A ship monitoring system based on AIS data and ocean hydrological data

Abstract

The present invention relates to the field of ship navigation monitoring, and provides a ship monitoring system based on AIS data and marine hydrological data. The system includes a model unit that constructs a first judgment matrix of the navigation safety scores for each water area using the expert scoring method, and a second judgment matrix of each safety factor for each water area. A calculation unit calculates a first weight vector of the first judgment matrix and a second weight vector of the second judgment matrix respectively; a factor scoring module is used to obtain the AIS data and marine hydrological data of the ship passing through the water area, extract and grade the safety factors thereof, and obtain a safety score matrix of each safety factor in each water area; an operation feedback module calculates the navigation safety score according to the first weight vector, the second weight vector and the safety score matrix. The present invention realizes the quantification of the knowledge of experts in special fields, combines the weight vectors of the analytic hierarchy process, and realizes the monitoring of ship navigation safety.

Description

Technical Field

[0001] The present invention relates to the field of ship navigation safety monitoring, and particularly to a ship monitoring system based on AIS data and marine hydrological data. Background Art

[0002] With the opening of the very high frequency communication of the Automatic Identification System (AIS) for ships and the mandatory installation of its transceiver devices, as well as the commercial satellite AIS data services provided by Orbcomm in the United States and ExactEarth in Canada, it has become more convenient to obtain AIS data, and thus it has also become more convenient to obtain a large amount of inshore and offshore ship trajectory data. The ship trajectory data in AIS data is a typical spatio-temporal big data, which contains ship behavior pattern information concerned by governments and commercial companies, such as ship spatio-temporal distribution, ship maneuvering behavior characteristics, ship traffic flow characteristics, ship habitual route distribution characteristics, route meteorological data, route ocean current data, etc. Mining of ship behavior characteristics based on AIS data has become a research hotspot in the field of spatio-temporal big data at home and abroad. Detection of abnormal ship behaviors in sensitive waters is an important part of the national marine security strategy, which can detect and give early warnings of potential threat behaviors such as illegal operations, fishing, surveying, and reconnaissance, and provide support for subsequent response and handling.

[0003] Based on AIS data, both the normal behaviors of ships can be modeled and monitored, and the abnormal behaviors of ships can be summarized and induced, which requires the close cooperation and coordination of practitioners, technicians, and scientific research institutions in special fields.

[0004] Therefore, how to quantify the knowledge of experts in special fields, so that the ship monitoring model can combine AIS data of different waters and different types is a technical problem to be solved at present. Summary of the Invention

[0005] For this purpose, the present invention provides a ship monitoring system based on AIS data and marine hydrological data. By using the expert scoring method to construct the judgment matrix of the analytic hierarchy process (AHP), the knowledge of experts in special fields is quantified, and thus the monitoring model can better fit the expert's experience and common sense. Also, by referring to the idea of the analytic hierarchy process (the calculation process of obtaining the navigation safety score is different from the conventional analytic hierarchy process), combining the weight vector of the analytic hierarchy process and the safety score matrix based on AIS data and marine hydrological data, the navigation safety score of the ship considering multiple water area characteristics is jointly calculated, and thus the navigation safety level of the ship can be accurately monitored.

[0006] To achieve the above object, the present invention proposes a ship monitoring system based on AIS data and marine hydrological data, including a judgment matrix module, a factor scoring module, and an operation feedback module;

[0007] The judgment matrix module includes a model unit and a calculation unit. The model unit is equipped with a model based on the analytic hierarchy process. The target layer of the model is the navigation safety score, the criterion layer is multiple waters, and the scheme layer is safety factors. The model obtains the first judgment matrix of each water area for the navigation safety score constructed by the expert scoring method, and the second judgment matrix of each safety factor for each water area. The calculation unit calculates the first weight vector of the first judgment matrix and the second weight vector of the second judgment matrix respectively;

[0008] The factor scoring module is used to obtain the AIS data and marine hydrological data of the ship passing through the water area, extract and grade the safety factors of the AIS data and marine hydrological data, and obtain the safety score matrix of each safety factor in each water area;

[0009] The operation feedback module calculates the navigation safety score according to the first weight vector, the second weight vector and the safety score matrix. The navigation safety score is used to monitor the navigation safety degree of the routes in multiple waters.

[0010] Further, the calculation formula of the navigation safety score is:

[0011] A = W A1 B 1 + W A2 B 2 +…+ W Ai B i ;

[0012] In the formula, A is the navigation safety score, W A1 to W Ai is the first weight vector, and B 1 to B i are the safety scores from the first water area to the i-th water area;

[0013] Among them, the calculation formula of the safety scores B 1 to B i from the first water area to the i-th water area is:

[0014]

[0015] In the formula, B 1 to B i are the safety scores from the first water area to the i-th water area, W B11 to W B1j are the elements of the sub-vector belonging to the first water area in the second weight vector, and W B21 to W B2j are the elements of the sub-vector belonging to the second water area in the second weight vector, and W Bi1 to W Bijis an element of the sub-vector belonging to the i-th water area in the second weight vector, C 11 to C i1 is an element of the safety score matrix of the first safety factor in the first to i-th water areas, C 12 to C i2 is an element of the safety score matrix of the second safety factor in the first to i-th water areas, C 1j to C ij is an element of the safety score matrix of the j-th safety factor in the first to i-th water areas;

[0016] wherein, both i and j are greater than or equal to 3.

[0017] Furthermore, the model unit includes a score acquisition sub-unit, a level acquisition sub-unit and a calculation sub-unit;

[0018] The acquisition sub-unit is used to acquire the first scoring grade of the importance of each water area to the navigation safety score judged by the expert group, and the second scoring grade of the safety importance of each safety factor to each water area;

[0019] The level acquisition sub-unit acquires the weight grade of the academic level of each expert in the expert group;

[0020] The calculation sub-unit calculates the first weighted average by calculating the first scoring grade and the weight grade, calculates the second weighted average by calculating the second scoring grade and the weight grade, divides the corresponding multiple first weighted averages to obtain the first judgment matrix, and divides the corresponding multiple second weighted averages to obtain the second judgment matrix.

[0021] Furthermore, the calculation unit includes an inspection sub-unit;

[0022] The inspection sub-unit is used to calculate the maximum eigenvalue of the first judgment matrix and the second judgment matrix respectively, and analyze and judge whether the first judgment matrix and the second judgment matrix meet the consistency requirement according to the maximum eigenvalue and the consistency inspection formula of the analytic hierarchy process. If so, calculate the first weight vector and the second weight vector. If not, feedback to the score acquisition sub-unit, and the score acquisition sub-unit modifies the first scoring grade and the second scoring grade.

[0023] Furthermore, the factor scoring module includes an extraction unit and a grading and scoring unit;

[0024] The extraction unit calculates and extracts at least the ocean current flow direction information of each water area in the ocean hydrological data, the passing time information, the speed information of each water area in the AIS data, and the course information of the ship;

[0025] The safety factors at least include a first safety factor to a third safety factor, which are respectively the drift difference information, passage time information, and speed information calculated from the course information and the ocean current direction information;

[0026] The grading and scoring unit respectively corresponds the drift difference information, passage time information, and speed information to grade ranges, obtains the scores of the grade ranges, and constructs the safety score matrix according to the multiple scores.

[0027] Further, the speed information includes the instant speed, average speed, and average economic speed;

[0028] The grading and scoring unit obtains a speed ratio according to the instant speed, corresponds the speed ratio to a grade range, and obtains the score of the grade range.

[0029] Further, the safety factors further include a fourth safety factor and a fifth safety factor, which are respectively the moving distance information and the meteorological warning level information;

[0030] The extraction unit also extracts the moving distance information of the ships in each water area from the AIS data and the meteorological warning level information of each water area from the ocean hydrological data through algorithm calculation;

[0031] The grading and scoring unit respectively corresponds the moving distance information and the meteorological warning level information to grade ranges, and obtains the scores of the grade ranges.

[0032] Further, the meteorological warning level information is the weighted average of the visibility warning level information of a first set multiple and the storm surge warning data of a second set multiple;

[0033] The first set multiple is obtained through algorithm calculation from the occurrence probability of grounding and ship collision accidents in the ocean hydrological data, and the second set multiple is obtained through algorithm calculation from the occurrence probability of hull capsizing in the ocean hydrological data.

[0034] Further, the factor scoring module includes a trajectory fitting unit;

[0035] If the trajectory fitting unit determines that the trajectory of the AIS data of the ship passing through the water area is discontinuous, it determines the passage time information and the moving distance information by connecting the two end points or extending the trajectory near one end point;

[0036] The factor scoring module includes an identity recognition unit;

[0037] When the identity recognition unit determines that the ship is carrying multiple AISs, it obtains the AIS data with the same identity as the ship's maritime mobile service identity code, and the factor scoring module extracts and grades the security factors of the AIS data with the same identity.

[0038] Further, the operation feedback module generates the risk range of the shipping route according to the magnitude ranking of multiple navigation safety scores of a ship on a shipping route.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows.

[0040] 1. By drawing on the idea of the analytic hierarchy process and combining the weight vector of the analytic hierarchy process and the safety score matrix based on AIS data and ocean hydrological data, the navigation safety score of the ship considering multiple water area characteristics is calculated jointly, and thus the accurate monitoring of the navigation safety level of the ship can be carried out.

[0041] 2. By using the expert scoring method to construct the judgment matrix of the analytic hierarchy process, the knowledge of experts in special fields is quantified, and thus the monitoring model can be more in line with the expert's experience and common sense. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the basic framework of the model based on the analytic hierarchy process according to an embodiment of the present invention;

[0043] Figure 2 It is a schematic diagram of the specific framework of the model based on the analytic hierarchy process according to an embodiment of the present invention;

[0044] Figure 3 It is a schematic diagram of the specific framework of the model based on the analytic hierarchy process according to another embodiment of the present invention;

[0045] Figure 4 It is a schematic diagram of the processing flow according to an embodiment of the present invention;

[0046] Figure 5 It is a schematic diagram of the scoring and grade scale of the first to third safety factors according to an embodiment of the present invention;

[0047] Figure 6 It is a schematic diagram of the scoring and grade scale of the third to fifth safety factors according to an embodiment of the present invention;

[0048] Figure 7 It is a schematic diagram of a calculation process according to an embodiment of the present invention;

[0049] Figure 8 It is a schematic diagram of a judgment matrix and weight vector constructed according to an embodiment of the present invention;

[0050] Figure 9Schematic diagram of a safety score matrix obtained from an embodiment of the present invention;

[0051] Figure 10 Schematic diagram of a set of navigation safety scores constructed according to an embodiment of the present invention. Detailed implementation manners

[0052] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0054] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0055] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0056] As Figures 1 to 10 shown, the present invention provides a ship monitoring system based on AIS data and ocean hydrological data. By using the expert scoring method to construct the judgment matrix of the analytic hierarchy process, the knowledge of experts in special fields is quantified, so that the monitoring model can better conform to the expert's experience and common sense; also by drawing on the idea of the analytic hierarchy process, combining the weight vector of the analytic hierarchy process and the safety score matrix based on AIS data and ocean hydrological data, the navigation safety score of the ship considering multiple water area characteristics is calculated jointly, and then the navigation safety degree of the ship can be accurately monitored.

[0057] Among them, Figure 1 is the schematic diagram of the basic framework of the model based on the analytic hierarchy process according to the embodiment of the present invention; Figure 2 is the schematic diagram of the specific framework of the model based on the analytic hierarchy process according to an embodiment of the present invention; Figure 3Schematic diagram of the specific framework of the model based on the analytic hierarchy process for another embodiment of the present invention; Figure 4 Schematic diagram of the processing flow of the embodiment of the present invention; Figure 5 Schematic diagram of the scoring and grade scale of the first to third safety factors in the embodiment of the present invention; Figure 6 Schematic diagram of the scoring and grade scale of the third to fifth safety factors in the embodiment of the present invention; Figure 7 Schematic diagram of a calculation process in the embodiment of the present invention; Figure 8 Schematic diagram of a judgment matrix and weight vector constructed in the embodiment of the present invention; Figure 9 Schematic diagram of a safety score matrix obtained in the embodiment of the present invention; Figure 10 Schematic diagram of a set of navigation safety scores constructed in the embodiment of the present invention.

[0058] Embodiment 1:

[0059] As Figures 1 to 10 shown, this embodiment proposes a ship monitoring system based on AIS data and ocean hydrological data.

[0060] As Figure 1 shown, the ship monitoring system includes a judgment matrix module, a factor scoring module, and an operation feedback module;

[0061] The judgment matrix module includes a model unit and a calculation unit. The model unit is equipped with a model based on the analytic hierarchy process. The target layer of the model is the navigation safety score, the criterion layer is multiple water areas, and the scheme layer is safety factors. The model obtains the first judgment matrix of each water area for the navigation safety score constructed by the expert scoring method, and the second judgment matrix of each safety factor for each water area. The calculation unit calculates the first weight vector of the first judgment matrix and the second weight vector of the second judgment matrix respectively;

[0062] The factor scoring module is used to obtain the AIS data and ocean hydrological data of the ship passing through the water area, extract and grade and score the safety factors for the AIS data and ocean hydrological data respectively, and obtain the safety score matrix of each safety factor in each water area;

[0063] The operation feedback module calculates the navigation safety score according to the first weight vector, the second weight vector, and the safety score matrix. The navigation safety score is used to monitor the navigation safety level of the routes in multiple water areas. The calculation formula of the navigation safety score is:

[0064] A = W A1 B 1 + W A2 B 2 + … + W Ai B i ;

[0065] In the formula, A is the navigation safety score, and W A1 to W Ai is the first weight vector, and B 1 to B i is the safety score from the first water area to the i-th water area;

[0066] Among them, the safety score B 1 to B i from the first water area to the i-th water area is calculated by the formula:

[0067]

[0068] In the formula, B 1 to B i is the safety score from the first water area to the i-th water area, and W B11 to W B1j are the elements of the sub-vector belonging to the first water area in the second weight vector, and W B21 to W B2j are the elements of the sub-vector belonging to the second water area in the second weight vector, and W Bi1 to W Bij are the elements of the sub-vector belonging to the i-th water area in the second weight vector, and C 11 to C i1 are the elements of the first safety factor in the safety score matrix from the first to the i-th water area, and C 12 to C i2 are the elements of the second safety factor in the safety score matrix from the first to the i-th water area, and C 1j to C ij are the elements of the j-th safety factor in the safety score matrix from the first to the i-th water area;

[0069] Among them, both i and j are greater than or equal to 3.

[0070] It should be noted that the marine hydrological data mentioned in this embodiment generally refers to comprehensive hydrological data related to the ocean, including but not limited to the physical properties of seawater in the narrow sense and the occurrence and development laws of various seawater movements. The source of the marine hydrological data is the Marine Science Data Center of the Chinese Academy of Sciences, the Marine Science Data Center of the European Academy of Sciences, or major marine data websites. Therefore, the marine hydrological data can be understood as data directly obtained from the above sources through a set data collection tool (such as a website data crawler) or a set program algorithm, such as ocean current data, meteorological data, and the number of occurrences of various accidents in each water area, as well as seawater temperature, salinity, density, transparency, water color, tides, waves, sea ice, coastal sediment, seawater chemical components, etc., all of which will affect navigation safety to varying degrees. Therefore, the present invention is not limited to specific data types, and the focus of the present invention lies in the calculation model (formula) of the navigation safety score.

[0071] Furthermore, the model unit includes a score acquisition sub-unit, a level acquisition sub-unit, and a calculation sub-unit; the acquisition sub-unit is used to acquire the first scoring grade of the importance of each water area to the navigation safety score judged by the expert group, and the second scoring grade of the safety importance of each safety factor to each water area; the level acquisition sub-unit acquires the weight grade of the academic level of each expert in the expert group; the calculation sub-unit calculates the first weighted average by calculating the first scoring grade and the weight grade, calculates the second weighted average by calculating the second scoring grade and the weight grade, divides the corresponding multiple first weighted averages to obtain the first judgment matrix, and divides the corresponding multiple second weighted averages to obtain the second judgment matrix.

[0072] Furthermore, the calculation unit includes an inspection sub-unit; the inspection sub-unit is used to calculate the maximum eigenvalue of the first judgment matrix and the second judgment matrix respectively, and analyze and judge whether the first judgment matrix and the second judgment matrix meet the consistency requirement according to the maximum eigenvalue and the consistency inspection formula of the analytic hierarchy process. If so, calculate the first weight vector and the second weight vector. If not, feedback to the score acquisition sub-unit, and the score acquisition sub-unit modifies the first scoring grade and the second scoring grade.

[0073] Specifically, the modification of the first scoring grade and the second scoring grade can be to reduce the set value of the maximum value of the weight grade and increase the set value of the minimum value. Then, recalculate the first weighted average, the second weighted average, the first judgment matrix, and the second judgment matrix, and judge whether the new first judgment matrix and the second judgment matrix meet the consistency requirement. Since the modified first weighted average and the second weighted average are more consistent, the first judgment matrix and the second judgment matrix constructed by them are more likely to meet the consistency requirement.

[0074] Furthermore, asFigure 2 As shown in the figure, the factor scoring module includes an extraction unit and a grading and scoring unit; the extraction unit calculates and extracts at least the ocean current flow direction information of each water area in the ocean hydrological data, the passing time information, the speed information of each water area in the AIS data, and the course information of the ship; the safety factors at least include the first safety factor to the third safety factor, which are the drift angle difference information, the passing time information, and the speed information calculated from the course information and the ocean current flow direction information respectively; the grading and scoring unit corresponds the drift angle difference information, the passing time information, and the speed information to the grade ranges respectively, obtains the scores of the grade ranges, and constructs the safety score matrix according to the multiple scores.

[0075] It should be noted that the process of calculating and extracting by the algorithm described in this embodiment is a conventional data processing process, that is, the corresponding safety factors can be automatically extracted according to the relevant fields of the AIS data and the ocean hydrological data.

[0076] It can be understood that the drift angle difference is the angle difference between the ocean current flow direction and the course in navigation, and the drift angle difference directly affects the ship's speed and track. Sailing with the current can increase the speed, saving both time and fuel; sailing against the current is the opposite. Sailing across the current will deviate from the planned course. If not corrected in time, it will not only increase the sailing time, but also easily cause accidents.

[0077] Furthermore, the speed information includes the instant speed, the average speed, and the average economic speed;

[0078] The grading and scoring unit is equipped with a speed ratio calculation formula, specifically:

[0079]

[0080] In the formula, P is the speed ratio, V e is the average economic speed, is the average speed, and the average speed is the average value of multiple instant speeds;

[0081] The grading and scoring sub-unit corresponds the speed ratio to the grade range and obtains the score of the grade range.

[0082] Furthermore, as Figure 3 shown, the safety factors further include a fourth safety factor and a fifth safety factor, which are the moving distance information and the meteorological warning level information respectively; the extraction unit further calculates and extracts the moving distance information of the ships in each water area in the AIS data and the meteorological warning level information in each water area in the ocean hydrological data through the algorithm; the grading and scoring unit corresponds the moving distance information and the meteorological warning level information to the grade ranges respectively and obtains the scores of the grade ranges.

[0083] Further, the meteorological warning level information is the weighted average of the visibility warning level information of the first set multiple and the storm surge warning data of the second set multiple; the first set multiple is calculated by an algorithm based on the occurrence probability of grounding and ship collision accidents in the marine hydrological data, and the second set multiple is calculated by an algorithm based on the occurrence probability of hull capsizing in the marine hydrological data.

[0084] Specifically, the occurrence probability can be directly obtained from the source of the marine hydrological data through a set data collection tool (such as a website data crawler) or a set algorithm program, or the occurrence times of the corresponding accidents can be extracted by conventional keyword recognition, and the occurrence probability of accidents in each water area in a month, a quarter or a year can be obtained by dividing the occurrence times by the extraction duration.

[0085] Specifically, the first set multiple and the second set multiple can be adjusted according to the time correlation between the occurrence time of the corresponding accident and the time when the ship passes through this water area. For example, if a grounding, ship collision or hull capsizing accident occurs in the week or month before the ship passes through this water area, it means that this water area is more likely to have accidents due to low visibility, and due to the cooperation of storm surge and terrain, the sea waves are likely to generate rapid currents or vortices, and at this time, the first set multiple and the second set multiple are directly set to the maximum value.

[0086] Further, the factor scoring module includes a trajectory fitting unit; if the trajectory of the AIS data of the ship passing through this water area is determined to be discontinuous by the trajectory fitting unit, the passing time information and the moving distance information are determined by connecting the two end points or extending the trajectory near one end point.

[0087] The factor scoring module includes an identity recognition unit; when the identity recognition unit determines that the ship carries multiple AISs, it obtains the AIS data with the same identity as the ship's Maritime Mobile Service Identity (MMSI), and the factor scoring module extracts and classifies and scores the safety factors of the AIS data with the same identity.

[0088] It can be understood that if the ship carries multiple AISs for identity transformation, the AIS data with the same identity can be combined by combining the corresponding relationship between the ship's Maritime Mobile Service Identity (MMSI) and the real identity, so as to obtain accurate AIS data.

[0089] If a ship passes through sensitive waters with AIS turned off, the ship's AIS data cannot be obtained. However, considering that the sensitive waters are relatively small and the routes are relatively busy, ships will turn on AIS for safety reasons. Therefore, AIS data of various ships in the sensitive waters can generally be obtained, but due to the lack of AIS data outside the sensitive waters, the ship's trajectory is discontinuous; therefore, when processing the ship's passing time information and movement distance information, it is necessary to extend the trajectory through fitting to obtain accurate data.

[0090] Furthermore, the calculation feedback module generates a risk range of the route according to the order of multiple navigation safety scores of a ship in a route.

[0091] In a specific embodiment, the model is Figure 1 As shown in the figure: the first to third layers from top to bottom are the target layer, criterion layer and solution layer respectively, which are based on the idea of ​​hierarchical analysis method. The difference from the existing framework of hierarchical analysis method is that the calculation of the target layer is not obtained by multiplying the two feature weight vectors of the two judgment matrices of the target layer-criterion layer and the criterion layer-solution layer, but by multiplying the safety score matrix based on AIS and ocean hydrological data with the two feature weight vectors step by step, and the expert scoring method is used to construct the judgment matrix.

[0092] The feature weight vector is the feature vector of the judgment matrix.

[0093] The scoring rules of the expert scoring method are as follows:

[0094] 1. Questionnaire on the importance of each safety factor to navigation safety in each water area. The importance of each safety factor is divided into five levels, namely: very important, very important to not very important, and the corresponding scores are 9 to 1. Among them, very important means that the value of a certain safety factor will greatly characterize the safety behavior of ships in a certain water area, and not very important means that the value of a certain safety factor is difficult to characterize the safety behavior of ships in a certain water area.

[0095] 2. Questionnaire on the importance of each water area to navigation safety score. The importance of each sensitive water area is divided into 4 levels, namely: very important, relatively important, generally important to not very important, and the corresponding scores are 8 to 1. Among them, very important means that the safety value of a ship in a certain water area will greatly characterize the safety behavior of the ship, that is, it can be clearly seen in this water area whether the operation status of the ship is normal; not very important means that the abnormal value of a ship in a certain water area is difficult to characterize the safety behavior of the ship.

[0096] The consistency check of the judgment matrix can be a conventional calculation process of the hierarchical analysis method, preferably through the following formula:

[0097] CI=(λ max-(n) / (n - 1)

[0098] CR = CI / RI;

[0099] Where CI is the consistency index; λ max is the maximum eigenvalue of the judgment matrix; n is the number of water areas; RI is the average random consistency index; CR is the consistency ratio. The value of RI is a fixed constant and can be obtained by querying the average random consistency index value table using the analytic hierarchy process.

[0100] The safety factors described in this embodiment include:

[0101] The weighted average of the visibility level and wind speed, used to characterize the meteorological safety degree of a certain water area.

[0102] Passing time, used to characterize the time for a ship to pass through this water area. When a ship sails in open water, it usually sails at a constant speed in a straight line. If the passing time of a ship in a certain water area is too long, there may be abnormal navigation trajectory behaviors.

[0103] Speed ratio, used to characterize whether the ship's speed is within a reasonable range. The speed of a ship sailing normally in open water usually maintains within the most economical and reasonable range. Exceeding or falling below this range will lead to increased costs and may pose navigation risks. The speed ratio is defined as the magnitude of the deviation of the ship's average speed from the economic speed range divided by the average economic speed.

[0104] Moving distance, used to characterize the complexity of the water area's track.

[0105] Ocean current velocity, used to characterize the impact of ocean currents on navigation. When sailing downstream, the ship speed is fast; when sailing upstream, the ship speed is slow.

[0106] Figure 5 gives the scores and grade scales of the first to third safety factors.

[0107] Figure 6 gives the scores and grade scales of the third to fifth safety factors.

[0108] Figure 7 gives a calculation process of this embodiment.

[0109] In a specific implementation manner of this embodiment, as Figure 2 shown in the figure, where i = j = 3, the calculation formula for the navigation safety scores of the first to third safety factors in the first to third water areas is:

[0110] A = W A1 B 1 + W A2 B 2 + W A3 B3 ;

[0111] Wherein, A is the navigation safety score, and W A1 to W A3 is the first weight vector, and B 1 to B 3 are the safety scores of the first water area to the third water area;

[0112] Among them, the safety scores B 1 to B i from the first water area to the i-th water area are calculated by the following formula:

[0113]

[0114] Wherein, B 1 to B 3 are the safety scores of the first water area to the third water area, W B11 to W B13 are the elements of the sub-vector belonging to the first water area in the second weight vector, W B21 to W B23 are the elements of the sub-vector belonging to the second water area in the second weight vector, W B31 to W B33 are the elements of the sub-vector belonging to the third water area in the second weight vector, C 11 to C 31 are the elements of the safety score matrix of the first safety factor in the first to third water areas, C 12 to C 32 are the elements of the safety score matrix of the second safety factor in the first to third water areas, C 13 to C 33 are the elements of the safety score matrix of the third safety factor in the first to third water areas.

[0115] In a specific application, the results as shown in Figures 8 to 10 can be obtained, and then it can be concluded that the navigation of Ship 1 is relatively unsafe. It can be understood that the method described in this embodiment can also be used for a ship's route passing through multiple selected water areas, grouping the multiple selected water areas, calculating multiple navigation safety scores respectively, and then judging the relative risk points of the ship during navigation.

[0116] It is understandable that this embodiment reduces the complexity of anomaly detection caused by overlapping levels due to different safety monitoring situations in different waters; the feature matrix is established by the expert scoring method and the influence factor scoring table is constructed, which solves the problem that it is difficult to quantify expert experience and factors in ship safety behavior detection. The ship abnormal behavior detection framework based on AIS data and marine hydrological data can quickly and accurately detect the navigation safety level of ships, providing intelligence support for subsequent monitoring of whether the ships are in a normal navigation state.

[0117] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0118] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A ship monitoring system based on AIS data and oceanographic data, characterized in that: It includes judgment matrix module, factor scoring module and operation feedback module; The judgment matrix module includes a model unit and a calculation unit. The model unit carries a model based on the hierarchical analysis method. The target layer of the model is the navigation safety score, the criterion layer is multiple water areas, and the solution layer is the safety factor. The model uses the expert scoring method to construct a first judgment matrix of each water area for the navigation safety score, and a second judgment matrix of each safety factor for each water area. The calculation unit calculates the first weight vector of the first judgment matrix and the second weight vector of the second judgment matrix respectively. The factor scoring module is used to obtain AIS data and oceanographic data of ships passing through the waters, extract and grade safety factors of the AIS data and oceanographic data, and obtain a safety score matrix of each safety factor in each water. The operation feedback module calculates a navigation safety score according to the first weight vector, the second weight vector and the safety score matrix, and the navigation safety score is used to monitor the navigation safety level of multiple waters; The factor scoring module includes an extraction unit and a grading scoring unit; The extraction unit extracts at least the ocean current direction information of each water area in the ocean hydrological data, the passing time information, speed information and the heading information of the ship in each water area in the AIS data through algorithm calculation; The safety factors include at least a first safety factor to a third safety factor, which are respectively flow pressure difference information, passing time information and speed information calculated from the heading information and the ocean current direction information; The grading scoring unit corresponds the flow pressure difference information, the passing time information and the speed information to grade ranges respectively, obtains the scores of the grade ranges, and constructs the safety score matrix according to the multiple scores; The factor scoring module includes a trajectory fitting unit; If the trajectory fitting unit determines that the trajectory of the AIS data of the ship passing through the water area is discontinuous, the passing time information and the moving distance information are determined by connecting two end points or extending the trajectory near one end point; The factor scoring module includes an identity recognition unit; When the identity recognition unit determines that the ship carries multiple AIS, it obtains AIS data with the same identity as the ship's water mobile service identification code, and the factor scoring module extracts and grades the security factors of the AIS data with the same identity.

2. The ship monitoring system based on AIS data and ocean hydrological data according to claim 1, characterized in that: The calculation formula of the navigation safety score is: ； Where A is the navigation safety score, to is the first weight vector, to The safety scores from the first water area to the i-th water area; Among them, the safety scores of the first water area to the i-th water area to The calculation formula is: ； In the formula, to is the safety score from the first water area to the i-th water area, to is the element of the component vector belonging to the first water area in the second weight vector, to is the element of the component vector belonging to the second water area in the second weight vector, to is the element of the component vector belonging to the i-th water area in the second weight vector, to is the element of the safety score matrix of the first safety factor in the first to i-th water areas, to is the element of the safety score matrix of the second safety factor in the first to the i-th water area, to is the element of the safety score matrix of the jth safety factor in the first to the ith water area; Among them, i and j are both greater than or equal to 3.

3. The ship monitoring system based on AIS data and ocean hydrological data according to claim 1, characterized in that: The model unit includes a score acquisition subunit, a level acquisition subunit and a calculation subunit; The score acquisition subunit is used to acquire the first score level of the importance of each water area to the navigation safety score judged by the expert group, and the second score level of the safety importance of each safety factor to the safety of each water area; The level acquisition subunit acquires the weight level of the academic level of each expert in the expert group; The calculation subunit calculates the first scoring level and the weight level to obtain a first weighted average, calculates the second scoring level and the weight level to obtain a second weighted average, divides multiple first weighted averages correspondingly to obtain a first judgment matrix, and divides multiple second weighted averages correspondingly to obtain a second judgment matrix.

4. The ship monitoring system based on AIS data and ocean hydrological data according to claim 3, characterized in that: The computing unit includes a verification subunit; The verification subunit is used to calculate the maximum eigenvalues ​​of the first judgment matrix and the second judgment matrix respectively, and analyze and judge whether the first judgment matrix and the second judgment matrix meet the consistency requirements according to the consistency verification formula of the maximum eigenvalues ​​and the hierarchical analysis method. If so, the first weight vector and the second weight vector are calculated. If not, feedback is given to the score acquisition subunit, and the score acquisition subunit modifies the first score level and the second score level.

5. The ship monitoring system based on AIS data and ocean hydrological data according to claim 1, characterized in that: The speed information includes instantaneous speed, average speed and average economic speed; The grading and scoring unit obtains a speed ratio according to the instant speed, corresponds the speed ratio to a grade range, and obtains a score for the grade range.

6. The ship monitoring system based on AIS data and ocean hydrological data according to claim 1, characterized in that: The safety factors also include a fourth safety factor and a fifth safety factor, which are respectively movement distance information and weather warning level information; The extraction unit also extracts the movement distance information of the ships in each water area in the AIS data and the weather warning level information of each water area in the ocean hydrological data through algorithm calculation; The grading and scoring unit corresponds the moving distance information and the weather warning level information to level ranges respectively to obtain scores for the level ranges.

7. The ship monitoring system based on AIS data and ocean hydrological data according to claim 6, characterized in that: The meteorological warning level information is a weighted average of the visibility warning level information of a first set multiple and the storm surge warning data of a second set multiple; The first set multiple is obtained by calculating the probability of a ship-running-against-reef accident in the ocean hydrological data through an algorithm, and the second set multiple is obtained by calculating the probability of a ship-hull capsizing in the ocean hydrological data through an algorithm.

8. The ship monitoring system based on AIS data and oceanographic data according to any one of claims 1 to 7, characterized in that: The operation feedback module generates a risk range of the route by sorting multiple navigation safety scores of a ship in a route.

Images