A method, apparatus, and readable storage medium for analyzing illegal gas stations

Abstract

The present invention discloses a method, device and readable storage medium for analyzing illegal refueling points. The method includes: sequentially traversing the trajectories of vehicles within a past monitoring time period, identifying the position points where the vehicles are in a stationary state as target position points, obtaining the change amount of the fuel tank liquid level of the vehicle at the target position point relative to the previous position point, and judging whether the target position point is a suspected refueling point according to the change amount of the fuel tank liquid level; for each suspected refueling point, calling the data of the registered legal gas stations, and judging whether there is a legal gas station within a preset range based on the suspected refueling point. If not, the suspected refueling point is considered a suspected illegal refueling point; performing clustering analysis on all the suspected illegal refueling points to find all the clusters, and determining any one of the suspected illegal refueling points within each cluster as an illegal refueling point. In this way, the accuracy of the present invention is guaranteed, and it is not necessary to analyze multiple indicators as in the prior art, and the analysis efficiency is high.

Description

Technical Field

[0001] The present invention relates to the field of gas station analysis, and in particular, to a method, an apparatus, and a readable storage medium for analyzing illegal gas stations. Background Art

[0002] In the prior art, the analysis of gas stations is carried out by analyzing the refueling status. If there is no gas station meeting the national standards within the threshold range of the gas station, the vehicle is tracked and analyzed to determine whether the consumption data after refueling of the vehicle meets the set standards for emissions such as nitrogen oxides and PM. If not, the gas station is determined to be an illegal gas station.

[0003] This method in the prior art of comparing the consumption data of various oil products with the set standards to determine whether a gas station meets the national standards can accurately determine the type of gas station, but there are also some deficiencies:

[0004] 1) During the real-time analysis process, the instantaneous change of the fuel tank liquid level may cause misjudgment of the result.

[0005] 2) There are many analysis indicators for the consumption data of oil products, including the increase standard of fuel consumption per unit mileage, meeting the specified rated power standard of the engine, meeting the reactant consumption standard, meeting the nitrogen oxide emission standard, and meeting the PM emission standard. Such a large number of analysis indicators will inevitably lead to low data analysis efficiency.

[0006] 3) The timeliness of the tracking analysis is uncertain. Specifically, after the vehicle refuels at an illegal gas station, whether the consumption data of the oil product will change immediately and whether the change range is large. These uncertainties will also cause misjudgment of the result.

[0007] 4) There may be unregistered small workshops with low prices but the oil product consumption meets the set standards, which will also cause misjudgment of the result by the prior art. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to provide a method, an apparatus, and a readable storage medium for analyzing illegal gas stations in view of the above-mentioned defects of low accuracy and low efficiency in the prior art.

[0009] The technical solution adopted by the present invention to solve its technical problem is to construct a method for analyzing illegal gas stations, the method comprising sequentially performing the following steps:

[0010] Identifying refueling points: For each vehicle, sequentially traverse the trajectory of the vehicle within a past monitoring time period, identify the position points where the vehicle is in a stationary state as target position points, obtain the change in fuel tank liquid level of the vehicle at the target position point relative to the previous position point, and determine whether the target position point is a suspected refueling point based on the change in fuel tank liquid level;

[0011] Analyzing illegal refueling points: For each suspected refueling point, call the data of registered legal gas stations, and determine whether there is a legal gas station within a preset range based on the suspected refueling point. If not, consider the suspected refueling point as a suspected illegal refueling point;

[0012] Confirming illegal refueling points: Perform clustering analysis on all suspected illegal refueling points to find all clusters, and determine any suspected illegal refueling point within each cluster as an illegal refueling point.

[0013] Preferably, the method further includes, before performing the step of identifying refueling points, performing the following data preprocessing steps:

[0014] Obtain the reported data of each position point on the trajectory of each vehicle within a past monitoring time period. Each said reported data includes the reporting time, longitude and latitude of the position point, positioning status, fuel tank liquid level, speed, and engine-off status;

[0015] Clean and filter the reported data according to the positioning status and the data signs of longitude and latitude, and remove meaningless reported data.

[0016] Preferably, the cleaning and filtering of the reported data includes: Sort the reported data of each position point according to the sequence of reporting time, filter out the reported data with positioning status of base station positioning and WiFi positioning, only retain the reported data with positioning status of satellite positioning, and screen out the reported data with longitude and latitude being negative or all zeros.

[0017] Preferably, the sequentially traversing the trajectory of the vehicle within a past monitoring time period and identifying the position points where the vehicle is in a stationary state as target position points specifically includes:

[0018] Analyze the speed and engine-off status of each position point in the trajectory. If the speed corresponding to the position point is lower than the speed threshold and the engine-off status is off, determine that the position point is a target position point.

[0019] Preferably, the obtaining the change in fuel tank liquid level of the vehicle at the target position point relative to the previous position point and determining whether the target position point is a suspected refueling point based on the change in fuel tank liquid level includes:

[0020] The first-order difference is used to obtain the change in the fuel tank liquid level of the vehicle at the target position point relative to the previous position point. If the change in the fuel tank liquid level exceeds the set threshold, the target position point is determined to be a suspected refueling point.

[0021] Preferably, the clustering analysis of all suspected illegal refueling points to find all clusters includes:

[0022] Select a suspected illegal refueling point for marking and use it as the target point for the following clustering analysis: If the number of other suspected illegal refueling points within the preset radius centered on this target point is greater than or equal to the quantity threshold, it is determined that all suspected illegal refueling points within the preset radius centered on this target point form a cluster, and each suspected illegal refueling point within the cluster except this target point when the cluster is first formed and each suspected illegal refueling point within the preset radius of each newly added suspected illegal refueling point to this cluster are added to this cluster, and all suspected illegal refueling points within this cluster are marked;

[0023] Select the next unmarked suspected illegal refueling point for marking and use it as the new target point for the same clustering analysis until all suspected illegal refueling points are marked.

[0024] On the other hand, the present invention also constructs a device for analyzing illegal refueling points, and the device includes:

[0025] A refueling point recognition module, which is used to sequentially traverse the trajectories of each vehicle during a past monitoring time period, recognize the position points where the vehicle is in a stationary state as target position points, obtain the change in the fuel tank liquid level of the vehicle at the target position point relative to the previous position point, and determine whether the target position point is a suspected refueling point according to the change in the fuel tank liquid level;

[0026] An illegal refueling point analysis module, which is used to call the data of registered legal gas stations for each suspected refueling point and determine whether there is a legal gas station within the preset range centered on this suspected refueling point. If not, this suspected refueling point is considered a suspected illegal refueling point;

[0027] A confirmed illegal refueling point module, which is used to perform clustering analysis on each of all suspected illegal refueling points one by one. If it is found that a cluster is formed, any suspected illegal refueling point within this cluster is determined to be an illegal refueling point.

[0028] Preferably, the refueling point identification module is specifically configured to: sort the reported data of each position point according to the reporting time sequence, analyze the speed and the engine-off state of each position point in the trajectory. If the speed corresponding to a position point is lower than the speed threshold and the engine-off state is engine-off, then determine that this position point is the target position point; and, use the first-order difference to obtain the fuel tank liquid level change amount of the vehicle at the target position point relative to the previous position point. If the fuel tank liquid level change amount exceeds the set threshold, then determine that the target position point is a suspected refueling point;

[0029] The illegal refueling point confirmation module is specifically configured to: select a suspected illegal refueling point for marking and use it as the target point for the following clustering analysis: If the number of other suspected illegal refueling points within the preset radius centered on this target point is greater than or equal to the quantity threshold, then determine that all the suspected illegal refueling points within the preset radius centered on this target point form a cluster, and add each suspected illegal refueling point within the preset radius of each suspected illegal refueling point other than this target point in the cluster when the cluster is first formed and each suspected illegal refueling point newly added to the cluster thereafter to the cluster, and mark all the suspected illegal refueling points within the cluster; select the next unmarked suspected illegal refueling point for marking and use it as the new target point for the same clustering analysis until all the suspected illegal refueling points are marked; determine any one of the suspected illegal refueling points within each cluster as an illegal refueling point.

[0030] On the other hand, the present invention also constructs an apparatus for analyzing illegal refueling points, including a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, the steps of the method described in any one of the preceding items are implemented.

[0031] On the other hand, the present invention also constructs a computer-readable storage medium, characterized in that it stores a computer program, and when the computer program is executed by the processor, the steps of the method described in any one of the preceding items are implemented.

[0032] The method, apparatus, and readable storage medium for analyzing illegal refueling points of the present invention have the following beneficial effects: The present invention first traverses the vehicle trajectory, identifies the position points where the vehicle is in a stationary state, and obtains the fuel tank liquid level change amount at this position point, and determines whether the target position point is a suspected refueling point according to the fuel tank liquid level change amount; then for each suspected refueling point, calls the data of the registered legal gas stations to determine whether the suspected refueling point is a suspected illegal refueling point; finally, performs clustering analysis on all the suspected illegal refueling points to find all the clusters, and determines any one of the suspected illegal refueling points within each cluster as an illegal refueling point. In this way, the accuracy of the present invention is guaranteed, and there is no need to analyze multiple indicators as in the prior art, and the analysis efficiency is high. Description of the Drawings

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings:

[0034] Figure 1 It is a flowchart of the method for analyzing illegal gas stations in the first embodiment of the present invention;

[0035] Figure 2 It is a flowchart of a preferred embodiment in the first embodiment of the present invention;

[0036] Figure 3 It is a schematic diagram of the principle of cluster analysis;

[0037] Figure 4 It is a schematic structural diagram of a preferred implementation device in the second embodiment of the present invention. Detailed implementation manners

[0038] To facilitate the understanding of the present invention, the following will describe the present invention more comprehensively with reference to the relevant drawings. The typical embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0040] The ordinal terms such as "first" and "second" used in this specification can be used to describe various components, but these components are not limited by these terms. The purpose of using these terms is only to distinguish one component from other components. For example, without departing from the scope of the claims of the present invention, the first component can be named the second component, and similarly, the second component can also be named the first component.

[0041] The general idea of the present invention is as follows: First, for each vehicle, sequentially traverse the trajectory of the vehicle within a past monitoring time period, identify the position points where the vehicle is in a stationary state as target position points, obtain the change in fuel tank liquid level of the vehicle at the target position point relative to the previous position point, and determine whether the target position point is a suspected refueling point based on the change in fuel tank liquid level; Second, for each suspected refueling point, call the registered legal gas station data, and determine whether there is a legal gas station within a preset range based on the suspected refueling point. If not, the suspected refueling point is considered a suspected illegal refueling point; Finally, perform clustering analysis on all suspected illegal refueling points to find all clusters, and determine any suspected illegal refueling point within each cluster as an illegal refueling point.

[0042] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. Without conflict, the technical features in the embodiments of the present invention and the embodiments can be combined with each other.

[0043] Embodiment 1

[0044] The method of this embodiment can be executed by the server. The reported data of all vehicles will be uniformly reported to the server before. The server executes the following method to analyze illegal refueling points. Of course, a specific software platform can be designed for the server for users to access. The administrator can access the software platform through various terminals to achieve interactive control. For example, the administrator logs in to the software platform by opening a web page or an APP on the terminal. After logging in, the administrator can select the monitoring time period to be analyzed and set relevant parameters, such as various thresholds and clustering radii mentioned later. It can be understood that the server can be a single server or a group of servers. The server group can be centralized or distributed. Of course, a separate storage end can also be configured to store the reported data of the vehicles. The storage end can be a single memory or a group of memories. The server can retrieve data from the memory and execute the method of the present invention.

[0045] Reference Figure 1 , the method for analyzing illegal refueling points in this embodiment includes sequentially performing the following steps:

[0046] S100. Data preprocessing: Obtain the reported data of each position point on the trajectory of each vehicle within a past monitoring time period, and clean and filter the reported data according to the positioning status and the data symbols of longitude and latitude to remove meaningless reported data.

[0047] Specifically, each piece of reported data includes the reporting time, the longitude and latitude of the location point, the positioning status, the fuel tank level, the speed, and the ignition-off status. The data of the fuel tank level is actually a proportional value representing the proportion of the fuel volume. The ignition-off status includes the ignition-off state and the ignition state. The positioning status includes satellite positioning, base station positioning, and WiFi positioning data.

[0048] In this step, the reported data of each position point on the trajectory of each vehicle in the past monitoring period is obtained. Specifically, the reported data with the reporting time within the past monitoring period is obtained. It can be understood that the past monitoring period can be set as needed. Generally, a default value will be set during product development. Of course, the administrator can also set the specific start and end times of the past monitoring period. Then, when performing data preprocessing in this step, the server will retrieve the reported data with the reporting time between the start and end times set by the administrator.

[0049] The method of the present invention can be implemented based on various languages. In this embodiment, it is preferably implemented in Python language. The reported data of the vehicle is pre-stored in the Mysql database. Therefore, we can directly retrieve all the vehicle data from the database, and then retrieve the reported data of the vehicle according to the start and end times of the monitoring period, and then clean and filter the retrieved reported data.

[0050] Among them, the cleaning and filtering of the reported data include: for the reported data of each vehicle, sorting them in chronological order of the reporting time; since non-positioning data is meaningless and the base station positioning and WiFi positioning data may not be accurate enough, the reported data with the positioning status of base station positioning and WiFi positioning is filtered out, and only the reported data with the positioning status of satellite positioning is retained; the invalid data misreported by the vehicle is deleted, for example, the reported data with negative or all-zero longitude and latitude is screened out.

[0051] S101. Identify refueling points: For each vehicle, sequentially traverse the trajectory of the vehicle in the past monitoring period, identify the position points where the vehicle is in a stationary state as target position points, obtain the change in the fuel tank level of the vehicle at the target position point relative to the previous position point, and determine whether the target position point is a suspected refueling point based on the change in the fuel tank level;

[0052] It should be noted that when analyzing the present invention, the reported data is used as the basic analysis object. The reported data of different vehicles is independent. Therefore, even if the target position points analyzed from different vehicles are essentially the same position point, they are still treated as two target position points.

[0053] Specifically, referring to Figure 2 , in a specific embodiment, this step specifically includes the following steps:

[0054] a1: For each vehicle, sequentially traverse the vehicle's trajectory within a past monitoring time period, and analyze the speed and point flameout status of each position point in the trajectory;

[0055] a2: If the speed corresponding to the position point is lower than the speed threshold and the point flameout status is flameout, then it is determined that the vehicle is in a stationary state, and this position point is the target position point.

[0056] The speed threshold is a value approaching zero.

[0057] a3: Use the first-order difference to obtain the change amount of the fuel tank liquid level of the vehicle at the target position point relative to the previous position point. If the change amount of the fuel tank liquid level exceeds the set threshold, then it is determined that the target position point is a suspected refueling point.

[0058] As mentioned above, the reported data of each position point is sorted in the order of the reporting time. Therefore, we can use the first-order difference to obtain the change amount of the fuel tank liquid level of the vehicle at the target position point relative to the previous position point. The so-called first-order difference is to subtract the previous data from the latter data. If there is no data before the first data bit, then subtract 0 directly.

[0059] The set threshold is preferably set to 20%.

[0060] S102. Analyze illegal refueling points: For each suspected refueling point, call the data of the registered legal gas stations, and determine whether there is a legal gas station within a preset range based on this suspected refueling point. If not, then this suspected refueling point is considered a suspected illegal refueling point;

[0061] Among them, the preset range is a circle with the longitude and latitude of the suspected refueling point as the center and the set error value as the radius. For example, the error value is preferably taken as 2 kilometers.

[0062] Specifically, the data of the registered legal gas stations can be obtained from Baidu POI. Baidu POI records the information of all registered gas stations in the country that meet the national standards. Therefore, refer to Figure 2 , in a specific implementation manner, in step a4, call Baidu POI to determine whether there is a legal gas station within the preset range of the suspected refueling point. If there is, then it is considered that the change in the fuel tank liquid level is caused by normal refueling behavior. Otherwise, this suspected refueling point is considered a suspected illegal refueling point.

[0063] S103. Confirm illegal refueling points: Perform clustering analysis on all suspected illegal refueling points to find all clusters, and determine any suspected illegal refueling point within each cluster as an illegal refueling point.

[0064] Specifically, refer to Figure 2 , in a specific implementation manner, this step specifically includes the following steps:

[0065] a5: Select a suspected illegal refueling point for marking and use it as the target point for the following clustering analysis: If the number of other suspected illegal refueling points within the preset radius centered on this target point is greater than or equal to the quantity threshold, it is determined that all suspected illegal refueling points within the preset radius centered on this target point form a cluster, and the target point is the core point of this cluster. After finding the cluster, then spread all the points inside this cluster. The specific spreading method is: on the one hand, add the other suspected illegal refueling points within the preset radius of each suspected illegal refueling point inside the cluster except this target point when the cluster is first formed to this cluster; on the other hand, also add the other suspected illegal refueling points within the preset radius of each newly added suspected illegal refueling point to this cluster later. Finally, mark all the suspected illegal refueling points inside this cluster.

[0066] It can be understood that the purpose of marking the suspected illegal refueling points is to not consider the already marked points when selecting a new target point in the subsequent step a6.

[0067] The DBSCAN algorithm is a density-based clustering algorithm that can divide areas with sufficient high density into clusters. DBSCAN requires two parameters, the radius Eps (i.e., the above-mentioned preset radius) and the minimum number of points MinPts (i.e., the above-mentioned quantity threshold), that is, if the number of points within the circle with the current point as the center and Eps as the radius is greater than or equal to MinPts, then the current point and the nearby MinPts points form a cluster. Since DBSCAN uses the Euclidean distance for calculation, during the clustering analysis, it is necessary to convert the longitude and latitude of the suspected illegal refueling points into points on the plane rectangular coordinate system, and then use DBSCAN for clustering. If there are some suspected illegal refueling points that can form a cluster through this clustering algorithm, it indicates that there are suspected illegal refueling points in this preset radius area; otherwise, it belongs to a misjudgment.

[0068] a6: Select the next unmarked suspected illegal refueling point for marking and use it as the new target point for the same clustering analysis until all suspected illegal refueling points are marked.

[0069] a7: Determine any suspected illegal refueling point within each cluster as an illegal refueling point.

[0070] Reference Figure 3, assuming that A1, A2, A3, and A4 are suspected illegal refueling points analyzed from vehicle A’s data; B1 and B2 are suspected illegal refueling points analyzed from vehicle B’s data, and the cluster analysis’s MinPts=2. Then it is necessary to perform cluster analysis on A1, A2, A3, A4, B1, B2, and B3 one by one. First, cluster analysis is performed on A1, and the corresponding analysis range is circle Q-A1 with A1 as the center. Because points A1, A2, and B1 are in circle Q-A1, they meet the requirement of being greater than or equal to MinPts. Therefore, it is considered that points A1, A2, and B1 form a cluster. When the cluster is first formed, each suspected illegal refueling point in the cluster except point A1, that is, other suspected illegal refueling points within the preset radius of A2 and B1 are added to the cluster. That is, circle Q-A2 with A2 as the center and circle Q-B1 with B1 as the center are searched respectively. It is found that there is no new point in circle Q-A2, and a new point B2 is found in circle Q-B1, so B2 is added to the cluster. Then, each suspected illegal refueling point newly added to the cluster, that is, other suspected illegal refueling points within the preset radius of B2 are added to the cluster. It is found that there is no new point in circle Q-B2. Therefore, the clusters finally formed are A1, A2, B1, and B2. Then A1, A2, B1, and B2 are all marked as visited. Then cluster analysis is performed on the next point A3 that is not marked as visited. It is found that the points in circle Q-A3 are not clustered. A3 is marked as visited. Then cluster analysis is performed on the next point A4 that is not marked as visited. It is found that the points in circle Q-A4 are not clustered. A4 is marked as visited. So far, all points have been marked as visited. So next, for each cluster found before, a suspected illegal refueling point is randomly selected from the cluster to be determined as an illegal refueling point. In other words, the number of clusters corresponds to the number of illegal refueling points. For example, this time we only found the cluster A1, A2, B1, and B2. Therefore, we can arbitrarily select a point from A1, A2, B1, and B2 as an illegal refueling point.

[0071] Based on the above method, this embodiment improves the accuracy of the analysis of illegal refueling points through cluster analysis, and the present invention does not need to analyze multiple indicators like the prior art, and has high analysis efficiency.

[0072] Embodiment 2

[0073] refer to Figure 4 Based on the same concept, this embodiment discloses a device for analyzing illegal refueling points, the device comprising: a data preprocessing module 200, a refueling point identification module 201, an illegal refueling point analysis module 202, and an illegal refueling point confirmation module 203.

[0074] The data preprocessing module 200 is used to obtain the reported data of each position point on the trajectory of each vehicle within a past monitoring time period, clean and filter the reported data according to the positioning status and the data symbols of longitude and latitude, and remove meaningless reported data. For more details, see the part of step S100 in the above-mentioned first embodiment.

[0075] The refueling point identification module 201 is used to sequentially traverse the trajectory of each vehicle within a past monitoring time period for each vehicle, identify the position points where the vehicle is in a stationary state as target position points, obtain the change amount of the fuel tank liquid level of the vehicle at the target position point relative to the previous position point, and determine whether the target position point is a suspected refueling point according to the change amount of the fuel tank liquid level.

[0076] Specifically, the refueling point identification module 201 sorts the reported data of each position point according to the sequence of the reporting time, analyzes the speed and the point flameout state of each position point in the trajectory. If the speed corresponding to the position point is lower than the speed threshold and the point flameout state is flameout, then it is determined that the position point is a target position point; and, the change amount of the fuel tank liquid level of the vehicle at the target position point relative to the previous position point is obtained by using the first-order difference. If the change amount of the fuel tank liquid level exceeds the set threshold, it is determined that the target position point is a suspected refueling point. For more details, see the part of step S101 in the above-mentioned first embodiment.

[0077] The illegal refueling point analysis module 202 is used to call the data of the registered legal gas stations for each suspected refueling point, and determine whether there is a legal gas station within a preset range based on the suspected refueling point. If not, the suspected refueling point is considered a suspected illegal refueling point. For more details, see the part of step S102 in the above-mentioned first embodiment.

[0078] The illegal refueling point confirmation module 203 is used to perform clustering analysis on all suspected illegal refueling points one by one. If it is found through analysis that a cluster is formed, any one of the suspected illegal refueling points within the cluster is determined as an illegal refueling point.

[0079] Specifically, the illegal gas station confirmation module 203 is specifically configured to: select a suspected illegal gas station for marking and use it as a target point for the following clustering analysis: if the number of other suspected illegal gas stations within a preset radius centered on the target point is greater than or equal to the quantity threshold, it is determined that all suspected illegal gas stations within the preset radius centered on the target point form a cluster, and each suspected illegal gas station within the cluster except the target point when the cluster is first formed and each suspected illegal gas station within the preset radius of each newly added suspected illegal gas station after that are added to the cluster, and all suspected illegal gas stations within the cluster are marked; select the next unmarked suspected illegal gas station for marking and use it as a new target point for the same clustering analysis until all suspected illegal gas stations are marked; finally, any suspected illegal gas station within each cluster is determined as an illegal gas station. For more details, refer to the part of step S103 in the above-mentioned embodiment 1.

[0080] The functions of the functional modules of the device according to the embodiments of the present invention can be specifically implemented according to the methods in the above method embodiments, and the specific implementation process can refer to the relevant descriptions of the above method embodiments, which will not be elaborated here.

[0081] The above description involves various modules. These modules generally include hardware and / or a combination of hardware and software. These modules may also include a computer-readable medium containing instructions, and when the processor executes these instructions, various functional features of the present invention can be executed. Accordingly, unless explicitly required, the scope of the present invention is not limited by the specific hardware and / or software characteristics in the modules explicitly mentioned in the embodiments. As a non-limiting example, the present invention can be implemented by one or more processors executing software instructions in the embodiments. It should be noted that in the above description of various modules, dividing them into these modules is for the sake of clarity. However, in actual implementation, the boundaries of various modules can be blurred. For example, any or all of the functional modules herein can share various hardware and / or software elements. Also, for example, any and / or all of the functional modules herein can be fully or partially implemented by a shared processor executing software instructions. Additionally, various software sub-modules executed by one or more processors can be shared among various software modules. Accordingly, unless explicitly required, the scope of the present invention is not limited by the mandatory boundaries between various hardware and / or software elements.

[0082] Embodiment 3

[0083] Based on the same inventive concept, an embodiment of the present invention further provides a device for analyzing illegal gas stations, including a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the steps of the method described in the above embodiments are implemented. The specific implementation process can refer to the description of the above method embodiments and will not be elaborated here.

[0084] Embodiment 4

[0085] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium storing a computer program. When the computer program is executed by the processor, the steps of the method described in the above embodiments are implemented. The specific implementation process can refer to the description of the above method embodiments and will not be elaborated here.

[0086] In summary, the method, device, and readable storage medium for analyzing illegal gas stations of the present invention have the following beneficial effects: First, by traversing vehicle trajectories, the present invention identifies the position points where the vehicle is in a stationary state and obtains the change amount of the fuel tank liquid level at these position points. Then, it determines whether the target position point is a suspected gas station based on the change amount of the fuel tank liquid level. Next, for each suspected gas station, it calls the data of registered legal gas stations to determine whether the suspected gas station is a suspected illegal gas station. Finally, it performs clustering analysis on all suspected illegal gas stations to find all clusters and determines any one of the suspected illegal gas stations within each cluster as an illegal gas station. In this way, the accuracy of the present invention is guaranteed, and it is not necessary to analyze multiple indicators as in the prior art, so the analysis efficiency is high.

[0087] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit and scope protected by the present invention and the claims. All of these are within the protection scope of the present invention.

Claims

1. A method for analyzing illegal gas stations, characterized in that, The method includes sequentially performing the following steps: Identifying refueling points: For each vehicle, sequentially traverse the trajectory of the vehicle within a past monitoring time period, identify the position points where the vehicle is in a stationary state as target position points, obtain the change in fuel tank liquid level of the vehicle at the target position point relative to the previous position point, and determine whether the target position point is a suspected refueling point based on the change in fuel tank liquid level; Analyzing illegal refueling points: For each suspected refueling point, call the data of the registered legal gas stations, and determine whether there is a legal gas station within a preset range with the suspected refueling point as the reference. If not, the suspected refueling point is considered a suspected illegal refueling point; Confirming illegal refueling points: Perform clustering analysis on all suspected illegal refueling points to find all clusters, and determine any one of the suspected illegal refueling points within each cluster as an illegal refueling point; The performing clustering analysis on all suspected illegal refueling points to find all clusters includes: Select a suspected illegal refueling point for marking and use it as a target point for the following clustering analysis: If the number of other suspected illegal refueling points within a preset radius with the target point as the center is greater than or equal to the quantity threshold, it is determined that all the suspected illegal refueling points within the preset radius with the target point as the center form a cluster, and add each suspected illegal refueling point within the cluster except the target point when the cluster is first formed and each suspected illegal refueling point within the preset radius of each newly added suspected illegal refueling point within the cluster to the cluster, and mark all the suspected illegal refueling points within the cluster; Select the next unmarked suspected illegal refueling point for marking and use it as a new target point for the same clustering analysis until all suspected illegal refueling points are marked.

2. The method for analyzing illegal gas stations according to claim 1, wherein The method further includes, before performing the step of identifying refueling points, performing the following data preprocessing steps: Obtain the reported data of each position point on the trajectory of each vehicle within a past monitoring time period, and each said reported data includes the reporting time, longitude and latitude of the position point, positioning status, fuel tank liquid level, speed, and engine-off status; Clean and filter the reported data according to the positioning status and the data signs of longitude and latitude, and remove meaningless reported data.

3. The method according to claim 2, characterized in that The cleaning and filtering of the reported data includes: Sort the reported data of each position point in chronological order of the reporting time, filter out the reported data with the positioning status of base station positioning and WiFi positioning, only retain the reported data with the positioning status of satellite positioning, and screen out the reported data with negative or all-zero longitude and latitude.

4. The method for analyzing illegal gas stations according to claim 1, characterized in that The sequentially traversing the trajectory of the vehicle within a past monitoring time period and identifying the position points where the vehicle is in a stationary state as target position points specifically includes: Analyze the speed and engine-off status of each position point in the trajectory. If the speed corresponding to the position point is lower than the speed threshold and the engine-off status is engine-off, it is determined that the position point is a target position point.

5. The method for analyzing illegal gas stations according to claim 1, characterized in that, The obtaining the change in fuel tank liquid level of the vehicle at the target position point relative to the previous position point and determining whether the target position point is a suspected refueling point based on the change in fuel tank liquid level includes: The first-order difference is used to obtain the change in the fuel tank liquid level of the vehicle at the target position point relative to the previous position point. If the change in the fuel tank liquid level exceeds a set threshold, the target position point is determined to be a suspected refueling point.

6. An apparatus for analyzing an illegal gas station, characterized in that, The device includes: A refueling point identification module, which is used to sequentially traverse the trajectories of each vehicle within a past monitoring time period, identify the position points where the vehicle is in a stationary state as target position points, obtain the change in the fuel tank liquid level of the vehicle at the target position point relative to the previous position point, and determine whether the target position point is a suspected refueling point based on the change in the fuel tank liquid level; An illegal refueling point analysis module, which is used to, for each suspected refueling point, call the data of registered legal gas stations and determine whether there is a legal gas station within a preset range centered on the suspected refueling point. If not, the suspected refueling point is considered a suspected illegal refueling point; An illegal refueling point confirmation module, which is used to perform clustering analysis on all suspected illegal refueling points one by one. If it is found through analysis that a cluster is formed, any one of the suspected illegal refueling points within the cluster is determined to be an illegal refueling point; The illegal refueling point confirmation module specifically is used to: select a suspected illegal refueling point for marking and use it as a target point for the following clustering analysis: if the number of other suspected illegal refueling points within a preset radius centered on the target point is greater than or equal to a quantity threshold, it is determined that all suspected illegal refueling points within the preset radius centered on the target point form a cluster, and each suspected illegal refueling point within the cluster except the target point when the cluster is first formed and each suspected illegal refueling point newly added to the cluster and other suspected illegal refueling points within their preset radii are added to the cluster, and all suspected illegal refueling points within the cluster are marked; select the next unmarked suspected illegal refueling point for marking and use it as a new target point for the same clustering analysis until all suspected illegal refueling points are marked; determine any one of the suspected illegal refueling points within each cluster to be an illegal refueling point.

7. The device for analyzing illegal refueling points according to claim 6, wherein The refueling point identification module specifically is used to: sort the reported data of each position point in the order of the reporting time, analyze the speed and the engine-off state of each position point in the trajectory. If the speed corresponding to the position point is lower than a speed threshold and the engine-off state is engine-off, then it is determined that the position point is a target position point; and the first-order difference is used to obtain the change in the fuel tank liquid level of the vehicle at the target position point relative to the previous position point. If the change in the fuel tank liquid level exceeds a set threshold, the target position point is determined to be a suspected refueling point.

8. An apparatus for analyzing an illegal gas station, characterized in that, It includes a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, the steps of the method according to any one of claims 1-5 are implemented.

9. A computer-readable storage medium, characterized in that, Stores a computer program, and when the computer program is executed by the processor, the steps of the method according to any one of claims 1-5 are implemented.

Images