33 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.

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.

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 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.

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 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 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.

The invention relates to the technical field of power grid map consistency checking, and particularly discloses a power grid distribution line map digitization method and system. According to the method, the historical distribution line drawing of the target transformer area is converted into the digital image, and the digital image is subjected to geographical registration to introduce the geographic information so as to obtain the distribution line map, so that the digitization of the power grid distribution line map of the old transformer area is realized. The method comprises the following steps: firstly, determining a proper zoom factor based on a reference object to adjust a digital image and a target court map, then overlapping the two images, adjusting a mutual range to realize multi-position overlapping to serve as a geographic alignment reference, then carrying out grid division and carrying out elastic deformation correction on the digital image, and finally, carrying out correction on the elastic deformation of the digital image. And finding a geographic object in a target station area map according to the power grid equipment conformity of the digital image, thereby realizing the geographic registration of the digital image. According to the invention, the problem that the digitization of the power grid distribution line cannot be realized in the existing transformer area is solved.

The invention discloses an unsupervised change monitoring method and system based on depth features, and the method comprises the steps: constructing an object-level aligned image pair through a semantic segmentation model, providing a training target with pure semantics for unsupervised feature learning, and solving a feature confusion problem caused by conventional random sampling; secondly, embedding an anisotropic sensing module in an encoder, explicitly modeling long-distance and multi-direction spatial dependence in the remote sensing image, and extracting depth features which are robust to imaging differences and sensitive to real changes; and finally, a geographic object pattern spot is introduced as an analysis unit, and a pixel-level initial result is improved into a change pattern spot with a complete boundary and coherent semantics through three-level voting decision and differential morphological optimization, so that the interpretability of the result and the GIS direct availability are remarkably improved.

The present invention proposes an AI system based on a pair of spatiotemporal information, enabling the construction of a device capable of acquiring data over 720° by integrating and organizing pairs of visual, auditory, and olfactory acquisition devices, and recording continuous, multidimensional spatiotemporal information pairs such as the position, shape, state of motion, sound, and odor of the device's environment or of the same spatial object in the environment in real time. These information pairs include not only the spatial relationship and the clock attribute, but also rich labeling attributes, such as signs of the acquisition equipment, names and categories of geographic objects, and patterns of human behavior.The system performs fusion storage, analysis, and processing on pairs of spatiotemporal information collected simultaneously in pairs to form three-dimensional processing results or video streams that verify each other and have depth of field and sign attributes, in order to provide AI software and hardware support to equipment such as humanoid robots, driverless cars, smart glasses, and inspection equipment. (Figure for abbreviation: Fig.2).

The application discloses a kind of cross overall different type geographical object space correlation mining method and system, the method includes obtaining the city road data in research area and the POI data of first geographical object total geographical object total and second geographical object total and is preprocessed;The POI data of first geographical object total and second geographical object total is divided into different category subsets according to priori knowledge;Zero hypothesis is set and the statistical index of binary spatial correlation is defined;From the global and local measurement level, the observation count of different category subsets in another geographical object total is carried out in spatial neighborhood, and the statistical index of binary spatial correlation is calculated;Significance test, correlation analysis and visual display are carried out.Compared with the traditional binary spatial correlation mining method, the application is suitable for mining the binary spatial correlation between the cross overall, large-scale data set, and can reveal the potential contact and dependent relationship between any two different geographical object totals.

The present application relates to the technical field of geographic resource management, and more particularly to a geographic object life cycle management method and device based on a spatiotemporal knowledge graph and an electronic device. The geographic object life cycle management method comprises: after obtaining a spatial data file related to a geographic object, performing data analysis and feature information extraction on the spatial data file to obtain feature information related to the geographic object; and finally constructing a spatiotemporal knowledge graph for storing the geographic object and related feature information according to the feature information related to the geographic object. According to the spatiotemporal knowledge graph, the change information of the geographic object throughout the life cycle can be fully described and stored, technical problems such as a large amount of data overlap, data layer fracture and redundant storage do not occur, and data query of the geographic object is facilitated.

The present invention discloses a method and device for constructing a temporal geographic data model based on hierarchical compressed linear referencing technology, as well as a method for constructing an index structure. The method for constructing the temporal geographic data model includes: step 1, establishing a hierarchical road network structure and establishing a hierarchical linear referencing system based on the hierarchical road network structure; step 2, using compressed linear referencing technology to perform spatiotemporal dimensionality reduction on temporal geographic objects and their spatiotemporal relationships; step 3, storing the temporal geographic objects in a relational database based on the OpenGIS specification; and step 4, using hierarchical compressed linear referencing technology to establish a temporal geographic data model. The method of the present invention can solve the problem of efficient storage, management, and query of massive temporal geographic entities with complex spatiotemporal characteristics and spatiotemporal relationships, and has superior computing performance to existing spatiotemporal data models and spatiotemporal index structures, thus having promising business and application prospects.

Embodiments of the invention provide a geographic object description information generation method and apparatus, and an electronic device. The method comprises the steps of obtaining an object information set of a target geographic object from a data information base; and generating target description information of at least one information type corresponding to the target geographic object according to the object information set of the target geographic object, thereby generating the target description information of the target geographic object according to the target description information of at least one information type corresponding to the target geographic object. In the embodiment of the invention, the data information base contains the data information of the target geographic object in multiple dimensions, so that the data information of the target geographic object in multiple dimensions can be obtained through the object information set of the target geographic object obtained by the data information base. The target description information of the target geographic object is generated based on the data information of the target geographic object in the multiple dimensions, and the content richness and the coverage range of the target description information of the target geographic object are improved.

The embodiment of the invention provides a position data determination method, electronic equipment, a storage medium and a program product. The method comprises the following steps: acquiring first information and a geographic object associated with the first information; acquiring first attribute information of the geographic object based on the first information, wherein the first attribute information comprises at least one piece of second attribute information of the geographic object; according to the first attribute information, one piece of candidate position data is selected from a candidate position set to serve as first position data of the geographic object, and the candidate position set comprises at least one piece of candidate position data; and outputting the first position data. By means of the technical scheme, the accuracy of the determined position data can be improved.

The application discloses a geographic space-time modeling method, system, product, equipment and storage medium for twin space virtual-real interaction, abstracts geographic entities, sensors, geographic data, geographic models, rule knowledge, geographic objects and controllers in twin space virtual-real interaction into corresponding nodes respectively, constructs edges connecting the nodes according to predefined logical relationships between the nodes, and generates a semantic and logical expression model for twin space virtual-real interaction; based on a graph database and the semantic and logical expression model, node storage files of the nodes and edge storage files of the edges are constructed; based on an object-relational database, an object storage table is constructed; through a geographic object identifier, an association between an object node in the graph database and a geographic object table record in the object-relational database is established, and the problem of element fragmentation and process breakpoint in existing virtual-real interaction modeling is solved.

The invention relates to a verbal identification method for a geographic area. The technical effect consists in improving the accuracy of identifying geographic areas of various sizes on the whole earth surface. The proposed computer-implemented method for identifying a geographic area comprises: creating a layer of a digital geographic map in the form of a grid of square cells of base size covering the entire earth surface using a geocentric coordinate system; extracting map making data about the geographic object of each created square cell from the corresponding map layer; iteratively subdividing each square cell containing at least a part of geographic objects into four equal square cells; at least one vocabulary and one vocabulary from a common spoken language vocabulary set are allocated to each square cell which is not divided, the at least one vocabulary represents a geographic name of a geographic object at least partially contained in the square cell, and the allocated vocabulary jointly forms a unique identification word group; and providing access to the created layer to the remote computing device by referencing the undivided square cells based on the geographic coordinates to obtain the corresponding unique identification phrases, or by referencing the unique identification phrases to obtain the geographic coordinates of the corresponding undivided square cells.