Anti-cheating method based on trajectory end point in multi-tenant row

Abstract

The invention discloses an anti-cheating method based on a track terminal point in a multi-tenant row, and particularly relates to the technical field of track terminal point anti-cheating, and the method comprises the following steps: S1, collecting the track data of vehicle driving, monitoring the track data, obtaining a position point finally uploaded by a driver and a penultimate position point at the end of a journey, and carrying out the monitoring of the track data; whether cheating behaviors exist or not is judged in an auxiliary mode by analyzing the behaviors of other drivers in the same tenant at the same position point. The system can collect and compare information such as driving tracks, driving speeds and travel fees of other drivers in the same tenant at the same position point so as to establish a datum reference. Then, the behavior of the driver which is being detected is compared with the benchmark reference, if it is found that the behavior of the driver is obviously different from that of other drivers or abnormal conditions exist, the system can mark the driver as an object possibly having cheating behaviors, and then monitoring and review are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of anti-cheating at the endpoint of a track, and more specifically, to an anti-cheating method for the endpoint of a track in a multi-tenant operation. Background Art

[0002] In current online ride-hailing services, the calculation of trip fees usually includes starting fees, mileage fees, and duration fees. The mileage fee is calculated based on the driver's actual driving trajectory, which is a series of coordinate points recorded by the order-taking software during the driving process. It is important to note that the last point in the entire trajectory is uploaded when the driver slides to the destination, which is crucial to the accurate counting of the overall mileage.

[0003] However, some drivers use cheating software to simulate positioning. When they slide to the destination, they simulate the destination location to a farther place, which will affect the overall mileage statistics. As a result, passengers will bear unnecessary costs.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an anti-cheating method based on multi-tenant in-line trajectory endpoints to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An anti-cheating method based on multi-tenant mid-trajectory endpoint includes the following steps:

[0008] S1: Collect and monitor the vehicle's travel trajectory data. At the end of the trip, obtain the driver's last uploaded location and the last location.

[0009] S2: Calculate the distance and time between the driver's last uploaded location and the last location to calculate the driver's driving speed at the location;

[0010] S3: Observe whether other drivers of the same tenant have similar situations at the same location, and generate corresponding probabilities based on the observation results;

[0011] S4: Determine whether the driver has cheated based on the obtained probability.

[0012] Preferably, when estimating the driving speed of the driver at the location point, the time when the driver uploaded the last location point is T1 in seconds, the time when the second to last location point is uploaded is T2 in seconds, and the distance between the last location point and the first to last location point is S in meters;

[0013] Specific formula:

[0014] Among them, the highway speed is marked as X;

[0015] All drivers are driving on the highway and the speed is X. The speed V calculated from the last position point and the last position point should be less than X. If it is greater, it is cheating, and T1, T2, V, X, and S are all greater than 0.

[0016] Preferably, the method for acquiring vehicle data in step S1 comprises the following steps:

[0017] Use GPS devices to record the vehicle's location information in real time, and use the API provided by the online ride-hailing platform to obtain the vehicle's location data in real time;

[0018] Real-time monitoring of vehicle location data, including the vehicle's real-time location and driving speed;

[0019] At the end of the trip, the last location point uploaded by the driver and the last location point are extracted from the collected trajectory data;

[0020] According to the sign of the end of the trip, the end time of the trip is determined, and the position point corresponding to the time is obtained from the trajectory data.

[0021] Preferably, the straight-line distance between the two location points is calculated based on the latitude and longitude information of the last uploaded location point and the last last location point;

[0022] Determine the timestamp of the driver's last uploaded location and the last last location, and record the upload time of the timestamp;

[0023] Calculate the time difference between two timestamps to get the time interval between the location points.

[0024] Preferably, the location information and driving time of other drivers of the same tenant at the same location are collected;

[0025] Compare the distance and time interval between the driver's last uploaded location and the last location, and compare with the situation of other drivers of the same tenant at the same location;

[0026] Determine whether the distance and time interval between the last uploaded position point and the last last position point are within a similar range;

[0027] Calculate the ratio of the number of drivers with similar situations at the same location to the total number of drivers with the same tenant to get the probability value.

[0028] Preferably, when determining the probability in step S4, a threshold range is set as a standard for determining whether the driver has cheated; the obtained probability is compared with the set threshold to determine whether there is an abnormality.

[0029] Preferably, when the observed probability value is lower than a set threshold, the system will automatically determine that the driver has cheated.

[0030] The basis for the judgment is that the probability value is lower than the threshold, indicating that the possibility of abnormal conditions occurring at the same location point is low.

[0031] Once the system automatically determines that the driver has cheated, it will automatically upload the driver's driving record, location information, and cheating behavior to the system;

[0032] If the observed probability value is greater than the set threshold range, it is determined to be a regional problem and a software problem; software problems include abnormalities in the order-taking software or positioning software, and regional problems include poor regional network signals or the nearest network base station is located far away.

[0033] Preferably, after obtaining the cheating information, an analysis model will be used to further review the driver's behavior, and the logic of the cheating information review is:

[0034] The driver's driving record, location information, driving speed, etc., as well as other features related to cheating behavior, such as the strangeness of the driving route, the inconsistency of driving distance and time interval, are extracted from the cheating information. By analyzing the driver's driving record, location information, driving speed and other features related to cheating behavior and establishing a corresponding analysis model, cheating behavior can be identified more accurately.

[0035] According to the extracted features, the corresponding analysis model is established, and the model is modeled using rule engines, etc., and the established analysis model is trained using historical data to learn the difference between normal behavior patterns and cheating behavior patterns, so that cheating behavior can be better identified; the established analysis model will learn the difference between normal behavior patterns and cheating behavior patterns based on historical data, so that new cheating information can be better identified and classified. This helps reduce misjudgments and unnecessary penalties, and ensures that only drivers who actually cheat are marked as cheating.

[0036] Use the trained analysis model to identify and classify new cheating information to determine whether the information is cheating behavior. Cheating information involves anomaly detection, singularity detection, and cluster analysis of the driver's driving record. By performing anomaly detection, singularity detection, and cluster analysis on the driver's driving record, cheating behavior can be reviewed more comprehensively and the review efficiency can be improved. This helps the platform to detect and deal with cheating behavior in a timely manner.

[0037] Preferably, based on the output of the analysis model, the driver's behavior is marked as normal or cheating, and the relevant review results are recorded. The logic for obtaining the output of the model is:

[0038] The data extracted from the cheating information includes the driver's driving record, location information, driving speed, etc., as well as other features related to cheating behavior, such as the strangeness of the driving route and the inconsistency of driving distance and time interval. By analyzing this data and establishing corresponding analysis models, the driver's cheating behavior can be identified more accurately. These models will comprehensively consider the driver's driving behavior and related characteristics, thereby improving the detection and identification capabilities of cheating behavior.

[0039] Based on the extracted features, a corresponding analysis model is established, and modeling is performed using a rule engine. The established analysis model is trained using historical data to learn the differences between normal behavior patterns and cheating behavior patterns, so that cheating behavior can be better identified.

[0040] Use the trained analysis model to identify and classify new cheating information to determine whether the information is cheating behavior. Cheating information involves anomaly detection, singularity detection, and cluster analysis of the driver's driving record. By performing anomaly detection, singularity detection, and cluster analysis on the driver's driving record, cheating behavior can be reviewed more comprehensively and the review efficiency can be improved. This helps the platform to detect and deal with cheating behavior in a timely manner.

[0041] Based on the output of the analysis model, the driver's behavior is marked as normal or cheating, and the relevant review results are recorded. Based on the output of the analysis model, the driver's behavior is marked as normal or cheating, and the relevant review results are recorded. The analysis model can automatically mark the driver's behavior without manual intervention, saving a lot of manpower costs and time. The analysis model can automatically mark the driver's behavior without manual intervention, saving a lot of manpower costs and time. Automatically marking behavior and recording review results can improve processing efficiency and data reliability, and reduce errors and delays caused by human factors.

[0042] Preferably, the probability value is set to P, the cheating formation features are set to X1, X2, X3...Xn, and the total number of features is marked as Gn, and the formula is:

[0043] Among them, X1, X2, X3....Xn, Gn are all greater than 0.

[0044] Technical effects and advantages of the present invention:

[0045] 1. The present invention assists in determining whether cheating occurs by analyzing the behavior of other drivers in the same tenant at the same location. The system collects and compares the driving trajectory, driving speed, travel cost and other information of other drivers in the same tenant at the same location to establish a benchmark reference. Then, the behavior of the driver being tested is compared with this benchmark reference. If it is found that the driver's behavior is significantly different or abnormal compared to other drivers, the system will mark it as a possible cheating object, and then strengthen monitoring and review. This multi-tenant-based auxiliary judgment method can improve the accuracy and reliability of cheating detection, thereby protecting the rights and interests of passengers and maintaining a fair competition environment in the industry.

[0046] 2. If this application finds that the driver has cheated, the system will immediately mark and record his behavior, and automatically upload the relevant information to the system for further investigation and processing by relevant departments. This timely feedback and processing mechanism can effectively prevent the potential impact of cheating on the interests of passengers and protect the safety and rights of passengers. At the same time, by strengthening the supervision and control of driver behavior, the overall integrity of the industry can be improved and passengers' trust in online car-hailing services can be enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0048] Figure 1 This is a schematic diagram of the structure of Example 1 of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Example 1

[0051] Figure 1 The present invention provides an anti-cheating method based on a multi-tenant mid-trajectory endpoint, comprising the following steps:

[0052] S1: Collect and monitor the vehicle's driving trajectory data. At the end of the trip, obtain the last uploaded location and the last location of the driver. By monitoring the vehicle's driving trajectory, especially obtaining the last uploaded location and the last location at the end of the trip, it can ensure that the driver drives according to the prescribed route and reduce unnecessary safety risks encountered by passengers during the trip, such as detours or dangerous behaviors caused by fatigue driving. Obtaining the location information at the end of the trip can help detect whether the driver has committed fraud, such as falsely reporting the trip distance to obtain additional fees. This can protect passengers from unnecessary financial losses,

[0053] S2: Calculate the distance and time between the driver's last uploaded location and the last location to infer the driver's driving speed at the location. By calculating the distance and time between the driver's last uploaded location and the last location, the driver's average driving speed during this period can be inferred. Such calculations help detect whether there are abnormal behaviors, such as the driver may falsely report the travel distance or perform irregular driving behaviors. By calculating the driving speed, it is effective to prevent drivers from defrauding passengers by falsely reporting the travel distance. Timely detection of these abnormal behaviors can protect the rights and interests of passengers and prevent customers from paying unnecessary fees or suffering from poor service experience.

[0054] S3: Observe whether other drivers in the same tenant have similar situations at the same location, and generate corresponding probabilities based on the observation results. This comparison can improve the accuracy of identifying abnormal situations. If other drivers have similar behavior patterns at the same location, then the situation may be normal, rather than the driver deliberately cheating. Such comparisons can reduce misjudgments and unnecessary penalties. On the other hand, if other drivers do not have similar situations at the same location, but the driver has abnormal behavior, then there is a high possibility of cheating. This comparison helps to detect and deal with cheating in a timely manner and protect the rights and interests of passengers.

[0055] S4: Determine whether the driver has cheated based on the obtained probability.

[0056] In this embodiment, when estimating the driving speed of the driver at the location point, the time when the driver uploaded the last location point is T1 in seconds, the time when the second to last location point is uploaded is T2 in seconds, and the distance between the last location point and the first to last location point is S in meters;

[0057] Specific formula:

[0058] Among them, the highway speed is marked as X;

[0059] All drivers are driving on the highway at a speed of X. The speed V calculated from the last position point and the last position point should be less than X. If it is greater, it is cheating, and T1, T2, V, X, and S are all greater than 0. By reflecting the actual driving conditions of the driver, it helps to detect abnormal behavior in a timely manner. By providing clear and specific formulas and calculation processes, the method of detecting cheating behavior can be made more standardized and transparent. This helps operators to conduct detection quickly and accurately, reduces the possibility of misjudgment, and improves detection efficiency and reliability.

[0060] In this embodiment, the method for acquiring vehicle data in step S1 includes the following steps:

[0061] Use GPS devices to record the location information of vehicles in real time, and use the API provided by the online ride-hailing platform to obtain the location data of vehicles in real time; By using GPS devices to record the location information of vehicles in real time, and using the API provided by the online ride-hailing platform to obtain the location data of vehicles in real time, it is possible to monitor the location and speed of vehicles in real time. This helps service providers to understand the actual operation of vehicles in a timely manner, including the current location of the vehicle, driving speed and other information

[0062] Real-time monitoring of vehicle location data, including the vehicle's real-time location and driving speed; by real-time monitoring of vehicle location data, it can ensure that the collected data is accurate and real-time. It helps to improve the accurate grasp of vehicle driving conditions, so as to conduct subsequent analysis and processing more reliably.

[0063] At the end of the trip, the last location uploaded by the driver and the last location are extracted from the collected trajectory data. This data processing process is automated and can effectively improve processing efficiency and accuracy. This method can avoid manual intervention and possible errors, and ensure the integrity and accuracy of the data.

[0064] Determining the end time of the trip based on the end-of-trip sign and obtaining the location point corresponding to that time from the trajectory data helps ensure the accuracy of recording the end time of the trip. This can provide an accurate time reference for subsequent data analysis and processing, thereby effectively evaluating the duration and path of the trip.

[0065] In this embodiment, the straight-line distance between the two location points is calculated based on the latitude and longitude information of the last uploaded location point and the last last location point;

[0066] Determine the timestamp of the driver's last uploaded location and the last last location, and record the upload time of the timestamp;

[0067] Calculate the time difference between two timestamps to get the time interval between the location points.

[0068] In this embodiment, the location information and driving time of other drivers of the same tenant at the same location point are collected;

[0069] Compare the distance and time interval between the driver's last uploaded location and the last location, and compare with the situation of other drivers of the same tenant at the same location;

[0070] Determine whether the distance and time interval between the last uploaded position point and the last last position point are within a similar range;

[0071] Calculate the ratio of the number of drivers with similar situations at the same location to the total number of drivers with the same tenant to get the probability value.

[0072] In this embodiment, when judging the probability in step S4, a threshold range is set as a standard for judging whether the driver has cheated; the obtained probability is compared with the set threshold to determine whether there is an abnormal situation. Setting the probability threshold range in step S4 can help determine whether the driver has cheated. By comparing the obtained probability with the set threshold, abnormal situations can be identified quickly and accurately. Such a setting makes the judgment process more standardized and controllable, helps operators to be more confident when dealing with abnormal situations, reduces the possibility of misjudgment, and improves detection efficiency and reliability.

[0073] When the observed probability value is lower than the set threshold, the system will automatically determine that the driver has cheated.

[0074] The basis for the judgment is that the probability value is lower than the threshold, indicating that the possibility of abnormal conditions occurring at the same location point is low.

[0075] Once the system automatically determines that the driver has cheated, it will automatically upload the driver's driving record, location information, and cheating behavior to the system;

[0076] If the observed probability value is greater than the set threshold range, it is determined to be a regional problem and a software problem; software problems include abnormalities in the order-taking software or positioning software, and regional problems include poor regional network signals or the nearest network base station is far away. By setting a threshold range and comparing the obtained probability with the threshold, the system can automatically determine whether the driver has cheated. The automated detection mechanism can help the system detect potential cheating behaviors in a timely manner without manual intervention, thereby improving the efficiency and accuracy of detection. After automatically determining that the driver has cheated, the system will automatically upload the driver's driving record, location information, and cheating behavior to the system. Such operations can improve the protection of passenger rights, prevent users from paying unnecessary fees or suffering from poor service experience, and enhance users' trust and satisfaction with the platform.

[0077] When the system detects an abnormal situation with a driver, it will automatically trigger an alarm and notify the relevant operation personnel or management personnel. The purpose of the alarm is to remind them that an abnormal situation has been discovered so that they can take timely measures. At the same time, the system will automatically temporarily freeze or disable the driver's account suspected of cheating to prevent him from continuing to engage in improper behavior.

[0078] Secondly, after obtaining the cheating information, the analysis model will be used to further review the driver's behavior. The logic of the cheating information review is:

[0079] The data extracted from the cheating information includes the driver's driving record, location information, driving speed, etc., as well as other features related to cheating behavior, such as the strangeness of the driving route and the inconsistency of driving distance and time interval. By analyzing this data and establishing corresponding analysis models, the driver's cheating behavior can be identified more accurately. These models will comprehensively consider the driver's driving behavior and related characteristics, thereby improving the detection and identification capabilities of cheating behavior.

[0080] According to the extracted features, the corresponding analysis model is established, and the model is modeled using rule engines, etc., and the established analysis model is trained using historical data to learn the difference between normal behavior patterns and cheating behavior patterns, so that cheating behavior can be better identified; the established analysis model will learn the difference between normal behavior patterns and cheating behavior patterns based on historical data, so that new cheating information can be better identified and classified. This helps reduce misjudgments and unnecessary penalties, and ensures that only drivers who actually cheat are marked as cheating.

[0081] Use the trained analysis model to identify and classify new cheating information to determine whether the information is cheating behavior. Cheating information involves anomaly detection, singularity detection, and cluster analysis of the driver's driving record. By performing anomaly detection, singularity detection, and cluster analysis on the driver's driving record, cheating behavior can be reviewed more comprehensively and the review efficiency can be improved. This helps the platform to detect and deal with cheating behavior in a timely manner.

[0082] Based on the output of the analysis model, the driver's behavior is marked as normal or cheating, and the relevant review results are recorded. Based on the output of the analysis model, the driver's behavior is marked as normal or cheating, and the relevant review results are recorded. The analysis model can automatically mark the driver's behavior without manual intervention, saving a lot of manpower costs and time. The analysis model can automatically mark the driver's behavior without manual intervention, saving a lot of manpower costs and time. Automatically marking behavior and recording review results can improve processing efficiency and data reliability, and reduce errors and delays caused by human factors.

[0083] Set the probability value to P, set the cheating features to X1, X2, X3...Xn, and mark the total number of features as Gn. The formula is:

[0084] Among them, X1, X2, X3....Xn, Gn are all greater than 0.

[0085] The probability value will be compared with the threshold, and the threshold will be set at 20% or below 15%. If 20% of the drivers have this problem, it will be judged as a software problem and not cheating. If 15% of the drivers of the same tenant also have this problem, it will be judged as a regional problem, perhaps the network signal in the area is not good, or the location of the nearest network base station. If it is below 15%, it will be judged as cheating.

[0086] The present invention assists in determining whether cheating occurs by analyzing the behavior of other drivers in the same tenant at the same location. The system collects and compares the driving trajectory, driving speed, travel cost and other information of other drivers in the same tenant at the same location to establish a baseline reference. Then, the behavior of the driver being tested is compared with this baseline reference. If it is found that the driver's behavior is significantly different or abnormal compared to other drivers, the system will mark it as a possible cheating object, and then strengthen monitoring and review. This multi-tenant-based auxiliary judgment method can improve the accuracy and reliability of cheating detection, thereby protecting the rights and interests of passengers and maintaining a fair competition environment in the industry.

[0087] If this application finds that the driver has cheated, the system will immediately mark and record his behavior, and automatically upload relevant information to the system for further investigation and processing by relevant departments. This timely feedback and processing mechanism can effectively prevent the potential impact of cheating on the interests of passengers and protect the safety and rights of passengers. At the same time, by strengthening the supervision and control of driver behavior, the overall integrity of the industry can be improved and passengers' trust in online car-hailing services can be enhanced.

[0088] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0089] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0090] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0091] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An anti-cheating method based on multi-tenant in-line trajectory endpoint, characterized by: The steps include: S1: Collect and monitor the vehicle's travel trajectory data. At the end of the trip, obtain the driver's last uploaded location and the last location. S2: Calculate the distance and time between the driver's last uploaded location and the last location to calculate the driver's driving speed at the location; S3: Observe whether other drivers of the same tenant have similar situations at the same location, and generate corresponding probabilities based on the observation results; S4: Determine whether the driver has cheated based on the obtained probability.

2. According to claim 1, a multi-tenant in-traffic endpoint anti-cheating method is characterized by: When estimating the driving speed of the driver at the location point, the time when the driver uploaded the last location point is T1 in seconds, the time when the second to last location point is T2 in seconds, and the distance between the last location point and the first to last location point is S in meters; Specific formula: Among them, the highway speed is marked as X; All drivers are driving on the highway and the speed is X. The speed V calculated from the last position point and the last position point should be less than X. If it is greater, it is cheating, and T1, T2, V, X, and S are all greater than 0.

3. According to claim 1, a multi-tenant in-traffic endpoint anti-cheating method is characterized by: The method for acquiring vehicle data in step S1 includes the following steps: Use GPS devices to record the vehicle's location information in real time, and use the API provided by the online ride-hailing platform to obtain the vehicle's location data in real time; Real-time monitoring of vehicle location data, including the vehicle's real-time location and driving speed; At the end of the trip, the last location point uploaded by the driver and the last location point are extracted from the collected trajectory data; According to the sign of the end of the trip, the end time of the trip is determined, and the position point corresponding to the time is obtained from the trajectory data.

4. According to claim 1, a multi-tenant in-traffic endpoint anti-cheating method is characterized by: Calculate the straight-line distance between the two locations based on the latitude and longitude information of the last uploaded location and the last last location; Determine the timestamp of the driver's last uploaded location and the last last location, and record the upload time of the timestamp; Calculate the time difference between two timestamps to get the time interval between the location points.

5. According to claim 1, a multi-tenant in-traffic endpoint anti-cheating method is characterized by: Collect location information and travel time of other drivers of the same tenant at the same location; Compare the distance and time interval between the driver's last uploaded location and the last location, and compare with the situation of other drivers of the same tenant at the same location; Determine whether the distance and time interval between the last uploaded position point and the last last position point are within a similar range; Calculate the ratio of the number of drivers with similar situations at the same location to the total number of drivers with the same tenant to get the probability value.

6. According to claim 1, a multi-tenant in-traffic endpoint anti-cheating method is characterized by: When judging the probability in step S4, a threshold range is set as a standard for judging whether the driver has cheated; the obtained probability is compared with the set threshold to determine whether there is an abnormality.

7. According to claim 6, a multi-tenant in-traffic endpoint anti-cheating method is characterized by: When the observed probability value is lower than the set threshold, the system will automatically determine that the driver has cheated; The judgment is based on the probability value being lower than the threshold, indicating that the probability of an abnormal situation occurring at the same location point is low; Once the system automatically determines that the driver has cheated, it will automatically upload the driver's driving record, location information, and cheating behavior to the system; If the observed probability value is greater than the set threshold range, it is determined to be a regional problem and a software problem; software problems include abnormalities in the order-taking software or positioning software, and regional problems include poor regional network signals or the remote location of the nearest network base station.

8. According to claim 6, a multi-tenant in-traffic endpoint anti-cheating method is characterized by: Set the probability value to P, set the cheating features to X1, X2, X3...Xn, and mark the total number of features as Gn. The formula is: Among them, X1, X2, X3....Xn, Gn are all greater than 0.

Images