72 results about "Geographical maps" patented technology

The invention relates to an intelligent map making system and method based on a large language model, and the method comprises the steps: enabling a client to input data analysis information and a map making demand to a task planning Agent of a server, and carrying out the reasoning and disassembly of the input information into preliminary planning information through a double-LLM mechanism, the method comprises the following steps that Agent is used as a tool library, a tool library document, a knowledge library and a memory library are further inquired, a tool is selected through RAG and sent to a client side, if an existing tool cannot meet requirements, the Agent will generate a special code to complete a task, the client side calls the tool to carry out specific drawing according to received information, and a user can re-plan and adjust the drawing process through dialogue. The memory bank records session information and charting interaction operation information of this time and history. The problem of system fragmentation is solved through a unified architecture, stability and flexibility are balanced by combining large language model driving, tool agent and code generation, domain knowledge is introduced to enhance decision and improve specialty, and a user preference memory mechanism is constructed to realize personalized services.

The invention discloses a structured corpus generation method and device for geological map multi-modal large model training, and the method comprises the steps: preprocessing geological vector data, and constructing a semantic aligned geological data set; randomly selecting a data viewport, and setting the geographic space range and size of a map viewport; configuring a plurality of visual parameter items, performing controllable random adjustment on text labels, element symbols and map maps, and customizing and producing geological map samples as required; extracting multi-dimensional attribute information of the geological map sample to construct structured meta-information annotation data, and constructing a geological element mask annotation file to obtain a structured corpus for geological map multi-modal large model training. According to the method, large-scale production of the training samples with diversity, high quality and image-text alignment features is realized, the geological map corpus meets the requirements of multi-modal large model training on data scale, diversity, labeling precision and modal alignment, and the training efficiency and generalization ability of a geological map intelligent interpretation understanding model are remarkably improved.

The invention relates to the technical field of robot positioning and map construction, and particularly discloses a self-adaptive LiDAR-IMU SLAM method fusing intensity features and Riemannian manifold ground constraints, and the LiDAR-IMU SLAM method comprises the following steps: a, original measurement; b, data preprocessing; c, feature extraction; d, carrying out ground manifold constraint; e, optimizing the factor graph; and f, outputting data. The method can solve the problems that in the prior art, matching fails in a low-texture environment due to dependence on geometric features, positioning drifting is caused by point cloud distortion and inertial accumulative errors, and Z-axis errors are continuously expanded due to lack of dynamic adaptation to complex terrains. Experimental results show that according to the self-adaptive LiDAR-IMU SLAM method, the Z-axis drift error is remarkably reduced by 67.78%, the minimum absolute pose error is 0.254 m, the environment sensing and mapping capacity of the mobile robot in the complex underground space is remarkably improved, and reliable technical support is provided for intelligent inspection and infrastructure monitoring of the underground space.

The invention belongs to the technical field of maps, discloses a method and a system for improving forest environment SLAM precision by using TLS high-precision map constraint, and provides a method and a system for improving forest environment SLAM precision by using a millimeter-level point cloud map scanned by ground-based laser scanning (TLS) under a static condition as a space reference. And calculating the relative pose transformation between the PLShh scanning point cloud and the TLS point cloud as an external absolute constraint, introducing the external absolute constraint into the SLAM system by constructing a factor graph, and performing global optimization to improve the trajectory precision and map consistency. In addition, the scheme can be seamlessly fused with the existing SLAM framework, and has important significance for promoting the application of the PLShh in forestry investigation and ecological monitoring.

The invention relates to the technical field of SLAM (Simultaneous Localization and Mapping), and provides a dynamic SLAM method and system based on static semantic anchor points, comprising the steps of static structure semantic anchor point generation, anchor point-based robust tracking and multi-sensor tight coupling fusion, back-end optimization and static semantic map construction. By actively selecting high-stability static structure features and combining lightweight semantic segmentation and space-time consistency verification, the problems of poor dynamic elimination effect and high calculation overhead in the prior art are solved. According to the method, the positioning robustness and precision in a dynamic scene are improved, the calculation overhead is reduced, the static map rich in semantics is generated, and the universality is high.

To provide a device and method that can provide an environment in which participants in a "space" for thinking and discussing can consider things from a wide variety of perspectives. [Solution] According to this embodiment, the map classifies fields related to society in the first direction, classifies the level of each field in the second direction (social domain in the Arctic direction), and classifies words related to individuals in the third direction (personal domain in the Antarctic direction). Multiple nodes with semantic content are placed in the social domain and the personal domain according to the words (attribute information) at their placement location.

The application belongs to the technical field of map knowledge, and particularly relates to a map knowledge representation method based on a knowledge graph. The method first acquires map data, extracts map knowledge therefrom, including concept class knowledge and rule class knowledge, the concept class knowledge being common sense knowledge in the field of cartography and including map element knowledge; the rule class knowledge being various models, rules and principles formed in the process of map making; then generates a map knowledge network graph based on the knowledge graph according to the map element knowledge; and finally performs knowledge reasoning according to the rule class knowledge, completes the map knowledge network graph, and generates new entities and / or new entity relationships. The application fully mines geographical knowledge contained in a map, provides a basis for all-round knowledge mining and fusion of the map, and has certain reference value for realizing the transformation of 'data-information-knowledge'.

The application relates to the technical field of robots, in particular to a lightweight topological map construction method for scene recognition, which comprises the following steps: collecting data and processing the data to obtain accumulated point cloud; extracting scene descriptors; calculating the similarity between the descriptors to generate topological nodes; and calculating an optimal topological map. The application describes a scene according to multi-frame point cloud data accumulated according to a robot running track, extracts a descriptor of the point cloud, and judges whether to generate a topological node according to the similarity of the descriptor; the application can guarantee effective construction of a lightweight topological map, is particularly suitable for the demand of large-range scene topological map construction, and compared with an appearance-based topological map construction method, the number of topological map nodes constructed by the application is greatly reduced, but the reliable scene recognition performance can still be guaranteed.

Embodiments herein disclose methods for indicating a spatial map employment for a localization service. The method includes sending, by a first entity (102), a subscribe request to subscribe for a spatial map employed event to a second entity (112). The subscribe request may include a map identity, an identity associated with a requestor, and at least one security parameter. The method further includes receiving, by the first entity (102), a success response from the second entity (112) based on the subscribe request. The success response may include a subscription identity.

A community-based nature conservation planning system for pilgrimage cities, consisting of: A data collection module gathers qualitative data from various stakeholder groups, including residents, government officials, non-governmental organizations, tourists, pilgrims and businesses, using surveys and questionnaires; a module for identifying interest groups, configured to classify interest groups based on their attributes such as power, legitimacy and urgency, and to divide the interest groups into primary, secondary and tertiary interest groups; a community mapping module configured to generate a shared cultural heritage map by aggregating data on cultural heritage sites, priority intervention areas, indicators of physical impact, indicators of economic impact, and indicators of socio-cultural impact of pilgrimage tourism; a participation assessment module configured to evaluate the level of citizen participation in urban conservation by analyzing stakeholder responses and determining the level of participation based on predefined criteria; a framework generation module consisting of a computing processor configured to generate a cyclical and iterative community-based nature conservation framework consisting of several phases, including defining objectives based on community needs and goals, analyzing information exchange, identifying appropriate forms of community participation, jointly developing nature conservation plans, and identifying intervention strategies; a data storage module configured to store the collected data, the shared cultural heritage map, the evaluation results, and the generated framework; and a user interface connected to the data storage module and configured to display conservation strategies and dissemination recommendations based on the generated framework for implementation in the pilgrimage cities.

The invention relates to a method of performing a map learning via a unified framework comprising the steps on a computing device (10): - Retrieving data comprising features that are geospatially referenced and / or localized with respect to geospatially referenced; (S1) - Arranging the features in relation to each other on the basis of their localization and / or their geospatially referenced features, whereby a lane is determined and / or aligned; (S2) - Aggregate and / or cluster geometric features; (S3) - Determine a lane divider and / or lane segments based on the geometric features and / or based on lanes traveled; (S4) - Deriving a lane topology based on a connectivity of the lane segments; (S5) and - Semantic learning based on the lane topology, whereby features are assigned a function and the map is thus created or expanded. (S6) Furthermore, the invention relates to computer program and a computing device (10).

The application relates to the field of space-time data processing, and provides a space-time narrative map generation method and system and a storage medium, wherein deep semantic understanding ability of a large language model (LLM) is innovatively integrated, space-time knowledge is formally represented, a reliable reasoning and checking mechanism is introduced, a verified structured space-time knowledge graph is generated, and finally a complete reasoning chain is visually presented by using an interactive map. Compared with a traditional method, the core advantage of the application lies in that reliable and real-time updating of the space-time knowledge graph is realized, the reasoning process is transparent and intelligent, the reliability of space-time decision support is greatly improved, and the depth and efficiency of information transmission are improved.

The invention relates to a geographic interest point retrieval method based on tree sampling and a large language model. The method is suitable for location-based service scenes such as map navigation and online travel. The core process of the method comprises the following steps of: mapping a POI geographic coordinate into a character string through Geohash coding, and constructing a prefix tree index; sampling positive and negative samples on the basis of a spatial proximity strategy of a prefix tree, and training a representation model with spatial semantic expression ability in combination with unsupervised spatial contrast loss; and recalling a candidate POI set through a vector database, constructing a Prompt template by the candidate POI set and user query, inputting a large language model after LoRA fine tuning, and completing semantic rearrangement in combination with a retrieval enhancement generation (RAG) mechanism. According to the scheme, unified modeling of geographic space and text semantics is achieved, the comprehensive matching precision of retrieval results is effectively improved, dynamic changes such as POI addition and position change can be rapidly adapted, the cross-region and cross-domain generalization ability is achieved, and a more accurate and efficient retrieval solution is provided for various position-based service systems.

This application discloses a land use change prediction method, apparatus, device, and medium based on map representation generation learning, relating to the fields of spatiotemporal big data mining and urban planning technology. The method includes: constructing multi-source map submaps and performing binarization and attention weighting to obtain binarized land use submaps and weighted geographic environment submap features; extracting deep aggregated spatial features from both to generate latent vector representations; flattening the representation into a one-dimensional feature sequence and querying the index of each element in a landscape codebook to form a vectorized index sequence; combining relative distance encoding, using a map sequence generation learning model to predict future vectorized index sequences, and querying the landscape codebook to obtain future vectorized tensors; iteratively decoding the tensor using a map decoder to generate land use change results. This application achieves more accurate land use change prediction by capturing mesoscale spatial local information and reducing unit-level error accumulation.

The present application relates to the technical field of cartography, and particularly relates to a cartography method, a cartography system and a storage medium. The method sets a user terminal, a map tool service subsystem, a map pipeline subsystem and a task running service subsystem, the user terminal loads a corresponding user interface, determines a cartography pipeline request in response to an operation on the user interface, and sends a sub-map tool service subsystem; the map tool service subsystem obtains corresponding map data from a map pipeline database according to the cartography pipeline request, and sends the map data to a map pipeline service subsystem; the map pipeline service subsystem performs cartography operation according to the map data, generates a complete version of a map and a cartography task request, and sends the cartography task request to a task running service subsystem; the task running service subsystem starts a cartography process according to the cartography task request, and performs map production, publication and release on the complete version of the map. The method realizes automatic operation of cartography, and improves the efficiency of cartography.

The system according to the embodiment aims to visually reproduce the past scenery and buildings of a specific location. [Solution] A system according to an embodiment includes a reception unit, a collection unit, a generation unit, and a provision unit. The reception unit receives a specification of a specific location and time from a user. The collection unit collects data on historical photographs, documents, and maps based on the specification received by the reception unit. The generation unit analyzes the data collected by the collection unit and generates a past landscape. The provision unit provides the past landscape generated by the generation unit to a user.

The invention discloses an intelligent design method and system for an electronic map, and aims to solve the problems of lack of intelligent style configuration, low manual customization efficiency, lack of an effective mapping mechanism between natural language description and map styles and the like of an existing electronic map in multiple scenes. By constructing an integrated and intelligent map intelligent design system, an intelligent mapping and rendering process from natural language input to structured map style and mapping output is realized, and the mapping efficiency and style diversification generation of the electronic map are remarkably improved.

The invention provides a charting method, device, equipment and system based on large language model driving, and belongs to the field of data processing. The method comprises the following steps: outputting first demand guidance information, wherein the first demand guidance information is used for indicating a map type; acquiring first reply information for the first demand guide information; analyzing the first reply information through a large language model, and determining a target map type; outputting second demand guide information according to the target map type, wherein the second demand guide information is used for acquiring map parameters; acquiring second reply information for the second demand guide information; analyzing the second reply information through a large language model to obtain target map parameters; generating a target map according to the target map type and the target map parameters; and obtaining an output instruction for the target map, converting the target map into the target output format, and outputting the target map. The drawing threshold of non-professionals can be reduced, and the drawing efficiency and quality are improved.

This invention discloses a robot cost map construction method based on information entropy and semantic weights, belonging to the field of robot environment perception and map construction technology. This invention introduces semantic weights w... class This technology enables differentiated handling of "walls" (requiring high passability) and "pedestrians" (requiring high safety). The robot can be relatively "aggressive" when squeezing through door gaps and relatively "conservative" when avoiding pedestrians, without compromising global parameters. It transforms semantic information extracted from deep learning into "potential field geometry information" understandable by the navigation layer, achieving deep integration of perception and decision-making, and improving the robot's adaptability in unstructured environments. The spatiotemporal uncertainty diffusion technology based on predicted trajectories allows the robot to naturally avoid obstacles based on their movement trends, filling the gap of traditional expansion layers lacking a time dimension. In densely populated scenarios, it significantly reduces the number of sudden stops and path replanning, improving traffic efficiency.

The embodiment of the invention provides a map element topological relation judgment method and device, equipment, a medium and a product. The method comprises the following steps: acquiring geometric positions of a road line and a plurality of linear elements in a map, establishing a reference line based on the road line, projecting the linear elements, and judging a topological relation among different linear elements according to projection coordinates. Aiming at the problem of space calculation complexity of linear elements, a uniform reference line is projected, a multi-dimensional geometric position is mapped into a linear numerical value, and multi-dimensional geometric operation is replaced by one-dimensional numerical value comparison, so that the limitation of traditional geometric function superposition calculation can be broken through, the implementation complexity of topological relation judgment is remarkably reduced, and the calculation efficiency is improved; an operator can process map data more efficiently, and the map making and updating period is shortened.

The invention relates to the technical field of robots, and particularly discloses a humanoid robot high-precision map construction method fusing ontology perception and external semantics, and the method comprises the following steps: S1, multi-source data collection and preprocessing; s2, feature extraction and pose estimation; s3, performing multi-source data fusion and semantic association; s4, carrying out space-vision-language fusion; s5, constructing a multi-resolution semantic map; s6, dynamic target elimination and map consistency maintenance; s7, VLM auxiliary verification and false alarm correction are carried out; and S8, incremental map updating and long-term learning. According to the method, full-link enhancement from data acquisition, fusion and understanding to optimization is realized, and finally, the robot can construct and utilize a high-precision and high-reliability semantic map to carry out high-level autonomous navigation and natural interaction.

The embodiment of the invention provides a conflict processing method and device. The method comprises the steps that map data, planning reference information related to cultural relic protection and land planning information related to reserve land are acquired; according to the map data, the planning reference information and the land planning information, determining a space associated land parcel of the cultural relic protection and reserve land in the map data; according to the evaluation dimension, evaluating the conflict between the reserve land and the cultural relic protection in the space-associated land parcel to obtain conflict evaluation information of the space-associated land parcel; the evaluation dimensions comprise a space dimension, a function dimension, a visual dimension and an environment dimension; and according to the conflict evaluation information, generating a conflict processing strategy of the space associated plot. Through the embodiment, the accuracy of conflict processing can be improved.

The invention relates to an electronic historical map information marking method and an electronic map recommendation method based on character recognition, and the method comprises the steps: collecting and arranging electronic historical maps in a plurality of historical periods, and setting a corresponding database; adding information marks on a data layer according to a time and / or dynasty sequence based on the geographic coordinates or the block partitions or geographic units as small as possible; setting tags for the information marks according to categories, and setting tags for the electronic historical maps according to categories, or respectively associating, corresponding or linking the plurality of electronic historical maps with the data layer according to the sequence of time and / or dynasty; and a user performs label retrieval, matching and display on the information marks in the database through active or passive operation. According to the method, the electronic historical map is used as a mark editing object, so that the method has more extensive convenience and practicability, and readers can more systematically master knowledge contents in three dimensions of geography, humanity and history.

To provide a device and method that can provide an environment in which participants in a "space" for thinking and discussing can consider things from a wide variety of perspectives. [Solution] According to this embodiment, the map classifies fields related to society in the first direction, classifies the level of each field in the second direction (social domain in the Arctic direction), and classifies words related to individuals in the third direction (personal domain in the Antarctic direction). Multiple nodes with semantic content are placed in the social domain and the personal domain according to the words (attribute information) at their placement location.

A room manager can generate mappings for a real-world room that support a shared XR environment. For example, the real-world room can include real-world objects and surfaces, such as a table(s), chair(s), wall(s), door(s), window(s), etc. The room manager can generate XR object definitions based on information received about the real-world room, object(s), and surface(s). For example, the room manager can implement a flow that guides a user equipped with an XR system to provide information for the XR object definitions, such as real-world surfaces that map to the XR object(s), borders (e.g., measured using a component of the XR system), such as borders on real-world surfaces, semantic information (e.g., number of seat assignments at an XR table, size of XR objects, etc.), and other suitable information. Implementations generate previews of the shared XR environment, such as a local preview and a remote preview.