Abnormal equipment detection method and device, storage medium and electronic equipment

Abstract

The invention discloses an abnormal equipment detection method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring movement track data of at least two to-be-detected devices, the movement track data comprising position information of the to-be-detected devices at a preset statistical moment; distance information between every two to-be-detected devices at at least two moments is determined based on the movement track data, and the distance information represents the distance between the two to-be-detected devices at the same moment; and determining the to-be-detected equipment of which the distance information at the at least two moments meets a preset condition as abnormal equipment. According to the method and the device, the technical problem of low accuracy of identifying the specific type of equipment in the prior art is solved, and the effect of improving the accuracy of identifying the specific type of equipment is further achieved.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular, to a method, device, storage medium and electronic device for detecting abnormal devices. Background Art

[0002] In related technologies, image detection and other methods are usually used to identify the type of equipment. Taking the smuggling ship judgment scenario as an example, the abnormal behavior of the ship is judged based on the ship's detection image and historical trajectory. However, it can only identify smuggling ships within a specific size and speed range. The accuracy of image recognition is limited by weather and lighting conditions, and it is impossible to further distinguish abnormal behaviors such as obstacle avoidance, rescue, and smuggling.

[0003] It can be seen from this that there is a technical problem in the related art of low accuracy in identifying specific types of devices.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, an apparatus, a storage medium and an electronic device for detecting abnormal devices, so as to at least solve the technical problem of low recognition accuracy of specific types of devices in the related art.

[0006] According to one embodiment of the present invention, a method for detecting abnormal devices is provided, comprising: obtaining movement trajectory data of at least two devices to be detected, wherein the movement trajectory data includes position information of the devices to be detected at preset statistical moments; determining distance information between every two devices to be detected at at least two moments based on the movement trajectory data, wherein the distance information represents the distance between the two devices to be detected at the same moment; and determining the devices to be detected whose distance information at the at least two moments meets preset conditions as abnormal devices.

[0007] In an exemplary embodiment, determining the distance information between every two devices to be detected at at least two moments based on the movement trajectory data includes: determining a group of position points corresponding to each device to be detected at the preset statistical moment based on the movement trajectory data; determining the distance information at at least two moments based on the position information of two groups of position points corresponding to every two devices to be detected, wherein the distance information represents the average value of the distances between each pair of position points in the two groups of position points corresponding to the same moment.

[0008] In an exemplary embodiment, the device to be detected whose distance information at at least two moments all meets preset conditions is determined as an abnormal device, including: determining a group of sample position points corresponding to each abnormal sample device based on the sample movement trajectory data of each abnormal sample device; determining a group of sample distances based on the position information of two groups of sample position points corresponding to every two abnormal sample devices, and determining the sample average value of the group of sample distances; determining the maximum value of the sample average values ​​corresponding to each group of sample distances as the target distance threshold; determining the device to be detected whose distance information at at least two moments and the target distance threshold all meet the preset distance conditions as the abnormal device, wherein the preset conditions include the preset distance condition.

[0009] In an exemplary embodiment, the method further includes: determining a group of position points corresponding to each of the devices to be detected at the preset statistical moment based on the movement trajectory data; determining trajectory similarity information based on the position information of the two groups of position points corresponding to every two devices to be detected, wherein the trajectory similarity information represents the similarity between two trajectories formed by the two groups of position points, so as to indicate the degree of similarity between the movement trajectories of the corresponding two devices to be detected; and determining the device to be detected whose distance information and the trajectory similarity information at at least two moments satisfy the preset conditions as the abnormal device.

[0010] In an exemplary embodiment, determining the trajectory similarity information based on the position information of two groups of position points corresponding to every two of the devices to be detected includes: determining two trajectory lines based on the position information of two groups of position points corresponding to every two of the devices to be detected; and determining the distance between the two trajectory lines as the trajectory similarity information.

[0011] In an exemplary embodiment, the device to be detected whose distance information and trajectory similarity information at at least two moments both satisfy the preset conditions is determined as the abnormal device, including: determining a group of sample position points corresponding to each abnormal sample device based on the sample movement trajectory data of each abnormal sample device; determining two sample trajectory lines based on the position information corresponding to the two groups of sample position points corresponding to every two abnormal sample devices; determining a group of sample similarities based on the distance between every two sample trajectory lines, and grouping and marking the group of sample similarities to obtain a group of trajectory labels, wherein the sample similarity is used to indicate the similarity between the two sample trajectory lines, and the trajectory label is used to indicate the degree of similarity corresponding to the similarity grouping; the trajectory similarity information is corresponded to a target trajectory label, and the device to be detected whose distance information at at least two moments both satisfy the preset conditions is determined as the abnormal device, wherein the target trajectory label indicates that the trajectory similarity information belongs to a target similarity grouping, and the sample similarity in the target similarity grouping satisfies the first similarity condition.

[0012] In an exemplary embodiment, the method further includes: determining a group of position points corresponding to each of the devices to be detected at the preset statistical moment based on the movement trajectory data; determining speed change law information based on the speed information of each of the devices to be detected at the group of position points, wherein the speed change law information represents the speed change pattern of the device to be detected to indicate the speed change pattern of the device to be detected; and determining the device to be detected whose distance information and the speed change law information at at least two moments meet the preset conditions as an abnormal device.

[0013] In an exemplary embodiment, the determining of the speed variation law information based on the speed information of each of the devices to be detected at the group of position points includes: determining a group of speed values ​​based on the speed information of each of the devices to be detected at the group of position points; setting a speed label according to the speed interval to which each speed value in the group of speed values ​​belongs, and determining the speed variation law information based on the temporal change order of the speed labels.

[0014] In an exemplary embodiment, the device to be detected whose distance information and speed variation law information at at least two moments both meet preset conditions is determined as an abnormal device, including: determining a group of sample speed values ​​corresponding to each abnormal sample device based on sample movement trajectory data of each abnormal sample device; setting a sample speed label according to the speed interval to which each sample speed value in the group of sample speed values ​​belongs, and determining the sample speed variation law information based on the temporal change order of the sample speed label; and determining the device to be detected as the abnormal device if the speed variation law information satisfies a second similarity condition with the sample speed variation law information and the distance information at at least two moments both meet the preset conditions.

[0015] In an exemplary embodiment, the method further includes: determining clustering information of each of the devices to be detected based on the mobile trajectory data, wherein the clustering information indicates whether the location point of the device to be detected is isolated; marking the clustering information as a suspected device, and determining the device to be detected whose distance information at at least two moments satisfies the preset conditions as the abnormal device, wherein the suspected device indicates the device to be detected whose location point is isolated.

[0016] In an exemplary embodiment, determining the clustering information of each device to be detected based on the mobile trajectory data includes: determining the real-time location point of each device to be detected at the preset statistical moment based on the mobile trajectory data; performing a clustering operation on the real-time location point to determine the suspected device and mark it, wherein the suspected device represents the device to be detected corresponding to the isolated location point determined by the clustering operation.

[0017] In an exemplary embodiment, performing a clustering operation on the real-time location points to determine and mark the suspected devices includes: performing a clustering operation on the real-time location points to obtain at least one location point set and the isolated location points, wherein the isolated location points do not belong to any location point set in the at least one location point set; determining the device to be detected corresponding to the isolated location point as the suspected device, and marking the corresponding clustering information.

[0018] According to another embodiment of the present invention, there is provided a detection device for a target device, comprising: an acquisition module, used to acquire movement trajectory data of at least two devices to be detected, wherein the movement trajectory data comprises position information of the devices to be detected at preset statistical moments; a first determination module, used to determine distance information between every two devices to be detected at at least two moments based on the movement trajectory data, wherein the distance information represents the distance between the two devices to be detected at the same moment; and a second determination module, used to determine the devices to be detected whose distance information at the at least two moments satisfies preset conditions as abnormal devices.

[0019] According to yet another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any one of the above method embodiments when running.

[0020] According to another embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0021] According to yet another embodiment of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the method described in each embodiment of the present application are implemented.

[0022] Through the present invention, after obtaining the mobile device trajectory of the location information displayed by at least two devices to be detected at the preset statistical moment, the distance information between the devices to be detected at at least two moments can be determined according to the mobile device trajectory. When the distance information between the devices to be detected at at least two moments meets the preset conditions, the device to be detected can be determined as an abnormal device. Therefore, the technical problem of low accuracy in identifying specific types of devices existing in the related art can be solved, thereby achieving the effect of improving the accuracy of identifying specific types of devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 is a hardware structure block diagram of a mobile terminal according to a method for detecting abnormal devices according to an embodiment of the present invention;

[0025] Figure 2 is a flow chart of a method for detecting abnormal devices according to an embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of a ship smuggling transshipment mode according to an embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of the moving trajectory distance of a smuggling ship according to an embodiment of the present invention;

[0028] Figure 5 is a schematic diagram of a virtual trajectory of a ship in a stationary state according to an embodiment of the present invention;

[0029] Figure 6 is a schematic diagram of the similarity results of the tracks of two ships in the stationary phase according to an embodiment of the present invention;

[0030] Figure 7 This is a diagram showing the clustering of ship positions based on the DBSCAN algorithm according to an embodiment of the present invention;

[0031] Figure 8 2. It is a schematic diagram of the overall process of the ship smuggling calculation solution according to an embodiment of the present invention;

[0032] Fig. 9 4 is a structural block diagram of an abnormal device detection device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] The present application is described below in conjunction with embodiments:

[0036] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for detecting abnormal devices according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0037] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the detection method of abnormal equipment in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0038] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0039] In this embodiment, a method for detecting a target device is provided. Figure 2 is a flow chart of a method for detecting abnormal devices according to an embodiment of the present invention. Figure 2As shown, the process includes the following steps:

[0040] Step S202, obtaining movement trajectory data of at least two devices to be detected, wherein the movement trajectory data includes location information of the devices to be detected at a preset statistical moment;

[0041] Step S204, determining distance information between every two of the devices to be detected at at least two moments based on the movement trajectory data, wherein the distance information represents the distance between the two devices to be detected at the same moment;

[0042] Step S206: Determine the device to be detected whose distance information at the at least two moments meets a preset condition as an abnormal device.

[0043] In the above embodiments, the device to be detected can be a ship, a vehicle, or a device such as a drone that has the ability to report position and speed. In the present invention, a ship is specifically used for explanation. In addition, the number of devices to be detected can be 2, 3, etc., but is not limited thereto. The movement trajectory data can be understood as the movement trajectory of the device to be detected in the sea area, and can include the location information of the device to be detected within a preset statistical time point. According to this location information, the distance between the devices to be detected at at least two moments (i.e., the above distance information) can be determined.

[0044] In the above embodiment, during the smuggling process, the transfer ship usually sails at a normal speed or quickly to the agreed location, and then the two ships slowly parallel or stationary to transfer the goods. This process usually lasts for a period of time. At this time, the distance between the two ships is relatively close. After the goods are transferred, the two ships accelerate or leave normally. Therefore, the cargo smuggling model can refer to Figure 3 , Figure 3 Schematic diagram of ship smuggling transshipment mode according to an embodiment of the present invention, Figure 3 As shown, mode 1 means that after the two ships sail normally to the agreed location, they sail slowly at a low speed to transfer goods, and then leave at a high speed or normally; mode 2 means that after the two ships sail normally to the agreed location, they transfer goods at a stationary speed, and then leave at a high speed or normally. Therefore, the judgment can be made based on the determination of the ship area, the distance between ships during the transaction, and the smuggling transfer mode. When the distance information of the device to be detected at at least two moments meets the preset conditions, the device to be detected can be determined as an abnormal device.

[0045] Through the present invention, after obtaining the mobile device trajectory of the location information displayed by at least two devices to be detected at the preset statistical moment, the distance information between the devices to be detected at at least two moments can be determined according to the mobile device trajectory. When the distance information between the devices to be detected at at least two moments meets the preset conditions, the device to be detected can be determined as an abnormal device. Therefore, the technical problem of low accuracy in identifying specific types of devices existing in the related art can be solved, thereby achieving the effect of improving the accuracy of identifying specific types of devices.

[0046] Optionally, the execution subject of the above steps may be a processor, but is not limited thereto.

[0047] In an exemplary embodiment, determining the distance information between every two devices to be detected at at least two moments based on the movement trajectory data includes: determining a group of position points corresponding to each device to be detected at the preset statistical moment based on the movement trajectory data; determining the distance information at at least two moments based on the position information of two groups of position points corresponding to every two devices to be detected, wherein the distance information represents the average value of the distances between each pair of position points in the two groups of position points corresponding to the same moment.

[0048] In the above embodiment, if Figure 3 As shown, the mobile trajectory data consists of real-time position points, each of which represents the moving position of the device to be detected at different times. The real-time position point information at different times can be counted to form a group of position points. The distance information between the two devices to be detected can be determined based on the position information of the two groups of position points corresponding to each two devices to be detected at at least two times, and the average value of the distance between each pair of position points in the two groups of position points is used as the distance information. The position point information is determined by the trajectory of the device to be detected during the movement, and the average value between the distances of each pair of position points is used as the judgment factor, which can improve the accuracy of identifying smuggling ships and reduce the impact of data mutation.

[0049] In an exemplary embodiment, the device to be detected whose distance information at at least two moments all meets preset conditions is determined as an abnormal device, including: determining a group of sample position points corresponding to each abnormal sample device based on the sample movement trajectory data of each abnormal sample device; determining a group of sample distances based on the position information of two groups of sample position points corresponding to every two abnormal sample devices, and determining the sample average value of the group of sample distances; determining the maximum value of the sample average values ​​corresponding to each group of sample distances as the target distance threshold; determining the device to be detected whose distance information at at least two moments and the target distance threshold all meet the preset distance conditions as the abnormal device, wherein the preset conditions include the preset distance condition.

[0050] In the above embodiment, the abnormal sample device can be understood as a ship device that has been determined to be a smuggling cargo behavior, and is used as training data to build a smuggling ship judgment model. The moving trajectory data of any two ships in the smuggling sample data during the low-speed transaction process is extracted, and each corresponding group of sample position point information is determined respectively. According to the sample position point information, the distance between the two smuggling ships (i.e., the above sample distance) can be determined respectively, and the sample average corresponding to all groups of sample distances is calculated. The maximum value of the above sample averages can be determined as the target distance threshold. Figure 4 Schematic diagram of the moving track distance of a smuggling ship according to an embodiment of the present invention. Figure 4 As shown, C i , C j They represent the moving trajectories of the two smuggling ships during the low-speed navigation phase, and d i Indicates T i The average distance between the two ship tracks can be expressed as d i,j Represents (i.e. the above distance information), which can be calculated by the following formula: Where n represents the number of time points. The average distance set in the process of low-speed ship trading in the sample data set can be {d 1,2 ,d 3,5 ,…,d i,j …,d m,n}, (i≠j), the average distance can be concentrated to the maximum value θ=max(d 1,2 ,d 3,5 ,…,d i,j …,d m,n ) is determined as the target distance threshold. For example, the distance between a smuggling ship C1 and C2 in the sea area at time T1 is d1 = 10m, the distance at time T2 is d2 = 8m, and the distance at time T3 is d3 = 12m. The average distance d 1,2 =(10+8+12) / 3=10; For the smuggling ships C3 and C4, the corresponding distances at T1, T2, and T3 are 9, 14, and 11 respectively, then d 3,4 =(9+14+11) / 3=8; the distances corresponding to the smuggling ships C5 and C6 at T1, T2, and T3 are 6, 10, and 15 respectively, so d 5,6 =(6+10+15) / 3=7. The average distance set is {10,3,7}, and the maximum value 10 in the average distance set is taken as the target distance threshold for judging whether the ship is a smuggling behavior.

[0051] In the above embodiment, the preset distance condition may be that the distance information is less than the target distance threshold, or that the distance information is equal to the target distance threshold, or that the difference between the two is less than a certain threshold. When the distance information and the target distance threshold at at least two moments meet the preset distance condition, the device to be detected whose distance information and the target distance threshold both meet the preset condition can be determined as an abnormal device. By analyzing the abnormal samples and calculating and comparing the average distance information, it is possible to accurately determine whether the device to be detected has smuggled.

[0052] In an exemplary embodiment, the method further includes: determining a group of position points corresponding to each of the devices to be detected at the preset statistical moment based on the movement trajectory data; determining trajectory similarity information based on the position information of the two groups of position points corresponding to every two devices to be detected, wherein the trajectory similarity information represents the similarity between two trajectories formed by the two groups of position points, so as to indicate the degree of similarity between the movement trajectories of the corresponding two devices to be detected; and determining the device to be detected whose distance information and the trajectory similarity information at at least two moments satisfy the preset conditions as the abnormal device.

[0053] In the above embodiment, the trajectory similarity information can also be determined by two sets of position point information corresponding to each two devices to be detected in the mobile trajectory data, wherein the trajectory similarity information can be understood as the degree of similarity between the two trajectories formed by the position points of the devices to be detected, and can be used to indicate the degree of similarity between the moving trajectories of the two devices to be detected. When the distance information and trajectory similarity information between the devices to be detected at at least two moments meet the preset conditions, the device to be detected can be determined as an abnormal device. Among them, the preset conditions can be that the distance information is less than the target distance threshold, the trajectory similarity is greater than the trajectory similarity between abnormal samples, or the distance information is equal to the target distance threshold, the trajectory similarity is equal to the trajectory similarity between abnormal samples, or the difference between the two is less than a certain threshold.

[0054] In an exemplary embodiment, determining the trajectory similarity information based on the position information of two groups of position points corresponding to every two of the devices to be detected includes: determining two trajectory lines based on the position information of two groups of position points corresponding to every two of the devices to be detected; and determining the distance between the two trajectory lines as the trajectory similarity information.

[0055] In the above embodiment, the position point information of the ship during the voyage constitutes the entire voyage route. Two trajectory lines can be determined according to the position point information corresponding to each two devices to be detected, and the trajectory similarity information can be determined by the distance between the two trajectory lines. The use of graded prediction and classification based on the suspected degree of smuggling can enable relevant departments to deal with smuggling problems according to urgency and give priority to targets with high suspicion.

[0056] In an exemplary embodiment, the device to be detected whose distance information and trajectory similarity information at at least two moments both satisfy the preset conditions is determined as the abnormal device, including: determining a group of sample position points corresponding to each abnormal sample device based on the sample movement trajectory data of each abnormal sample device; determining two sample trajectory lines based on the position information corresponding to the two groups of sample position points corresponding to every two abnormal sample devices; determining a group of sample similarities based on the distance between every two sample trajectory lines, and grouping and marking the group of sample similarities to obtain a group of trajectory labels, wherein the sample similarity is used to indicate the similarity between the two sample trajectory lines, and the trajectory label is used to indicate the degree of similarity corresponding to the similarity grouping; the trajectory similarity information is corresponded to a target trajectory label, and the device to be detected whose distance information at at least two moments both satisfy the preset conditions is determined as the abnormal device, wherein the target trajectory label indicates that the trajectory similarity information belongs to a target similarity grouping, and the sample similarity in the target similarity grouping satisfies the first similarity condition.

[0057] In the above embodiment, a set of sample position points corresponding to the abnormal sample device can be determined according to the sample movement trajectory data, and the sample trajectory line can be determined by the position information of the sample position points. The sample similarity of each pair of smuggling docking ships in the sample data is calculated and grouped and marked to obtain a trajectory label, as shown in Table 1. The similarity grouping sim (Similarity) of the trajectory label can include: low, medium, high, relatively high, and extremely high. The similarity between the sample trajectories can be judged by the trajectory label. If the distance information corresponding to the trajectory similarity information and the target trajectory label meets the preset conditions, the device to be detected is determined as an abnormal device.

[0058] Table 1 SIM similarity level

[0059] Similarity level Numerical range Low [0-0.6) middle [0.6-0.7) high [0.7-0.8) Higher [0.8-0.85) Very high [0.85-1]

[0060] In the above embodiment, the key to judging whether the smuggling ships have the same track during the transaction period is to judge whether the two ships are in a low-speed accompanying or stationary state. The low-speed accompanying transfer of ships will form two routes with similar trajectories, such as Figure 3As shown in the first model, for a ship trading in a stationary state, a virtual track can also be drawn. Figure 5 As shown, the virtual track in the box represents the virtual route with a speed of 0 formed by the ship at different time points, so the track similarity calculation can be converted into the geometric similarity calculation of two lines.

[0061] In the above embodiment, the similarity of two lines in the space can be calculated by using the Fleche distance, or by using the Hausdorff distance, but is not limited thereto. The calculation formula for calculating the similarity of two lines using the Fleche distance is as follows: Among them, inf represents the infimum, and max represents the maximum mapping distance. The similarity results of the two ship tracks in the stationary phase obtained by calculating the stationary speed route can be referred to Figure 6 As shown in the figure, the similarity between the two tracks is 0.8438, which corresponds to a higher level in the track label. Defining the track similarity level corresponding to different track Fréchet distance values ​​and grading the ship tracks can enable users to give priority to abnormal ships with high suspicion.

[0062] In an exemplary embodiment, the method further includes: determining a group of position points corresponding to each of the devices to be detected at the preset statistical moment based on the movement trajectory data; determining speed change law information based on the speed information of each of the devices to be detected at the group of position points, wherein the speed change law information represents the speed change pattern of the device to be detected to indicate the speed change pattern of the device to be detected; and determining the device to be detected whose distance information and the speed change law information at at least two moments meet the preset conditions as an abnormal device.

[0063] In the above embodiment, the position and speed information of the device to be detected within a preset statistical time point can also be determined based on the movement trajectory data, and the speed change of the device to be detected (i.e. the above speed change law information) can be determined based on this position and speed information. Figure 3 As shown, the movement trajectory data is composed of real-time position points, and the real-time position point information can constitute a group of position points, each group of position points contains the speed information of the ship, and the speed information on the detection group of position points can determine the speed change mode of the device to be detected (i.e., the above-mentioned speed change mode), wherein the speed change can include fast-slow, normal-fast, etc., but not limited to this. The device to be detected whose speed change law information and distance information at at least two moments meet the preset conditions can be determined as an abnormal device.

[0064] In an exemplary embodiment, the determining of the speed variation law information based on the speed information of each of the devices to be detected at the group of position points includes: determining a group of speed values ​​based on the speed information of each of the devices to be detected at the group of position points; setting a speed label according to the speed interval to which each speed value in the group of speed values ​​belongs, and determining the speed variation law information based on the temporal change order of the speed labels.

[0065] In the above embodiment, each position point information contains the speed information of the ship at this location. A group of speed values ​​can be determined by the speed information at a group of position points of the device to be detected. A speed label is set for the speed interval to which each speed value belongs. The speed change law information can be determined according to the time change sequence of the speed label. If the speed behavior of the ship is consistent with the speed change of the smuggling ship, the ship can be further calculated for trajectory similarity, otherwise it can be excluded, which can reduce unnecessary calculations and improve detection efficiency.

[0066] In an exemplary embodiment, the device to be detected whose distance information and speed variation law information at at least two moments both meet preset conditions is determined as an abnormal device, including: determining a group of sample speed values ​​corresponding to each abnormal sample device based on sample movement trajectory data of each abnormal sample device; setting a sample speed label according to the speed interval to which each sample speed value in the group of sample speed values ​​belongs, and determining the sample speed variation law information based on the temporal change order of the sample speed label; and determining the device to be detected as the abnormal device if the speed variation law information satisfies a second similarity condition with the sample speed variation law information and the distance information at at least two moments both meet the preset conditions.

[0067] In the above embodiment, the speed mode of the smuggling ship (i.e., corresponding to the sample speed label reflected above) can be used to determine whether the ship meets the speed change during the smuggling process. As one of the determination conditions of the smuggling mode, if the ship's speed behavior meets the speed change of the smuggling ship, the ship can be further subjected to trajectory similarity calculation, otherwise it is excluded. Based on the sample movement trajectory data of the abnormal sample device, a corresponding set of sample speed values ​​can be determined, and the sample speed change law information can be determined by setting a sample speed label for the speed interval to which each sample speed value belongs, wherein the sample speed label can be fast, slow, stationary, normal speed, etc. The device to be detected can be determined as the abnormal device if the speed change law information meets the sample speed change law information and the distance information at at least two moments meets the preset conditions. Among them, the second similarity condition can be that the speed change law information is the same as the sample speed change law information, or the speed change law information meets several sample speed labels in the sample speed change law information, but is not limited to this. The ship smuggling speed mode can refer to Table 2. As shown in Table 2, it can include the full process speed mode and the transaction speed mode, wherein the sample speed label in the full process speed mode can be fast-slow-fast, fast-stationary-fast, fast-slow-normal speed, and the sample speed label in the transaction speed mode can be fast-slow, fast-stationary, normal speed-slow, etc., but not limited to this. If it meets one of the smuggling ship speed modes, it can be sorted from high to low according to the similarity of the ship track and the suspicion of the final ship smuggling can be determined. First, the ship smuggling speed mode is judged, and when it is determined that the ship is actually in the transaction speed mode, subsequent calculations are performed, which can effectively save processor calculation time, avoid additional unnecessary calculations, and greatly improve the processing speed and accuracy.

[0068] Table 2 Ship smuggling speed patterns

[0069] Full speed mode Speed ​​mode in transaction Fast-slow-fast speed Fast-Standstill-Fast Fast-Still Fast-Slow-Normal Speed Normal speed - slow …… ……

[0070] In an exemplary embodiment, the method further includes: determining clustering information of each of the devices to be detected based on the mobile trajectory data, wherein the clustering information indicates whether the location point of the device to be detected is isolated; marking the clustering information as a suspected device, and determining the device to be detected whose distance information at at least two moments satisfies the preset conditions as the abnormal device, wherein the suspected device indicates the device to be detected whose location point is isolated.

[0071] In the above embodiment, it is also possible to determine whether the device to be detected deviates from the normal route area to become an isolated point (i.e., the above clustering information) based on the movement trajectory data. Since the time of smuggling goods is generally chosen at night, early morning, foggy days and other periods with low visibility, and transactions are carried out in remote and difficult to monitor sea areas, ships that are not traveling in the normal route area and form isolated points can be marked as suspected devices. The clustering information can be marked as a suspected device, and the device to be detected whose distance information at at least two moments meets the preset conditions is determined as a target device.

[0072] In an exemplary embodiment, determining the clustering information of each device to be detected based on the mobile trajectory data includes: determining the real-time location point of each device to be detected at the preset statistical moment based on the mobile trajectory data; performing a clustering operation on the real-time location point to determine the suspected device and mark it, wherein the suspected device represents the device to be detected corresponding to the isolated location point determined by the clustering operation.

[0073] In the above embodiment, the mobile trajectory data is composed of the actual position information at each moment, and the real-time point position at the preset statistical moment can be determined by the position information in the mobile trajectory data. The device to be detected is clustered according to the real-time point position, and the device that meets the clustering information (i.e., deviates from the normal route area to become an isolated point) is determined as a suspected device and marked. Among them, the clustering operation can be a step of calculating the device to be detected by a clustering algorithm, and the clustering algorithm can be a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) density-based clustering algorithm, or a K-mean mean clustering algorithm. Among them, the DBSCAN density-based clustering algorithm can define a cluster as the maximum set of density-connected points, divide the area with sufficiently high density into clusters, and find clusters of any shape in a spatial database with noise; the K-mean mean clustering algorithm can divide the data into K groups, and randomly select K objects as the initial clustering centers, and then calculate the distance between each object and each seed clustering center, and assign each object to the clustering center closest to it.

[0074] In an exemplary embodiment, performing a clustering operation on the real-time location points to determine and mark the suspected devices includes: performing a clustering operation on the real-time location points to obtain at least one location point set and the isolated location points, wherein the isolated location points do not belong to any location point set in the at least one location point set; determining the device to be detected corresponding to the isolated location point as the suspected device, and marking the corresponding clustering information.

[0075] In the above embodiment, ships usually sail along a route, and multiple ships sailing on the route form a route belt with a certain width (i.e., the above-mentioned set of position points). The route belt is usually a long and narrow belt. Ships that deviate from the route will not be within the route belt and become isolated points (i.e., the above-mentioned isolated position points). Isolated points can be found by clustering the real-time position points. Figure 7 : is a clustering effect diagram of ship positions based on the DBSCAN algorithm according to an embodiment of the present invention, such as Figure 7 As shown in the figure, multiple ships show a route belt on the route, forming a set of location points. There are few ships in the black frame marked area, forming isolated location points, which do not belong to any location point set and can be identified as remote areas. These ships can be marked as suspected equipment. Only calculating ships in the abnormal route area can enable the system to respond and process data faster.

[0076] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0077] In an exemplary embodiment, the overall process of the ship smuggling calculation solution can be referred to Figure 8 , Figure 8 FIG. 1 is a schematic diagram of the overall process of the ship smuggling calculation solution according to an embodiment of the present invention. Figure 8 As shown, the method mainly includes:

[0078] Step 802, selecting the track data of the smuggling vessels in a certain monitoring area as sample data;

[0079] Step 804, by analyzing the sample data and combining with manual experience, a smuggling ship judgment model is constructed, including a smuggling ship speed change law model, a track pattern during the smuggling transshipment process, and a distance threshold for analyzing smuggling ships;

[0080] Step 806, obtaining real-time data of ships sailing in a certain monitoring area, including time, speed, and location information;

[0081] Step 808, clustering the positions of the ships using a clustering algorithm, and the ships that fall into small clusters and outliers after clustering are further analyzed as suspicious objects;

[0082] Step 810, determine whether the ship is suspected of smuggling. Determine the distance between the two ships. If the distance is within the distance threshold of the smuggling ship, the two ships will be further determined, otherwise they will be excluded. Calculate the similarity between the ship's track and the smuggling barge track, and classify them according to the similarity. Determine the similarity between the ship's speed change and the smuggling ship's speed change model. Calculate the suspicion that the ship is a smuggling behavior based on the similarity between the ship's track and the smuggling barge track and the similarity between the ship's speed change and the smuggling ship's speed change model;

[0083] Step 812, dynamic monitoring, continuously updating the ship's suspicion level.

[0084] In the above embodiment, when selecting sample data, the quality and representativeness of the sample data are ensured, and the characteristics and patterns of ship smuggling behavior can be accurately reflected. The data can include information such as the real-time position, speed, heading, time, etc. of the ship. In addition, the number of samples is large enough, and data of different ship types, regions, time periods, and weather conditions are collected, which can ensure the representativeness of the data and improve the robustness of the model.

[0085] In the above embodiment, when constructing the speed change law model of smuggling ships, the DBSCAN algorithm can be used to cluster the real-time positions of ships, exclude normal sailing ships, and filter out ships with abnormal positions. By calculating the mean of the distance between each pair of sample smuggling ships during the transshipment process, and taking the maximum value as the smuggling ship distance threshold in this model, the calculation formula for the average distance between ships during the transaction process can be: The calculation formula for the smuggling ship spacing threshold can be θ = max(d i,j ), in the present invention, the smuggling vessel threshold may be 600 meters, and may be adjusted according to actual conditions, and the adjustment range may be 400≤θ≤1000.

[0086] In the above embodiment, the change of ship speed can be analyzed according to the ship trajectory, and ships meeting the characteristics of "normal-slow", "fast-slow", "fast-stationary", etc. can be further screened. The track pattern in the smuggling transshipment process can be obtained by the ship track similarity calculation method, which can be calculated based on the path similarity of the two ships in a stationary or slow state during the suspected transaction process, and the path is converted into a line in space. The ship path similarity is calculated by calculating the similarity of the shapes of the two lines. The Fleche distance, Hausdorff distance and other calculation formulas can be used to judge the level of transshipment smuggling of the two ships based on the similarity.

[0087] In the above embodiment, the real-time data of the ship's navigation in the monitoring area, including time, speed, and position information, can be used as the input of the model to determine whether the ship is a suspected smuggling ship. The position information can be used to determine whether the ship is in an abnormal route area, the route trajectory composed of position and time can be used to calculate the ship's track similarity, and the speed and time data can be used to analyze the speed change law of the ship.

[0088] In the above embodiment, the DBSCAN clustering method and K-mean can be used to implement isolated point detection. When the DBSCAN algorithm clusters ships, the neighborhood parameter eps can be 0.4, and the minimum point minPts can be 6.

[0089] In the above embodiment, the ships entering the monitoring range can be monitored in real time and dynamically, and the suspicion of ship smuggling transactions can be continuously calculated and updated through the continuously updated ship navigation data. By determining whether the transaction ship is in the normal route area, the distance between the two ships, the speed characteristics of the ship from the connection to the transfer process meet the characteristics of "fast-slow", "fast-stationary" and the similarity of the two ship tracks, the comprehensive judgment can more accurately judge the ship transfer smuggling behavior and avoid misjudgment. On the basis of clustering and judging abnormal behaviors of ships, a comprehensive judgment can be made based on multiple characteristics such as ship distance, speed change, and trajectory similarity, and the transfer smuggling behavior can be further screened from a variety of abnormal behaviors of ships to achieve accurate judgment of ship smuggling. At the same time, the judgment model constructed using AIS and radar data is less affected by weather and time, and can provide more accurate and reliable marine monitoring, reduce the dependence on image recognition, and thus maintain high accuracy and stability at night or in bad weather. In addition, the abnormal tracks and navigation areas are automatically identified by machine learning algorithms, which improves the efficiency of monitoring without manual intervention.

[0090] In this embodiment, a detection device for a target device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0091] Fig. 9 is a structural block diagram of a detection device for a target device according to an embodiment of the present invention. Fig. 9 As shown, the device comprises:

[0092] An acquisition module 902 is configured to acquire movement trajectory data of at least two devices to be detected, wherein the movement trajectory data includes location information of the devices to be detected at a preset statistical moment;

[0093] A first determining module 904 determines distance information between every two of the devices to be detected at at least two moments based on the movement trajectory data, wherein the distance information represents the distance between the two devices to be detected at the same moment;

[0094] The second determining module 906 determines the device to be detected whose distance information at the at least two moments meets a preset condition as an abnormal device.

[0095] In an exemplary embodiment, the first determination module 904 can implement the determination of the distance information between every two devices to be detected at at least two moments based on the movement trajectory data in the following manner: determine a group of position points corresponding to each device to be detected at the preset statistical moment based on the movement trajectory data; determine the distance information at at least two moments based on the position information of two groups of position points corresponding to every two devices to be detected, wherein the distance information represents the average value of the distances between each pair of position points in the two groups of position points corresponding to the same moment.

[0096] In an exemplary embodiment, the device can achieve the determination of the device to be detected whose distance information at the at least two moments meets the preset conditions as an abnormal device in the following manner: determine a group of sample position points corresponding to each abnormal sample device based on the sample movement trajectory data of each abnormal sample device; determine a group of sample distances based on the position information of the two groups of sample position points corresponding to every two abnormal sample devices, and determine the sample average value of the group of sample distances; determine the maximum value of the sample average values ​​corresponding to each group of sample distances as the target distance threshold; determine the device to be detected whose distance information at the at least two moments and the target distance threshold meet the preset distance conditions as the abnormal device, wherein the preset conditions include the preset distance conditions.

[0097] In an exemplary embodiment, the device can be used to: determine a group of position points corresponding to each of the devices to be detected at the preset statistical moment based on the movement trajectory data; determine trajectory similarity information based on the position information of the two groups of position points corresponding to every two devices to be detected, wherein the trajectory similarity information represents the similarity between two trajectories formed by the two groups of position points, so as to indicate the degree of similarity between the movement trajectories of the corresponding two devices to be detected; and determine the device to be detected whose distance information and the trajectory similarity information at at least two moments satisfy the preset conditions as the abnormal device.

[0098] In an exemplary embodiment, the device can also implement the determination of trajectory similarity information based on the position information of two groups of position points corresponding to every two devices to be detected in the following manner: determine two trajectory lines based on the position information of two groups of position points corresponding to every two devices to be detected; and determine the distance between the two trajectory lines as the trajectory similarity information.

[0099] In an exemplary embodiment, the device can also implement the determination of the device to be detected whose distance information and trajectory similarity information meet the preset conditions with the abnormal sample device as the target device in the following manner: determine a group of sample position points corresponding to each abnormal sample device based on the sample movement trajectory data of each abnormal sample device; determine two sample trajectory lines based on the position information corresponding to the two groups of sample position points corresponding to every two abnormal sample devices; determine a group of sample similarities based on the distance between every two sample trajectory lines, and group and mark the group of sample similarities to obtain a group of trajectory labels, wherein the sample similarity is used to indicate the similarity between the two sample trajectory lines, and the trajectory label is used to indicate the degree of similarity corresponding to the similarity grouping; correspond the trajectory similarity information to the target trajectory label, and determine the device to be detected whose distance information meets the preset conditions with the abnormal sample device as the target device, wherein the target trajectory label indicates that the trajectory similarity information belongs to the target similarity grouping, and the sample similarity in the target similarity grouping meets the first similarity condition.

[0100] In an exemplary embodiment, the device can also be used to: determine a group of position points corresponding to each of the devices to be detected at the preset statistical moment based on the movement trajectory data; determine the speed change law information based on the speed information of each of the devices to be detected at the group of position points, wherein the speed change law information represents the speed change pattern of the device to be detected to indicate the speed change pattern of the device to be detected; determine the device to be detected whose distance information and the speed change law information at at least two moments meet the preset conditions as an abnormal device.

[0101] In an exemplary embodiment, the device can also implement the determination of the speed variation law information based on the speed information of each of the devices to be detected at the group of position points in the following manner: determine a group of speed values ​​based on the speed information of each of the devices to be detected at the group of position points; set a speed label according to the speed range to which each speed value in the group of speed values ​​belongs, and determine the speed variation law information based on the temporal change order of the speed label.

[0102] In an exemplary embodiment, the device can also achieve the determination of the device to be detected as an abnormal device in the following manner: determining a group of sample speed values ​​corresponding to each abnormal sample device based on the sample movement trajectory data of each abnormal sample device; setting a sample speed label according to the speed interval to which each sample speed value in the group of sample speed values ​​belongs, and determining the sample speed change law information based on the temporal change order of the sample speed label; determining the device to be detected as the abnormal device if the speed change law information satisfies the second similarity condition with the sample speed change law information and the distance information at the at least two moments satisfies the preset conditions.

[0103] In an exemplary embodiment, the device can also be used to: determine the clustering information of each of the devices to be detected based on the mobile trajectory data, wherein the clustering information indicates whether the location point of the device to be detected is isolated; mark the clustering information as a suspected device, and the device to be detected whose distance information at at least two moments satisfies the preset conditions is determined as the abnormal device, wherein the suspected device represents the device to be detected whose location point is isolated.

[0104] In an exemplary embodiment, the device can implement the clustering information of each device to be detected based on the mobile trajectory data in the following manner: determine the real-time location point of each device to be detected at the preset statistical moment based on the mobile trajectory data; perform a clustering operation on the real-time location point, determine the suspected device and mark it, wherein the suspected device represents the device to be detected corresponding to the isolated location point determined by the clustering operation.

[0105] In an exemplary embodiment, the device can implement the clustering operation on the real-time location points, determine the suspected device and mark it in the following manner: perform a clustering operation on the real-time location points to obtain at least one location point set and the isolated location point, wherein the isolated location point does not belong to any location point set in the at least one location point set; determine the device to be detected corresponding to the isolated location point as the suspected device, and mark the corresponding clustering information.

[0106] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0107] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0108] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0109] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0110] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0111] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the steps of the method in each embodiment of the present application when the computer program is executed by a processor.

[0112] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0113] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for detecting abnormal equipment, characterized in that: include: Acquire movement trajectory data of at least two devices to be detected, wherein the movement trajectory data includes location information of the devices to be detected at a preset statistical moment; Determine the distance information between every two of the devices to be detected at at least two moments based on the movement trajectory data, wherein the distance information represents the distance between the two devices to be detected at the same moment; The device to be detected whose distance information at the at least two moments meets a preset condition is determined as an abnormal device.

2. The method according to claim 1, characterized in that The determining, based on the movement trajectory data, the distance information between every two of the devices to be detected at at least two moments includes: Determine a group of position points corresponding to each of the devices to be detected at the preset statistical time based on the movement trajectory data; The distance information at at least two moments is determined based on the position information of two groups of position points corresponding to every two of the devices to be detected, wherein the distance information represents the average value of the distances between each pair of position points in the two groups of position points corresponding to the same moment.

3. The method according to claim 2, characterized in that The step of determining the device to be detected whose distance information at the at least two moments satisfies a preset condition as an abnormal device includes: Determine a group of sample position points corresponding to each abnormal sample device based on the sample movement trajectory data of each abnormal sample device; Determine a set of sample distances based on the position information of the two sets of sample position points corresponding to every two of the abnormal sample devices, and determine a sample average value of the set of sample distances; Determine the maximum value among the sample average values ​​corresponding to the sample distances of each group as the target distance threshold; The device to be detected, for which the distance information at the at least two moments and the target distance threshold both satisfy a preset distance condition, is determined as the abnormal device, wherein the preset condition includes the preset distance condition.

4. The method according to claim 1, characterized in that The method further comprises: Determine a group of position points corresponding to each of the devices to be detected at the preset statistical time based on the movement trajectory data; Determining trajectory similarity information based on the position information of two groups of position points corresponding to each two of the devices to be detected, wherein the trajectory similarity information represents the similarity between two trajectories formed by the two groups of position points, so as to indicate the similarity between the corresponding movement trajectories of the two devices to be detected; The device to be detected whose distance information and trajectory similarity information at the at least two moments both meet the preset condition is determined as the abnormal device.

5. The method according to claim 4, characterized in that The determining of trajectory similarity information based on the position information of two groups of position points corresponding to every two of the devices to be detected includes: Determine two trajectory lines based on the position information of two groups of position points corresponding to every two of the devices to be detected; The distance between the two trajectory lines is determined as the trajectory similarity information.

6. The method according to claim 5, characterized in that The step of determining the device to be detected, whose distance information and trajectory similarity information at the at least two moments both satisfy the preset condition, as the abnormal device includes: Determine a group of sample position points corresponding to each abnormal sample device based on the sample movement trajectory data of each abnormal sample device; Determine two sample trajectory lines based on the position information corresponding to the two groups of sample position points corresponding to every two of the abnormal sample devices; Determine a set of sample similarities based on the distance between every two of the sample trajectory lines, and group and label the set of sample similarities to obtain a set of trajectory labels, wherein the sample similarity is used to indicate the similarity between the two sample trajectory lines, and the trajectory label is used to indicate the degree of similarity corresponding to the similarity grouping; The trajectory similarity information is corresponded to the target trajectory label, and the device to be detected whose distance information at at least two moments satisfies the preset condition is determined as the abnormal device, wherein the target trajectory label indicates that the trajectory similarity information belongs to a target similarity group, and the sample similarity in the target similarity group satisfies a first similarity condition.

7. The method according to claim 1, characterized in that The method further comprises: Determine a group of position points corresponding to each of the devices to be detected at the preset statistical time based on the movement trajectory data; Determine the speed variation law information based on the speed information of each of the devices to be detected at the set of position points, wherein the speed variation law information represents the speed variation mode of the devices to be detected, so as to indicate the speed variation mode of the devices to be detected; The device to be detected whose distance information and speed change law information at the at least two moments both meet preset conditions is determined as an abnormal device.

8. The method according to claim 7, characterized in that The determining of the speed variation law information based on the speed information of each of the devices to be detected at the set of position points includes: Determine a set of speed values ​​based on the speed information of each of the devices to be detected at the set of position points; A speed label is set according to a speed interval to which each speed value in the set of speed values ​​belongs, and the speed variation law information is determined based on a temporal variation sequence of the speed label.

9. The method according to claim 8, characterized in that The step of determining the device to be detected, whose distance information and speed change law information at the at least two moments both meet preset conditions, as an abnormal device includes: Determine a group of sample speed values ​​corresponding to each of the abnormal sample devices based on the sample movement trajectory data of each of the abnormal sample devices; Setting a sample speed label according to the speed interval to which each sample speed value in the set of sample speed values ​​belongs, and determining sample speed change rule information based on the temporal change sequence of the sample speed labels; The device to be detected, whose speed variation law information and sample speed variation law information satisfy a second similarity condition and whose distance information at at least two moments satisfies the preset condition, is determined as the abnormal device.

10. The method according to claim 1, characterized in that The method further comprises: Determine clustering information of each of the devices to be detected based on the movement trajectory data, wherein the clustering information indicates whether a location point of the device to be detected is isolated; The clustering information is marked as a suspected device, and the device to be detected whose distance information at at least two moments satisfies the preset condition is determined as the abnormal device, wherein the suspected device refers to the device to be detected whose location point is isolated.

11. The method according to claim 10, characterized in that The determining the clustering information of each of the devices to be detected based on the movement trajectory data includes: Determine the real-time position point of each of the devices to be detected at the preset statistical moment based on the movement trajectory data; A clustering operation is performed on the real-time location points to determine and mark the suspected devices, wherein the suspected devices represent the devices to be detected corresponding to the isolated location points determined by the clustering operation.

12. The method according to claim 11, characterized in that The performing a clustering operation on the real-time location points to determine and mark the suspected devices includes: Performing a clustering operation on the real-time location points to obtain at least one location point set and the isolated location point, wherein the isolated location point does not belong to any location point set in the at least one location point set; The device to be detected corresponding to the isolated location point is determined as the suspected device, and the corresponding clustering information is marked.

13. A device for detecting abnormal equipment, characterized in that: include: An acquisition module, used to acquire movement trajectory data of at least two devices to be detected, wherein the movement trajectory data includes location information of the devices to be detected at a preset statistical moment; A first determination module, configured to determine distance information between every two of the devices to be detected at at least two moments based on the movement trajectory data, wherein the distance information represents the distance between the two devices to be detected at the same moment; The second determination module is used to determine the device to be detected whose distance information at the at least two moments meets a preset condition as an abnormal device.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein the computer program can be executed by an electronic device to perform the method described in any one of claims 1 to 12.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 12 are implemented.

16. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 12 through the computer program.

Images