A Method and System for Detecting Duplicate Numbers in MMSI Based on Dynamic Information from AIS Messages

Abstract

This invention relates to a method and system for detecting duplicate MMSI numbers based on dynamic information from AIS messages. The method comprises: continuously receiving and parsing AIS dynamic messages within a preset time period to obtain the MMSI; storing the dynamic messages of the target MMSI to be detected; parsing the stored AIS dynamic messages to obtain the ship dynamic information contained therein, including position information, ground speed, and time stamp; calculating the actual displacement between two adjacent messages based on the position information; calculating the theoretical maximum displacement between two adjacent messages based on the ground speed and time stamp; and comparing the actual displacement D. A and the theoretical maximum displacement D T D A ≤D T This is a normal result, D A >D T The system is considered an abnormal result; a threshold judgment is made, with a preset threshold value. When the proportion of abnormal results is not greater than the preset threshold value, the MMSI is determined to be normal; otherwise, the MMSI is determined to be a duplicate number. The system includes a memory and a processor, and the processor is used to call and run instructions from the memory to execute the duplicate number detection method.

Description

Technical Field

[0001] This invention relates to wireless communication network monitoring technology, and more particularly to a method and system for detecting duplicate MMSI numbers based on dynamic information of AIS messages. Background Technology

[0002] AIS (Automatic Identification System) is a system for automatically exchanging information between ships and between ships and shore. It is an important means to improve navigation safety, enhance maritime traffic management, and promote shipping efficiency. In the AIS system, the MMSI (Maritime Mobile Service Identity) code is a unique identifier assigned to a vessel by the International Maritime Organization (IMO). Its function is similar to a citizen's ID number, serving as the fundamental basis for identifying and tracking vessels. However, for reasons such as evading supervision, illegal operations, or other purposes, some illegal vessels deliberately copy or steal the MMSI codes of legitimate vessels, leading to frequent instances of duplicate codes ("one code for multiple vessels"). When two or more vessels use the same MMSI code at different locations, ground-based or satellite AIS receiving systems will receive track data from the same MMSI but with inconsistent locations. This can cause serious misjudgments by the Vessel Traffic Service (VTS) system, increasing the risk of collisions with legitimate vessels. Furthermore, in the event of a maritime accident, erroneous positioning information can severely interfere with the efficiency of emergency search and rescue operations, posing a serious challenge to maritime shipping management.

[0003] The AIS system uses the concept of frames, with one frame equal to 1 minute and divided into 2250 time slots. Each time slot is 26.67 ms long and is connected to the VDL at the beginning of each time slot. There are 27 message formats for AIS data broadcast on the VDL. Among them, messages 1, 2, 3 and 18 are ship dynamic messages, which contain parameters related to the ship's navigation dynamics, and their broadcast frequency is closely related to the ship's navigation status and speed.

[0004] Under normal circumstances, a ship's navigation trajectory is physically continuous, and its distance traveled in a short period of time is limited by its maximum speed. However, two ships using the same MMSI (Multiple Dimensional Ship Indicator) are often far apart (the purpose of MMSI overlap is to avoid detection of illegal vessels; therefore, the two overlapping ships are usually far beyond the line of sight, tens of nautical miles apart). When the system receives AIS messages from two ships with the same MMSI, the AIS messages are adjacent in time, but exhibit a "momentary" spatial shift. This invention utilizes this phenomenon to propose a method for detecting duplicate MMSI numbers based on dynamic information from AIS messages. Summary of the Invention

[0005] The technical problem to be solved by this invention is how to detect duplicate MMSI numbers based on dynamic information from AIS messages when the same MMSI appears on two ships.

[0006] To solve the above problems, the technical solution adopted by the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for detecting duplicate MMSI numbers based on dynamic information of AIS messages, the method comprising the following steps:

[0008] Step S1: Continuously receive AIS dynamic messages and parse them to obtain MMSI within a preset time period, and store the dynamic messages of the target MMSI to be detected.

[0009] Step S2: Parse the stored AIS dynamic message to obtain the ship dynamic information contained therein. The dynamic information includes position information (lat, lon), ground speed SOG, and time stamp; where lat is the latitude value and lon is the longitude value.

[0010] Step S3: Calculate the actual displacement D between two adjacent messages based on the location information (lat, lon). A Based on the ground speed SOG and time stamp, calculate the theoretical maximum displacement D between two adjacent messages. T ;

[0011] Step S4: Compare the actual displacement D A and the theoretical maximum displacement D T ,

[0012] D A ≤D T At that time, the actual displacement D A This is a normal result.

[0013] D A >D T At that time, the actual displacement D A This is an abnormal result;

[0014] Step S5, Threshold decision,

[0015] A preset threshold is set. If the percentage of abnormal results is not greater than the preset threshold, the MMSI is considered normal; otherwise, the MMSI is considered a duplicate.

[0016] Furthermore, in step S3, the theoretical maximum displacement D T The following method is used for calculation:

[0017] Calculate the time difference between two adjacent messages based on their timestamps. Compare the ground speeds of two adjacent messages and select the larger value. Calculate the theoretical maximum displacement D T , .

[0018] Furthermore, the theoretical maximum displacement D is calculated. T When a tolerance coefficient α is introduced, the theoretical maximum displacement D T Calculated using the following formula:

[0019] , where the value of α is 2-5.

[0020] Furthermore, the actual displacement D A The following method is used for calculation:

[0021] ;

[0022] ;

[0023] ;

[0024] Where n is the index of the point, i.e., the nth point, a n c is a dimensionless intermediate computational quantity. n Let D be the central angle of the great circle between two points on the surface of the sphere. An For the nth actual displacement D A ;

[0025] , They are the nth D A Two points of latitude , ;

[0026] , ;

[0027] R is the Earth's average radius. It is a two-parameter arctangent function.

[0028] Furthermore, in step S1, the preset time period for continuously receiving AIS dynamic messages is 0.5~1h.

[0029] Furthermore, in step S1, the preset time period for continuously receiving AIS dynamic messages is 1 hour; in step S5, the threshold decision adopts a segmented multi-threshold decision, and the threshold value is set as follows for different numbers of comparison results:

[0030] When m≤50, the threshold value is 80%;

[0031] When 50 < m ≤ 420, the threshold value is 8.4%;

[0032] When 420 < m ≤ 790, the threshold value is 80%;

[0033] When 790 < m ≤ 2000, the threshold value is 1.76%;

[0034] When 2000 < m ≤ 2380, the threshold value is 26.64%;

[0035] When m > 2380, the threshold value is 80%;

[0036] Where m is the total number of comparison results.

[0037] Furthermore, MMSIs identified as duplicates are reported to the VDL system, while MMSIs identified as normal are subjected to cyclical testing.

[0038] Secondly, the present invention provides an MMSI duplicate number detection device for AIS message dynamic information, the device comprising:

[0039] The dynamic message receiving and parsing unit continuously receives AIS dynamic messages within a preset time period and parses them to obtain MMSI and ship dynamic information. The dynamic information includes position information (lat, lon), ground speed SOG, and time stamp; where lat is the latitude value and lon is the longitude value.

[0040] The dynamic message storage unit identifies the target MMSI to be detected and stores its message.

[0041] The displacement calculation unit calculates the actual displacement D between two adjacent messages based on the position information (lat, lon). A Based on the ground speed SOG and time stamp, calculate the theoretical maximum displacement D between two adjacent messages. T ;

[0042] The duplicate number detection unit compares the actual displacement D. A and the theoretical maximum displacement D T D A ≤D T At that time, the actual displacement D A For normal results, D A >D T At that time, the actual displacement D A This is considered an abnormal result. A preset threshold value is set. If the proportion of abnormal results is not greater than the set threshold value, the MMSI is considered normal; otherwise, the MMSI is considered a duplicate number.

[0043] Thirdly, the present invention provides an MMSI duplicate number detection system based on AIS message dynamic information, the system comprising:

[0044] One or more memories for storing instructions; and

[0045] One or more processors are configured to retrieve and execute the instructions from the memory to perform the method described in the first aspect of the present invention.

[0046] Fourthly, the present invention provides a computer-readable storage medium, the computer-readable storage medium comprising:

[0047] The program, when run by a processor, executes the method described in the first aspect of the present invention.

[0048] The beneficial effects of adopting the above technical solution are as follows:

[0049] The duplicate number detection method provided by this invention can effectively distinguish between normal MMSI and MMSI with duplicate numbers from two ships. This detection method only needs to parse and analyze the received AIS messages to realize timely detection and real-time monitoring of MMSI duplicate number behavior, providing maritime regulatory authorities with an efficient and reliable automated MMSI duplicate number identification technology.

[0050] The detection method provided by this invention continuously monitors ship messages, enabling real-time identification of duplicate MMSI numbers. MMSIs identified as duplicates are reported to the VDL system for handling by relevant departments, ensuring timely resolution of illegal activities. This invention reduces the risk of MMSI theft and collisions caused by duplicate MMSI numbers, ensuring safe navigation and preventing disruptions to maritime emergency search and rescue and shipping management. Attached Figure Description

[0051] Figure 1 This is a flowchart of the detection method of the present invention.

[0052] Figure 2 This is a normal ship navigation trajectory.

[0053] Figure 3 It is the navigation trajectory of a ship with a MMSI repeated number (different frequency).

[0054] Figure 4 It is the navigation trajectory of a ship with the same MMSI serial number (same frequency).

[0055] Figure 5 This is a comparison chart of the actual displacement of a normal ship and its theoretical maximum displacement.

[0056] Figure 6 This is a comparison chart of the actual displacement and theoretical maximum displacement of two MMSI heavy-duty ships. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described clearly and completely below in conjunction with specific embodiments.

[0058] A sequence of AIS messages generated by a single vessel appears as a continuous, smooth trajectory on geographic coordinates. The distance between any two consecutive message points matches the time interval and the vessel's speed. When two or more vessels far apart impersonate the same MMSI, the monitoring system receives a set of messages broadcast by these vessels in an interleaved manner. At the data level, this presents as a pseudo-track that frequently and irregularly "jumps" in space. The location of the previous message may be in sea area A, while the location of the next message may instantly appear in sea area B, tens or hundreds of nautical miles away. This phenomenon of huge positional changes in a very short time is called spatial discontinuity of the track or track point jumps.

[0059] Assuming at time point A message was received from vessel A, which included location information. and ground speed At the next point in time. The next message received from ship B is located at ( Because ships A and B are geographically far apart, the geographical distance between the locations (latitude and longitude coordinates) contained in these two consecutive messages will be very large, far exceeding that of a single ship. ( The distance a ship may travel within a given time period, i.e., the "jump" in the ship's trajectory, is the basic basis for identifying MMSI duplicate numbers.

[0060] Example 1

[0061] refer to Figure 1 Based on the above phenomena, this invention proposes a method for detecting duplicate MMSI numbers based on dynamic information of AIS messages. This method is designed for situations where the same MMSI appears on two ships, and includes the following steps:

[0062] Step S1: Continuously receive AIS dynamic messages and parse them to obtain MMSIs within a preset time period, store the dynamic messages of several target MMSIs to be detected, and do not store the dynamic messages of non-target MMSIs.

[0063] Step S2: Parse the stored AIS dynamic message to obtain the ship dynamic information contained therein. The dynamic information includes position information (lat, lon), ground speed SOG, and time stamp; where lat is the latitude value and lon is the longitude value.

[0064] Step S3: Calculate the actual displacement D between two adjacent messages based on the location information (lat, lon). A Based on the ground speed SOG and time stamp, calculate the theoretical maximum displacement D between two adjacent messages. T Each MMSI to be detected corresponds to several messages, thus multiple actual displacements D can be obtained. A and multiple theoretical maximum displacements D T ;

[0065] Step S4: Compare the calculated actual displacement D A and the theoretical maximum displacement D T ,

[0066] D A ≤D T At that time, the trajectory was normal, and the actual displacement D was... A This is a normal result; D A >D T At that time, the trajectory was abnormal, and the actual displacement D was... A This is an abnormal result;

[0067] Step S5, Threshold decision,

[0068] A preset threshold is set. If the percentage of abnormal results is not greater than the preset threshold, the MMSI is considered normal; otherwise, the MMSI is considered a duplicate.

[0069] In step S3, the theoretical maximum displacement D T The following method is used for calculation:

[0070] Calculate the time difference between two adjacent messages based on their timestamps. Compare the ground speeds of two adjacent messages and select the larger value. , .

[0071] By parsing the messages, the UTC second count at the time of transmission of two adjacent messages can be obtained from the dynamic messages. Simultaneously, the message receiving time slot is displayed at the message receiving end, thus allowing the ratio to be calculated. More precise millisecond count t ms In the AIS system, 1 minute contains 2250 time slots, each with a length of 26.67 ms. Therefore, the time t at which the message was transmitted can be obtained by counting the number of time slots occupied by the receiver. ms The calculation process is shown in the following formula:

[0072] Slot num This is the time slot number corresponding to the message, i.e., which time slot it is.

[0073] Furthermore, the spatial transmission path of the message is very short, and the transmission and reception times of the message are basically the same. Therefore, by parsing the message to obtain the UTC second count and combining it with the local time, the UTC time can be determined. h , UTC m By counting, the transmission time of the message can be obtained, that is:

[0074] ;

[0075] Furthermore, the time difference required to calculate the theoretical displacement. As shown in the following formula:

[0076] .

[0077] Theoretical maximum displacement D T It is used to measure the actual displacement D A Whether the scale is reasonable is a complex issue. Theoretically, actual displacement = velocity × time. However, in actual calculations, considering the uncertainties caused by external environment and sensor errors during navigation, it is difficult to obtain the ship's speed accurately in real time. Therefore, it is necessary to perform a correction process on the ship's speed to ensure the theoretical maximum displacement D is accurate. T To ensure the reliability of the calculation, the larger value among the ground speeds recorded in two adjacent message records is selected for calculating the theoretical maximum displacement D. T When the two ground speeds are equal, either one can be chosen.

[0078] Calculate the theoretical maximum displacement D T Besides the time difference, another important parameter is the ship's speed, V. When a ship corresponds to one MMSI, the SOG at two points on the ship will not change much. When calculating V, the average of the SOG at two moments can be used to obtain a relatively neutral speed. However, if there is a problem of duplicate MMSI numbers, the speeds of the two ships often differ greatly by SOG. The calculation of V cannot be simply done by averaging. Moreover, the speed V is also the basis for calculating the theoretical maximum displacement D. T The key factor is the calculation method, which directly affects the reliability of the MMSI duplicate number detection algorithm. Therefore, it is crucial to select a reasonable speed V to calculate the theoretical maximum distance. Since the ship's speed is closely related to the message playback frequency, as shown in Table 1 (taking Class A ships as an example), the message playback combinations of two ships using the same MMSI are shown in Table 2. The table only lists the special case of the two ships' playback frequencies. As will be seen through subsequent analysis, other cases will be included after considering the special case.

[0079] Table 1 Reporting Intervals for Category A Ships

[0080]

[0081] Table 2. Message broadcast combinations for two ships with the same MMSI

[0082]

[0083] Combining Tables 1 and 2, it can be seen that when two ships use the same MMSI, the greatest difference occurs in scenario two of Table 2, which is 3 minutes and 2 seconds, corresponding to speeds of stationary (0) and exceeding 23 knots, respectively. Since the core of MMSI duplicate number detection is D... T With D A In the case of no duplicate signs, the two are equal or similar, where D A It is accurate, if D T The calculation error is too large, and the error result of the comparison between the two is also too large. Combining Table 1 and Table 2, it can be seen that the error δ generated when the two ships are in the second situation is too large. D The maximum is shown in the following formula:

[0084] .

[0085] In the formula, kn represents a knot, one knot equals 1n mile / h, and one nautical mile equals 1.852 km.

[0086] In actual cases of duplicate MMSI numbers, it was found that two vessels using the same MMSI were geographically far apart, typically by tens of nautical miles (due to MMSI spoofing to evade monitoring). Therefore, the error caused by SOG is negligible compared to the actual distance between the two vessels. (D) T With D A When comparing D, if A Greater than D T This indicates an anomaly in the calculated ship trajectory. To reduce the possibility of misjudgment, D T The calculated result should be appropriately higher than the actual calculated value; therefore, a tolerance coefficient α is introduced. Then the theoretical maximum displacement D... T Calculated using the following formula:

[0087] , where the value of α is 2-5.

[0088] The value of α can be selected and adjusted during actual operation based on the accuracy of the actual detection results.

[0089] In D AThe Euclidean distance formula based on plane geometry cannot be used in the calculation, as it would introduce huge errors. Therefore, a spherical geometry method is adopted, specifically the Great-Circle Distance, because it represents the shortest path between two points on a sphere. Among many Great-Circle Distance formulas, the Haversine (semi-versine) formula is used. This formula calculates the angular distance between two points and then multiplies it by the Earth's radius to obtain the actual distance. Its advantage is that it maintains high numerical stability even when the two points are very close, effectively avoiding the accuracy loss problems that may occur in other formulas (such as the spherical cosine law) when calculating small angles. Therefore, the actual displacement D... A The calculation method is as follows:

[0090] ;

[0091] ;

[0092] ;

[0093] Where n is the index of the point, i.e., the nth point, a n c is a dimensionless intermediate computational quantity. n Let D be the central angle of the great circle between two points on the surface of the sphere. An For the nth actual displacement D A ;

[0094] , They are the nth D A Two points of latitude , ;

[0095] , ;

[0096] R is the Earth's average radius (6371 km). It is a two-parameter arctangent function.

[0097] In practical applications, factors such as AIS equipment performance, flight environment, and data transmission delays may result in suboptimal received messages, leading to inaccuracies in single calculations. Therefore, a single judgment result cannot be used to determine whether an MMSI has a duplicate number. To reduce or avoid the possibility of misjudgment and improve the reliability of the MMSI duplicate number detection algorithm, this invention employs a segmented statistical threshold decision algorithm. This involves setting corresponding threshold values ​​for different numbers of comparison results and calculating multiple D values ​​for a single MMSI. A and D T The comparison is performed, and the results of multiple comparisons are judged as a whole.

[0098] Since the frequency of message broadcasting is closely related to the ship's sailing speed, the slowest broadcast frequency of dynamic messages is 3 minutes and the fastest is 2 seconds. To ensure sufficient threshold decision data, the time length of segmented statistical data is selected as 0.5~1h (i.e., the preset time period is 0.5~1h).

[0099] Considering different ship conditions, the duration of the preset time period is such that it can satisfy all MMSIs with enough message data, while also avoiding excessive data that cannot be stored. Therefore, the preferred preset time period is set to 1 hour.

[0100] Due to the uncertainty of the ship's navigation status, the minimum number of comparison results within 1 hour is 20, and the maximum is 3600 (assuming duplicate MMSI numbers and both ships broadcast at a frequency of 2 seconds / message). After determining the time for segmented statistics, the decision threshold needs to be discussed and reasonably quantified in the case of duplicate MMSI numbers, as follows:

[0101] When the message broadcasting frequency of two ships is the same, theoretically the judgment results are both abnormal, and the detection threshold for MMSI anomalies should be less than or equal to 100%.

[0102] When the message broadcast frequencies of the two ships are different and there is a big difference, such as scenario two in Table 2, there are only 40 outliers in 1820 comparison results. In order to make a successful judgment, the detection threshold of outliers should be less than or equal to 2.2%.

[0103] Therefore, it can be seen that due to the different states of the ships, when the MMSI numbers of the two ships are the same, their D... A and D T The proportion of outliers in the comparison results ranged from 2.2% to 100%, which is too wide a range to be effectively determined using a single threshold value.

[0104] The number of single comparison results for two ships with the same MMSI number under different broadcast frequency combinations is shown in Table 3.

[0105] Table 3 Number of single comparison results under different broadcast frequency combinations

[0106]

[0107] The number of the above comparison results is the number under ideal conditions, that is, the messages are received and stored at both the start and end endpoints within 1 hour, and no messages are lost during the reception process. This embodiment only uses this to calculate the proportion of abnormal results when the two ships have the same number.

[0108] As can be seen from the analysis in Table 3, the threshold values ​​are different for different numbers of comparison results under the condition of duplicate numbers. Combined with the AIS message receiving error rate requirement of 20% and the success rate of 80%, the actual threshold values ​​are set at 80% of their theoretical threshold values.

[0109] Since the number of abnormal MMSI results is greater than the number of normal MMSI results in each case, the segmentation limits are set based on the number of abnormal MMSI results (i.e., 40, 380, 720, 1820, 2160, 3600). To ensure that the segmentation limits cover the benchmark, the segmentation limit values ​​are increased by 10% based on the number of benchmark points and rounded to the nearest ten (i.e., 50, 420, 790, 2000, 2380).

[0110] The threshold values ​​corresponding to the comparison results of each quantity are shown in Table 4 below.

[0111] Table 4 MMSI Duplicate Number Detection Multiple Threshold Settings

[0112]

[0113] Since the threshold value is related to the comparison result, and the comparison result is related to the reception duration and the ship's broadcast frequency, this application only lists the comparison result when the reception duration is 1 hour. With sufficient comparison results and sufficient storage capacity, the reception duration can be adjusted within a certain range. When the reception duration changes, the threshold value should also change accordingly. If the value of m is outside the set threshold range due to factors such as ship positioning or message transmission delay, the calculation result should be discarded, and the MMSI number should be re-evaluated.

[0114] Using the above method, multiple MMSIs can be simultaneously identified as having duplicate numbers. MMSIs identified as having duplicate numbers are reported to the VDL system, where relevant departments will conduct further processing based on this information, such as further verification of duplicate numbers or enforcement actions. MMSIs identified as normal will be repeatedly tested.

[0115] In other words, this method simultaneously checks for duplicate numbers in M ​​(e.g., 100) MMSIs. Each round of detection stores the messages corresponding to the predetermined M MMSIs; messages outside this range are not stored. After duplicate number detection, if all M MMSIs are normal, the remaining MMSIs are checked until all MMSIs have been checked. Then, all MMSIs are checked again, and this process is repeated continuously. If an MMSI is determined to be a duplicate number during detection, it is immediately reported to the VDL system. For MMSIs not determined to be duplicate numbers, cyclical (or repeated) detection is performed to continuously monitor whether duplicate numbers exist in all MMSIs.

[0116] To verify the effectiveness and reliability of the MMSI duplicate number detection method based on AIS message dynamic information proposed in this invention, we built a simulation environment on the MATLAB R2022b platform to test and analyze the method. The core of the simulation lies in constructing a dataset that can simulate the characteristics of real AIS messages, including normal tracks and typical duplicate number tracks. The duplicate number tracks include both different-frequency and same-frequency types. The simulation results are as follows: Figures 2 to 6 As shown.

[0117] Figure 2 It shows the normal navigation trajectory of a ship over one hour. The trajectory is continuous and smooth, conforming to the laws of physics.

[0118] Figure 3 The simulation involved a stationary ship (top dot in the diagram) and a high-speed ship (bottom line segment) simultaneously using the same MMSI code, meaning the two ships using the same MMSI code broadcast messages at different frequencies. The simulation results showed that waypoints appeared between two geographically distant locations.

[0119] Figure 4 The simulation showed that two high-speed ships using the same MMSI code simultaneously would alternate between two geographically distant locations, and the trajectories formed by the two ships would be similar.

[0120] Figure 5 This is a comparison chart of the actual displacement and the theoretical maximum displacement of a normal ship. As can be seen from the chart, the trajectories of the "actual displacement" (solid blue line) and the "theoretical maximum displacement" (dashed red line) are basically consistent, and the actual displacement remains consistently below the theoretical maximum displacement without any abnormal spikes. This clearly demonstrates the stability and accuracy of the algorithm when processing normal trajectories.

[0121] Figure 6 The graph shows a comparison between the actual displacement and the theoretical maximum displacement of two ships with the same MMSI registration number. It illustrates the algorithm's detection performance when two ships are using the same MMSI registration number. The blue spikes in the graph represent the huge actual displacements caused by the "jumps" in space due to the track. These spikes far exceed the theoretical maximum displacement (red dashed line), and can therefore be identified as having the same registration number by the detection method provided in this embodiment, and reported to the VDL system.

[0122] Example 2

[0123] Secondly, the present invention provides an MMSI duplicate number detection device for AIS message dynamic information, the device comprising:

[0124] The dynamic message receiving and parsing unit continuously receives AIS dynamic messages through the AIS data center within a preset time period, and parses them to obtain MMSI and ship dynamic information. The dynamic information includes location information (lat, lon), ground speed SOG, and time stamp; where lat is the latitude value and lon is the longitude value.

[0125] The dynamic message storage unit identifies the target MMSI to be detected and stores its message.

[0126] The displacement calculation unit calculates the actual displacement D between two adjacent messages based on the position information (lat, lon). A Based on the ground speed SOG and time stamp, calculate the theoretical maximum displacement D between two adjacent messages. T ;

[0127] The duplicate number detection unit compares the actual displacement D. A and the theoretical maximum displacement D T D A ≤D T At that time, the trajectory was normal, and the actual displacement D was... A For normal results, D A >D T At that time, the trajectory was abnormal, and the actual displacement D was... A This is considered an abnormal result. A preset threshold value is set. If the proportion of abnormal results is not greater than the set threshold value, the MMSI is considered normal; otherwise, the MMSI is considered a duplicate number.

[0128] In one example, the unit in the above-described device may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0129] For example, when the units in the device can be implemented through a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these units can be integrated together to form a system-on-a-chip (SOC).

[0130] Example 3

[0131] Thirdly, the present invention provides an MMSI duplicate number detection system based on AIS message dynamic information, the system comprising:

[0132] One or more memories for storing instructions; and

[0133] One or more processors are configured to call and execute the instructions from the memory, performing the method as described in Example 1.

[0134] The aforementioned processor can be a CPU, microprocessor, ASIC, or one or more integrated circuits that execute a program for controlling the aforementioned feedback information transmission method. The memory is used to store necessary program instructions and data. The processor and the memory can be decoupled and located on different devices, connected via wired or wireless means to support the chip system in implementing the various functions described in the above embodiments. Alternatively, the processor and the memory can be coupled to the same device. Optionally, the memory can be an internal storage unit within the chip, such as a register or cache. Alternatively, the memory can be an external storage unit within the terminal, such as ROM or other types of static storage devices capable of storing static information and instructions, such as RAM.

[0135] Example 4

[0136] Fourthly, the present invention provides a computer-readable storage medium, the computer-readable storage medium comprising:

[0137] When the program is run by the processor, it executes the MMSI duplicate number detection method based on AIS message dynamic information as described in Embodiment 1 of the present invention.

[0138] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features; and these 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 detecting duplicate MMSI numbers based on dynamic information of AIS messages, characterized in that, Includes the following steps: Step S1: Continuously receive dynamic messages from the Automatic Identification System (AIS) within a preset time period, parse and obtain the Maritime Mobile Service Identifier (MMSI), and store the dynamic messages of the target MMSI to be detected. Step S2: Parse the stored AIS dynamic message to obtain the ship dynamic information contained therein. The dynamic information includes position information (lat, lon), ground speed SOG, and time stamp; where lat is the latitude value and lon is the longitude value. Step S3: Calculate the actual displacement D between two adjacent messages based on the location information (lat, lon). A Based on the ground speed SOG and time stamp, calculate the theoretical maximum displacement D between two adjacent messages. T ; Step S4: Compare the actual displacement D A and the theoretical maximum displacement D T , D A ≤D T At that time, the actual displacement D A This is a normal result. D A >D T At that time, the actual displacement D A This is an abnormal result; Step S5, Threshold decision, A preset threshold is set. If the percentage of abnormal results is not greater than the preset threshold, the MMSI is considered normal; otherwise, the MMSI is considered a duplicate.

2. The MMSI duplicate number detection method based on AIS message dynamic information according to claim 1, characterized in that, In step S3, the theoretical maximum displacement D T The following method is used for calculation: Calculate the time difference between two adjacent messages based on their timestamps. Compare the ground speeds of two adjacent messages and select the larger value. Calculate the theoretical maximum displacement D T , .

3. The MMSI duplicate number detection method based on AIS message dynamic information according to claim 2, characterized in that, Calculate the theoretical maximum displacement D T When a tolerance coefficient α is introduced, the theoretical maximum displacement D T Calculated using the following formula: , where the value of α is 2-5.

4. The MMSI duplicate number detection method based on AIS message dynamic information according to claim 1, characterized in that, The actual displacement D A The following method is used for calculation: ； ； ； Where n is the index of the point, a n c is a dimensionless intermediate computational quantity. n Let D be the central angle of the great circle between two points on the surface of the sphere. An For the nth actual displacement D A ; , They are the nth D A Two points of latitude , ; ， ； R is the average radius of the Earth.

5. The MMSI duplicate number detection method based on AIS message dynamic information according to claim 1, characterized in that, In step S1, the preset time period for continuously receiving AIS dynamic messages is 0.5~1h.

6. The MMSI duplicate number detection method based on AIS message dynamic information according to claim 5, characterized in that, In step S1, the preset time period for continuously receiving AIS dynamic messages is 1 hour; In step S5, the threshold decision adopts a segmented multi-threshold decision, and the threshold values ​​are set as follows for different numbers of comparison results: When m≤50, the threshold value is 80%; When 50 < m ≤ 420, the threshold value is 8.4%; When 420 < m ≤ 790, the threshold value is 80%; When 790 < m ≤ 2000, the threshold value is 1.76%; When 2000 < m ≤ 2380, the threshold value is 26.64%; When m > 2380, the threshold value is 80%; Where m is the total number of comparison results.

7. The MMSI duplicate number detection method based on AIS message dynamic information according to claim 1, characterized in that, MMSIs identified as duplicates are reported to the VDL system, while MMSIs identified as normal are subjected to cyclical testing.

8. A device for detecting duplicate MMSI numbers in AIS message dynamic information, characterized in that, include: The dynamic message receiving and parsing unit continuously receives dynamic messages from the Automatic Identification System (AIS) within a preset time period, and parses them to obtain the Maritime Mobile Service Identifier (MMSI) and vessel dynamic information. The dynamic information includes location information (lat, lon), ground speed (SOG), and time stamp; where lat is the latitude value and lon is the longitude value. The dynamic message storage unit identifies the target MMSI to be detected and stores its message. The displacement calculation unit calculates the actual displacement D between two adjacent messages based on the position information (lat, lon). A Based on the ground speed SOG and time stamp, calculate the theoretical maximum displacement D between two adjacent messages. T ; The duplicate number detection unit compares the actual displacement D. A and the theoretical maximum displacement D T D A ≤D T At that time, the actual displacement D A For normal results, D A >D T At that time, the actual displacement D A This is considered an abnormal result. A preset threshold value is set. If the proportion of abnormal results is not greater than the set threshold value, the MMSI is considered normal; otherwise, the MMSI is considered a duplicate number.

9. A duplicate number detection system for MMSI based on dynamic information of AIS messages, characterized in that, The system includes: One or more memories for storing instructions; and One or more processors are configured to retrieve and execute the instructions from the memory to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes: The program, when run by the processor, executes the method as described in any one of claims 1 to 7.

Images