Ship position monitoring method and system based on multi-data correction

Abstract

The application discloses a ship position monitoring method and system based on multi-data correction, and the method comprises the following steps: acquiring a plurality of historical AIS data and a plurality of satellite communication data of a target ship in a historical time period; determining a plurality of associated data combinations corresponding to the historical AIS data and the satellite communication data based on a clustering association algorithm; calculating a position calculation result corresponding to each associated data combination based on a position calculation algorithm; and determining a corrected position trajectory corresponding to the target ship according to an association degree corresponding to each associated data combination and all the position calculation results. It can be seen that the application can realize deep fusion and position correction of heterogeneous ship monitoring data, thereby effectively solving the problem of insufficient positioning accuracy of a single data source and significantly improving the continuity and accuracy of target ship trajectory reconstruction.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for monitoring ship position based on multi-data correction. Background Technology

[0002] With the continuous growth of global shipping, real-time monitoring and trajectory reconstruction of vessel positions have become crucial for maintaining maritime traffic order and navigation safety. Currently, shipping regulatory agencies typically utilize Automatic Identification Systems (AIS) or satellite communication data to locate and track vessels, thereby understanding their dynamic course. However, existing vessel monitoring technologies often process or simply overlay data from a single data source. The lack of technical support for acquiring historical AIS and satellite communication data over a given period and using clustering algorithms to determine correlation combinations makes it impossible to calculate position results and determine corrected positions and trajectories based on correlation levels. This hinders the deep fusion and position correction of heterogeneous vessel monitoring data, leading to insufficient positioning accuracy from a single data source and reducing the continuity and accuracy of target vessel trajectory reconstruction. Ultimately, this limits the reliability of maritime traffic management systems in perceiving target vessel positions. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a ship position monitoring method and system based on multi-data correction, which can realize the deep fusion and position correction of heterogeneous ship monitoring data, thereby effectively solving the problem of insufficient positioning accuracy of a single data source and significantly improving the continuity and accuracy of target ship trajectory reconstruction.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a ship position monitoring method based on multi-data correction, the method comprising: Acquire multiple historical AIS data and multiple satellite communication data of the target vessel within a historical time period; Based on the clustering association algorithm, multiple associated data combinations corresponding to the historical AIS data and the satellite communication data are determined; Based on the location calculation algorithm, the location calculation result corresponding to each of the aforementioned associated data combinations is calculated; Based on the degree of association corresponding to each of the aforementioned data combinations and all the aforementioned position calculation results, the corrected position trajectory corresponding to the target vessel is determined.

[0005] As an optional implementation, in the first aspect of the present invention, determining multiple associated data combinations corresponding to the historical AIS data and the satellite communication data based on a clustering association algorithm includes: For any of the historical AIS data and any of the satellite communication data, calculate the temporal similarity between the historical AIS data and the satellite communication data; Calculate the similarity of ship activity between the historical AIS data and the satellite communication data; Calculate the weighted average of the time similarity and the ship activity similarity to obtain the correlation between the historical AIS data and the satellite communication data; Based on the correlation, multiple associated data combinations corresponding to the historical AIS data and the satellite communication data are determined according to the clustering algorithm.

[0006] As an optional implementation, in the first aspect of the invention, calculating the temporal similarity between the historical AIS data and the satellite communication data includes: Calculate the first time difference between the data acquisition period of the historical AIS data and the communication period of the satellite communication data; Calculate the second time difference between the data collection time of the historical AIS data and the communication time of the satellite communication data; Calculate the vector similarity between the time information vector of the historical AIS data and the time information vector of the satellite communication data; the time information vector is obtained by processing all time-related information through a vectorization model; Calculate the weighted average of the first time difference, the second time difference, and the vector similarity to obtain the time similarity between the historical AIS data and the satellite communication data; wherein, the weight of the first time difference is greater than the weight of the second time difference, and the weights of both the first time difference and the second time difference are less than the weight of the vector similarity.

[0007] As an optional implementation, in the first aspect of the invention, calculating the similarity of ship activities between the historical AIS data and the satellite communication data includes: Identify all sensor data related to the operation of the target vessel in the historical AIS data to obtain the first sensor data; The first judgment result is obtained by determining whether there is data related to ship activities in the satellite communication data. When the first judgment result is yes, the existing ship activity-related data is identified as the ship activity data corresponding to the satellite communication data; The ship activity data is input into the sensor prediction model to obtain the corresponding predicted sensor data. Calculate the similarity between the first sensing data and the predicted sensing data to obtain the ship activity similarity between the historical AIS data and the satellite communication data; If the first determination result is negative, the second sensor data recorded by the AIS equipment of the target ship during the communication period of the satellite communication data is obtained; Calculate the similarity between the first sensing data and the predicted sensing data to obtain the ship activity similarity between the historical AIS data and the satellite communication data.

[0008] As an optional implementation, in the first aspect of the present invention, determining multiple associated data combinations corresponding to the historical AIS data and the satellite communication data based on the correlation degree and according to a clustering algorithm includes: The first objective function is set to minimize the total number of combinations of all calculated related data. The first constraint conditions include: The correlation between two historical AIS data and satellite communication data belonging to the same associated data combination is greater than a preset first correlation threshold. The correlation between two historical AIS data and satellite communication data that do not belong to the same associated data combination is less than a preset second correlation threshold; the second correlation threshold is less than the first correlation threshold; Based on the first objective function and the first constraint, the clustering algorithm is used to iteratively calculate all the historical AIS data and the satellite communication data until the optimal result is obtained, resulting in multiple corresponding combinations of related data.

[0009] As an optional implementation, in the first aspect of the present invention, the step of calculating the location calculation result corresponding to each of the associated data combinations based on the location calculation algorithm includes: For each of the associated data combinations, the average position of the ship in all the historical AIS data in the associated data combination is calculated to obtain a first position result; Based on the satellite positioning algorithm, the average position of the satellite positioning locations corresponding to all the satellite communication data in the associated data combination is calculated to obtain the second position result; Determine whether the positional distance between the first position result and the second position result is greater than a preset distance threshold to obtain a second determination result; When the first judgment result is yes, both the first position result and the second position result are determined as the position calculation result corresponding to the associated data combination. If the first judgment result is negative, calculate the weighted average position of the first position result and the second position result to obtain the position calculation result corresponding to the associated data combination.

[0010] As an optional implementation, in the first aspect of the invention, determining the corrected position trajectory corresponding to the target vessel based on the correlation degree corresponding to each of the associated data combinations and all the position calculation results includes: Calculate the average of the correlation degree among all data in each of the associated data combinations to obtain the combined correlation degree corresponding to each of the associated data combinations; Based on the dynamic programming algorithm and the second constraint related to the combined correlation degree, the trajectory that can be formed by all the position calculation results is iteratively calculated until the optimal one is obtained, so as to obtain the corrected position trajectory corresponding to the target ship.

[0011] As an optional implementation, in the first aspect of the present invention, the second objective function of the dynamic programming algorithm is to minimize the average curvature of the calculated position trajectory; The second constraint includes: The correlation difference between any two adjacent position calculation results in the position trajectory is less than a preset first difference threshold; the correlation difference is the product of the position distance and the correlation difference between the two position calculation results; the correlation difference is the difference between the combination correlation degree corresponding to the correlation combination to which the two position calculation results belong respectively; The correlation difference between any calculated position that belongs to the location trajectory and any calculated position that does not belong to the location trajectory is less than a preset second difference threshold.

[0012] A second aspect of this invention discloses a ship position monitoring system based on multiple data correction, the system comprising: The acquisition module is used to acquire multiple historical AIS data and multiple satellite communication data of the target vessel within a historical time period; The clustering module is used to determine multiple associated data combinations corresponding to the historical AIS data and the satellite communication data based on a clustering association algorithm; The calculation module is used to calculate the location calculation result corresponding to each of the associated data combinations based on the location calculation algorithm; The positioning module is used to determine the corrected position trajectory of the target vessel based on the degree of association corresponding to each of the associated data combinations and all the position calculation results.

[0013] As an optional implementation, in a second aspect of the invention, the clustering module determines, based on a clustering association algorithm, the specific method for determining multiple associated data combinations corresponding to the historical AIS data and the satellite communication data, including: For any of the historical AIS data and any of the satellite communication data, calculate the temporal similarity between the historical AIS data and the satellite communication data; Calculate the similarity of ship activity between the historical AIS data and the satellite communication data; Calculate the weighted average of the time similarity and the ship activity similarity to obtain the correlation between the historical AIS data and the satellite communication data; Based on the correlation, multiple associated data combinations corresponding to the historical AIS data and the satellite communication data are determined according to the clustering algorithm.

[0014] As an optional implementation, in a second aspect of the invention, the specific method by which the clustering module calculates the temporal similarity between the historical AIS data and the satellite communication data includes: Calculate the first time difference between the data acquisition period of the historical AIS data and the communication period of the satellite communication data; Calculate the second time difference between the data collection time of the historical AIS data and the communication time of the satellite communication data; Calculate the vector similarity between the time information vector of the historical AIS data and the time information vector of the satellite communication data; the time information vector is obtained by processing all time-related information through a vectorization model; Calculate the weighted average of the first time difference, the second time difference, and the vector similarity to obtain the time similarity between the historical AIS data and the satellite communication data; wherein, the weight of the first time difference is greater than the weight of the second time difference, and the weights of both the first time difference and the second time difference are less than the weight of the vector similarity.

[0015] As an optional implementation, in a second aspect of the invention, the specific method by which the clustering module calculates the similarity of ship activities between the historical AIS data and the satellite communication data includes: Identify all sensor data related to the operation of the target vessel in the historical AIS data to obtain the first sensor data; The first judgment result is obtained by determining whether there is data related to ship activities in the satellite communication data. When the first judgment result is yes, the existing ship activity-related data is identified as the ship activity data corresponding to the satellite communication data; The ship activity data is input into the sensor prediction model to obtain the corresponding predicted sensor data. Calculate the similarity between the first sensing data and the predicted sensing data to obtain the ship activity similarity between the historical AIS data and the satellite communication data; If the first determination result is negative, the second sensor data recorded by the AIS equipment of the target ship during the communication period of the satellite communication data is obtained; Calculate the similarity between the first sensing data and the predicted sensing data to obtain the ship activity similarity between the historical AIS data and the satellite communication data.

[0016] As an optional implementation, in a second aspect of the invention, the clustering module determines, based on the correlation degree and according to a clustering algorithm, a specific method for combining multiple associated data sets corresponding to the historical AIS data and the satellite communication data, including: The first objective function is set to minimize the total number of combinations of all calculated related data. The first constraint conditions include: The correlation between two historical AIS data and satellite communication data belonging to the same associated data combination is greater than a preset first correlation threshold. The correlation between two historical AIS data and satellite communication data that do not belong to the same associated data combination is less than a preset second correlation threshold; the second correlation threshold is less than the first correlation threshold; Based on the first objective function and the first constraint, the clustering algorithm is used to iteratively calculate all the historical AIS data and the satellite communication data until the optimal result is obtained, resulting in multiple corresponding combinations of related data.

[0017] As an optional implementation, in the second aspect of the present invention, the specific method by which the calculation module calculates the location calculation result corresponding to each of the associated data combinations based on a location calculation algorithm includes: For each of the associated data combinations, the average position of the ship in all the historical AIS data in the associated data combination is calculated to obtain a first position result; Based on the satellite positioning algorithm, the average position of the satellite positioning locations corresponding to all the satellite communication data in the associated data combination is calculated to obtain the second position result; Determine whether the positional distance between the first position result and the second position result is greater than a preset distance threshold to obtain a second determination result; When the first judgment result is yes, both the first position result and the second position result are determined as the position calculation result corresponding to the associated data combination. If the first judgment result is negative, calculate the weighted average position of the first position result and the second position result to obtain the position calculation result corresponding to the associated data combination.

[0018] As an optional implementation, in a second aspect of the invention, the positioning module determines the specific method for determining the corrected position trajectory corresponding to the target vessel based on the correlation degree corresponding to each of the associated data combinations and all the position calculation results, including: Calculate the average of the correlation degree among all data in each of the associated data combinations to obtain the combined correlation degree corresponding to each of the associated data combinations; Based on the dynamic programming algorithm and the second constraint related to the combined correlation degree, the trajectory that can be formed by all the position calculation results is iteratively calculated until the optimal one is obtained, so as to obtain the corrected position trajectory corresponding to the target ship.

[0019] As an optional implementation, in a second aspect of the invention, the second objective function of the dynamic programming algorithm is to minimize the average curvature of the calculated position trajectory; The second constraint includes: The correlation difference between any two adjacent position calculation results in the position trajectory is less than a preset first difference threshold; the correlation difference is the product of the position distance and the correlation difference between the two position calculation results; the correlation difference is the difference between the combination correlation degree corresponding to the correlation combination to which the two position calculation results belong respectively; The correlation difference between any calculated position that belongs to the location trajectory and any calculated position that does not belong to the location trajectory is less than a preset second difference threshold.

[0020] A third aspect of the present invention discloses another ship position monitoring system based on multi-data correction, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the ship position monitoring method based on multiple data correction disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the ship position monitoring method based on multiple data correction disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention acquires historical AIS data and satellite communication data over a historical time period and uses a clustering association algorithm to determine the associated combinations. It then calculates the location results and determines the corrected location trajectory based on the degree of association. This enables deep fusion and location correction of heterogeneous ship monitoring data, effectively solving the problem of insufficient positioning accuracy from a single data source and significantly improving the continuity and accuracy of target ship trajectory reconstruction. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a ship position monitoring method based on multi-data correction disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of a ship position monitoring system based on multi-data correction disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another ship position monitoring system based on multi-data correction disclosed in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] This invention discloses a ship position monitoring method and system based on multi-data correction. By acquiring historical AIS data and satellite communication data over a historical time period and using a clustering association algorithm to determine the associated combinations, the system calculates the position result and determines the corrected position trajectory based on the degree of association. This enables deep fusion and position correction of heterogeneous ship monitoring data, effectively solving the problem of insufficient positioning accuracy from a single data source and significantly improving the continuity and accuracy of target ship trajectory reconstruction. Detailed explanations follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a ship position monitoring method based on multi-data correction disclosed in an embodiment of the present invention. Wherein, Figure 1 The described multi-data correction-based ship position monitoring method can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). For example... Figure 1 As shown, the ship position monitoring method based on multi-data correction may include the following operations: 101. Obtain multiple historical AIS data and multiple satellite communication data of the target vessel within a historical time period.

[0032] Optionally, the historical AIS data may include the vessel's call sign, draft, destination port, estimated time of arrival, and turning rate; this invention does not impose any limitations on this.

[0033] Optionally, the satellite communication data may include the signal transmission object, transmission path information, signal-to-noise ratio (SNR), received signal strength indication (RSSI), Doppler frequency shift parameters, and communication protocol version, which are not limited in this invention.

[0034] 102. Based on the clustering association algorithm, multiple associated data combinations corresponding to historical AIS data and satellite communication data are identified.

[0035] Optionally, the clustering association algorithm may employ hierarchical clustering, expectation-maximization (EM) algorithm, or Gaussian mixture model (GMM), and this invention does not impose any limitations.

[0036] 103. Based on the location calculation algorithm, calculate the location calculation result corresponding to each combination of associated data.

[0037] 104. Based on the correlation degree of each associated data combination and the calculation results of all positions, determine the corrected position trajectory of the target vessel.

[0038] As can be seen, the above-described embodiments of the invention acquire historical AIS data and satellite communication data over a historical period and use clustering association algorithms to determine the associated combinations, thereby calculating the location results and determining the corrected location trajectory based on the degree of association. This enables deep fusion and location correction of heterogeneous ship monitoring data, effectively solving the problem of insufficient positioning accuracy from a single data source and significantly improving the continuity and accuracy of target ship trajectory reconstruction.

[0039] As an optional embodiment, the above steps, based on a clustering association algorithm, determine multiple associated data combinations corresponding to historical AIS data and satellite communication data, including: For any historical AIS data and any satellite communication data, calculate the temporal similarity between the historical AIS data and the satellite communication data; Calculate the similarity of ship activity between the historical AIS data and the satellite communication data; The weighted average of time similarity and ship activity similarity is calculated to obtain the correlation between the historical AIS data and the satellite communication data; Based on the correlation, multiple related data combinations corresponding to historical AIS data and satellite communication data were determined using clustering algorithms.

[0040] Optionally, the weights of the weighted average can be dynamically adjusted according to the complexity of the electromagnetic environment of the sea area where the ship is located, but this invention does not limit this.

[0041] As can be seen, by calculating the temporal similarity and ship activity similarity between historical AIS data and satellite communication data, and clustering based on the correlation obtained by weighted summation to determine the combination of related data, it is possible to achieve fine matching of multi-source data in terms of time dimension and behavioral pattern. This can provide quantitative evaluation indicators for the accurate association of heterogeneous data and significantly improve the scientificity and logic of the combination division.

[0042] As an optional embodiment, the step of calculating the temporal similarity between the historical AIS data and the satellite communication data in the above steps includes: Calculate the first time difference between the data acquisition period of the historical AIS data and the communication period of the satellite communication data; Calculate the second time difference between the data collection time of the historical AIS data and the communication time of the satellite communication data; Calculate the vector similarity between the time information vector of the historical AIS data and the time information vector of the satellite communication data; The weighted average of the first time difference, the second time difference, and the vector similarity is calculated to obtain the time similarity between the historical AIS data and the satellite communication data.

[0043] Optionally, the time information vector is obtained by processing all time-related information through a vectorization model.

[0044] Optionally, the weight of the first time difference is greater than the weight of the second time difference.

[0045] Optionally, the weights of the first and second time differences are both less than the weights of vector similarity.

[0046] Optionally, the time-related information may include the sampling time point, sampling frequency, clock synchronization accuracy, epoch start time, and leap second correction parameters, which are not limited in this invention.

[0047] Optionally, the vectorization model can use Word2Vec, FastText, or a simple feature normalization mapping layer; this invention does not limit the specific model.

[0048] As can be seen, through the above optional embodiments, by comprehensively calculating the first time difference, the second time difference, and the similarity of time information vectors and assigning the highest weight to the vector similarity to obtain the time similarity, it is possible to achieve a comprehensive representation of the time characteristics of multi-source data. This can greatly eliminate the time bias caused by sampling differences and significantly enhance the robustness and authenticity of the time similarity calculation results.

[0049] As an optional embodiment, the step of calculating the similarity of ship activities between the historical AIS data and the satellite communication data in the above steps includes: Identify all sensor data related to the operation of the target vessel in the historical AIS data to obtain the first sensor data; The first judgment result is obtained by determining whether there is data related to ship activities in the satellite communication data. If the first judgment result is yes, the existing ship activity-related data will be identified as the ship activity data corresponding to the satellite communication data; Ship activity data is input into the sensor prediction model to obtain the corresponding predictive sensor data; Calculate the similarity between the first sensor data and the predicted sensor data to obtain the ship activity similarity between the historical AIS data and the satellite communication data; If the first judgment result is negative, the second sensor data recorded by the AIS equipment of the target ship during the communication period of acquiring the satellite communication data is obtained; Calculate the similarity between the first sensor data and the predicted sensor data to obtain the ship activity similarity between the historical AIS data and the satellite communication data.

[0050] Optionally, the first sensing data may include main engine speed, rudder angle feedback value, fuel consumption rate, and propeller thrust data, which are not limited in this invention.

[0051] Optionally, the sensing prediction model can employ a deep residual network (ResNet) or a spatiotemporal graph convolutional network (STGCN), and this invention does not impose any limitations.

[0052] Optionally, the second sensing data can be time-aligned using cubic spline interpolation or linear regression interpolation algorithms to adapt to the time nodes of satellite communication.

[0053] As can be seen, by extracting operational sensor data and using prediction models or AIS devices to record similarity comparisons to determine the similarity of ship activities, it is possible to verify the consistency of ship behavior under different data acquisition conditions. This enables in-depth mining of the physical activity characteristics behind the data and effectively reduces the risk of trajectory deviation caused by false associations or missing data.

[0054] As an optional embodiment, in the above steps, based on the correlation degree and according to the clustering algorithm, multiple related data combinations corresponding to historical AIS data and satellite communication data are determined, including: The first objective function is set to minimize the total number of combinations of all calculated related data. The first constraint conditions include: The correlation between two historical AIS data and satellite communication data belonging to the same associated data combination is greater than the preset first correlation threshold; The correlation between two historical AIS data and satellite communication data that do not belong to the same associated data combination is less than the preset second correlation threshold; Based on the first objective function and the first constraint, the clustering algorithm iteratively calculates all historical AIS data and satellite communication data until the optimal result is obtained, resulting in multiple corresponding combinations of related data.

[0055] Optionally, the second correlation threshold is less than the first correlation threshold.

[0056] Optionally, the clustering algorithm may employ a density-based clustering method with noise (DBSCAN) or a mean shift algorithm, and this invention does not limit the method.

[0057] As can be seen, by using the above optional embodiments, and taking the minimization of the number of combinations as the objective function, and combining the dual constraints of high correlation within the same group and low correlation between different groups to perform iterative clustering calculations on all data, the optimal clustering division of massive and messy monitoring data can be achieved. This ensures the compactness and independence of the associated data combinations and significantly improves the automation and computational efficiency of the association calculation process.

[0058] As an optional embodiment, the step above, calculating the location calculation result corresponding to each combination of associated data based on the location calculation algorithm, includes: For each associated data combination, the average position of the ship in all historical AIS data in that associated data combination is calculated to obtain the first position result; Based on the satellite positioning algorithm, the average position of the satellite positioning locations corresponding to all satellite communication data in the associated data combination is calculated to obtain the second position result; Determine whether the positional distance between the first position result and the second position result is greater than a preset distance threshold, and obtain the second determination result; If the first judgment result is yes, both the first position result and the second position result are determined as the position calculation result corresponding to the associated data combination. If the first judgment result is negative, calculate the weighted average position of the first position result and the second position result to obtain the position calculation result corresponding to the associated data combination.

[0059] Optionally, the satellite positioning algorithm can use single-point positioning technology, differential positioning technology (DGPS) or carrier phase observation value positioning, and this invention does not limit it.

[0060] Optionally, the distance threshold can be dynamically adjusted according to the target vessel's speed level; for example, the threshold can be appropriately increased when sailing at high speed.

[0061] As can be seen, through the above optional embodiments, by calculating the AIS average position and the satellite positioning average position, and taking differentiated processing based on whether the position distance exceeds the threshold to retain the dual results or calculate the weighted average position, it is possible to achieve intelligent identification and coordination of positioning conflict data. This can take into account the original characteristics and advantages of different positioning methods and provide more representative coordinate data for position trajectory correction.

[0062] As an optional embodiment, the step above, determining the corrected position trajectory of the target vessel based on the correlation degree corresponding to each combination of associated data and all position calculation results, includes: Calculate the average degree of association between all data in each associated data combination to obtain the combined association degree corresponding to each associated data combination; Based on the dynamic programming algorithm and the second constraint related to the combined correlation degree, the possible trajectories formed by all position calculation results are iteratively calculated until the optimal one is obtained, so as to obtain the corrected position trajectory corresponding to the target ship.

[0063] Optionally, the dynamic programming algorithm can be the Viterbi algorithm or the A* search algorithm, and this invention does not limit it.

[0064] As can be seen, through the above optional embodiments, by calculating the combined correlation degree and using the dynamic programming algorithm to iteratively calculate the trajectory formed by the location calculation results under the correlation difference constraint, it is possible to achieve the global optimal path planning for discrete location points. This can effectively filter out the clutter interference caused by random positioning errors and ensure that the final generated corrected location trajectory has logical rigor in the time series.

[0065] As an optional embodiment, in the above steps, the second objective function of the dynamic programming algorithm is to minimize the average curvature of the calculated position trajectory; The second constraint includes: The correlation difference between any two adjacent location calculation results in the location trajectory is less than a preset first difference threshold; optionally, the correlation difference is the product of the location distance between the two location calculation results and the correlation difference; the correlation difference is the difference between the combination correlation degree corresponding to the correlation combination to which the two location calculation results belong respectively; The correlation difference between the calculation result of any position on the location trajectory and the calculation result of any position not on the location trajectory is less than the preset second difference threshold.

[0066] Optionally, the average curvature can be calculated using the formula for the radius of curvature of a discrete point sequence, which can reflect the smoothness of the trajectory.

[0067] Optionally, the first difference threshold can be set based on the ship's maneuverability index (such as the K index or T index).

[0068] As can be seen, by minimizing the average curvature of the trajectory as the objective and introducing a correlation difference constraint composed of position distance and correlation degree difference, it is possible to ensure that the generated ship trajectory remains smooth and stable in physical space layout and has a high degree of consistency in data correlation dimension. This can effectively eliminate abnormal offset points and greatly improve the realism of trajectory fitting in complex navigation environments.

[0069] Example 2 Please see Figure 2, Figure 2 This is a schematic diagram of a ship position monitoring system based on multi-data correction disclosed in an embodiment of the present invention. Figure 2 The described multi-data correction-based ship position monitoring system can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 2 As shown, the ship position monitoring system based on multi-data correction may include: The acquisition module 201 is used to acquire multiple historical AIS data and multiple satellite communication data of the target ship within a historical time period.

[0070] Clustering module 202 is used to determine multiple associated data combinations corresponding to historical AIS data and satellite communication data based on clustering association algorithms.

[0071] The calculation module 203 is used to calculate the location calculation result corresponding to each combination of associated data based on the location calculation algorithm.

[0072] The positioning module 204 is used to determine the corrected position trajectory of the target vessel based on the degree of association corresponding to each combination of associated data and the results of all position calculations.

[0073] As can be seen, the above-described embodiments of the invention acquire historical AIS data and satellite communication data over a historical period and use clustering association algorithms to determine the associated combinations, thereby calculating the location results and determining the corrected location trajectory based on the degree of association. This enables deep fusion and location correction of heterogeneous ship monitoring data, effectively solving the problem of insufficient positioning accuracy from a single data source and significantly improving the continuity and accuracy of target ship trajectory reconstruction.

[0074] As an optional implementation, the clustering module determines the specific method for combining multiple associated data sets corresponding to historical AIS data and satellite communication data based on a clustering association algorithm, including: For any historical AIS data and any satellite communication data, calculate the temporal similarity between the historical AIS data and the satellite communication data; Calculate the similarity of ship activity between the historical AIS data and the satellite communication data; The weighted average of time similarity and ship activity similarity is calculated to obtain the correlation between the historical AIS data and the satellite communication data; Based on the correlation, multiple related data combinations corresponding to historical AIS data and satellite communication data were determined using clustering algorithms.

[0075] As can be seen, by calculating the temporal similarity and ship activity similarity between historical AIS data and satellite communication data, and clustering based on the correlation obtained by weighted summation to determine the combination of related data, it is possible to achieve fine matching of multi-source data in terms of time dimension and behavioral pattern. This can provide quantitative evaluation indicators for the accurate association of heterogeneous data and significantly improve the scientificity and logic of the combination division.

[0076] As an optional embodiment, the specific method by which the clustering module calculates the temporal similarity between the historical AIS data and the satellite communication data includes: Calculate the first time difference between the data acquisition period of the historical AIS data and the communication period of the satellite communication data; Calculate the second time difference between the data collection time of the historical AIS data and the communication time of the satellite communication data; Calculate the vector similarity between the time information vector of the historical AIS data and the time information vector of the satellite communication data; optionally, the time information vector is obtained by processing all time-related information through a vectorization model; The weighted average of the first time difference, the second time difference, and the vector similarity is calculated to obtain the time similarity between the historical AIS data and the satellite communication data; wherein, the weight of the first time difference is greater than the weight of the second time difference, and the weights of both the first time difference and the second time difference are less than the weight of the vector similarity.

[0077] As can be seen, through the above optional embodiments, by comprehensively calculating the first time difference, the second time difference, and the similarity of time information vectors and assigning the highest weight to the vector similarity to obtain the time similarity, it is possible to achieve a comprehensive representation of the time characteristics of multi-source data. This can greatly eliminate the time bias caused by sampling differences and significantly enhance the robustness and authenticity of the time similarity calculation results.

[0078] As an optional embodiment, the specific method by which the clustering module calculates the similarity of ship activities between the historical AIS data and the satellite communication data includes: Identify all sensor data related to the operation of the target vessel in the historical AIS data to obtain the first sensor data; The first judgment result is obtained by determining whether there is data related to ship activities in the satellite communication data. If the first judgment result is yes, the existing ship activity-related data will be identified as the ship activity data corresponding to the satellite communication data; Ship activity data is input into the sensor prediction model to obtain the corresponding predictive sensor data; Calculate the similarity between the first sensor data and the predicted sensor data to obtain the ship activity similarity between the historical AIS data and the satellite communication data; If the first judgment result is negative, the second sensor data recorded by the AIS equipment of the target ship during the communication period of acquiring the satellite communication data is obtained; Calculate the similarity between the first sensor data and the predicted sensor data to obtain the ship activity similarity between the historical AIS data and the satellite communication data.

[0079] As can be seen, by extracting operational sensor data and using prediction models or AIS devices to record similarity comparisons to determine the similarity of ship activities, it is possible to verify the consistency of ship behavior under different data acquisition conditions. This enables in-depth mining of the physical activity characteristics behind the data and effectively reduces the risk of trajectory deviation caused by false associations or missing data.

[0080] As an optional implementation, the clustering module determines, based on correlation degree and according to a clustering algorithm, the specific method for combining multiple associated data sets corresponding to historical AIS data and satellite communication data, including: The first objective function is set to minimize the total number of combinations of all calculated related data. The first constraint conditions include: The correlation between two historical AIS data and satellite communication data belonging to the same associated data combination is greater than the preset first correlation threshold; The correlation between two historical AIS data and satellite communication data that do not belong to the same associated data combination is less than a preset second correlation threshold; optionally, the second correlation threshold is less than the first correlation threshold. Based on the first objective function and the first constraint, the clustering algorithm iteratively calculates all historical AIS data and satellite communication data until the optimal result is obtained, resulting in multiple corresponding combinations of related data.

[0081] As can be seen, by using the above optional embodiments, and taking the minimization of the number of combinations as the objective function, and combining the dual constraints of high correlation within the same group and low correlation between different groups to perform iterative clustering calculations on all data, the optimal clustering division of massive and messy monitoring data can be achieved. This ensures the compactness and independence of the associated data combinations and significantly improves the automation and computational efficiency of the association calculation process.

[0082] As an optional embodiment, the calculation module calculates the location calculation result corresponding to each combination of associated data based on the location calculation algorithm in the following specific ways: For each associated data combination, the average position of the ship in all historical AIS data in that associated data combination is calculated to obtain the first position result; Based on the satellite positioning algorithm, the average position of the satellite positioning locations corresponding to all satellite communication data in the associated data combination is calculated to obtain the second position result; Determine whether the positional distance between the first position result and the second position result is greater than a preset distance threshold, and obtain the second determination result; If the first judgment result is yes, both the first position result and the second position result are determined as the position calculation result corresponding to the associated data combination. If the first judgment result is negative, calculate the weighted average position of the first position result and the second position result to obtain the position calculation result corresponding to the associated data combination.

[0083] As can be seen, through the above optional embodiments, by calculating the AIS average position and the satellite positioning average position, and taking differentiated processing based on whether the position distance exceeds the threshold to retain the dual results or calculate the weighted average position, it is possible to achieve intelligent identification and coordination of positioning conflict data. This can take into account the original characteristics and advantages of different positioning methods and provide more representative coordinate data for position trajectory correction.

[0084] As an optional embodiment, the positioning module determines the specific method of the corrected position trajectory corresponding to the target vessel based on the correlation degree corresponding to each combination of associated data and the results of all position calculations, including: Calculate the average degree of association between all data in each associated data combination to obtain the combined association degree corresponding to each associated data combination; Based on the dynamic programming algorithm and the second constraint related to the combined correlation degree, the possible trajectories formed by all position calculation results are iteratively calculated until the optimal one is obtained, so as to obtain the corrected position trajectory corresponding to the target ship.

[0085] As can be seen, through the above optional embodiments, by calculating the combined correlation degree and using the dynamic programming algorithm to iteratively calculate the trajectory formed by the location calculation results under the correlation difference constraint, it is possible to achieve the global optimal path planning for discrete location points. This can effectively filter out the clutter interference caused by random positioning errors and ensure that the final generated corrected location trajectory has logical rigor in the time series.

[0086] As an optional implementation, the second objective function of the dynamic programming algorithm is to minimize the average curvature of the calculated position trajectory; The second constraint includes: The correlation difference between any two adjacent location calculation results in the location trajectory is less than a preset first difference threshold; optionally, the correlation difference is the product of the location distance between the two location calculation results and the correlation difference; the correlation difference is the difference between the combination correlation degree corresponding to the correlation combination to which the two location calculation results belong respectively; The correlation difference between the calculation result of any position on the location trajectory and the calculation result of any position not on the location trajectory is less than the preset second difference threshold.

[0087] As can be seen, by minimizing the average curvature of the trajectory as the objective and introducing a correlation difference constraint composed of position distance and correlation degree difference, it is possible to ensure that the generated ship trajectory remains smooth and stable in physical space layout and has a high degree of consistency in data correlation dimension. This can effectively eliminate abnormal offset points and greatly improve the realism of trajectory fitting in complex navigation environments.

[0088] Example 3 Please see Figure 3 , Figure 3 This is another ship position monitoring system based on multi-data correction disclosed in the embodiments of the present invention. Figure 3 The described multi-data correction-based ship position monitoring system is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the ship position monitoring system based on multi-data correction may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the ship position monitoring method based on multi-data correction described in Embodiment 1.

[0089] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the ship position monitoring method based on multiple data correction described in Embodiment 1.

[0090] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the ship position monitoring method based on multiple data correction described in Embodiment 1.

[0091] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0093] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0094] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0096] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0098] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0099] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0100] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0101] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0102] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0103] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0104] Finally, it should be noted that the ship position monitoring method and system based on multi-data correction disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring ship position based on multi-data correction, characterized in that, The method includes: Acquire multiple historical AIS data and multiple satellite communication data of the target vessel within a historical time period; Based on the clustering association algorithm, multiple associated data combinations corresponding to the historical AIS data and the satellite communication data are determined; Based on the location calculation algorithm, the location calculation result corresponding to each of the aforementioned associated data combinations is calculated; Based on the degree of association corresponding to each of the aforementioned data combinations and all the aforementioned position calculation results, the corrected position trajectory corresponding to the target vessel is determined.

2. The ship position monitoring method based on multi-data correction according to claim 1, characterized in that, The clustering association algorithm determines multiple associated data combinations corresponding to the historical AIS data and the satellite communication data, including: For any of the historical AIS data and any of the satellite communication data, calculate the temporal similarity between the historical AIS data and the satellite communication data; Calculate the similarity of ship activity between the historical AIS data and the satellite communication data; Calculate the weighted average of the time similarity and the ship activity similarity to obtain the correlation between the historical AIS data and the satellite communication data; Based on the correlation, multiple associated data combinations corresponding to the historical AIS data and the satellite communication data are determined according to the clustering algorithm.

3. The ship position monitoring method based on multi-data correction according to claim 2, characterized in that, The calculation of the temporal similarity between the historical AIS data and the satellite communication data includes: Calculate the first time difference between the data acquisition period of the historical AIS data and the communication period of the satellite communication data; Calculate the second time difference between the data collection time of the historical AIS data and the communication time of the satellite communication data; Calculate the vector similarity between the time information vector of the historical AIS data and the time information vector of the satellite communication data; the time information vector is obtained by processing all time-related information through a vectorization model; Calculate the weighted average of the first time difference, the second time difference, and the vector similarity to obtain the time similarity between the historical AIS data and the satellite communication data; wherein, the weight of the first time difference is greater than the weight of the second time difference, and the weights of both the first time difference and the second time difference are less than the weight of the vector similarity.

4. The ship position monitoring method based on multi-data correction according to claim 2, characterized in that, The calculation of the similarity of ship activities between the historical AIS data and the satellite communication data includes: Identify all sensor data related to the operation of the target vessel in the historical AIS data to obtain the first sensor data; The first judgment result is obtained by determining whether there is data related to ship activities in the satellite communication data. When the first judgment result is yes, the existing ship activity-related data is determined as the ship activity data corresponding to the satellite communication data; The ship activity data is input into the sensor prediction model to obtain the corresponding predicted sensor data. Calculate the similarity between the first sensing data and the predicted sensing data to obtain the ship activity similarity between the historical AIS data and the satellite communication data; If the first determination result is negative, the second sensor data recorded by the AIS equipment of the target ship during the communication period of the satellite communication data is obtained; Calculate the similarity between the first sensing data and the predicted sensing data to obtain the ship activity similarity between the historical AIS data and the satellite communication data.

5. The ship position monitoring method based on multi-data correction according to claim 2, characterized in that, Based on the correlation degree, and according to a clustering algorithm, multiple associated data combinations corresponding to the historical AIS data and the satellite communication data are determined, including: The first objective function is set to minimize the total number of combinations of all calculated related data. The first constraint conditions include: The correlation between two historical AIS data and satellite communication data belonging to the same associated data combination is greater than a preset first correlation threshold. The correlation between two historical AIS data and satellite communication data that do not belong to the same associated data combination is less than a preset second correlation threshold; the second correlation threshold is less than the first correlation threshold; Based on the first objective function and the first constraint, the clustering algorithm is used to iteratively calculate all the historical AIS data and the satellite communication data until the optimal result is obtained, resulting in multiple corresponding combinations of related data.

6. The ship position monitoring method based on multi-data correction according to claim 1, characterized in that, The location-based calculation algorithm calculates the location calculation result corresponding to each of the associated data combinations, including: For each of the associated data combinations, the average position of the ship in all the historical AIS data in the associated data combination is calculated to obtain a first position result; Based on the satellite positioning algorithm, the average position of the satellite positioning locations corresponding to all the satellite communication data in the associated data combination is calculated to obtain the second position result; Determine whether the positional distance between the first position result and the second position result is greater than a preset distance threshold to obtain a second determination result; When the first judgment result is yes, both the first position result and the second position result are determined as the position calculation result corresponding to the associated data combination. If the first judgment result is negative, calculate the weighted average position of the first position result and the second position result to obtain the position calculation result corresponding to the associated data combination.

7. The ship position monitoring method based on multi-data correction according to claim 2, characterized in that, The step of determining the corrected position trajectory of the target vessel based on the correlation degree corresponding to each of the associated data combinations and all the position calculation results includes: Calculate the average of the correlation degree among all data in each of the associated data combinations to obtain the combined correlation degree corresponding to each of the associated data combinations; Based on the dynamic programming algorithm and the second constraint related to the combined correlation degree, the trajectory that can be formed by all the position calculation results is iteratively calculated until the optimal one is obtained, so as to obtain the corrected position trajectory corresponding to the target ship.

8. The ship position monitoring method based on multi-data correction according to claim 7, characterized in that, The second objective function of the dynamic programming algorithm is to minimize the average curvature of the calculated position trajectory. The second constraint includes: The correlation difference between any two adjacent position calculation results in the position trajectory is less than a preset first difference threshold; the correlation difference is the product of the position distance and the correlation difference between the two position calculation results; the correlation difference is the difference between the combination correlation degree corresponding to the correlation combination to which the two position calculation results belong respectively; The correlation difference between any calculated position that belongs to the location trajectory and any calculated position that does not belong to the location trajectory is less than a preset second difference threshold.

9. A ship position monitoring system based on multi-data correction, characterized in that, The system includes: The acquisition module is used to acquire multiple historical AIS data and multiple satellite communication data of the target vessel within a historical time period; The clustering module is used to determine multiple associated data combinations corresponding to the historical AIS data and the satellite communication data based on a clustering association algorithm; The calculation module is used to calculate the location calculation result corresponding to each of the associated data combinations based on the location calculation algorithm; The positioning module is used to determine the corrected position trajectory of the target vessel based on the degree of association corresponding to each of the associated data combinations and all the position calculation results.

10. A ship position monitoring system based on multi-data correction, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the ship position monitoring method based on multiple data correction as described in any one of claims 1-8.

Images