50 results about "Geographic object" patented technology

The invention discloses a travel map searching system and method based on deep learning and a Beidou database, and the method comprises the following steps: obtaining the position and track data of a user, loading a geographic object, and constructing a heterogeneous map; receiving a natural language request, extracting a semantic vector and writing the semantic vector into the graph; constructing a graph comparison learning network, generating a view and executing embedded learning; optimizing structural parameters by using a pigeon inspired algorithm, and outputting an optimal model; constructing a current position node, extracting a local sub-graph, and generating a sorting list; executing path reasoning, generating a recommendation result, and feeding back and updating. According to the method, deep semantic understanding and geographical trajectory modeling are fused, so that high-precision, interpretable and self-learning travel map intelligent search recommendation under the driving of the current position of the user is realized.

The invention discloses a remote sensing time series data analysis method and system considering geographic object space-time correlation, and belongs to the technical field of data analysis. The method comprises the following steps: acquiring and preprocessing a multi-source multi-temporal remote sensing image and auxiliary data to generate a consistent time sequence data stack; dividing the image into voxels in a three-dimensional time-space domain, carrying out adjacent tracking, identifying a geographic process object with an evolution behavior, and recording the attribute of the geographic process object; judging a space-time topological relation between geographic process objects, and generating a unified space-time relation table through composite reasoning; constructing a geographic process object space-time diagram model by taking the geographic process object as a node and the space-time relationship as an edge, and extracting and standardizing attribute features of the node and the edge; a graph convolutional network and a topology dynamic mechanism are used for joint modeling, and the importance index of each node is calculated. According to the method, closed-loop analysis from data processing, relation modeling and importance evaluation to decision support is realized, and the interpretability of remote sensing time sequence change detection and decision effectiveness are improved.

The invention provides a satellite map geographic object desensitization method and system based on a vector map, and relates to the technical field of geographic information security, and the method comprises the steps: obtaining first information including to-be-trained vector map data and satellite map data, and second information including to-be-desensitized vector map data and satellite map data; and determining whether a sample set can be constructed or not through the judgment model, if yes, matching and subdividing the first information to obtain the sample set, and performing learning training on the sample set by using a convolutional coding and decoding neural network model to generate a trained satellite map data desensitization model. And processing specific geographic elements in the second information vector map data, and sending the processed specific geographic elements to a satellite map data desensitization model to perform desensitization processing on a specific geographic object in a satellite map. According to the method, the sensitive geographic objects of the satellite map can be hidden by deleting the specific vector geographic elements, diversified desensitization can be carried out on the geographic objects of the satellite map, and the purpose of controllable desensitization of the geographic objects is achieved.

The invention provides a reverse geocoding method and device, and the method can quickly obtain the data of a plurality of rectangular regions corresponding to a target latitude and longitude coordinate through a first data structure, and at the moment, the target region is located in a first region where a plurality of rectangular regions corresponding to a plurality of geographic regions are overlapped. The first geographic area where the target latitude and longitude coordinates are located is obtained by screening the geographic areas corresponding to the multiple rectangular areas through a ray method, the first geographic area corresponds to the first geographic position information, and compared with a Geohash method, the boundary problem caused when the target latitude and longitude coordinates are close to the boundary of the geographic areas is avoided, and the accuracy of the target latitude and longitude coordinates is improved. As the first geographic area is the area covered by the geographic object in the actual space, the distance between the geographic position corresponding to the obtained target latitude and longitude coordinate and the actual geographic position can be effectively avoided, and the obtained position information of the target latitude and longitude coordinate is more accurate.

In order to improve the efficiency and accuracy of place name address search in a complex semantic environment, the invention discloses an address search method for enhancing LLM based on a spatial relation knowledge graph. According to the method, place name addresses and related information contained in a Chinese natural language under complex semantics (nested spatial relationship semantics) can be converted into spatial positions of the addresses or geographic entities related to the positions. According to the method, geographical name and address information extraction in a Chinese natural language is focused on, and complex spatial relationship semantic geographical name and address contained in the Chinese natural language are analyzed by utilizing the analysis capability of a large language model on the Chinese natural language and are organized into structured parameters; then converting the structured parameters into a retrieval instruction stream of spatial data through a spatial relationship knowledge graph; therefore, the corresponding geographic position and the geographic object associated with the position are obtained. According to the method, a Chinese natural language geographic information retrieval function module is constructed based on the method, and the practicability of the process is verified by utilizing a query example.

The invention relates to the technical field of computer vision and geographic information, and particularly discloses a cross-view geographic positioning acceleration method based on semantic description, which comprises the following steps of: performing instruction fine tuning on an input query image and a database image by adopting a visual language model to generate natural language description; coding the natural language description into a low-dimensional semantic vector by utilizing a word embedding model; constructing a semantic keyword association graph based on a graph embedding technology, and fusing a general semantic knowledge base and a geographic domain ontology to construct a surface feature special semantic tree; screening candidate subsets according to a preset ground feature priority and a saliency detection result of the query image; extracting global features and local key point descriptors of the images in the candidate subsets by adopting a lightweight model; constructing a visual similarity calculation model based on the state space model, and modeling a feature sequence dependency relationship; and fusing the semantic matching score and the visual similarity, outputting a final matching result by adopting a weighted sorting strategy, and cooperatively accelerating according to the matching result in combination with a lightweight model.

Method (300) and device for creating (330) a digital map, wherein map data values ​​representing a base map are retrieved, the base map comprising information on traffic routes with one or more lanes and environmental features, wherein this information represents at least one lane configuration, wherein the environmental features represent geographical objects that can be detected by means of an environmental sensor of a vehicle, wherein areas are determined which enable automated driving, depending on the lane configuration and depending on the environmental features, and method (400) for operating (430) an automated vehicle, wherein a driving strategy is determined depending on the current position, based on a digital map, wherein the driving strategy comprises a trajectory to an area which enables automated driving, wherein the automated vehicle,depending on the driving strategy.

The application discloses a remote sensing ground object knowledge graph construction method based on cooperation of geographical object geometric features and graph enhancement retrieval, and comprises the following steps: data set preparation; basic triple extraction and feature analysis; LLM-assisted semantic and relationship enhancement; flexible quantization and output of ground object knowledge graph knowledge; knowledge conflict correction and final version graph construction. The application utilizes a tensor decomposition model to train a ground object knowledge graph to obtain a knowledge graph embedding vector, and through an unsupervised / semi-supervised mode, utilizes a low-dimensional vector representation of a ground object category learned from a knowledge graph triple to embed the semantic relationship among categories in the knowledge graph embedding vector, so as to provide global semantic prior knowledge for a downstream model, and effectively solve the semantic confusion problem in a remote sensing image.

The invention discloses a remote sensing ground object knowledge graph construction method based on geographic object geometric features and graph enhancement retrieval collaboration. The method comprises the following steps: preparing a data set; basic triple extraction and feature analysis are carried out; semantic and relation enhancement assisted by LLM; flexible quantification and output of knowledge of the ground object knowledge graph; and correcting knowledge conflicts and constructing a final edition map. According to the method, a tensor decomposition model is used for training a ground feature knowledge graph to obtain a knowledge graph embedded vector, through an unsupervised / semi-supervised mode, low-dimensional vector representation of ground feature categories is learned from a knowledge graph triple, the knowledge graph embedded vector is used for embedding a semantic relationship between categories, global semantic priori knowledge is provided for a downstream model, and the global semantic priori knowledge is provided for the downstream model. And the semantic confusion problem in the remote sensing image is effectively solved.

The present invention discloses a feature selection method for object-oriented image analysis of geographical objects, which can optimize the feature space by simulating the process of manually constructing ground object extraction rules, use self-created evaluation indicators to achieve feature decorrelation and optimization of feature subsets, and give the classification order and soft threshold of features, which can be directly used as input to obtain a detailed dataset of regional land cover types. Compared with other feature selection algorithms, this method uses a feature combination evaluation indicator to construct a ground object classification rule instead of using a single feature evaluation indicator, and the constructed ground object extraction rule is more reasonable; it uses a membership function combined with a soft threshold to describe ground objects, rather than a "non-zero or one" classification criterion, making the classification result closer to the language and thinking mode of humans. The implementation process of the present invention is simple, greatly reducing the influence of manual intervention, with remarkable application effects, and can realize the automatic construction of ground object extraction rules in the process of object-oriented ground object classification.

The embodiment of the invention provides an information recommendation method and device, a storage medium and a program product. In the embodiment of the invention, the target geographic object associated with the user and the attribute data of the target geographic object in the target library are introduced, and the geographic semantic feature, the distance feature and the geographic context feature are incorporated into the user modeling process, so that the data normal form which only depends on established behavior data and static portraits is broken through; on this basis, according to attribute data and historical behavior data of the target geographic object, steady-state demand potential information and dynamic interest intention information of the user are predicted, and user demand features are described from two dimensions of long-term steady-state demand and short-term dynamic interest; furthermore, the steady-state demand potential information and the dynamic interest intention information are combined with candidate information objects in the target application scene to perform joint information recommendation, so that the recommendation result can not only fit the current interest of the user, but also keep the consistency with the long-term demand of the user, and the recommendation effect is greatly improved.

The present invention relates to the technical field of consistency verification of power grid maps, and specifically discloses a method and system for digitizing power grid distribution line maps. The present invention converts the historical distribution line drawings of the target substation into digital images, and geo-references the digital images to introduce geographic information to obtain a distribution line map, thereby realizing the digitization of the power grid distribution line map of the old substation. The present invention first determines a suitable scaling factor based on a reference object to adjust the digital image and the target substation map, then overlaps the two images and adjusts the mutual range to achieve multiple overlaps as a geographic alignment benchmark, then performs grid division and elastic deformation correction on the digital image, and then finds the geographic object in the target substation map based on the power grid equipment in the digital image, thereby realizing geographic reference of the digital image. The present invention solves the problem that the existing substations fail to realize the digitization of power grid distribution lines.

This invention discloses a cultural tourism map search system and method based on deep learning and the BeiDou database, comprising the following steps: acquiring user location and trajectory data, loading geographic objects, and constructing a heterogeneous graph; receiving natural language requests, extracting semantic vectors and writing them into the graph; constructing a graph contrastive learning network, generating views and performing embedding learning; optimizing structural parameters using a pigeon flocking algorithm and outputting the optimal model; constructing the current location node, extracting local subgraphs, and generating a sorted list; performing path reasoning, generating recommendation results, and providing feedback updates. This invention, by integrating deep semantic understanding and geographic trajectory modeling, achieves high-precision, interpretable, and self-learning intelligent search and recommendation of cultural tourism maps driven by the user's current location.

The present invention discloses a method for integrated segmentation of high-resolution optical and SAR images for geographic objects, comprising the following steps: obtaining a reliable set of geographic objects by segmenting the optical image; adaptively extracting marker points for each object, and projecting them into the SAR image based on the coarse registration result; finally, performing region growth based on the marker points in the SAR image, and finally obtaining a set of objects that match the segmented objects of the optical image. The experimental results of the present invention on multiple groups of optical and SAR images show that the optical-SAR matching object set extracted by the proposed method is closer to the actual geographic object, and the J-value can reach above 7.8, which is significantly better than the comparison method in both visual analysis and quantitative evaluation.

The invention relates to a method of a control device of a first vehicle, having the steps of: receiving object information detected by means of a surrounding sensor and relating to a geographical object; determining the absence of a database entry in a database relating to the geographical object and corresponding to the object information; creating an information unit relating to the geographical object from the detected object information; and transmitting a verification request relating to the geographical object to a traffic infrastructure unit and / or a second vehicle together with the created information unit. The invention also relates to a method of a traffic infrastructure unit or a server, a control device of a vehicle, a control unit of a traffic infrastructure unit or a server, and a computer program.

The application discloses a kind of remote sensing time series data analysis method and system considering the spatio-temporal correlation of geographical object, belong to data analysis technical field.The method includes: obtaining multi-source multi-temporal remote sensing image and auxiliary data and pre-processing, generate consistent time series data stack;In three-dimensional space-time domain, image is divided into voxel and is adjacent tracking, identify geographical process object with evolution behavior and record its attribute;Determine the spatio-temporal topological relationship between geographical process object, generate unified spatio-temporal relationship table by composite reasoning;With geographical process object as node, spatio-temporal relationship as edge constructs geographical process object spatio-temporal graph model, extracts and standardizes the attribute characteristics of node and edge;Importance index of each node is calculated by using graph convolution network and topological dynamic mechanism joint modeling.The application realizes closed-loop analysis from data processing, relationship modeling, importance evaluation to decision support, improves the interpretability and decision effectiveness of remote sensing time series change detection.

The present application discloses a geographic object processing method, apparatus, electronic device, and computer storage medium. The method comprises: obtaining a non-ontology library geographic object and an ontology library geographic object set, wherein the non-ontology library geographic object is a geographic object that does not originate from the ontology library geographic object set; determining the address text matching degree and geographic location matching degree between the non-ontology library geographic object and any ontology library geographic object in the ontology library object set; determining whether the non-ontology library geographic object and any ontology library geographic object are the same geographic object based on the address text matching degree and the geographic location matching degree; and if so, associating the non-ontology library geographic object with the ontology library geographic object of the same geographic object in a mapping relationship table. This method improves the mounting rate and mounting accuracy of non-ontology library geographic objects and ontology library geographic objects.

A system and method is provided that displays cursors for street level images, where the cursor changes appearance based on the objects in the image, such as the geographic distance between the objects and the camera position and the surface of the objects. For example, the cursor may appear to lie flat against the objects in the image change size based on the distance between the camera and object's surface.

The invention provides a multi-modal remote sensing image segmentation method based on MRF semantic reasoning. The method is used for solving the technical problem that an existing multi-modal data classification method is difficult to achieve semantic information reasoning of different modal data on the same position. The method comprises the following steps: carrying out successive training learning on multi-modal data to obtain an initial semantic segmentation result of each modal, carrying out deep feature fusion on the multi-modal data to obtain deep fusion features of the multi-modal data, then establishing a self-learning updated multi-modal semantic reasoning model under an MRF framework, and carrying out multi-modal semantic reasoning based on the multi-modal semantic reasoning model. And updating a multi-modal semantic segmentation result through cooperation of the multi-modal depth features and semantic reasoning. According to the method, fusion of multi-modal data features and semantic association information among different modals are fully considered, and accurate reasoning and classification of geographic objects are realized through the synergistic effect of the CNN model and the Markov random field. Experimental results show that the model provided by the invention has better performance on different data sets.

The application discloses a kind of heterologous remote sensing image object level change detection method, through design a kind of multiscale feature extraction difference module to realize the extraction of multiscale feature difference map, and as the supplementary input of UNet++, to improve the learning ability of network to the feature of change area;On this basis, to realize the mapping of pixel level result to geographical object, design different scale adaptive evidence confidence index, and then construct a kind of WDSEF identification strategy based on DS evidence theory, realize the leap of pixel level detection result to object.Experiments are carried out to two multi-temporal heterologous image data sets of ZY-3 / GF-2 and GF-1 / GF-2, and compared with a variety of deep learning methods, the results show that the application can significantly improve the recognition ability to the change area, and effectively reduce the influence of "pseudo change", OA and F1 can reach more than 95% and 63.31% respectively, and visual analysis and quantitative evaluation are significantly better than comparative method.

The application provides a position determination method and device, relates to the technical field of data processing, and can realize conversion of address text into position information of a geographic space structure. The specific scheme comprises the following steps: firstly, address text is acquired; geographic entities and spatial relationship entities in the address text are extracted; the geographic entities represent geographic objects occupying spatial positions in a geographic space, and the spatial relationship entities represent spatial relationships between the geographic entities; and the geographic space position corresponding to the address text is determined according to the geographic entities and the spatial relationship entities.

The invention relates to the technical field of marine meteorological condition analysis, in particular to a fishing boat operation condition analysis method based on fishing area and high score meteorological data, which comprises the following steps: S1, fusion analysis; s2, intelligent screening; s3, weather early warning; s4, early warning information release: when it is detected that some ships possibly have dangerous cases due to some weather and other reasons, the alarm information can be actively sent to the ships through the Beidou terminal; s5, performing information linkage, sending the information to a law enforcement terminal APP, and informing a corresponding responsible person of the working condition of the fishing boat, and the method has the following beneficial effects: superposing and screening spatial attribute data of different geographic features such as weather forecast data, a fishing area map, real-time position data of the boat and the like to generate multiple features of a spatial area, and improving the working efficiency of the fishing boat. The spatial corresponding relation between geographic objects is established, the problem of safe salvage of fishery ships under complex marine meteorological conditions is solved, the safety supervision capability of the fishery ships is improved, and economic benefits are generated.

The invention discloses a geographic object data processing method and device, electronic equipment and a computer storage medium. The method comprises the steps of obtaining a non-ontology library geographic object; determining geographic position data of a geographic object of a non-ontology library; based on the geographic position data of the non-ontology library geographic object, determining a geographic space grid where the non-ontology library geographic object is located, and taking the geographic space grid as a target geographic space grid; according to a preset grid object mapping table, determining any ontology library geographic object in the target geographic space grid as a first target ontology library geographic object; judging whether the non-ontology library geographic object and the first target ontology library geographic object are the same geographic object or not according to the geographic position data of the non-ontology library geographic object and the geographic position data of the first target ontology library geographic object; and if yes, taking the geographic object data of the non-ontology library geographic object as supplementary geographic object data of the first target ontology library geographic object.

Method (300) and device for creating (330) a digital map, in which map data values representative of a base map are invoked, the base map comprising indications about a traffic path having one or more lanes and surrounding characteristics, the indications representative of at least one configuration of the lanes, and the surrounding characteristics of the traffic path having one or more lanes. The invention relates to a method (400) for operating (430) an automated vehicle, in which a configuration of a lane is determined and a surrounding feature is determined, which represents a geographic object that can be detected by means of an environment sensor of the vehicle, in which an area that enables automated driving according to the configuration of the lane and according to the surrounding feature is determined, and a method (400) for operating (430) an automated vehicle, the driving strategy is determined on the basis of a digital map as a function of the current position, the driving strategy comprising a trajectory to an area that enables automated driving, and the automated vehicle is operated as a function of the driving strategy.

The invention discloses a cross-population different-type geographic object space association mining method and system. The method comprises the steps that urban road data in a research area and POI data of a first geographic object population and a second geographic object population are acquired and preprocessed; dividing the POI data of the first geographic object population and the second geographic object population into different category subsets according to priori knowledge; setting a zero hypothesis and defining a statistical index associated with the binary space; performing observation counting on different types of subsets in another geographic object population in a spatial neighborhood from global and local measurement levels, and calculating a statistical index associated with a binary space; and carrying out significance test, correlation analysis and visual display. Compared with a traditional binary space association mining method, the method is suitable for mining the binary space association between cross-population and large-scale data sets, and can reveal the potential association and dependency relationship between any two different geographic object populations.

A method for providing information about a geographic object, according to an embodiment, is performed by the steps of: classifying each of a plurality of lines connected to define an area of the ground, by using type and shape information of geographic objects adjoining each other across a corresponding line; grouping the plurality of lines by using a result of the classification and the shape information of the plurality of lines; deriving, for each group that is a result of the grouping, a candidate footprint area for a building to have a maximum area; and determining a footprint area for the building from among the derived one or more candidate footprint areas by considering a predetermined constraint. Here, in the step of deriving the candidate footprint area, in a group including one line from among groups that are a result of the grouping, the one line becomes a reference line and is used to derive a candidate footprint area, and in a group including two or more lines, one line obtained by merging the two or more lines becomes a reference line and is used to derive a candidate footprint area.

The embodiment of the invention discloses a method, a device and equipment for constructing a three-dimensional geographic model based on geographic space data. The method comprises the following steps: extracting geometric information and attribute information of a geographic object in the geographic space data; converting the coordinates of the geometric information to a target coordinate system; constructing a three-dimensional OBJ model based on the geometric information and the attribute information; exporting the three-dimensional OBJ model as an OBJ file in which basic information of the three-dimensional OBJ model is recorded and an MTL file in which attribute information of the three-dimensional OBJ model is recorded; converting the content of the OBJ file into a GLTF format or a GLB format to obtain a GLTF file or a GLB file, associating attribute information of the geographic object to a corresponding node in the GLTF file or the GLB file, and associating attribute information of the three-dimensional OBJ model in the MTL file to a corresponding node in the GLTF file or the GLB file; and generating a file in a B3DM format.

The application discloses a boundary detection method based on a maximum inscribed convex polygon and a separation axis theorem, comprising: acquiring an irregular geographic polygon, constructing a maximum inscribed convex polygon located inside the irregular geographic polygon, and performing convex decomposition on a difference set region of the two to obtain a convex polygon set of edge corner regions; performing global filtering according to the spatial range of a target geographic object and the irregular geographic polygon; when not excluded, detecting whether the target geographic object intersects with the maximum inscribed convex polygon based on the separation axis theorem, and outputting an intersection result if the target geographic object intersects with the maximum inscribed convex polygon; and if the target geographic object does not intersect with the maximum inscribed convex polygon, querying a convex polygon candidate of an edge corner region through a spatial index structure and detecting whether the target geographic object intersects with the convex polygon candidate based on the separation axis theorem, and outputting an intersection or non-intersection result. The application can reduce redundant calculation in irregular geographic boundary detection and improve detection efficiency.

The invention relates to the technical field of geographic information systems, particularly discloses a three-dimensional geographic information visualization system supporting dynamic interaction, and aims to solve the problems of high data processing delay, low resource utilization rate and event and object semantic mapping deficiency in the prior art. Comprising a real-time data stream access and preprocessing module used for receiving and standardizing heterogeneous sensor data in parallel; the space-time event stream processing engine is used for performing incremental state management and updating based on the geographic grid index; the geographic object semantic dynamic binding module is used for realizing automatic association between event data and scene object attributes through declarative rules; the distributed memory geographic state database is used for high-concurrency storage and query of object states; and the asynchronous non-blocking rendering pipeline is used for driving the graphics engine to perform local redrawing. According to the method and the device, millisecond-level response from data access to visual rendering is realized, and the resource utilization rate and the system usability are improved.