Asset positioning method based on multi-dimensional holographic data fusion
Through multimodal sensor data acquisition and deep learning model, combined with particle filtering algorithm to correct positioning deviations, high-precision and real-time asset positioning are achieved, positioning accuracy and robustness problems in complex environments are solved, and intelligent early warning and visual management are provided.
Patent Information
- Application Number
- CN202510375123.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-27
- Publication Date
- 2025-08-05
AI Technical Summary
The existing technology has low asset positioning accuracy and poor robustness in complex environments, making it difficult to cope with electromagnetic interference and dynamic environment changes, and lacks multi-dimensional information fusion.
Multimodal sensors are used to integrate data acquisition, combine deep learning algorithms to build a multi-dimensional holographic model, and use particle filtering and video inversion algorithm to correct positioning deviations, and realize full-process management through intelligent early warning and visualization.
It improves the accuracy and real-timeness of asset positioning, provides a more efficient and intuitive asset management solution, and enhances robustness and real-timeness in complex environments.
Smart Images
Figure CN120430737A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of asset positioning and data fusion, and specifically relates to a method for dynamic asset positioning based on multimodal sensor data and holographic modeling technology. The method is suitable for high-precision real-time tracking and management of assets in complex scenarios such as smart cities, power systems, and industrial Internet of Things. Background Art
[0002] Existing methods rely on single data sources (such as GPS and RFID) or static two-dimensional models, making them difficult to handle with electromagnetic interference, dynamic environmental changes, and non-specific target motion, resulting in low positioning accuracy and poor robustness. Furthermore, with the development of the Industrial Internet of Things, there is an urgent need to integrate multi-source heterogeneous data (such as spatiotemporal coordinates, environmental parameters, and visual features), but existing technologies lack the systematic integration of holographic data. Summary of the Invention
[0003] The present invention proposes an asset positioning method based on multi-dimensional holographic data fusion, which is implemented through the following technical solutions: An asset positioning method based on multi-dimensional holographic data fusion consists of four parts: multi-module data acquisition, multi-dimensional holographic modeling, adaptive data fusion, and intelligent early warning and visualization.
[0004] The multimodal data collection part is used for dynamic positioning of assets. Its innovative features include: By integrating LiDAR, cameras, electromagnetic sensors and other sensors, the asset's spatiotemporal coordinates, three-dimensional holographic images, and environmental parameters such as temperature, humidity, and electromagnetic field strength are simultaneously collected to achieve comprehensive perception of the asset status in complex scenarios.
[0005] The multi-dimensional holographic modeling part is used to build a holographic positioning model for assets. Its innovations include: Based on deep learning algorithms, a multi-dimensional dynamic model of the spatial and temporal dimensions of the interaction between asset motion trajectories and the environment is constructed to support real-time tracking and high-precision positioning of non-specific targets.
[0006] The adaptive data fusion part uses a heterogeneous data fusion algorithm, and its innovations include: Combining particle filtering with video inversion algorithms, it corrects positioning deviations caused by electromagnetic interference and significantly improves the robustness and real-time performance of positioning in complex environments.
[0007] The intelligent early warning and visualization is based on a dynamic risk assessment model, and its innovations include: Based on the risk assessment model, historical and real-time data are analyzed to trigger early warnings of abnormal asset status, achieving closed-loop management of the entire process from data collection to decision support.
[0008] Through these improvements, the present invention further enhances the accuracy and real-time performance of asset positioning in complex and dynamic environments, overcoming the limitations of traditional methods such as electromagnetic interference and insufficient multi-dimensional information fusion. Furthermore, through intelligent risk warnings and holographic visualization, it provides a more efficient and intuitive solution for asset management. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Figure 1 This is a flowchart of the asset positioning method. DETAILED DESCRIPTION
[0010] In order to make the purpose, technical solutions and advantages of the present invention more clear, the technical solutions of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, ordinary technicians in this field can easily make the following descriptions without creative work. All other embodiments obtained under the premise of the above-mentioned embodiment fall within the scope of protection of the present invention.
[0011] The following is combined Figure 1 The asset positioning method based on multi-dimensional holographic data fusion of the present invention is described.
[0012] Figure 1 This is a flow chart of the asset positioning method based on multi-dimensional holographic data fusion provided by the present invention. Figure 1 As shown, the asset positioning method based on multi-dimensional holographic data fusion includes the following steps: Step 110: Multimodal data collection: By deploying a variety of sensor devices, a multimodal data collection network covering the asset operating environment is constructed.
[0013] In this embodiment, the specific implementation details are as follows: Deploy LiDAR sensors, high-definition cameras, electromagnetic sensors and other equipment to simultaneously collect the asset's spatiotemporal coordinates, 3D holographic images, and environmental parameters such as temperature, humidity, and electromagnetic field strength, enabling comprehensive perception in complex scenarios. Dynamic holographic capture technology is used to generate a four-dimensional space-time trajectory model of assets, ensuring real-time tracking and high-precision positioning of non-specific targets.
[0014] Step 120: Multi-dimensional holographic modeling, building a multi-dimensional holographic dynamic model of the asset based on the collected multi-modal data.
[0015] In this embodiment, the specific implementation details are as follows: Using LSTM-GRU hybrid neural network deep learning to model the interaction between asset trajectory and environment, the input dimensions include multi-dimensional data such as spatiotemporal trajectory, environmental parameters, and visual features; Build multi-dimensional dynamic models including spatial and temporal dimensions to support real-time status updates and predictions of assets in complex environments.
[0016] Step 130: Adaptive data fusion, using multi-source heterogeneous data fusion technology to improve the robustness and accuracy of asset positioning.
[0017] In this embodiment, the specific implementation details are as follows: Combining particle filtering with video inversion algorithms, it corrects positioning deviations caused by complex environments and ensures centimeter-level positioning accuracy. Utilize multimodal data fusion models to comprehensively process multiple types of data such as text, images, and audio to enhance the accuracy of asset holographic portraits.
[0018] Step 140: Intelligent early warning and visualization, using holographic space-time diagrams and risk assessment models to achieve real-time display of asset status and abnormal early warning.
[0019] In this embodiment, the specific implementation details are as follows: Build a holographic space-time map of assets, supporting AR terminals to view asset trajectories and status changes in real time; Based on the risk assessment model, historical and real-time data are analyzed to trigger early warnings of abnormal asset status, achieving closed-loop management of the entire process from data collection to decision-making.
[0020] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.
Claims
1. A multi-dimensional holographic data fusion asset positioning method, characterized in that: It consists of four parts: multi-module data acquisition, multi-dimensional holographic modeling, adaptive data fusion, and intelligent early warning and visualization.
2. The asset positioning method based on multi-dimensional holographic data fusion according to claim 1, characterized in that: The multi-module data acquisition part uses sensors to synchronously collect the asset's spatiotemporal coordinates, three-dimensional holographic images, and environmental parameters such as temperature, humidity, and electromagnetic field strength.
3. The asset positioning method based on multi-dimensional holographic data fusion according to claim 1, characterized in that: The multi-dimensional holographic modeling part, based on deep learning algorithms, constructs a multi-dimensional dynamic model of the spatial and temporal dimensions of the interaction between the asset's movement trajectory and the environment, supporting real-time tracking and high-precision positioning of non-specific targets.
4. The asset positioning method based on multi-dimensional holographic data fusion according to claim 1, characterized in that: The adaptive data fusion part combines particle filtering with video inversion algorithm to correct positioning deviation caused by electromagnetic interference.
5. The asset positioning method based on multi-dimensional holographic data fusion according to claim 1, characterized in that: The intelligent early warning and visualization part analyzes historical and real-time data based on the risk assessment model to trigger early warning of abnormal asset status.