Method and system for correcting deviation of map moving track

Abstract

The invention discloses a map moving track deviation correction method and system, belongs to the technical field of electronic maps, and aims to solve the technical problems that in the prior art, deviation exists in GPS track data, so that position information in map application is not accurate, and the map moving track deviation is not accurate. According to the technical scheme, the method comprises the following steps: data acquisition: receiving original latitude and longitude coordinate data and sensor data from a GPS satellite; data preprocessing: denoising and missing value processing are performed on the original GPS trajectory data, and the data quality is improved by using a Kalman filtering algorithm; feature extraction: extracting spatio-temporal features from the preprocessed data; constructing a deep learning model: constructing a deep neural network model for learning the spatial pattern and time sequence features of the trajectory data; the deep learning model inputs the spatial pattern and the time sequence characteristics of the trajectory data, and outputs the trajectory point coordinates after deviation correction; training and optimizing; correcting deviation in real time; and dynamically adapting.

Description

Technical Field

[0001] The invention relates to the technical field of electronic maps, in particular to a method and system for correcting deviation of a map running track. Background Art

[0002] In modern navigation, logistics tracking, outdoor sports and other fields, the accuracy of GPS trajectory data is crucial. However, due to factors such as satellite signal obstruction and multipath effects, GPS data is often accompanied by varying degrees of position offset, which seriously affects the accuracy of the trajectory and user experience. Traditional correction methods mostly rely on map matching algorithms, but such methods often have unsatisfactory correction effects in complex urban environments, especially in viaducts, tunnels, and densely built areas. Summary of the invention

[0003] The technical task of the present invention is to provide a map running trajectory correction method and system to solve the problem that the GPS trajectory data in the prior art has deviations, resulting in inaccurate position information in map applications.

[0004] The technical task of the present invention is achieved in the following way: a method for correcting the deviation of a map running track, the method is as follows:

[0005] Data collection: receiving raw latitude and longitude coordinate data and sensor data from GPS satellites;

[0006] Data preprocessing: denoising and missing value processing of original GPS trajectory data, and using Kalman filtering algorithm to improve data quality;

[0007] Feature extraction: extracting spatiotemporal features from preprocessed data;

[0008] Build a deep learning model: Build a deep neural network model to learn the spatial pattern and time series characteristics of trajectory data; the deep learning model inputs the spatial pattern and time series characteristics of trajectory data, and outputs the coordinates of trajectory points after correction;

[0009] Training and optimization: Use known accurate trajectory data and GPS observation data to train the deep learning model, use mean square error (MSE) or mean absolute error (MAE) as the loss function, and optimize the model parameters through the back propagation algorithm;

[0010] Real-time correction: The deep learning model receives real-time GPS data streams, instantly predicts and corrects the position of each track point, while taking into account historical tracks and current environmental factors to improve the timeliness and accuracy of correction;

[0011] Dynamic Adaptation: The deep learning model has the ability to learn online and continuously optimize the correction model based on new data to adapt to environmental changes caused by the opening of new roads and the addition of new buildings.

[0012] Preferably, the spatiotemporal features include location coordinates, speed, acceleration, time series information, and geographic context features matched with an electronic map;

[0013] Among them, the geographic context features matched by the electronic map include road network and terrain information.

[0014] Preferably, the deep learning model includes a convolutional neural network (CNN) and a recurrent neural network (RNN).

[0015] A map running track correction system, the system comprising:

[0016] The data collection layer is used to receive raw latitude and longitude coordinate data and sensor data from GPS satellites;

[0017] The preprocessing layer is used to remove noise and process missing values ​​of the original GPS trajectory data, and improve the data quality using the Kalman filter algorithm;

[0018] The correction service layer is used to compare the trajectory points with the map road network and obtain the corrected trajectory;

[0019] The post-processing and optimization layer is used to optimize the trajectory after correction;

[0020] The application and display layer is used to integrate the corrected trajectory data into the corresponding application through the map;

[0021] The management and monitoring layer is used to manage access to the map API and monitor the performance and stability of the correction service.

[0022] Preferably, the data acquisition layer comprises:

[0023] The GPS signal receiving module is used to receive the original longitude and latitude coordinate data from the GPS satellite, and the original longitude and latitude coordinate data has a certain error;

[0024] Sensor fusion module, which integrates accelerometer and gyroscope sensor data to help improve positioning accuracy and motion direction judgment;

[0025] Map data module, used to obtain map data;

[0026] The pre-processing layer comprises:

[0027] Data filtering module, used to apply Kalman filtering algorithm to remove GPS noise and smooth the original trajectory data;

[0028] Coordinate replacement module, used to convert the original GPS coordinates (such as WGS84 coordinate system) into the coordinate system required by the map service provider (such as Amap, Baidu or National Bureau of Surveying and Mapping coordinate system);

[0029] The data fusion module is used to fuse the original trajectory data with the coordinate system required by the map service provider.

[0030] Preferably, the correction service layer includes:

[0031] Correction algorithm module for map matching, road network constraints and geo-fencing applications;

[0032] The database query module is used to query the correction database and correct the coordinates using the pre-calculated offset.

[0033] Preferably, the post-processing and optimization layer comprises:

[0034] The smoothing module is used to interpolate and smooth the trajectory after correction to eliminate burrs and unnatural inflection points;

[0035] The quality assessment module is used to evaluate the quality of the trajectory after correction, including the fit with the actual road and the continuity index.

[0036] Preferably, the application and display layer includes:

[0037] Map SDK integration module, used to integrate the corrected trajectory data into the application through the map SDK (such as Amap SDK);

[0038] The user interface module is used to display the smooth trajectory after correction and provide interactive functions of playing, pausing and fast-forwarding the trajectory animation;

[0039] The data analysis module is used to provide trajectory analysis functions, which include travel statistics and speed distribution.

[0040] Preferably, the management and monitoring layer includes:

[0041] API Key management module, used to manage keys for accessing the map API and control access rights and usage;

[0042] Performance monitoring module, used to monitor the performance and stability of the correction service to ensure efficient operation of the service;

[0043] The log and error reporting module is used to record operation logs and collect error reports for troubleshooting and system optimization.

[0044] Preferably, the working process of the correction service layer is as follows:

[0045] (1) Map matching algorithm: Compare the trajectory points with the map road network and correct the points that deviate from the road to the nearest legal route;

[0046] (2) Road network constraints: Use vehicle driving logic (such as speed and direction) to optimize the correction results to ensure that the trajectory is continuous and reasonable;

[0047] (3) Geographical fencing application: Apply specific correction rules in specific areas, such as city centers and complex intersections.

[0048] The map running track correction method and system of the present invention have the following advantages:

[0049] (1) The present invention can effectively improve the accuracy and availability of trajectory data through data preprocessing, feature extraction, deep learning model construction, training and optimization, real-time correction and dynamic adaptation, and use spatiotemporal features and map information to learn and predict the trajectory coordinates after correction, providing a solid foundation for various location-based service applications;

[0050] (ii) The present invention effectively reduces the deviation of GPS trajectory data and improves trajectory accuracy through the high abstraction and generalization capabilities of the deep learning model; especially in complex urban environments and dynamically changing scenarios, the correction effect is more significant, which helps to improve the service quality and user experience of various map applications;

[0051] (III) The present invention solves the problem of inaccurate location information in map applications caused by deviations in GPS trajectory data in the prior art by integrating GPS data, map information and deep learning models, realizes intelligent deviation correction of trajectory data and significantly improves trajectory positioning accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The present invention is further described below in conjunction with the accompanying drawings.

[0053] Attached Figure 1 This is a structural diagram of the map running trajectory correction system. DETAILED DESCRIPTION

[0054] The map running track correction method and system of the present invention are described in detail below with reference to the accompanying drawings and specific embodiments of the specification.

[0055] Example 1

[0056] This embodiment provides a method for correcting the deviation of a map running track, which is specifically as follows:

[0057] S1, data collection: receiving original latitude and longitude coordinate data and sensor data from GPS satellites;

[0058] S2, data preprocessing: denoising and missing value processing of the original GPS trajectory data, and using the Kalman filter algorithm to improve data quality;

[0059] S3, feature extraction: extracting spatiotemporal features from the preprocessed data;

[0060] S4. Build a deep learning model: Build a deep neural network model to learn the spatial pattern and time series characteristics of trajectory data; the deep learning model inputs the spatial pattern and time series characteristics of trajectory data, and outputs the coordinates of the trajectory points after correction;

[0061] S5, training and optimization: use known accurate trajectory data and GPS observation data to train the deep learning model, use mean square error (MSE) or mean absolute error (MAE) as the loss function, and optimize the model parameters through the back propagation algorithm;

[0062] S6, Real-time correction: The deep learning model receives real-time GPS data stream, instantly predicts and corrects the position of each track point, while considering historical tracks and current environmental factors to improve the timeliness and accuracy of correction;

[0063] S7. Dynamic Adaptation: The deep learning model has the ability to learn online and continuously optimize the correction model based on new data to adapt to environmental changes caused by the opening of new roads and the addition of new buildings.

[0064] The spatiotemporal features in step S3 of this embodiment include position coordinates, speed, acceleration, time series information, and geographic context features matched with the electronic map;

[0065] Among them, the geographic context features matched by the electronic map include road network and terrain information.

[0066] The deep learning model in step S4 of this embodiment includes a convolutional neural network (CNN) and a recurrent neural network (RNN).

[0067] Embodiment 2:

[0068] As attached Figure 1 As shown, this embodiment provides a map running track correction system, the system comprising:

[0069] The data collection layer is used to receive raw latitude and longitude coordinate data and sensor data from GPS satellites;

[0070] The preprocessing layer is used to remove noise and process missing values ​​of the original GPS trajectory data, and improve the data quality using the Kalman filter algorithm;

[0071] The correction service layer is used to compare the trajectory points with the map road network and obtain the corrected trajectory;

[0072] The post-processing and optimization layer is used to optimize the trajectory after correction;

[0073] The application and display layer is used to integrate the corrected trajectory data into the corresponding application through the map;

[0074] The management and monitoring layer is used to manage access to the map API and monitor the performance and stability of the correction service.

[0075] The data collection layer in this embodiment includes:

[0076] The GPS signal receiving module is used to receive the original longitude and latitude coordinate data from the GPS satellite, and the original longitude and latitude coordinate data has a certain error;

[0077] Sensor fusion module, which integrates accelerometer and gyroscope sensor data to help improve positioning accuracy and motion direction judgment;

[0078] Map data module, used to obtain map data.

[0079] The pre-processing layer in this embodiment includes:

[0080] Data filtering module, used to apply Kalman filtering algorithm to remove GPS noise and smooth the original trajectory data;

[0081] Coordinate replacement module, used to convert the original GPS coordinates (such as WGS84 coordinate system) into the coordinate system required by the map service provider (such as Amap, Baidu or National Bureau of Surveying and Mapping coordinate system);

[0082] The data fusion module is used to fuse the original trajectory data with the coordinate system required by the map service provider.

[0083] The correction service layer in this embodiment includes:

[0084] Correction algorithm module for map matching, road network constraints and geo-fencing applications;

[0085] The database query module is used to query the correction database and correct the coordinates using the pre-calculated offset.

[0086] The post-processing and optimization layer in this embodiment includes:

[0087] The smoothing module is used to interpolate and smooth the trajectory after correction to eliminate burrs and unnatural inflection points;

[0088] The quality assessment module is used to evaluate the quality of the trajectory after correction, including the fit with the actual road and the continuity index.

[0089] The application and presentation layer in this embodiment includes:

[0090] Map SDK integration module, used to integrate the corrected trajectory data into the application through the map SDK (such as Amap SDK);

[0091] The user interface module is used to display the smooth trajectory after correction and provide interactive functions of playing, pausing and fast-forwarding the trajectory animation;

[0092] The data analysis module is used to provide trajectory analysis functions, which include travel statistics and speed distribution.

[0093] The management and monitoring layer in this embodiment includes:

[0094] API Key management module, used to manage keys for accessing the map API and control access rights and usage;

[0095] Performance monitoring module, used to monitor the performance and stability of the correction service to ensure efficient operation of the service;

[0096] The log and error reporting module is used to record operation logs and collect error reports for troubleshooting and system optimization.

[0097] The working process of the correction service layer in this embodiment is as follows:

[0098] (1) Map matching algorithm: Compare the trajectory points with the map road network and correct the points that deviate from the road to the nearest legal route;

[0099] (2) Road network constraints: Use vehicle driving logic (such as speed and direction) to optimize the correction results to ensure that the trajectory is continuous and reasonable;

[0100] (3) Geographical fencing application: Apply specific correction rules in specific areas, such as city centers and complex intersections.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for correcting a map running trajectory, characterized in that: The method is as follows: Data collection: receiving raw latitude and longitude coordinate data and sensor data from GPS satellites; Data preprocessing: denoising and missing value processing of original GPS trajectory data, and using Kalman filtering algorithm to improve data quality; Feature extraction: extracting spatiotemporal features from preprocessed data; Build a deep learning model: Build a deep neural network model to learn the spatial patterns and time series features of trajectory data; The deep learning model inputs the spatial pattern and time series characteristics of the trajectory data, and outputs the coordinates of the trajectory points after correction; Training and optimization: Use known accurate trajectory data and GPS observation data to train the deep learning model, use mean square error or mean absolute error as the loss function, and optimize the model parameters through the back propagation algorithm; Real-time correction: The deep learning model receives real-time GPS data streams, instantly predicts and corrects the position of each track point, while taking into account historical tracks and current environmental factors to improve the timeliness and accuracy of correction; Dynamic Adaptation: The deep learning model has the ability to learn online and continuously optimize the correction model based on new data to adapt to environmental changes caused by the opening of new roads and the addition of new buildings.

2. The map running track correction method according to claim 1, characterized in that: Spatiotemporal features include location coordinates, velocity, acceleration, time series information, and geographic context features matched with electronic maps; Among them, the geographic context features matched by the electronic map include road network and terrain information.

3. The map running track correction method according to claim 1 or 2, characterized in that: Deep learning models include convolutional neural networks and recurrent neural networks.

4. A map running track correction system, characterized in that: The system includes: The data collection layer is used to receive raw latitude and longitude coordinate data and sensor data from GPS satellites; The preprocessing layer is used to remove noise and process missing values ​​of the original GPS trajectory data, and improve the data quality using the Kalman filter algorithm; The correction service layer is used to compare the trajectory points with the map road network and obtain the corrected trajectory; The post-processing and optimization layer is used to optimize the trajectory after correction; The application and display layer is used to integrate the corrected trajectory data into the corresponding application through the map; The management and monitoring layer is used to manage access to the map API and monitor the performance and stability of the correction service.

5. The map running track correction system according to claim 4, characterized in that: The data collection layer includes: GPS signal receiving module, used to receive original latitude and longitude coordinate data from GPS satellites; Sensor fusion module, which integrates accelerometer and gyroscope sensor data to help improve positioning accuracy and motion direction judgment; Map data module, used to obtain map data; The pre-processing layer comprises: Data filtering module, used to apply Kalman filtering algorithm to remove GPS noise and smooth the original trajectory data; Coordinate substitution module, used to convert the original GPS coordinates into the coordinate system required by the map service provider; The data fusion module is used to fuse the original trajectory data with the coordinate system required by the map service provider.

6. The map running track correction system according to claim 4, characterized in that: The correction service layer includes: Correction algorithm module for map matching, road network constraints and geo-fencing applications; The database query module is used to query the correction database and correct the coordinates using the pre-calculated offset.

7. The map running track correction system according to claim 4, characterized in that: The post-processing and optimization layer includes: The smoothing module is used to interpolate and smooth the trajectory after correction to eliminate burrs and unnatural inflection points; The quality assessment module is used to evaluate the quality of the trajectory after correction, including the fit with the actual road and the continuity index.

8. The map running track correction system according to claim 4, characterized in that: The application and presentation layer includes: Map SDK integration module, used to integrate the corrected trajectory data into the application through the map SDK; The user interface module is used to display the smooth trajectory after correction and provide interactive functions of playing, pausing and fast-forwarding the trajectory animation; The data analysis module is used to provide trajectory analysis functions, which include travel statistics and speed distribution.

9. The map running track correction system according to any one of claims 4 to 8, characterized in that: The management and monitoring layer includes: API Key management module, used to manage keys for accessing the map API and control access rights and usage; Performance monitoring module, used to monitor the performance and stability of the correction service; The log and error reporting module is used to record operation logs and collect error reports for troubleshooting and system optimization.

10. The map running track correction system according to claim 6, characterized in that: The working process of the correction service layer is as follows: (1) Map matching algorithm: Compare the trajectory points with the map road network and correct the points that deviate from the road to the nearest legal route; (2) Road network constraints: Use vehicle driving logic to optimize the correction results to ensure that the trajectory is continuous and reasonable; (3) Geofence application: Apply specific correction rules in a specific area.

Images