poor dynamic adaptability, insufficient cooperative competition relation processing and the like still exist, and the specific expressions are low exploration efficiency, insufficient sample utilization, slow convergence speed and even non-convergence. For this purpose, a multi-agent depth deterministic strategy gradient algorithm (AECL-MADDPG) based on adaptive exploration and course learning is designed, and centralized training is adopted. A distributed execution framework is adopted, the obstacle avoidance capability and the implicit cooperation efficiency of the AGV in a high-density environment are enhanced by sensing the environment congestion degree and decision uncertainty in real time to dynamically adjust the exploration strength, meanwhile, a course learning-based priority experience playback mechanism is constructed, a training normal form from easy to difficult is combined with key experience priority sampling, and the accuracy and the robustness of the AGV are improved. Model convergence is remarkably accelerated; and the robustness of a final strategy is improved. The algorithm established and designed under the actual operation condition in the automation and intelligent logistics field shows significant advantages in key indexes such as convergence speed, task success rate, average path length and the like, and an efficient and reliable solution is provided for the multi-agent path planning problem in a complex dynamic environment.

The present invention discloses an abnormal detection method and system for a subway air-conditioning compressor based on isolation forest. The above method includes: acquiring the exhaust temperature data of the air-conditioning compressor in the subway train and grouping it; calculating the statistical features of each group of exhaust temperature data to obtain a sample matrix; constructing an isolation forest abnormal detection model, inputting the sample matrix into the isolation forest abnormal detection model to obtain the average path length of each sample in the sample matrix; obtaining the score of the sample according to the average path length of each sample, and detecting whether the score of each sample is abnormal according to the abnormal threshold to obtain the abnormal detection result. The present invention uses a data-driven method to detect the abnormality of the air-conditioning compressor, which can predict the occurrence of faults in advance and reduce the occurrence of faults during the normal operation of the train.

The invention discloses a combat system vulnerability multi-dimensional evaluation method, and belongs to the technical field of complex system safety evaluation. According to the method, a combat system is decomposed into a physical layer, a logic layer and a cross-layer coupling layer for multi-dimensional modeling; the physical layer calculates topological indexes such as degree centrality and betweenness centrality based on a complex network theory; the logic layer searches a killing chain through a Ullmann algorithm based on a killing chain theory and quantifies indexes such as the chain number and the average path length; and the cross-layer coupling layer analyzes the element failure cascade effect and the capability recovery degree. And integrating multi-dimensional evaluation results through intersection and union set operation to form a vulnerability interval based on the average path length of the killing chain. According to the method, the problems of one-sided single-dimensional evaluation and lack of cross-layer coupling analysis in the prior art are solved, the multi-dimensional quantitative evaluation of the combat system vulnerability is realized, and a scientific basis is provided for system destroy-resistant optimization and key node protection.

The application provides a wind direction sensor abnormal data detection method, comprising the following steps: acquiring Gray code data of a wind direction sensor; selecting one bit value, dividing the one bit value into data units with the same data according to time sequence, and counting the number of data in each data unit as a data point, and storing the data point into a to-be-detected data set; then, a non-replacement sampling is performed to generate a sub-sample, a plurality of isolated trees are constructed until all data points are sampled, and the skewness of the sub-sample is calculated; a split point is generated according to the skewness, the data of the sub-sample is recursively divided into two subsets until a stop condition is met; the average path length of each data point in the isolated tree is calculated to determine whether the data point is an abnormal data point; the foregoing steps are repeated until each bit value of the Gray code data is selected, the skewness is used to dynamically adjust the split strategy, the split point is closer to the abnormal data dense area, and the abnormal data elimination speed and accuracy are improved.

The present invention relates to the technical field of data processing, and in particular, to a vehicle-mounted data processing method and system. The method includes the steps of: taking any feature of the data points in the vehicle-mounted data set as a target feature, and obtaining a correlation sequence of the time series of the target feature; calculating a combined value of the target feature of the data points, and selecting a segmentation point in the time series of the combined value of the target feature to construct an isolation forest of the target feature; obtaining a density feature of the isolation forest of the target feature through the difference between each data point in the isolation forest of the target feature and the median; obtaining the weight of the isolation forest of the target feature through the density feature of the isolation forest of the target feature; obtaining the average path length of the data point in each isolation forest of the target feature, and obtaining the anomaly score of the data point, so as to realize vehicle-mounted data processing, effectively improving the accuracy of vehicle-mounted data anomaly monitoring.