Ship accompanying motion pattern mining method, system, device and storage medium

Abstract

The present application relates to a kind of ship accompanying movement mode mining method, system, equipment and storage medium, ship accompanying movement mode mining method includes: preliminary construction movement object set Ai;Based on space position setting buffer zone, screen out potential accompanying point set S in buffer zone and the movement object set T1 corresponding to potential accompanying point;Based on time point position, obtain movement object set T2;Whether one movement object of movement object set T2 at any time point position meets accompanying point condition with Ai is calculated, and the number r of point position that meets condition is counted;According to the number r of point position and preset point number m, it is judged whether corresponding movement object T2i exists accompanying movement with Ai, if yes, then corresponding T2i is stored in accompanying movement result set.The present application, shorten the time-consuming of accompanying mode mining analysis, is conducive to the quick use of accompanying mode mining analysis, meet the need of quick mining of movement object accompanying mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of spatiotemporal trajectory data mining, and particularly relates to a ship accompanying movement mode mining method and system, equipment and a storage medium. BACKGROUND

[0002] With the development of mobile Internet and big data technology, and the wide application of satellite navigation positioning equipment and mobile location services, a large amount of track point data is generated by moving objects, which is collectively referred to as spatiotemporal trajectory data. With the development of the water transportation industry, in order to ensure the safe navigation of ships, the International Maritime Organization, the International Navigation Association and the International Telecommunication Union strongly promote the installation of automatic identification systems (AIS) on various ships for identification and tracking of various ships. The widespread application of the automatic identification system of ships has generated a large amount of spatiotemporal trajectory data of water surface ships.

[0003] The research content of spatiotemporal trajectory mode mainly includes frequent pattern mining, abnormal pattern mining, clustering pattern mining and accompanying pattern mining. Frequent pattern mining mainly mines regular behavior patterns of humans. Abnormal pattern mining usually mines "infrequent" behavior patterns that are opposite to frequent patterns, and has wide application in the field of intelligent transportation. Unlike hot spot discovery, clustering pattern mining mines human behavior patterns and discovers hot streets or shopping malls. Accompanying patterns are an important content of spatiotemporal trajectory patterns, and have wide application in mining groups of mobile objects with the same or similar movement patterns and studying the closeness between objects in the group. A group of mobile objects exhibits the same or similar movement patterns, and the patterns are maintained for a long enough time, then the patterns can be considered as accompanying patterns, and all accompanying patterns can generate spatiotemporal trajectories.

[0004] There are generally two processing methods for frequent pattern mining of spatiotemporal trajectories. The first method is to take multiple trajectory sequences as the processing object, and to mine meaningful frequent patterns by calculating the similarity between trajectories. This method needs to consider how to define the distance between trajectories. According to the time interval involved in similarity measurement, similarity measurement can be divided into full-time interval corresponding similarity, full-time interval transformation corresponding similarity, multiple sub-interval corresponding similarity, single sub-interval corresponding similarity, single point corresponding similarity and no interval corresponding similarity. The second method first preprocesses the trajectory sampling point sequence into corresponding entity sequence, i.e. POI (point of interest) sequence, and then mines frequent patterns.

[0005] The spatio-temporal trajectory data has rich spatio-temporal feature information, and the activity rule and behavior characteristics can be mined based on the data mining technology, including flight path extraction, trajectory classification, trajectory anomaly detection, trajectory pattern mining and the like. The trajectory pattern mining mainly studies how to discover the motion pattern of the moving object from a large amount of trajectory data. The accompanied motion pattern mining is one of the trajectory pattern mining, and mainly studies the group co-occurrence behavior rule and characteristics of multiple moving objects at multiple time points. The accompanied motion pattern mining has important application value in the fields of military surveillance, species migration, traffic event detection and the like.

[0006] In 2013, Zheng Yu applied the concept of Travelling Buddy to more complex scenarios on the basis of the original research, and the experiment showed that the mining algorithm based on Travelling Buddy has higher time efficiency than the existing accompanied pattern mining algorithm.

[0007] In 2008, the CMC algorithm for mining Convoy pattern proposed by Hoyoung Jeung and Zhou Xiaofang and the like is one of the most classic algorithms, and the algorithm idea deeply influences many subsequent accompanied pattern mining algorithms. However, the algorithm has low time efficiency, and may incorrectly judge the spatio-temporal trajectory pattern formed by the moving object group staying in a fixed area as the accompanied pattern. In addition, the algorithm requires that the sampling intervals of all moving objects are the same, and this condition is difficult to meet in real life.

[0008] In 2012, the accompanied pattern mining algorithm based on Travelling Buddy proposed by Zheng Yu and the like has greatly improved the time efficiency compared with the previous algorithm, but has not optimized the performance in the current big data environment. When facing big data, the time consumption of the algorithm and other existing algorithms will be unacceptable. For example, a client needs to mine the accompanied pattern hidden in the spatio-temporal data collected in one year or even several years in a short time, and the existing algorithm will not be able to complete the task. In the current production and life, there is a huge demand for real-time accompanied pattern mining, and obviously the existing algorithm cannot meet the actual needs.

[0009] In summary, for each time point position of a given moving object, it is necessary to traverse all other moving objects to search whether the time point is an accompanied point, and the search space is large, the calculation amount is large, the time consumption is long, and the main problem of the accompanied pattern mining is that the existing computing power is insufficient to support the timely mining and analysis of the accompanied motion pattern. SUMMARY

[0010] To solve the technical problems existing in the prior art, the purpose of the present application is to provide a ship accompanying motion pattern mining method, system, device and storage medium, which shortens the time-consuming of accompanying pattern mining analysis and meets the need of rapid mining of accompanying patterns of moving objects.

[0011] To achieve the above-mentioned purpose of the application, the technical scheme of the present application is:

[0012] The present application provides a ship accompanying motion pattern mining method, comprising the following steps:

[0013] Step S1, initially constructing a moving object set Ai;

[0014] Step S2, setting a buffer zone based on spatial position, screening out a set of potential accompanying points S in the buffer zone and a set of moving objects T1 corresponding to the potential accompanying points;

[0015] Step S3, obtaining a set of moving objects T2 based on time point position;

[0016] Step S4, calculating whether a moving object in the set of moving objects T2 at any time point position satisfies the accompanying point condition with Ai, and counting the number r of point positions satisfying the condition;

[0017] Step S5, judging whether the corresponding moving object T2i exists in the accompanying motion with Ai according to the number r of point positions and a preset number m of point positions, and if so, storing the corresponding T2i in an accompanying motion result set.

[0018] According to one aspect of the present application, before the step S3, an attention mechanism is introduced to update the set of moving objects T1 with a key target chain.

[0019] According to one aspect of the present application, in the step S1, it comprises:

[0020] In a time period with a time range of Ts-Te, n moving objects contained in the space-time trajectory data are acquired, a set of moving objects Ai, i = 1, 2, …, n is determined, and a preset number m of point positions is set.

[0021] According to one aspect of the present application, in the step S2, it comprises:

[0022] Step S21, determining a track of a moving object Ai in the time range Ts-Te;

[0023] Step S22, setting a region with a radius d as a buffer zone along the track of the moving object Ai;

[0024] Step S23, screening out a set of potential accompanying points S in the buffer zone and a set of moving objects T1 corresponding to the potential accompanying points.

[0025] According to an aspect of the present application, in the step S3, specifically comprising:

[0026] Step S31, determining one moving object T1i in the moving object set Ti;

[0027] Step S32, judging whether the number of falling into the potential accompanying point set S of the moving object T1i is greater than a preset threshold p;

[0028] Step S32, if yes, adding the corresponding moving object T1i into the update set T2.

[0029] According to an aspect of the present application, in updating the moving object set T1 with the key target chain, specifically comprising:

[0030] Step S25, dividing the detection target into the key target chain and the non-key target chain;

[0031] Step S26, setting the calculation buffer corresponding to the key target chain and the sink buffer corresponding to the non-key target chain;

[0032] Step S27, traversing the moving object set T1, and calculating the calculation buffer and the sink buffer;

[0033] Step S28, updating the buffer with the calculation buffer.

[0034] According to an aspect of the present application, in the step S27, the formula for calculating the calculation buffer HA and the sink buffer HB is:

[0035]

[0036]

[0037] Wherein, Δσ is the average analysis time, and Tlink is the key target chain.

[0038] According to an aspect of the present application, a ship accompanying moving mode mining system is provided, comprising:

[0039] A construction unit is configured to initially construct a moving object set Ai;

[0040] A screening unit is configured to set a buffer based on a spatial position, screen out a potential accompanying point set S in the buffer and a moving object set T1 corresponding to the potential accompanying point;

[0041] A calculation unit is configured to obtain a moving object set T2 based on a time point position;

[0042] The calculation unit is further configured to calculate whether a moving object in the moving object set T2 satisfies an accompanying point condition with Ai at any time point position, and count the number r of the point positions satisfying the condition.

[0043] A judging unit is configured to judge whether the corresponding moving object T2i has the accompanying motion with Ai according to the point number r and the preset point number m, and if yes, the corresponding T2i is stored in the accompanying motion result set.

[0044] According to an aspect of the present application, an electronic device is provided, comprising one or more processors, one or more memories, and one or more computer programs; wherein the processor is connected with the memory, the one or more computer programs are stored in the memory, and when the electronic device is running, the processor executes the one or more computer programs stored in the memory, so that the electronic device executes a ship accompanying motion pattern mining method as described in any of the above technical solutions.

[0045] According to an aspect of the present application, a computer readable storage medium is provided for storing computer instructions, which, when executed by a processor, implement a ship accompanying motion pattern mining method as described in any of the above technical solutions.

[0046] Compared with the prior art, the present application has the following beneficial effects:

[0047] According to an aspect of the present application, through buffer area analysis, a moving object set in the buffer area is screened out from all spatiotemporal trajectories, and then the moving object set and the accompanying point that satisfy the accompanying motion condition are sought in a traversal manner, and the buffer area is updated in time and space, the search space is reduced, the calculation amount is reduced, the time consumption of the accompanying pattern mining analysis is shortened, and the rapid availability of the accompanying pattern mining analysis is improved, thereby meeting the rapid mining needs of the accompanying pattern of the moving object. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0049] Figure 1 A flow chart of a ship accompanying motion pattern mining method provided by an embodiment of the present application is schematically shown;

[0050] Figure 2 A flow chart of a ship accompanying motion pattern mining method provided by an embodiment of the present application is schematically shown;

[0051] Figure 3 A structure schematic diagram of a ship accompanying motion pattern mining system provided by an embodiment of the present application is schematically shown. Detailed Implementation

[0052] The description of the embodiments in this specification should be taken in conjunction with the accompanying drawings, which should form part of the complete specification. In the drawings, the shape or thickness of the embodiments may be exaggerated and may be indicated in a simplified or convenient manner. Furthermore, parts of the various structures in the drawings will be described separately; it is worth noting that elements not shown in the figures or not described in words are in a form known to those skilled in the art.

[0053] The descriptions of the embodiments herein, including any references to directions and orientations, are for ease of description only and should not be construed as limiting the scope of the invention. The following description of preferred embodiments involves combinations of features, which may exist independently or in combination; the invention is not particularly limited to the preferred embodiments. The scope of the invention is defined by the claims.

[0054] like Figures 1 to 2 As shown, a method for mining ship accompaniment motion patterns according to the present invention includes the following steps:

[0055] Step S1: Initially construct the set of moving objects Ai;

[0056] Step S2: Set up a buffer based on spatial location, and filter out the set S of potential accompanying points and the set T1 of moving objects corresponding to the potential accompanying points within the buffer.

[0057] Step S3: Obtain the set of moving objects T2 based on the location at the time point;

[0058] Step S4: Calculate whether the position of a moving object in the set T2 at any time satisfies the associated point condition with Ai, and count the number of points r that satisfy the condition.

[0059] Step S5: Based on the number of points r and the preset number of points m, determine whether the corresponding moving object T2i has a companion motion with Ai. If so, store the corresponding T2i in the companion motion result set.

[0060] In this embodiment, by using buffer analysis, a set of moving objects within the buffer is selected from all spatiotemporal trajectories. Then, by traversing the buffer, a set of moving objects and their associated points that satisfy the conditions for accompanying motion are sought. The buffer is updated in both time and space, reducing the search space and computational load, thereby shortening the time required for accompanying pattern mining analysis. This is beneficial for improving the rapid availability of accompanying pattern mining analysis and meeting the need for rapid mining of accompanying patterns of moving objects.

[0061] In an embodiment of the present application, preferably, before the step S3, an attention mechanism is introduced to update the moving object set T1 with the key target chain.

[0062] In this embodiment, the attention mechanism is introduced to divide the moving objects in the moving object set into key targets and non-key targets, thereby forming a key target chain and a non-key target chain, which can optimize the update of the moving object set and reduce the amount of data.

[0063] For example, in the process of buffer update, taking the track of a ship target as an example, other moving objects such as battleships, cruisers, destroyers, and frigates can be set as key targets, and objects such as bulk carriers, bulk cargo ships, container ships, and fishing boats can be set as non-key targets.

[0064] In an embodiment of the present application, preferably, in the step S1, the following steps are included:

[0065] In a time period with a time range of Ts-Te, n moving objects are obtained in the space-time trajectory data, a moving object set Ai, i = 1, 2, …, n is determined, and a preset number of points m is set.

[0066] In an embodiment of the present application, preferably, in the step S2, the following steps are included:

[0067] Step S21, determining a track of a moving object Ai in a time range of Ts-Te;

[0068] Step S22, setting a region with a radius of d as a buffer zone along the track of the moving object Ai;

[0069] Step S23, screening out a set of potential companion points S in the buffer zone and a moving object set T1 corresponding to the potential companion points.

[0070] In an embodiment of the present application, preferably, in the step S3, the following steps are included:

[0071] Step S31, determining a moving object T1i in the moving object set Ti;

[0072] Step S32, judging whether the number of the moving object T1i falling into the set of potential companion points S is greater than a preset threshold p;

[0073] Step S32, if yes, the corresponding moving object T1i is added to the update set T2.

[0074] In the embodiment, one of the moving objects T1i in the moving object set Ti, on the trajectory of the moving object T1i, there are multiple points in the accompanying point set S based on the time point. Whether the number of points of the trajectory corresponding to the moving object T1i in the accompanying point set S is greater than the preset threshold p is judged, so as to eliminate the moving object that does not meet the accompanying motion.

[0075] Wherein, the value of p should meet: p≤m, m is a preset point number.

[0076] In an embodiment of the present application, preferably, in updating the moving object set T1 with the key target chain, specifically includes:

[0077] Step S25, the detection target is divided into a key target chain and a non-key target chain;

[0078] Step S26, setting the calculation buffer corresponding to the key target chain and the sink buffer corresponding to the non-key target chain;

[0079] Step S27, traversing the moving object set T1, and calculating the calculation buffer and the sink buffer;

[0080] Step S28, updating the buffer with the calculation buffer.

[0081] In an embodiment of the present application, preferably, in the step S27, the formula for calculating the calculation buffer HA and the sink buffer HB is:

[0082]

[0083]

[0084] Wherein, Δσ is the average analysis time, and Tlink is the key target chain.

[0085] As Figure 3 shown, according to one aspect of the present application, a ship accompanying motion pattern mining system is provided, comprising:

[0086] A construction unit is configured to initially construct a moving object set Ai;

[0087] A screening unit is configured to set a buffer based on a spatial position, screen out a potential accompanying point set S in the buffer and a moving object set T1 corresponding to the potential accompanying point;

[0088] A calculation unit is configured to obtain a moving object set T2 based on a time point position;

[0089] The calculation unit is further configured to calculate whether a moving object in the moving object set T2 at any time point meets the accompanying point condition with Ai, and count the number r of points meeting the condition.

[0090] A judging unit is configured to judge whether the corresponding moving object T2i has the accompanying motion with Ai according to the point number r and the preset point number m, and if yes, the corresponding T2i is stored in the accompanying motion result set.

[0091] According to an aspect of the present application, an electronic device is provided, comprising one or more processors, one or more memories, and one or more computer programs; wherein the processor is connected with the memory, and the one or more computer programs are stored in the memory, and when the electronic device is running, the processor executes the one or more computer programs stored in the memory, so that the electronic device executes the ship accompanying motion pattern mining method according to any one of the above technical solutions.

[0092] According to an aspect of the present application, a computer readable storage medium is provided for storing computer instructions, and when the computer instructions are executed by a processor, the ship accompanying motion pattern mining method according to any one of the above technical solutions is realized.

[0093] The ship accompanying motion pattern mining method, system, device and storage medium provided by the present application, the ship accompanying motion pattern mining method comprises: initially constructing a moving object set Ai; setting a buffer based on a spatial position, screening out a potential accompanying point set S in the buffer and a moving object set T1 corresponding to the potential accompanying point; obtaining a moving object set T2 based on a time point position; calculating whether a moving object in the moving object set T2 satisfies an accompanying point condition at any time point position, and counting a point number r satisfying the condition; judging whether the corresponding moving object T2i has the accompanying motion with Ai according to the point number r and a preset point number m, and if yes, the corresponding T2i is stored in an accompanying motion result set. Through buffer analysis, the moving object set in the buffer is screened out from all spatio-temporal trajectories, and then the moving object set and the accompanying point position satisfying the accompanying motion condition are sought in a traversal manner, the buffer is updated in time and space, the search space is reduced, the calculation amount is reduced, the time consumption of the accompanying pattern mining analysis is shortened, and the rapid availability of the accompanying pattern mining analysis is improved, so that the rapid mining needs of the accompanying pattern of the moving object are met.

[0094] In addition, it should be noted that the present application can be provided as a method, device or computer program product. Therefore, the embodiments of the present application can adopt a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present application can adopt the form of a computer program product implemented on one or more computer usable storage media containing computer usable program codes.

[0095] The embodiments of the present application are described with reference to the flowchart illustrations and / or block diagrams of the methods, terminal devices (systems) and computer program products according to embodiments of the present application. 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, or other programmable data processing terminal devices to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal devices, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0096] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal devices to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the function specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. These computer program instructions can also be loaded onto a computer or other programmable data processing terminal devices, such that a series of operational steps are performed on the computer or other programmable terminal devices to create a computer implemented process so that the instructions executed on the computer or other programmable terminal devices provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0097] It should also be noted that, in the present text, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, such that processes, methods, articles, or terminal devices that include a series of elements not only include those elements, but also include other elements not explicitly listed, or other elements inherent to such processes, methods, articles, or terminal devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0098] Finally, it should be noted that the above description is of preferred embodiments of the application, and that although preferred embodiments of the application have been described, numerous changes and modifications can be made to the preferred embodiments without departing from the principles of the application, and that such changes and modifications are contemplated as falling within the scope of the application. Accordingly, the appended claims are intended to embrace all such changes and modifications.

Claims

1. A ship-following motion pattern mining method characterized by comprising: The method comprises the following steps: Step S1, initially constructing a moving object set Ai; Step S2, setting a buffer zone based on a spatial position, screening out a set of potential accompanying points S in the buffer zone and a set of moving objects T1 corresponding to the potential accompanying points; Step S3, obtaining a moving object set T2 based on a time point position; Step S4, calculating whether a moving object in the moving object set T2 satisfies an accompanying point condition with Ai at any time point position, and counting the number r of point positions that satisfy the condition; Step S5, judging whether the corresponding moving object T2i exists in accompanying motion with Ai according to the number r of point positions and a preset number m of point positions, and if so, storing the corresponding T2i in an accompanying motion result set; In the step S2, the following steps are included: Step S21, determining a track of a moving object Ai within a time range Ts-Te; Step S22, setting a region with a radius d as a buffer zone along the track of the moving object Ai; Step S23, screening out a set of potential accompanying points S in the buffer zone and a set of moving objects T1 corresponding to the potential accompanying points; Before the step S3, a attention mechanism is introduced to update the moving object set T1 with a key target chain; In the step of updating the moving object set T1 with a key target chain, the following steps are included: Step S25, dividing detected targets into a key target chain and a non-key target chain; Step S26, setting a calculation buffer zone corresponding to the key target chain and a merging buffer zone corresponding to the non-key target chain; Step S27, traversing the moving object set T1 to calculate the calculation buffer zone and the merging buffer zone; Step S28, updating the buffer zone with the calculation buffer zone; In the step S3, the following steps are included: Step S31, determining a moving object T1i in the moving object set T1; Step S32, judging whether the number of the moving object T1i falling into the set of potential accompanying points S is greater than a preset threshold p; Step S32, if so, adding the corresponding moving object T1i into an updated set T2.

2. The ship's attendant motion pattern excavation method according to claim 1, characterized by, In the step S1, the following steps are included: In a time period with a time range Ts-Te, n moving objects contained in spatio-temporal trajectory data are acquired, a moving object set Ai is determined, i=1, 2, …, n, and a preset number m of point positions is set.

3. A shipboard motion pattern mining system for implementing the shipboard motion pattern mining method according to any one of claims 1 to 2, characterized by It comprises: A construction unit is configured to initially construct a moving object set Ai; A screening unit is configured to set a buffer zone based on a spatial position, screen out a set of potential accompanying points S in the buffer zone and a set of moving objects T1 corresponding to the potential accompanying points; A calculation unit is configured to obtain a moving object set T2 based on a time point position; The calculation unit is further configured to calculate whether a moving object in the moving object set T2 satisfies an accompanying point condition with Ai at any time point position, and count the number r of point positions that satisfy the condition; A judgment unit is configured to judge whether the corresponding moving object T2i exists in accompanying motion with Ai according to the number r of point positions and a preset number m of point positions, and if so, store the corresponding T2i in an accompanying motion result set.

4. An electronic device, comprising: It comprises: One or more processors, one or more memories, and one or more computer programs; wherein the processors are connected with the memories, and the one or more computer programs are stored in the memories, and when the electronic device is running, the processors execute the one or more computer programs stored in the memories, so that the electronic device executes the ship accompanying motion pattern mining method as claimed in any one of claims 1 to 2.

5. A computer readable storage medium, characterized in that, A computer program product for storing computer instructions, which, when executed by a processor, implement the ship accompanying motion pattern mining method as claimed in any one of claims 1 to 2.

Images