7results about How to "Improve clustering efficiency" patented technology

The invention provides an electric vehicle charging user clustering method and system based on knowledge graph representation learning, and the method comprises the steps: carrying out the processing of each user and each order for the charging of an electric vehicle through the knowledge graph representation learning, and obtaining the initial representation of the user and the order; inputting the user and order initial representation into a trained BERT model for representation learning, and obtaining a plurality of user relationship vectors; and clustering the plurality of user relationship vectors by adopting a hierarchical navigable small world algorithm to obtain a clustering result of the charging users. As the trained BERT model and the navigable small-world network algorithm are combined with the users and the orders for clustering, the users with similar charging behaviors can be effectively distinguished when complex electric vehicle charging data are processed, and the clustering efficiency and accuracy are improved.

This invention belongs to the field of computer technology and discloses a method, apparatus, device, and storage medium for generating webpage structural fingerprints. The method includes: parsing the current webpage into a DOM tree and obtaining the attribute features of each node in the DOM tree and the node relationship chain formed by each node; calculating the hash weight of each node based on the node relationship chain; generating the hash value of each node according to its attribute features; and generating the webpage structural fingerprint of the current webpage based on its hash weight and hash value. By parsing the webpage structure and generating fingerprints through the above method, differentiated webpage structures can be achieved, facilitating the aggregation of pages with similar structures and a high risk of cheating, improving the clustering efficiency of webpage structures, shortening the perception time of webpage generation groups, and providing data support for subsequent rapid detection of cheating website groups and prevention of mass piracy.

This application discloses a method, apparatus, device, and medium for event aggregation based on feature association, relating to the field of text classification and analysis. The method includes: acquiring multiple event texts to be aggregated and multiple historical event clusters; wherein each event text includes a title and a summary; based on single-pass clustering, clustering is performed on the title and summary respectively, using multiple historical event clusters, to determine the title identifier and summary identifier of each event text; traversing all summary identifiers, processing each event text to obtain multiple aggregated event clusters; wherein in each round of traversal, event texts are selected based on the current summary identifier to construct the current event set, and the current event set is updated according to the title identifiers of all event texts in the current event set to obtain the aggregated event clusters; and the historical event clusters and aggregated event clusters are merged and updated according to the title identifier and summary identifier to complete the event aggregation. Implementation of this application can improve the accuracy of event aggregation.

This application discloses a target object detection method, device, and storage medium. The method includes: acquiring a target point cloud, which is obtained by using a detection device to collect data from a detection area; performing dimensionality reduction mapping on the target point cloud to obtain two-dimensional point data, wherein the two-dimensional points in the two-dimensional point data are distributed in rows and columns; clustering the two-dimensional points in the two-dimensional point data to obtain clustering results; and determining the point cloud belonging to the target object based on the clustering results. Through the above methods, this application can improve the detection efficiency of target objects.

The application discloses an indoor positioning method and system fusing WiFi fingerprints and space information, the method realizes online positioning through offline construction of a fingerprint map. Wherein, WISP features fusing WiFi features and space features are proposed, the space features are classified and coded according to whether reference points are in straight corridors or corners. In addition, the application also constructs a bag-of-words tree, that is, the bag-of-words tree is used to represent the correlation between reference points, so that in the online positioning stage, firstly, the WISP features of the current position and the bag-of-words tree are used to calculate the similarity between the WISP features of the current position and the WISP features under each cluster; then the product of the similarity and the corresponding TF-IDF weight value is calculated, finally, the cluster with the maximum product value is selected, and the position corresponding to the WISP features under the cluster is used to deduce the final positioning result, effectively reducing the influence degree of the perception confusion of WiFi signals.

The present disclosure provides a node clustering method and device, electronic equipment and storage medium, the method comprising: determining a plurality of routing paths according to the calling relationship between a plurality of network nodes; determining a starting node and its belonging node hierarchy from the plurality of network nodes; traversing each routing path starting from the starting node; when traversing the current routing path, determining the hierarchy of each node according to the distance between each network node and the starting node and the hierarchy of the starting node; if the hierarchy of the next node of the current node has been determined, ending the traversal and recording the path traversal result; when the traversal of the plurality of routing paths is completed, clustering the network nodes at the same hierarchy into the same cluster node group according to all the results. The method clusters the network nodes according to the data flow direction in the network, and sets the traversal end condition, which can solve the problem that node clustering cannot be achieved in the presence of a loop.

The invention discloses an industrial waste gas emission supervision system and method. Waste gas emission source data in a supervision range are acquired and stored through an emission source information base module; internet public information is captured and analyzed through a public opinion monitoring module, so that public opinion event data is obtained; waste gas diffusion simulation is carried out through a waste gas emission source screening module in combination with waste gas emission source data, public opinion event data, meteorological data and geographic data, and influence evaluation of a waste gas emission source matched with a public opinion event is obtained.