A method and system for identifying a detour of a vehicle, an electronic device and a storage medium

Abstract

The application provides a vehicle detour identification method, system, electronic equipment and storage medium, and belongs to the detour identification field. The method comprises the following steps: acquiring real-time position information of a vehicle, and judging whether the vehicle is virtually positioned; if the vehicle is not virtually positioned, inputting the real-time position information into a pre-constructed multi-algorithm detour model to obtain an identification result of a vehicle detour; judging whether the identification result meets preset detour conditions, and determining that the vehicle detours when the identification result meets the detour conditions. The position trajectory of the vehicle is identified by using the multi-algorithm detour model, so that the inaccuracy caused by using a single algorithm is avoided, and the accuracy of identification is improved. The detour conditions are dynamically allocated to adapt to different cities, regions, times and specific roads, so that the detour determination is more in line with the actual situation. The detour behavior of the vehicle is reduced through the detour identification of the vehicle.

Description

Technical Field

[0001] This invention relates to the field of detour identification, and more specifically to a method, system, electronic device, and storage medium for identifying vehicle detours. Background Technology

[0002] Taking detours can lead to passenger fare disputes, resulting in numerous customer complaints and unpaid orders for the platform, causing both bad debts and out-of-pocket expenses. Detours also waste passengers' time and money, leading to a poor passenger experience and negatively impacting the ride-hailing platform's reputation. Furthermore, detours undermine fairness and motivation among drivers, and can easily lead to driver turnover. Summary of the Invention

[0003] In view of the shortcomings of the prior art, the present invention provides a method, system, electronic device and storage medium for identifying vehicle detours, so as to improve the technical problem that the prior art cannot accurately identify whether a vehicle has taken a detour.

[0004] To achieve the above and other related objectives, the present invention provides a method for identifying vehicle detours, comprising:

[0005] The system acquires the vehicle's real-time location information and determines whether the vehicle is virtually located. If the vehicle is not virtually located, the real-time location information is input into a pre-built multi-algorithm detour model to obtain the vehicle detour identification result. The system then determines whether the identification result meets the preset detour conditions and, if the identification result meets the detour conditions, determines that the vehicle is detouring.

[0006] In one example of the present invention, obtaining the real-time location of the vehicle and determining whether the vehicle is virtually located includes:

[0007] The system acquires multiple first location points and multiple second location points uploaded by the vehicle; wherein the first and second location points are acquired according to different positioning methods; it determines whether, within a preset time interval, the distance between the first location point and the corresponding second location point is greater than a preset distance threshold, and / or whether the vehicle speed between two adjacent second location points is greater than a preset speed threshold; if at least one of them is true, the vehicle is virtually positioned; if both are false, the vehicle is not virtually positioned.

[0008] In one example of the present invention, if the vehicle is not virtually located, the real-time location information is input into a pre-constructed multi-algorithm detour model to obtain the vehicle detour identification result, including:

[0009] Based on real-time location information, the vehicle's mileage is obtained; if the mileage is greater than a preset mileage threshold, the real-time location information is identified based on a trajectory anomaly detection algorithm to obtain a first identification result; if the mileage is less than or equal to the mileage threshold, the estimated path of the current order is obtained based on the vehicle's current order, and a second identification result is obtained based on the deviation between the real-time location and the estimated path according to a dynamic time correction algorithm; the first and second identification results are generated and returned as identification results.

[0010] In one example of the present invention, based on a trajectory anomaly detection algorithm, real-time location information is identified to obtain a first identification result, including:

[0011] Obtain the planar grid formed by segmenting the city map and obtain the number of all grids; map the location trajectory points to the planar grid and obtain the number of the grid where the trajectory point is located; use historical trajectories as a reference to determine whether all trajectory points are abnormal and count all abnormal trajectory points; take the proportion of abnormal trajectory points in all trajectory points as the first identification result.

[0012] In one example of the present invention, based on the vehicle's current order, the estimated route of the current order is obtained, and according to the dynamic time adjustment algorithm, based on the degree of deviation between the real-time location and the estimated route, a second identification result is obtained, including:

[0013] The system retrieves the vehicle's current order, extracts the corresponding estimated route from the current order, and obtains multiple estimated trajectory points along the estimated route based on a preset time interval. Using dynamic programming, it obtains the shortest path distance from the actual trajectory point to the corresponding estimated trajectory point. The system uses the actual trajectory points traversed by the shortest path and the corresponding estimated trajectory points as alignment points, and obtains the average shortest path distance based on the number of alignment points. It also obtains the detour mileage percentage based on the deviation between the real-time location's traversed path and the estimated path. Finally, it obtains the second recognition result based on the average shortest path distance and the detour mileage percentage.

[0014] In one example of the present invention, determining whether the identification result meets preset detour conditions, and determining that the vehicle detours when the identification result meets the detour conditions, includes:

[0015] Thresholds are dynamically assigned based on city, region, time, and specific route: the identification results are compared with the thresholds to determine whether the comparison results meet the set conditions; if the comparison results meet the set conditions, it is determined that the vehicle has taken a detour.

[0016] In one example of the present invention, after determining that the vehicle has taken a detour, the method further includes:

[0017] The detour results are verified based on the degree of deviation between the actual path and the estimated path. If the deviation is greater than a preset offset threshold, the result is uploaded and recorded as a detour for the vehicle. If the cumulative number of detour records for the vehicle is greater than or equal to a set threshold, the vehicle is penalized according to a preset first penalty rule. If the cumulative number of detours for the vehicle is less than the set threshold, the vehicle is penalized according to a preset second penalty rule. The penalty under the first penalty rule is more severe than that under the second penalty rule.

[0018] In one example of the present invention, a vehicle detour identification system is also provided, characterized in that it includes:

[0019] The location acquisition module is used to acquire the real-time location information of the vehicle and determine whether the vehicle is virtually located; the detour identification module is used to input the real-time location information into a pre-built multi-algorithm detour model if the vehicle is not virtually located, and obtain the vehicle detour identification result; the result judgment module is used to determine whether the identification result meets the preset detour conditions, and if the identification result meets the detour conditions, it determines that the vehicle has detoured.

[0020] In one example of the present invention, an electronic device is also provided, characterized in that the electronic device comprises:

[0021] One or more processors; a storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the vehicle detour identification method as described above.

[0022] In one example of the present invention, a computer-readable storage medium is also provided, characterized in that it stores a computer program thereon, which, when executed by a computer processor, causes the computer to perform the vehicle detour identification method described in any one of the above-described methods.

[0023] This invention provides a method, system, electronic device, and storage medium for identifying vehicle detours. The method uses a multi-algorithm detour model to identify vehicle location trajectories and detours, avoiding inaccuracies caused by using a single algorithm and improving accuracy. Detour conditions are dynamically allocated to adapt to different cities, regions, times, and specific roads, making detour determination more realistic. By identifying vehicle detours, detour behavior is reduced. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a vehicle detour identification method according to an embodiment of the present invention;

[0026] Figure 2 This is a flowchart for determining virtual location in one embodiment of the present invention;

[0027] Figure 3 This is a flowchart of a multi-algorithm bypass model in one embodiment of the present invention;

[0028] Figure 4 This is a flowchart of a trajectory anomaly detection algorithm in one embodiment of the present invention;

[0029] Figure 5 This is a flowchart of the dynamic time normalization algorithm in one embodiment of the present invention;

[0030] Figure 6 This is a flowchart illustrating the configuration of preset detour conditions in one embodiment of the present invention;

[0031] Figure 7 This is a flowchart illustrating the specific determination of virtual positioning in one embodiment of the present invention;

[0032] Figure 8 This is a schematic diagram of a computer system of an electronic device according to an embodiment of the present invention;

[0033] Figure 9 This is a structural block diagram of a vehicle detour identification system according to an embodiment of the present invention. Detailed Implementation

[0034] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features can be combined with each other. It should also be understood that the terminology used in the embodiments of the present invention is for describing specific implementation schemes and not for limiting the scope of protection of the present invention. Test methods in the following embodiments that do not specify specific conditions are generally performed under conventional conditions or according to the conditions recommended by the respective manufacturers.

[0035] When numerical ranges are given in the embodiments, it should be understood that, unless otherwise stated in the present invention, both endpoints of each numerical range and any value between the two endpoints may be selected. Unless otherwise defined, all technical and scientific terms used in this invention, as well as the prior art known to those skilled in the art and the description of this invention, may be implemented using any prior art methods, devices, and materials similar to or equivalent to those described, used, or made of materials in the embodiments of this invention.

[0036] It should be noted that the terms such as "upper", "lower", "left", "right", "middle" and "one" used in this specification are only for clarity of description and are not intended to limit the scope of the invention. Changes or adjustments to their relative relationships, without substantially altering the technical content, should also be considered as part of the scope of the invention.

[0037] Please see Figures 1 to 9 This invention provides a method for identifying vehicle detours. This method uses a multi-algorithm detour model to identify vehicle location trajectories and allocates detour conditions based on information such as city, region, time, and road conditions. This accurately identifies whether a vehicle is taking a detour, thus avoiding situations where excessive detour mileage leads to increased passenger costs and significantly improving the passenger experience. This addresses the technical problem in existing technologies that cannot accurately identify whether a vehicle is taking a detour.

[0038] Please see Figure 1 The method for identifying vehicle detours includes:

[0039] Step S100: Obtain the real-time location information of the vehicle and determine whether the vehicle is virtually located.

[0040] The backend system obtains the real-time location information of the vehicle's GPS (Global Positioning System) and Tbox (Telematics Box), uses this information to determine if the vehicle is being used for virtual positioning, and alerts the vehicle if virtual positioning is detected. In one embodiment, the location information includes longitude, latitude, positioning accuracy, speed, time, and direction. In other embodiments, the location information may include one or more of longitude, latitude, positioning accuracy, speed, time, and direction, as well as other information.

[0041] Please see Figure 2 In step S100, obtaining the real-time location of the vehicle and determining whether the vehicle is virtually located includes steps S110 to S140, which are detailed below:

[0042] Step S110: Obtain multiple first location points and multiple second location points uploaded by the vehicle; wherein the first location points and second location points are obtained according to different positioning methods;

[0043] Step S120: Determine whether the distance between the first position point and the corresponding second position point is greater than a preset distance threshold within a preset time interval, and / or whether the vehicle speed between two adjacent second position points is greater than a preset vehicle speed threshold.

[0044] Step S130: If at least one of them is true, then the vehicle is virtually located;

[0045] Step S140: If both are negative, then the vehicle is not virtually located.

[0046] The backend system acquires GPS location information as the first location point's trajectory point and Tbox location information as the second location point's trajectory point. During location information acquisition, noise reduction processing is performed to make the location information clearer. Noise reduction refers to reducing external interference encountered during information transmission to an acceptable range. At set time intervals, the backend system performs two judgment methods. First judgment method: The backend system randomly selects the distance between the GPS and Tbox location information and compares this distance with a set distance threshold to determine if it exceeds the threshold. The mileage distance between the two points is the mileage between two points on the Earth's sphere, calculated using the formula for the Earth's average radius and radians. This method is existing technology and will not be described in detail. Second judgment method: The backend system calculates the speed between all adjacent trajectory points of the GPS trajectory point and compares the speed with a set speed threshold to determine if it exceeds the threshold. If at least one of the two judgment methods is satisfied, the vehicle is in virtual positioning, and the backend system alerts the vehicle. If neither judgment method is satisfied, the vehicle is not in virtual positioning.

[0047] Please see Figure 7Considering that GPS positioning devices are easily affected by factors such as building obstruction, external electromagnetic interference, and equipment malfunctions, resulting in location data with significant deviations from the true values, and that human factors (such as drivers turning off in-vehicle GPS devices) can also cause the acquisition equipment to miss location information during certain periods, the collected trajectory data may suffer from problems such as latitude and longitude out-of-bounds errors, data loss, and numerical anomalies, severely affecting the accuracy of trajectory anomaly detection results. To reduce the impact of noisy data on anomaly detection performance, in one embodiment, when the backend system acquires GPS and Tbox location information, it first cleans the data using methods such as data anomaly filtering / threshold filtering, then verifies the data to determine if it is missing or contains errors, and corrects the trajectory data based on historical trend data. Subsequently, it uses techniques such as mean / median filters, Kalman filters, and particle filters to achieve smooth denoising of the data. Simultaneously, to reduce the scale of real-time trajectory big data processing, online data compression technology, sampling technology, or trajectory segmentation technology based on time intervals / trajectory shapes can be used to approximate the trajectory data after noise removal while preserving the spatiotemporal characteristics of the trajectory. After obtaining GPS and Tbox location information, the backend system checks for Tbox data. If no Tbox data is found, it checks for abnormal speed in the GPS location information. If abnormal speed is detected, the vehicle is determined to be in a virtual location, and the backend system alerts the vehicle. Alternatively, if Tbox data is detected, the backend system compares the GPS and Tbox locations. If the distance between them is greater than a preset distance threshold, the vehicle is determined to be in a virtual location; if the distance is less than the preset distance threshold, and abnormal speed is detected in the GPS location information, the vehicle is determined to be in a virtual location, and the backend system alerts the vehicle upon detecting a virtual location.

[0048] In step S200, if the vehicle is not virtually located, the real-time location information is input into the pre-built multi-algorithm detour model to obtain the vehicle detour identification result.

[0049] Specifically, the vehicle's journey is divided into the pick-up distance from receiving the order to the passenger's location and the mileage traveled from the start of service to the end of billing. The multi-algorithm detour model selects different algorithms based on the actual mileage and pick-up distance.

[0050] Please see Figure 3 In step S200, the real-time location information is input into the pre-built multi-algorithm detour model to obtain the vehicle detour identification result, including steps S210 to S240, which are detailed below:

[0051] Step S210: Based on real-time location information, obtain the vehicle's mileage;

[0052] Step S220: If the driving mileage is greater than the preset mileage threshold, the real-time location information is identified based on the trajectory anomaly detection algorithm to obtain the first identification result.

[0053] Step S230: If the driving mileage is less than or equal to the mileage threshold, then based on the vehicle's current order, obtain the estimated route of the current order, and based on the deviation between the real-time location and the estimated route according to the dynamic time adjustment algorithm, obtain the second recognition result.

[0054] Step S240: Generate and return the first and second recognition results.

[0055] Based on real-time location information and the vehicle's historical location information, the vehicle's current mileage can be obtained. When the mileage exceeds a certain threshold, the multi-algorithm detour model uses an isolation-based online anomalous trajectory detection (iBOAT) algorithm to identify the mileage at the real-time location. For example, if the mileage exceeds a set threshold of 5 km, the iBOAT algorithm is used. However, considering that the iBOAT algorithm cannot handle situations without historical trajectory data, and that precise grid division is impossible when the pick-up route is short, the iBOAT algorithm cannot accurately obtain the final result. Therefore, when the mileage is less than the threshold, the Dynamic Time Warping (DTW) algorithm is used for detour judgment. When the DTW algorithm is used for detour judgment (e.g., if the mileage is less than a set threshold of 5 km), the DTW algorithm is used for identification. It should be noted that, in addition to determining which iBOAT algorithm to use based on mileage, the algorithm can also be determined based on whether there is corresponding historical trajectory data for the current order's trajectory. When historical trajectory data is available and the driving mileage is long, a trajectory anomaly detection algorithm can be used to obtain the first identification result. If the current order does not have historical trajectory data, a dynamic time-normalization algorithm can be used to recall the order and obtain the second identification result after calculation. The multi-algorithm detour model returns the first and second identification results to the backend system. The first identification result is placed in the first position, and the second identification result is placed in the second position. If there is no first identification result, the first position is left empty. By using the multi-algorithm detour model, different trajectory anomaly detection algorithms are used to calculate based on different types of driving mileage, judging the severity of detours from multiple perspectives, thereby increasing the effectiveness and stability of the detour identification model. Multi-model adversarial approaches help improve accuracy and recall rates, with higher accuracy for special detour types such as driving in the wrong direction or spinning in place. By taking into account the degree of trajectory deviation, it has a certain degree of exclusion for non-malicious detours such as drivers taking the wrong route or temporarily choosing a route due to road closures.

[0056] Please see Figure 4 In step S220, the real-time location information is identified based on the trajectory anomaly detection algorithm to obtain the first identification result, including steps S221 to S224, which are detailed below:

[0057] Step S221: Obtain the planar grid formed by segmenting the city map, and obtain the number of all grids;

[0058] Step S222: Map the position trajectory points to the planar grid and obtain the grid number where the trajectory points are located;

[0059] Step S223: Using historical trajectories as a reference, determine whether all trajectory points are abnormal, and count all abnormal trajectory points.

[0060] Step S224: The proportion of abnormal trajectory points among all trajectory points is taken as the first identification result.

[0061] To manage GPS points effectively, we construct a finite abstract representation or decomposition of the original two-dimensional plane. A mapping component receives GPS points and maps them to one of the selected decomposition states. From then on, all computations are performed only on the mapped GPS points. The urban area is divided into a grid cell matrix, with each GPS point mapped to the grid cell where it "lands." The trajectory anomaly detection algorithm adds the GPS location information to the corresponding grid cell and records the grid number of the vehicle's path formed by the GPS location information in chronological order, creating a sequence of numbers. The algorithm uses the historical number sequence of all historical trajectories in the planar grid as a reference standard. The algorithm uses an inverted index mechanism to find the number of times each number in the vehicle path's number sequence appears in the historical number sequence along with its adjacent previous number. If the number is less than a set threshold, the number is considered an anomalous trajectory point. In one embodiment, the vehicle's number contains 10, and the number preceding 10 is 3. The trajectory anomaly detection algorithm finds the number of historical paths in the historical number sequence that include numbers 3 and 10, and the next number after 3 is 10. If the number is less than the set value of 3, then trajectory point numbered 10 in the current vehicle is determined to be abnormal. Specifically, the abnormal trajectory point is divided by the total value of all trajectory points to obtain the first identification result. The mileage is assessed using a dynamic time-normalization algorithm for detour detection. When the distance traveled is less than a certain threshold, the dynamic time-normalization algorithm is used for detour detection. For example, if the distance traveled is less than a set threshold of 5 km, the trajectory anomaly detection algorithm is used to identify the abnormal mileage.

[0062] Please see Figure 5 In step S230, based on the vehicle's current order, the estimated path of the current order is obtained, and based on the deviation between the real-time location and the estimated path using a dynamic time adjustment algorithm, a second identification result is obtained, including steps S231 to S235, which are detailed below:

[0063] Step S231: Obtain the current order of the vehicle, extract the corresponding estimated path from the current order, and obtain multiple estimated trajectory points of the estimated path based on a preset time interval.

[0064] Step S232: Based on the dynamic programming method, obtain the shortest path distance from the actual trajectory point to the corresponding estimated trajectory point;

[0065] Step S233: Take the actual trajectory points and the corresponding estimated trajectory points traversed by the shortest path distance as alignment points, and obtain the average distance of the shortest path points based on the number of alignment points.

[0066] Step S234: Obtain the detour mileage percentage based on the deviation between the real-time location's path and the estimated path.

[0067] Step S235: Obtain the second identification result based on the average distance of the shortest path point and the proportion of detour mileage.

[0068] The dynamic time warping algorithm is used to align the predicted trajectory points of the predicted path with the actual trajectory points. A distance matrix is ​​constructed based on the distances from each actual trajectory point to each predicted trajectory point. The shortest path distance is then calculated using the distance matrix. Specifically, the shortest path distance divided by the number of aligned points yields the average shortest path distance. The difference between the actual mileage and the predicted mileage, divided by the predicted mileage, is used as the detour mileage. Finally, the product of the average shortest path distance and the detour mileage is used as the second identification result.

[0069] Step S300: Determine whether the identification result meets the preset detour conditions, and if the identification result meets the detour conditions, determine that the vehicle is taking a detour.

[0070] Please see Figure 6 This process includes steps S310 to S330, which are detailed below:

[0071] Step S310: Dynamically allocate thresholds based on city, region, time, and specific route.

[0072] Step S320: Compare the recognition result with the threshold to determine whether the comparison result meets the set conditions.

[0073] Step S330: If the comparison results meet the set conditions, it is determined that the vehicle has taken a detour. Specifically, if at least one of the comparison results is greater than the dynamic threshold, it is determined that the vehicle has taken a detour.

[0074] The backend system dynamically assigns thresholds to the recognition results based on various influencing factors. These dynamic thresholds include a first dynamic threshold corresponding to the first recognition result and a second dynamic threshold corresponding to the second recognition result. The backend system compares the first recognition result with the first dynamic threshold to determine if the first recognition result is greater than the first dynamic threshold; it then compares the second recognition result with the second dynamic threshold to determine if the second recognition result is greater than the second dynamic threshold.

[0075] In one embodiment of the present invention, after determining that the vehicle has taken a detour, the method further includes:

[0076] The detour result is verified based on the deviation between the actual path and the estimated path. When a vehicle detours, the backend system compares the deviation between the actual path and the estimated path with a set detour threshold to determine whether the extra distance traveled by the vehicle exceeds the set detour threshold. This is to prevent the vehicle from being judged as detouring even if the actual distance traveled is greater than the preset distance. In one embodiment, the backend system obtains real-time road conditions, such as whether there is congestion or road construction. If the verification conditions are met, the result is returned to the client, notifying both the vehicle and the customer, so that the customer is aware and can confirm, thereby determining whether the vehicle has taken a detour.

[0077] If the deviation exceeds a preset offset threshold, the result is uploaded and recorded as a detour for the vehicle. When the distance taken by the vehicle through the detour exceeds a set detour threshold, the backend system classifies the vehicle's trip as a detour and records it.

[0078] If the number of times a vehicle has accumulated detours is greater than or equal to a set threshold, the vehicle will be penalized based on the preset first penalty rule.

[0079] If the cumulative number of detours by a vehicle is less than the set threshold, the vehicle will be penalized based on the preset second penalty rule; the penalty under the first penalty rule is more severe than that under the second penalty rule.

[0080] After the backend system determines that the vehicle has indeed taken a detour, it will return the detour information to the client, reduce the extra fees incurred by customer service due to the detour, and send the vehicle penalty result to the client.

[0081] In one embodiment of the present invention, the backend system uses 5 as a threshold for the number of detours. When the cumulative number of detours recorded by a vehicle exceeds five, the backend system will penalize the vehicle by taking it offline, prohibiting it from accepting orders, and suspending its account. When the number of detours is less than five, the backend system will issue a reminder or warning to the vehicle.

[0082] In one embodiment of the present invention, the backend system uses Kafka for data transmission, which ensures high transmission efficiency.

[0083] Please see Figure 9 In one embodiment of the present invention, a vehicle detour identification system 900 is also provided, comprising:

[0084] The location acquisition module 910 is used to acquire the real-time location information of the vehicle and determine whether the vehicle is virtually located; the detour identification module 920 is used to input the real-time location information into a pre-built multi-algorithm detour model if the vehicle is not virtually located, and obtain the vehicle detour identification result; the result judgment module 930 is used to determine whether the identification result meets the preset detour conditions, and if the identification result meets the detour conditions, determine that the vehicle has detoured.

[0085] It should be noted that the vehicle detour identification method and system provided in the above embodiments belong to the same concept, and the specific operation methods of each module have been described in detail in the method embodiments, and will not be repeated here. In practical applications, the vehicle detour identification judgment system provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above, and this is not a limitation here.

[0086] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the vehicle detour identification method as described above.

[0087] Figure 8 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 8 The computer system of the electronic device shown is merely one embodiment and should not impose any limitation on the functionality and scope of use of the embodiments in this application.

[0088] like Figure 8 As shown, the computer system includes a Central Processing Unit (CPU) 801, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 802 or programs loaded from storage portion 808 into Random Access Memory (RAM) 803, such as performing the methods described in the above embodiments. The RAM 803 also stores various programs and data required for system operation. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An Input / Output (I / O) interface 805 is also connected to the bus 804.

[0089] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.

[0090] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit (CPU) 801, it performs various functions defined in the system of this application.

[0091] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0092] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated 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 or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0093] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0094] Another aspect of this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer's processor, causes the computer to perform the vehicle detour identification method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0095] This invention employs a multi-algorithm detour model for judgment, improving the accuracy of detour detection. Furthermore, it deeply integrates detour detection with the business system, automatically handling orders with abnormal trajectories, enabling faster responses in dynamic confrontations with driver fraud. Therefore, this invention effectively overcomes some practical problems in existing technologies, thus possessing high utilization value and practical significance.

[0096] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for identifying vehicle detours, characterized in that, include: Obtain the real-time location information of the vehicle and determine whether the vehicle is virtually located; If the vehicle is not virtually located, the real-time location information is input into a pre-built multi-algorithm detour model to obtain the vehicle detour identification result. Determine whether the identification result meets the preset detour conditions, and if the identification result meets the detour conditions, determine that the vehicle is taking a detour; If the vehicle is not virtually located, the real-time location information is input into a pre-constructed multi-algorithm detour model to obtain the vehicle detour identification result, including: Based on the real-time location information, the vehicle's mileage is obtained; If the mileage exceeds a preset mileage threshold, the real-time location information is identified based on a trajectory anomaly detection algorithm to obtain a first identification result. If the mileage is less than or equal to the mileage threshold, then based on the vehicle's current order, the estimated path of the current order is obtained, and based on the deviation between the real-time location and the estimated path using a dynamic time adjustment algorithm, a second identification result is obtained. Generate and return the recognition result based on the first recognition result and the second recognition result.

2. The vehicle detour identification method according to claim 1, characterized in that, The step of obtaining the vehicle's real-time location information and determining whether the vehicle is virtually located includes: The vehicle uploads multiple first location points and multiple second location points; wherein the first location points and the second location points are obtained according to different positioning methods. Determine whether, within a preset time interval, the distance between the first location point and the corresponding second location point is greater than a preset distance threshold, and / or whether the vehicle speed between two adjacent second location points is greater than a preset vehicle speed threshold; If at least one of them is true, then the vehicle is a virtual location; If both are negative, then the vehicle is not virtually located.

3. The vehicle detour identification method according to claim 1, characterized in that, The trajectory anomaly detection algorithm identifies the real-time location information to obtain a first identification result, including: Obtain the planar grid formed by segmenting the city map, and obtain the number of each grid. Map the location trajectory points to a planar grid and obtain the grid number where the trajectory points are located; Using historical trajectories as a reference, determine whether all trajectory points are abnormal, and count all abnormal trajectory points; The proportion of abnormal trajectory points among all trajectory points is used as the first identification result.

4. The vehicle detour identification method according to claim 1, characterized in that, The step of obtaining the estimated path of the current order based on the vehicle, and obtaining the second recognition result based on the deviation between the real-time location and the estimated path according to the dynamic time adjustment algorithm, includes: Obtain the vehicle's current order, extract the corresponding estimated path from the current order, and obtain multiple estimated trajectory points of the estimated path based on a preset time interval; Based on the dynamic programming method, the shortest path distance from the actual trajectory point to the corresponding estimated trajectory point is obtained; The actual trajectory points and corresponding estimated trajectory points traversed by the shortest path distance are used as alignment points, and the average shortest path point distance is obtained based on the number of alignment points. The percentage of detour mileage is obtained based on the degree of deviation between the path taken by the real-time location and the estimated path. The second identification result is obtained based on the average distance of the shortest path point and the proportion of detour mileage.

5. The vehicle detour identification method according to claim 1, characterized in that, The step of determining whether the identification result meets the preset detour conditions, and determining that the vehicle detours when the identification result meets the detour conditions, includes: Thresholds are dynamically allocated based on city, region, time, and specific distance: The identification result is compared with the threshold to determine whether the comparison result meets the set conditions. If the comparison results meet the set conditions, it is determined that the vehicle has taken a detour.

6. The vehicle detour identification method according to claim 1, characterized in that, After determining that the vehicle has taken a detour, the following is also included: The detour results are verified based on the degree of deviation between the actual path and the estimated path. If the deviation is greater than the preset offset threshold, the result will be uploaded and recorded as a detour for the vehicle. If the number of times a vehicle has accumulated detour records is greater than or equal to the set threshold, the vehicle will be penalized based on the preset first penalty rule. If the cumulative number of detours by a vehicle is less than a set threshold, the vehicle will be penalized based on a preset second penalty rule; wherein the penalty severity of the first penalty rule is greater than that of the second penalty rule.

7. A vehicle detour identification system, employing the vehicle detour identification method as described in any one of claims 1 to 6, characterized in that, include: The location acquisition module is used to acquire the real-time location information of the vehicle and determine whether the vehicle is virtually located. The detour identification module is used to input the real-time location information into a pre-built multi-algorithm detour model to obtain the vehicle detour identification result if the vehicle is not virtually located. The result determination module is used to determine whether the identification result meets the preset detour conditions, and when the identification result meets the detour conditions, it determines that the vehicle detours.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the vehicle detour identification method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the vehicle detour identification method as described in any one of claims 1 to 6.

Images