Camp transfer non-vehicle abnormal behavior early warning method and device, electronic equipment and storage medium

Abstract

This invention provides a method, device, electronic device, and storage medium for early warning of abnormal behavior of vehicles transitioning from commercial to non-commercial use. Belonging to the technical field of smart city digital roads, this method constructs a refined spatiotemporal feature system with hourly granularity and utilizes a commercial operation behavior identification model to deeply mine the spatiotemporal evolution patterns of vehicles throughout the entire time period. This effectively overcomes the shortcomings of traditional investigation methods, which rely on manual experience, have single feature dimensions, and struggle to identify concealed illegal operation behaviors. This solution not only achieves automated and high-precision identification of abnormal operation modes of vehicles transitioning from commercial to non-commercial use, significantly reducing false alarm and false negative rates, but also accurately identifies high-risk vehicles suspected of long-term illegal operation through a dual verification mechanism of "daily suspicion score + periodic frequency." This greatly improves the investigation efficiency and early warning timeliness of regulatory departments, providing scientific and objective data-driven decision support for combating illegal operations.

Description

Technical Field

[0001] This invention relates to the technical field of smart city digital roads, and in particular to a method, device, electronic device, and storage medium for early warning of abnormal behavior of commercial-to-non-commercial vehicles. Background Technology

[0002] As the operating time of commercial vehicles increases, their maintenance and investment costs gradually rise. Some commercial vehicles are suspended from operation or resold to organizations or individuals before reaching their scrapping deadline, thus changing their original "commercial" status to "non-commercial." Some of these converted vehicles may be accident vehicles that have suffered serious collisions, affecting their structure and performance and posing potential safety issues. Most of these converted vehicles have typically been driven for a considerable period, experiencing wear and tear, and their braking, steering, or suspension systems may have potential malfunctions, increasing the risk of accidents. Continuing to operate such vehicles greatly increases the likelihood of serious traffic accidents, and in the event of an accident or service dispute, many passengers' legal rights are difficult to protect effectively. Therefore, investigating and prosecuting vehicles suspected of illegal operation after being converted from commercial to non-commercial use is of significant practical importance.

[0003] Currently, the investigation of vehicles suspected of illegal operation after being converted from commercial to non-commercial use mainly relies on manual checkpoints set up by law enforcement officers. However, these vehicles are highly camouflaged, with little difference in appearance from other ordinary non-commercial vehicles, and their drivers often communicate with each other, leading to reduced efficiency in vehicle inspections. Furthermore, manual checkpoints are not only costly in terms of manpower and resources but also inherently prone to inaccuracies and chance, failing to comprehensively cover all vehicles converted from commercial to non-commercial use and hindering precise enforcement.

[0004] In summary, traditional methods for investigating abnormal behavior of vehicles converted from commercial to non-commercial use suffer from technical problems such as low efficiency and low accuracy. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method, device, electronic device and storage medium for early warning of abnormal behavior of commercial vehicles converted to non-commercial vehicles, so as to alleviate the technical problems of low efficiency and low accuracy in the investigation of abnormal behavior of traditional commercial vehicles converted to non-commercial vehicles.

[0006] In a first aspect, the present invention provides a method for early warning of abnormal behavior of vehicles transitioning from commercial to non-commercial use, comprising: Collect raw vehicle passage data containing vehicle identification, vehicle attributes, and passage time and space information, and generate a standardized vehicle passage record set after preprocessing; Based on the standardized vehicle passage record set, multi-dimensional trajectory features are extracted with hours as the basic time unit, and the multi-dimensional trajectory features of each hour within a single day are aggregated in time sequence to construct a daily spatiotemporal behavior feature vector that characterizes the spatiotemporal evolution of vehicles throughout the entire time period. The daily spatiotemporal behavioral feature vectors of the vehicles to be detected as commercial vehicles are used to identify their operational behavior, and a daily suspicion score is obtained to determine the similarity between the daily behavior of the vehicles to be detected as commercial vehicles and the abnormal operation mode. The system calculates the cumulative frequency of daily suspicion scores exceeding a preset threshold within a preset period. If the cumulative frequency reaches the preset frequency threshold, an abnormal behavior warning signal containing vehicle identification and key suspected vehicles is generated.

[0007] Furthermore, raw vehicle passage data containing vehicle identification, vehicle attributes, and spatiotemporal information is collected, including: High-definition checkpoint equipment deployed at intersections captures real-time spatiotemporal information of passing vehicles, including at least: license plate number, vehicle type, direction of travel, and time of passage. The passage time and space information is transmitted to the central data server for storage in real time; Based on the aforementioned traffic time and space information, vehicle passage data for all intersections is extracted from the central data server as the original vehicle passage data; The preprocessing includes: cleaning, time alignment, and classification.

[0008] Furthermore, the multidimensional trajectory features include: hourly distribution features of vehicle activity frequency within an hour, hourly longitude range features of vehicle longitude variation range within an hour, hourly latitude range features of vehicle latitude variation range within an hour, hourly four-point area features of the hourly travel area coverage based on the four outermost points of the vehicle trajectory, hourly trajectory density features of the number and distribution density of trajectory points passed by the vehicle within an hour, hourly trajectory point number features of the number of all checkpoints passed by the vehicle within an hour, and hourly trajectory distance features of the total travel distance of the vehicle within an hour.

[0009] Furthermore, the operation behavior identification model includes a convolutional neural network model; the method further includes: Obtain a sample vehicle set with known operating attributes, wherein the sample vehicle set includes: sample data labeled as operating vehicles and non-operating vehicles; Extract the daily spatiotemporal behavior feature vectors of each vehicle in the sample vehicle set to obtain daily spatiotemporal behavior feature vectors with operational attributes. The convolutional neural network model is trained using daily spatiotemporal behavioral feature vectors with operational attributes to obtain the operational behavior recognition model, wherein the operational behavior recognition model can distinguish the differences in behavioral patterns between operational and non-operational vehicles in the time dimension.

[0010] Furthermore, the vehicles to be detected that have been converted from commercial to non-commercial use are vehicles whose vehicle operation attributes have been registered as such; the daily spatiotemporal behavioral feature vectors of the vehicles to be detected are used to identify their operational behavior using an operational behavior identification model, including: The daily spatiotemporal behavioral feature vector of the vehicle to be detected (transferring from commercial to non-commercial use) is input into the commercial behavior recognition model, and the daily suspicion score of the vehicle to be detected is output.

[0011] Further, the preset period is one week, and the preset frequency threshold is four times; the cumulative frequency of the daily suspicion score exceeding the preset threshold within the preset period is counted. If the cumulative frequency reaches the preset frequency threshold, it includes: The cumulative frequency of the daily suspicion score of the vehicle to be detected exceeding the preset threshold within one week is counted. If the cumulative frequency reaches the preset frequency threshold, the vehicle to be detected that is converted from commercial to non-commercial use will be marked as a key suspected vehicle.

[0012] Furthermore, the method also includes: The abnormal behavior warning signal is pushed to the monitoring terminal for display; And / or, automatically trigger on-site inspection instructions targeting the vehicle identification based on the key suspected vehicle.

[0013] Secondly, the present invention also provides an early warning device for abnormal behavior of vehicles converted from commercial to non-commercial use, comprising: The data acquisition and preprocessing unit is used to acquire raw vehicle passage data containing vehicle identification, vehicle attributes and passage time and space information, and after preprocessing, generate a standardized vehicle passage record set. The extraction and construction unit is used to extract multi-dimensional trajectory features based on the standardized vehicle passage record set, with the hour as the basic time unit, and to aggregate the multi-dimensional trajectory features of each hour within a single day in chronological order to construct a daily spatiotemporal behavior feature vector that characterizes the spatiotemporal evolution law of vehicles throughout the entire time period. The operation behavior identification unit is used to identify the operation behavior of the vehicle to be detected as a commercial vehicle using the daily spatiotemporal behavior feature vector of the vehicle to be detected as a commercial vehicle, and to obtain a daily suspicion score of the similarity between the daily behavior of the vehicle to be detected as a commercial vehicle and the abnormal operation mode. The early warning unit is used to count the cumulative frequency of the daily suspicion score exceeding a preset threshold within a preset period. If the cumulative frequency reaches the preset frequency threshold, an abnormal behavior early warning signal containing vehicle identification and key suspected vehicles is generated.

[0014] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method described in the first aspect.

[0015] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the method described in the first aspect.

[0016] This invention provides a method for early warning of abnormal behavior of vehicles transitioning from commercial to non-commercial use, comprising: collecting raw vehicle passage data including vehicle identification, vehicle attributes, and spatiotemporal information; generating a standardized vehicle passage record set after preprocessing; extracting multidimensional trajectory features based on the standardized vehicle passage record set, using hours as the basic time unit, and aggregating the multidimensional trajectory features of each hour within a single day in chronological order to construct a daily spatiotemporal behavior feature vector characterizing the spatiotemporal evolution pattern of the vehicle throughout the entire time period; using a commercial operation behavior identification model to identify the daily spatiotemporal behavior feature vector of the vehicle to be detected, obtaining a daily suspicion score indicating the similarity between the daily behavior of the vehicle to be detected and the abnormal operation mode; and counting the cumulative frequency of the daily suspicion score exceeding a preset threshold within a preset period. If the cumulative frequency reaches the preset frequency threshold, an abnormal behavior early warning signal including vehicle identification and key suspected vehicles is generated. As described above, the abnormal behavior early warning method for commercial-to-non-commercial vehicles of the present invention effectively overcomes the shortcomings of traditional investigation methods, which rely on manual experience, have single feature dimensions, and are difficult to identify concealed illegal operation behaviors, by constructing a refined spatiotemporal feature system with hourly granularity and using an operation behavior identification model to deeply mine the spatiotemporal evolution law of vehicles throughout the entire period. This solution not only realizes the automated and high-precision identification of abnormal operation modes of "commercial-to-non-commercial" vehicles, significantly reducing the false alarm rate and false negative rate, but also accurately locks high-risk vehicles suspected of long-term illegal operation through a dual verification mechanism of "daily suspicion score + periodic frequency". This greatly improves the investigation efficiency and early warning timeliness of regulatory departments, provides scientific and objective data decision support for combating illegal operation, and alleviates the technical problems of low efficiency and low accuracy in the investigation of abnormal behavior of traditional commercial-to-non-commercial vehicles. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1A flowchart of an early warning method for abnormal behavior of vehicles converted from commercial to non-commercial use, provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of an abnormal behavior warning device for commercial vehicles converted to non-commercial vehicles, provided in an embodiment of the present invention. Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Traditional methods for investigating abnormal behavior of vehicles converted from commercial to non-commercial use are inefficient and inaccurate.

[0021] Based on this, the abnormal behavior early warning method for commercial-to-non-commercial vehicles of the present invention constructs a refined spatiotemporal feature system with hourly granularity and utilizes a commercial operation behavior identification model to deeply mine the spatiotemporal evolution pattern of vehicles throughout the entire time period. This effectively overcomes the shortcomings of traditional investigation methods, which rely on manual experience, have single feature dimensions, and are difficult to identify concealed illegal operation behaviors. This solution not only achieves automated and high-precision identification of abnormal operation modes of "commercial-to-non-commercial" vehicles, significantly reducing the false alarm rate and false negative rate, but also accurately identifies high-risk vehicles suspected of long-term illegal operation through a dual verification mechanism of "daily suspicion score + periodic frequency". This greatly improves the investigation efficiency and early warning timeliness of regulatory departments and provides scientific and objective data decision support for combating illegal operation.

[0022] To facilitate understanding of this embodiment, a method for early warning of abnormal behavior of commercial vehicles converted to non-commercial vehicles, as disclosed in this embodiment of the invention, will first be described in detail.

[0023] Example 1: According to an embodiment of the present invention, an embodiment of a method for early warning of abnormal behavior of commercial vehicles converted to non-commercial vehicles is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] Figure 1 This is a flowchart of an abnormal behavior warning method for commercial vehicles converted to non-vehicle use according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps: Step S102: Collect raw vehicle passage data containing vehicle identification, vehicle attributes and passage time and space information, and generate a standardized vehicle passage record set after preprocessing; Step S104: Based on the standardized vehicle passage record set, multi-dimensional trajectory features are extracted with hours as the basic time unit, and the multi-dimensional trajectory features of each hour within a single day are aggregated in time sequence to construct a daily spatiotemporal behavior feature vector that characterizes the spatiotemporal evolution of vehicles throughout the entire time period. Step S106: The daily spatiotemporal behavioral feature vector of the vehicle to be detected as a commercial vehicle is used to identify its daily operational behavior, and the daily suspicion score of the similarity between the daily behavior of the vehicle to be detected as a commercial vehicle and the abnormal operation mode is obtained. Specifically, the aforementioned operational behavior identification model is pre-trained using daily spatiotemporal behavioral feature vector samples labeled with operational attributes. This operational behavior identification model can distinguish the differences in behavioral patterns of vehicles with different operational attributes in the time dimension. The aforementioned abnormal operational pattern refers to the operational pattern of operational vehicles. Because for the vehicle to be detected as a non-operational vehicle, its operational attribute has changed from operational to non-operational. Therefore, for the vehicle to be detected as a non-operational vehicle, its normal operational pattern should be the operational pattern of a non-operational vehicle, and its behavioral pattern should be the same as that of a non-operational vehicle. If its behavioral pattern is more similar to that of an operational vehicle, then the probability of it being suspected of abnormal operation is very high, that is, the daily suspicion score is high.

[0025] The aforementioned daily suspicion score is actually the probability value of the detected commercial-to-non-commercial vehicle having operational characteristics on that day (which is also the suspicion score of illegal operation on that day).

[0026] Vehicles converted from commercial to non-commercial use refer to vehicles that have been converted from commercial to non-commercial use. The transportation department revokes their road transport permits, and they no longer meet the conditions for operation.

[0027] Step S108: Calculate the cumulative frequency of daily suspicion scores exceeding a preset threshold within a preset period. If the cumulative frequency reaches the preset frequency threshold, generate an abnormal behavior warning signal that includes vehicle identification and key suspected vehicles.

[0028] Specifically, the aforementioned preset threshold is a reasonable suspicion threshold set based on historical data and / or actual circumstances. In implementation, original vehicle passage data from historical operating vehicles is selected, and daily spatiotemporal behavior feature vectors of historical operating vehicles are obtained based on this data. Then, an operating behavior identification model is used to identify the operating behavior of the historical operating vehicles using these daily spatiotemporal behavior feature vectors, resulting in daily suspicion scores for all historical operating vehicles. Finally, the average of the daily suspicion scores for all historical operating vehicles is calculated, and this average is set as the aforementioned preset threshold.

[0029] The above provides a brief overview of the abnormal behavior warning method for commercial vehicles converted to non-commercial use according to the present invention. The specific details involved are described in detail below.

[0030] In an optional embodiment of the present invention, collecting raw vehicle passage data including vehicle identification, vehicle attributes, and passage time and space information specifically includes the following steps: (1) Real-time capture of the spatiotemporal information of passing vehicles by high-definition checkpoint equipment deployed at intersections, wherein the spatiotemporal information includes at least: license plate number, vehicle type, driving direction and passing time; Specifically, high-definition checkpoints (i.e., high-definition checkpoint equipment) are installed at each intersection in all directions. These high-definition checkpoints can capture real-time spatiotemporal information of passing vehicles, including license plate number, vehicle type, direction of travel, and passage time.

[0031] (2) Transmit the travel time and space information to the central data server for storage in real time; Specifically, the spatiotemporal information of each high-definition checkpoint is transmitted to the central data server in real time, ensuring the integrity and timeliness of the information. This data is stored on the server, providing a basis for subsequent analysis and processing.

[0032] (3) Extract all intersection vehicle passage data from the central data server based on the spatiotemporal information of traffic, and use it as the raw vehicle passage data; Specifically, based on the spatiotemporal information of passage, the vehicle passage data recorded at all checkpoints is extracted from the central data server to obtain the raw vehicle passage data.

[0033] The above preprocessing includes: cleaning, time alignment, and classification.

[0034] The specific preprocessing process can be as follows: cleaning the original vehicle passage data, including removing duplicate records, completing missing key field records, and removing noisy data with logical anomalies; then, performing time alignment processing on the cleaned data, specifically unifying the timestamp format and mapping discrete vehicle passage times to a standard hourly time axis; finally, classifying and organizing the time-aligned data according to date and license plate number to generate a standardized vehicle passage record set.

[0035] In an optional embodiment of the present invention, the multidimensional trajectory features include: hourly distribution features of vehicle activity frequency within an hour (used to identify vehicle usage patterns, referring to dividing a 24-hour day into 24 time windows, counting the frequency of vehicle appearance in each window, and forming a vector characterizing the vehicle's work and rest patterns), hourly longitude range features of vehicle longitude variation within an hour (used to determine the vehicle's driving range and the east-west expansion of the trajectory), hourly latitude range features of vehicle latitude variation within an hour (used to determine the vehicle's driving range and the north-south expansion of the trajectory), hourly four-point area features of the hourly driving area coverage calculated based on the four outermost points of the vehicle trajectory, hourly trajectory density features of the number and distribution density of trajectory points passed by the vehicle within an hour (used to analyze the concentration of vehicle activity), hourly trajectory point number features of the number of all checkpoints passed by the vehicle within an hour (used to assess the frequency of vehicle activity), and hourly trajectory distance features of the total driving distance of the vehicle within an hour (used to analyze the vehicle's driving path and activity range during that time period).

[0036] Specifically, the calculation process of the above-mentioned multidimensional trajectory features is introduced as follows: Hourly longitude range: ,in, Indicates the first Longitude of the hour, in degrees (°).

[0037] Hourly latitude range: ,in, Indicates the first Latitude of the hour, in degrees (°).

[0038] Hourly boundaries and area: ,in, Indicates the first The area of ​​the four sides of the hour.

[0039] Hourly trajectory density: ,in, Indicates the number of sample points; and Indicates bandwidth parameters, respectively used for and Smoothness of direction; It is a kernel function; the kernel function used in this invention is... .

[0040] Hourly track distance: ,in, It is the first and the The distance between points; It represents the total number of points.

[0041] In an optional embodiment of the present invention, the operation behavior identification model includes: a convolutional neural network model; the method further includes: (1) Obtain a sample vehicle set with known operating attributes, wherein the sample vehicle set includes: sample data labeled as operating vehicles and non-operating vehicles; Specifically, the aforementioned sample vehicle set is also the original vehicle data.

[0042] (2) Extract the daily spatiotemporal behavior feature vectors of each vehicle in the sample vehicle set to obtain daily spatiotemporal behavior feature vectors with operational attributes. The extraction process described above is the same as the process for obtaining the daily spatiotemporal behavior feature vector described above, and will not be repeated here.

[0043] (3) The convolutional neural network model is trained using the daily spatiotemporal behavior feature vector with operational attributes to obtain the operational behavior recognition model. The operational behavior recognition model can distinguish the differences in the behavioral patterns of operational vehicles and non-operational vehicles in the time dimension.

[0044] In an optional embodiment of the present invention, the vehicle to be detected as a commercial-to-non-commercial vehicle is a vehicle whose vehicle operation attribute is registered as commercial-to-non-commercial; the operation behavior identification model is used to identify the operation behavior of the vehicle to be detected based on its daily spatiotemporal behavioral feature vector, specifically including the following steps: The daily spatiotemporal behavioral feature vectors of the vehicles to be detected as commercial vehicles are input into the commercial vehicle behavior recognition model, and the daily suspicion score of the vehicles to be detected as commercial vehicles is output.

[0045] In an optional embodiment of the present invention, the preset period is one week, and the preset frequency threshold is four times; the cumulative frequency of daily suspicion scores exceeding the preset threshold within the preset period is counted; if the cumulative frequency reaches the preset frequency threshold, the specific steps include the following: (1) Calculate the cumulative frequency of daily suspicion scores exceeding a preset threshold for vehicles to be tested that have been converted from commercial to non-commercial use within one week; (2) If the cumulative frequency reaches the preset frequency threshold, the vehicle to be detected that is converted from commercial to non-commercial use will be marked as a key suspected vehicle.

[0046] Specifically, if a vehicle undergoing commercial-to-non-commercial conversion exceeds a preset threshold in its daily suspicion score for at least four days within a week, it will be marked as a key suspect vehicle.

[0047] In an optional embodiment of the present invention, the method further includes the following steps: The abnormal behavior warning signal will be pushed to the monitoring terminal for display; And / or, Based on key suspected vehicles, an on-site inspection command targeting the vehicle's identification will be automatically triggered.

[0048] Example 2: This invention also provides an abnormal behavior warning device for commercial vehicles converted to non-commercial use. This device is mainly used to execute the abnormal behavior warning method for commercial vehicles converted to non-commercial use provided in Embodiment 1 of this invention. The following is a detailed description of the abnormal behavior warning device for commercial vehicles converted to non-commercial use provided in this invention.

[0049] Figure 2 This is a schematic diagram of an abnormal behavior warning device for commercial vehicles converted to non-vehicle use according to an embodiment of the present invention, as shown below. Figure 2 As shown, the device mainly includes: a data acquisition and preprocessing unit 10, an extraction and construction unit 20, an operation behavior identification unit 30, and an early warning unit 40, wherein: The data acquisition and preprocessing unit 10 is used to acquire raw vehicle passage data containing vehicle identification, vehicle attributes and passage time and space information, and generate a standardized vehicle passage record set after preprocessing. Extraction and construction unit 20 is used to extract multi-dimensional trajectory features based on a standardized vehicle passage record set, with hours as the basic time unit, and to aggregate the multi-dimensional trajectory features of each hour within a single day in chronological order to construct a daily spatiotemporal behavior feature vector that characterizes the spatiotemporal evolution of vehicles throughout the entire time period. The operation behavior identification unit 30 is used to identify the daily spatiotemporal behavior feature vector of the vehicle to be detected as a commercial vehicle using the operation behavior identification model, and obtain the daily suspicion score of the similarity between the daily behavior of the vehicle to be detected as a commercial vehicle and the abnormal operation mode. The early warning unit 40 is used to count the cumulative frequency of daily suspicion scores exceeding a preset threshold within a preset period. If the cumulative frequency reaches the preset frequency threshold, an abnormal behavior early warning signal containing vehicle identification and key suspected vehicles is generated.

[0050] Optionally, the acquisition and preprocessing unit is also used to: capture the spatiotemporal information of passing vehicles in real time through high-definition checkpoint equipment deployed at intersections, wherein the spatiotemporal information includes at least: license plate number, vehicle type, driving direction and passing time; transmit the spatiotemporal information to the central data server for storage in real time; extract the passing data of all intersections from the central data server based on the spatiotemporal information as the raw passing data; and preprocessing includes: cleaning, time alignment and classification.

[0051] Optionally, the multidimensional trajectory features include: hourly distribution features of vehicle activity frequency within an hour, hourly longitude range features of vehicle longitude variation range within an hour, hourly latitude range features of vehicle latitude variation range within an hour, hourly four-point area features of the hourly travel area coverage based on the four outermost points of the vehicle trajectory, hourly trajectory density features of the number and distribution density of trajectory points passed by the vehicle within an hour, hourly trajectory point number features of the number of all checkpoints passed by the vehicle within an hour, and hourly trajectory distance features of the total travel distance of the vehicle within an hour.

[0052] Optionally, the operation behavior recognition model includes a convolutional neural network model; the device is also used to: acquire a sample vehicle set with known operation attributes, wherein the sample vehicle set includes sample data labeled as operating vehicles and non-operating vehicles; extract daily spatiotemporal behavior feature vectors of each vehicle in the sample vehicle set to obtain daily spatiotemporal behavior feature vectors with operation attributes; and train the convolutional neural network model using the daily spatiotemporal behavior feature vectors with operation attributes to obtain the operation behavior recognition model, wherein the operation behavior recognition model can distinguish the differences in behavior patterns between operating vehicles and non-operating vehicles in the time dimension.

[0053] Optionally, the vehicle to be detected as a commercial-to-non-commercial vehicle is a vehicle whose vehicle operation attribute is registered as commercial-to-non-commercial; the commercial operation behavior identification unit is also used to: input the daily spatiotemporal behavior feature vector of the vehicle to be detected as a commercial-to-non-commercial vehicle into the commercial operation behavior identification model, and output the daily suspicion score of the vehicle to be detected as a commercial-to-non-commercial vehicle.

[0054] Optionally, the preset cycle is one week, and the preset frequency threshold is four times; the early warning unit is also used to: count the cumulative frequency of the daily suspicion score of the vehicle to be tested exceeding the preset threshold within one week; if the cumulative frequency reaches the preset frequency threshold, the vehicle to be tested will be marked as a key suspected vehicle.

[0055] Optionally, the device is also used to: push abnormal behavior warning signals to the monitoring terminal for display; and / or automatically trigger on-site inspection instructions for vehicle identification based on key suspected vehicles.

[0056] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0057] like Figure 3As shown in the embodiment of this application, an electronic device 600 includes a processor 601, a memory 602, and a bus. The memory 602 stores machine-readable instructions that can be executed by the processor 601. When the electronic device is running, the processor 601 communicates with the memory 602 via the bus. The processor 601 executes the machine-readable instructions to perform the steps of the above-described method for early warning of abnormal behavior of commercial vehicles converted to non-commercial vehicles.

[0058] Specifically, the memory 602 and processor 601 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 601 runs the computer program stored in the memory 602, it can execute the above-mentioned method for early warning of abnormal behavior of commercial vehicles converted to non-commercial vehicles.

[0059] The processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 601 or by instructions in software form. The processor 601 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 602, and processor 601 reads the information from memory 602 and, in conjunction with its hardware, completes the steps of the above method.

[0060] Corresponding to the above-mentioned method for early warning of abnormal behavior of commercial-to-non-commercial vehicles, this application embodiment also provides a computer-readable storage medium storing machine-executable instructions. When the machine-executable instructions are called and run by a processor, the machine-executable instructions cause the processor to perform the steps of the above-mentioned method for early warning of abnormal behavior of commercial-to-non-commercial vehicles.

[0061] The abnormal behavior warning device for commercial vehicles converted to non-commercial use provided in this application embodiment can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0062] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0063] For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0064] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0065] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0066] If the aforementioned function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the abnormal behavior warning method for commercial vehicles converted to non-commercial vehicles described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0067] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0068] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for early warning of abnormal behavior of vehicles converted from commercial to non-commercial use, characterized in that, include: Collect raw vehicle passage data containing vehicle identification, vehicle attributes, and passage time and space information, and generate a standardized vehicle passage record set after preprocessing; Based on the standardized vehicle passage record set, multi-dimensional trajectory features are extracted with hours as the basic time unit, and the multi-dimensional trajectory features of each hour within a single day are aggregated in time sequence to construct a daily spatiotemporal behavior feature vector that characterizes the spatiotemporal evolution of vehicles throughout the entire time period. The daily spatiotemporal behavioral feature vectors of the vehicles to be detected as commercial vehicles are used to identify their operational behavior, and a daily suspicion score is obtained to determine the similarity between the daily behavior of the vehicles to be detected as commercial vehicles and the abnormal operation mode. The system calculates the cumulative frequency of daily suspicion scores exceeding a preset threshold within a preset period. If the cumulative frequency reaches the preset frequency threshold, an abnormal behavior warning signal containing vehicle identification and key suspected vehicles is generated.

2. The method according to claim 1, characterized in that, Collect raw vehicle passage data containing vehicle identification, vehicle attributes, and passage time and space information, including: High-definition checkpoint equipment deployed at intersections captures real-time spatiotemporal information of passing vehicles, including at least: license plate number, vehicle type, direction of travel, and time of passage. The passage time and space information is transmitted to the central data server for storage in real time; Based on the aforementioned traffic time and space information, vehicle passage data for all intersections is extracted from the central data server as the original vehicle passage data; The preprocessing includes: cleaning, time alignment, and classification.

3. The method according to claim 1, characterized in that, The multidimensional trajectory features include: hourly distribution features of vehicle activity frequency per hour, hourly longitude range features of vehicle longitude variation range per hour, hourly latitude range features of vehicle latitude variation range per hour, hourly four-point area features of the hourly travel area coverage based on the four outermost points of the vehicle trajectory, hourly trajectory density features of the number and distribution density of trajectory points passed by the vehicle per hour, hourly trajectory point number features of the number of all checkpoints passed by the vehicle per hour, and hourly trajectory distance features of the total travel distance of the vehicle per hour.

4. The method according to claim 1, characterized in that, The operation behavior identification model includes: a convolutional neural network model; the method further includes: Obtain a sample vehicle set with known operating attributes, wherein the sample vehicle set includes: sample data labeled as operating vehicles and non-operating vehicles; Extract the daily spatiotemporal behavior feature vectors of each vehicle in the sample vehicle set to obtain daily spatiotemporal behavior feature vectors with operational attributes. The convolutional neural network model is trained using daily spatiotemporal behavioral feature vectors with operational attributes to obtain the operational behavior recognition model, wherein the operational behavior recognition model can distinguish the differences in behavioral patterns between operational and non-operational vehicles in the time dimension.

5. The method according to claim 1, characterized in that, The vehicles to be detected that have been converted from commercial to non-commercial use are those whose vehicle operation attributes have been registered as such. A commercial operation behavior identification model is used to identify the daily spatiotemporal behavioral feature vectors of the vehicles to be detected, including: The daily spatiotemporal behavioral feature vector of the vehicle to be detected (transferring from commercial to non-commercial use) is input into the commercial behavior recognition model, and the daily suspicion score of the vehicle to be detected is output.

6. The method according to claim 1, characterized in that, The preset period is one week, and the preset frequency threshold is four times; The cumulative frequency of daily suspicion scores exceeding a preset threshold within a preset period is counted. If the cumulative frequency reaches the preset frequency threshold, it includes: The cumulative frequency of the daily suspicion score of the vehicle to be detected exceeding the preset threshold within one week is counted. If the cumulative frequency reaches the preset frequency threshold, the vehicle to be detected that is converted from commercial to non-commercial use will be marked as a key suspected vehicle.

7. The method according to claim 1, characterized in that, The method further includes: The abnormal behavior warning signal is pushed to the monitoring terminal for display; And / or, automatically trigger on-site inspection instructions targeting the vehicle identification based on the key suspected vehicle.

8. A device for early warning of abnormal behavior of vehicles converted from commercial to non-commercial use, characterized in that, include: The data acquisition and preprocessing unit is used to acquire raw vehicle passage data containing vehicle identification, vehicle attributes and passage time and space information, and after preprocessing, generate a standardized vehicle passage record set. The extraction and construction unit is used to extract multi-dimensional trajectory features based on the standardized vehicle passage record set, with the hour as the basic time unit, and to aggregate the multi-dimensional trajectory features of each hour within a single day in chronological order to construct a daily spatiotemporal behavior feature vector that characterizes the spatiotemporal evolution law of vehicles throughout the entire time period. The operation behavior identification unit is used to identify the operation behavior of the vehicle to be detected as a commercial vehicle using the daily spatiotemporal behavior feature vector of the vehicle to be detected as a commercial vehicle, and to obtain a daily suspicion score of the similarity between the daily behavior of the vehicle to be detected as a commercial vehicle and the abnormal operation mode. The early warning unit is used to count the cumulative frequency of the daily suspicion score exceeding a preset threshold within a preset period. If the cumulative frequency reaches the preset frequency threshold, an abnormal behavior early warning signal containing vehicle identification and key suspected vehicles is generated.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program is executed by the processor to perform the method of any one of claims 1 to 7.

Images