Vehicle online state evaluation method and device and electronic equipment

Abstract

The invention discloses a vehicle online state evaluation method and device and electronic equipment, and belongs to the technical field of Internet of Vehicles. The method comprises the following steps: when a vehicle is in an online state on a service platform, acquiring multi-dimensional Internet of Vehicles data corresponding to a current moment; wherein the multi-dimensional Internet of Vehicles data comprises the following data of at least two dimensions: first state data of the vehicle, second state data of electronic equipment bound with the vehicle, and user interaction behavior data of a target application, corresponding to the service platform, on the electronic equipment. Service operation data of the vehicle on the service platform; and based on the multi-dimensional Internet of Vehicles data, determining an evaluation value that the online state is an abnormal state, so as to execute a corresponding target operation based on the evaluation value.

Description

Technical Field

[0001] This application belongs to the field of vehicle networking technology, specifically relating to a method, device, and electronic device for evaluating the online status of a vehicle. Background Technology

[0002] Currently, in the ride-hailing service industry, drivers are required to log on before accepting an order and log off after completing the service. However, in actual operation, drivers often forget to log off due to negligence or operational errors, for example: Drivers forget to log off when they are not interested in taking orders for extended periods, such as while their vehicles are charging, resting, or eating. The application process was abnormally terminated (e.g., the driver killed the application process directly) but no offline operation was triggered; The driver accidentally activated the online function without realizing it and failed to correct it in time.

[0003] The above situation results in drivers remaining online even when they have no intention of accepting orders, making them more susceptible to being assigned orders by the system. This leads to a series of problems such as passengers waiting longer, increased order cancellation rates, and more driver complaints, seriously damaging the driver and passenger experience and the platform's operational efficiency. Summary of the Invention

[0004] In view of the above problems, embodiments of this application provide a method, apparatus, and electronic device for evaluating the online status of a vehicle that overcomes or at least partially solves the above problems.

[0005] In a first aspect, embodiments of this application provide a method for evaluating the online status of a vehicle, including: When a vehicle is online on the service platform, multi-dimensional vehicle network data corresponding to the current moment is acquired; wherein, the multi-dimensional vehicle network data includes data in at least two of the following dimensions: the first state data of the vehicle, the second state data of the electronic device bound to the vehicle, the user interaction behavior data of the target application on the electronic device corresponding to the service platform, and the service operation data of the vehicle on the service platform; Based on the multi-dimensional vehicle network data, an evaluation value is determined for the online status to be an abnormal state, and the corresponding target operation is executed based on the evaluation value.

[0006] Secondly, embodiments of this application provide a vehicle online status assessment device, comprising: The acquisition module is used to acquire multi-dimensional vehicle network data corresponding to the current moment when the vehicle is online on the service platform; wherein, the multi-dimensional vehicle network data includes data of at least two of the following dimensions: the first state data of the vehicle, the second state data of the electronic device bound to the vehicle, the user interaction behavior data of the target application on the electronic device corresponding to the service platform, and the service operation data of the vehicle on the service platform; The processing module is used to determine an evaluation value for the online status as an abnormal state based on the multi-dimensional vehicle network data, and to perform the corresponding target operation based on the evaluation value.

[0007] Thirdly, embodiments of this application provide an electronic device including a processor and a memory, wherein the memory stores programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0008] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0009] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0010] In a sixth aspect, embodiments of this application provide a computer program product stored in a storage medium, which is executed by at least one processor to implement the method described in the first aspect.

[0011] In this embodiment, when the vehicle is online on the service platform, multi-dimensional vehicle network data corresponding to the current moment is acquired. The multi-dimensional vehicle network data includes data from at least two of the following dimensions: the vehicle's first state data, the second state data of the electronic devices bound to the vehicle, the user interaction behavior data of the target application on the electronic devices corresponding to the service platform, and the vehicle's service operation data on the service platform. Based on the above multi-dimensional vehicle network data, an assessment value is comprehensively evaluated to determine if the online state is an abnormal state. Based on the assessment value, the corresponding target operation is executed. The above scheme improves the accuracy of the assessment results by performing multi-dimensional abnormal assessments of the vehicle's current online state through multi-dimensional vehicle network data. The assessment results can determine the probability that the current online state is an abnormal online state, thereby enabling high-precision and low-latency determination of whether the user has forgotten to log off, reducing the invalid order dispatch rate, improving the driver and passenger experience, and enhancing the platform's operational efficiency. Attached Figure Description

[0012] Figure 1 This is a flowchart illustrating a method for evaluating the online status of a vehicle provided in some embodiments of this application; Figure 2 This is a schematic diagram of the structure of a vehicle online status assessment device provided in some embodiments of this application; Figure 3 These are structural block diagrams of electronic devices provided in some embodiments of this application. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0014] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0015] Currently, in the ride-hailing service industry, drivers often forget to log off due to negligence or operational errors. Common technical solutions to this problem are mainly based on simple timeout threshold mechanisms: when the system detects that a driver is online but has not received any orders or performed any operation for an extended period (e.g., 2 hours), the system automatically puts them offline or sends a one-time reminder notification. However, the above solutions have the following problems: 1. High error rate and low level of intelligence: The single timer mechanism cannot distinguish whether a driver "forgot to log off" or "is waiting for an order for a long time". For example, when a driver is patiently queuing in areas with high order volume such as airports and train stations, he may be wrongly judged as having forgotten to log off and forced to log off, which affects the driver's order-taking efficiency.

[0016] 2. Limited data dimensions and inaccurate identification: Existing solutions typically rely on only the single dimension of "online duration," lacking a multi-dimensional perception of the driver's real-time intentions, resulting in low identification accuracy.

[0017] 3. Delayed response and poor user experience: Due to the reliance on a fixed and long timeout threshold, the system has a high delay in recognizing the "forgot to log off" status. Invalid orders may still be dispatched within this window, and the problem cannot be resolved in a timely manner.

[0018] 4. Lack of adaptive and learning capabilities: Fixed thresholds cannot adapt to the individual behavioral habits of different drivers (e.g., some drivers are used to being online for long periods of time), nor can they be optimized based on historical feedback, resulting in rigid system strategies.

[0019] Therefore, this application provides a method, device, and electronic device for evaluating the online status of a vehicle. By using multi-dimensional vehicle network data to perform anomaly assessment on the current online status of the vehicle, the accuracy of the assessment results can be improved. The assessment results can determine the probability that the current online status is an abnormal online status, thereby enabling high-precision and low-latency determination of whether the user has forgotten to log off, reducing the invalid order dispatch rate, improving the driver and passenger experience, and enhancing the platform's operational efficiency.

[0020] The method for evaluating the online status of vehicles provided in this application will be described below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0021] like Figure 1 As shown in the figure, this application provides a method for evaluating the online status of a vehicle, which may specifically include the following steps: Step 101: When the vehicle is online on the service platform, acquire the multi-dimensional vehicle network data corresponding to the current moment; wherein, the multi-dimensional vehicle network data includes data in at least two of the following dimensions: the first state data of the vehicle, the second state data of the electronic device bound to the vehicle, the user interaction behavior data of the target application on the electronic device corresponding to the service platform, and the service operation data of the vehicle on the service platform.

[0022] If the vehicle is online on the service platform (i.e., the target application on the service platform displays the vehicle as online on the vehicle's bound electronic devices), the data acquisition module obtains multi-dimensional vehicle network data at the current moment, i.e., multi-dimensional vehicle network data. This multi-dimensional vehicle network data includes at least two of the following dimensions: the vehicle's first state data, the second state data of the electronic devices bound to the vehicle, user interaction behavior data on the electronic devices corresponding to the target application on the service platform, and the vehicle's service operation data on the service platform. The data acquisition module is deployed on the vehicle's bound electronic devices, the vehicle's infotainment system, the vehicle interface, and the service platform server (i.e., the cloud) to collect the aforementioned multi-dimensional vehicle network data in real time.

[0023] In one embodiment, when the multi-dimensional vehicle network data includes the first state data, the first state data includes, but is not limited to, at least one of the following: The vehicle's first speed, VehicleSpeed, is the vehicle's speed at the current moment, measured in km / h or m / s.

[0024] The first identifier, VehicleIsCharging, indicates whether the vehicle is currently charging. If it is charging, the first identifier can be set to 1; if it is not charging, the first identifier can be set to 0. Specifically, the vehicle's location at the current moment can be used to determine whether it is within the geofence of a charging station or charging pile. The On-Board Diagnostics (OBD) interface or Controller Area Network (CAN) can be used to determine whether the charging gun is physically connected and whether the charging circuit has been established. The vehicle's ignition or shutdown status can be used to determine the vehicle's status. By comprehensively considering the above factors, it can be determined whether the vehicle is currently charging.

[0025] In one embodiment, when the multi-dimensional vehicle network data includes the second state data, the second state data includes, but is not limited to, at least one of the following: The second speed of the electronic device, DeviceSpeed, is the speed of the electronic device attached to the vehicle at the current moment, in km / h or m / s.

[0026] The first position of the electronic device is its longitude GPS_Lat and latitude GPS_Lng at the current moment.

[0027] The electronic device's second position at a historical time corresponding to the current time is defined as the longitude (GPS_Lat_H) and latitude (GPS_Lng_H) of the historical time. For example, today's 6 PM is the current time, and yesterday's 6 PM is the corresponding historical time.

[0028] In one embodiment, when the multi-dimensional vehicle network data includes the user interaction behavior data, the user interaction behavior data includes, but is not limited to, at least one of the following: The running state of the target application, AppState, is defined as follows: if the target application is in the foreground at the current moment, then the running state of the target application is foreground running; if the target application is in the background at the current moment, then the running state of the target application is background running.

[0029] The LastOperationTimestamp is the timestamp of the last operation on the target application before the current time, which is the timestamp of the last operation on the target application by the user in the historical time before the current time, in seconds.

[0030] A second identifier indicating whether the target application's charging page is accessed within a first time period, wherein the first time period is the time period covered by a first duration traced back from the current moment, i.e., the end time of the first time period is the current moment.

[0031] The number of foreground / background switching operations performed on the target application and the number of operations performed on each page of the target application (e.g., clicks, swipes, etc.) within the second time period are counted. The second time period is the time period covered by a second duration counting backwards from the current moment, i.e., the end time of the second time period is the current moment. The number of operations performed on each different operation on each page of the target application within the second time period is counted, thus obtaining the number of operations corresponding to each operation on each page. Furthermore, the number of times the user switched between foreground and background on the target application within the second time period is also counted.

[0032] In one embodiment, when the multi-dimensional vehicle network data includes the service operation data, the service operation data includes, but is not limited to, at least one of the following: The current online time is the average of the online times of multiple historical online time periods. These multiple historical online time periods refer to the historical online time periods corresponding to the current time, specifically the time between the online and offline times within those periods. For example, if the current time is 6 PM today, the online time period for 6 PM is from 2 PM to 6 PM. If a user goes online at 2 PM, the online time period is between 2 PM and 6 PM, with 2 PM being the online time. Multiple historical times include 6 PM yesterday, 6 PM the day before yesterday, etc. Yesterday's 6 PM historical online time period was from 2 PM to 7 PM, with the historical online time being 2 PM. If the user went offline at 6 PM yesterday, then the online time period before 6 PM is the historical online time period for yesterday's 6 PM, i.e., from 1 PM to 5 PM, with the historical online time being 1 PM.

[0033] The online duration between the current online time and the current online time, and the average of the historical online durations corresponding to multiple historical online time periods (i.e., the average of multiple historical online durations), are considered. The duration between the current online time and the online time is the online duration. For example, if the current online time is 6 PM today and the online time is 2 PM, then the 4 hours between 2 PM and 6 PM are the online duration. If the historical online time is 6 PM yesterday, and the historical online time period for yesterday's 6 PM is from 2 PM to 7 PM, then the historical online duration is the 5 hours between 2 PM and 7 PM.

[0034] The average order interval between any two adjacent orders within the third time period and the average historical order interval between any two adjacent orders within the corresponding historical time period are calculated. The third time period is the time period covered by tracing back three times from the current moment, meaning the end time of the third time period is the current moment. The first, second, and third time periods can be the same or different time periods. The interval between any two adjacent orders within the third time period (i.e., the order interval) is calculated, and these intervals are summed to calculate the average (i.e., the average order interval). Furthermore, the average historical order interval for the corresponding historical time period is calculated in the same way. For example, if the third time period is from 2 PM to 6 PM today, then the historical time periods are from 2 PM to 6 PM yesterday, from 2 PM to 6 PM the day before yesterday, and so on.

[0035] Step 102: Based on the multi-dimensional vehicle network data, determine the evaluation value of the online status as an abnormal state, and perform the corresponding target operation based on the evaluation value.

[0036] By using the aforementioned multi-dimensional vehicle network data, a comprehensive user status profile is constructed, adding data for judging vehicle charging, and comprehensively calculating the evaluation value of online status as abnormal, which can significantly reduce the false judgment rate of abnormal online status.

[0037] The strategy execution module performs tiered and precise target operations based on evaluation values, such as prompting, confirmation, or automatic offline operations.

[0038] The evaluation values ​​are categorized to allow for the execution of corresponding target operations, as follows: When the evaluation value is between 0.3 and 0.6, a first-level target operation is performed, which is to send a context-aware intelligent reminder notification to the electronic device, such as: "Your vehicle is being charged. Please ignore this message if you need to accept an order." A "one-click offline" option is also provided so that users can easily handle the offline operation.

[0039] If the evaluation value is between 0.6 and 0.8, a secondary target operation is performed. This involves triggering a secondary confirmation mechanism before order dispatch by displaying a pop-up message on the electronic device, requiring the user to confirm whether they are willing to accept the order. If there is no response, the order dispatch is delayed.

[0040] When the evaluation value is between 0.8 and 1, a level 3 target operation is performed, which means that after a short period of waiting (e.g., 5 minutes) and no user feedback, the system automatically sets the online status to offline status.

[0041] The above embodiments avoid the crude "one-size-fits-all" approach by using a tiered operation strategy. When the evaluation value is low, only a mild reminder is given, while when the evaluation value is high, strong signals such as vehicle status are used for precise intervention. In addition, a confirmation step is added before dispatching orders, which fully respects the user's wishes and improves the user's satisfaction with the service platform.

[0042] In this embodiment, when the vehicle is online on the service platform, multi-dimensional vehicle network data corresponding to the current moment is acquired. The multi-dimensional vehicle network data includes data from at least two of the following dimensions: the vehicle's first state data, the second state data of the electronic devices bound to the vehicle, the user interaction behavior data of the target application on the electronic devices corresponding to the service platform, and the vehicle's service operation data on the service platform. Based on the above multi-dimensional vehicle network data, an assessment value is comprehensively evaluated to determine if the online state is an abnormal state. Based on the assessment value, the corresponding target operation is executed. The above scheme improves the accuracy of the assessment results by performing multi-dimensional abnormal assessments of the vehicle's current online state through multi-dimensional vehicle network data. The assessment results can determine the probability that the current online state is an abnormal online state, thereby enabling high-precision and low-latency determination of whether the user has forgotten to log off, reducing the invalid order dispatch rate, improving the driver and passenger experience, and enhancing the platform's operational efficiency.

[0043] In an optional specific embodiment, step 102, based on the multi-dimensional vehicle network data, determines the evaluation value for the online status as an abnormal state, including steps 1021 and 1022: Step 1021: Perform data processing on the multi-dimensional vehicle network data to obtain at least one vehicle network feature data.

[0044] Specifically, the feature engineering module processes multi-dimensional vehicle network data to extract high-value feature data that can characterize a user's willingness to accept orders, i.e., at least one vehicle network feature data. The feature engineering module is deployed in the cloud and is used to receive multi-dimensional vehicle network data and perform data processing to output standardized vehicle network feature data.

[0045] Step 1022: Input the at least one vehicle network feature data into the anomaly assessment model to obtain the assessment value of the online state being an abnormal state.

[0046] Specifically, at least one vehicle-to-everything (V2X) feature data is input into the anomaly assessment model. The intelligent judgment module in the anomaly assessment model processes the at least one V2X feature data and outputs an assessment value between 0 and 1 indicating that the online status is an abnormal state, i.e., the probability value of forgetting to go offline.

[0047] Among these, anomaly assessment models can include Gradient Boosting Decision Tree (GBDT), Random Forest, or Long Short-Term Memory (LSTM). GBDT excels at handling structured features, while LSTM is better at learning time-series behavioral patterns.

[0048] The closed-loop learning mechanism utilizes driver feedback data to continuously optimize the recognition model.

[0049] Furthermore, it can record user feedback on target actions, such as clicking the "One-Click Logout" selection control, ignoring notification messages, and confirming order acceptance. This user feedback data is used as labeled data for periodic retraining and optimization of the anomaly assessment model, forming a closed-loop optimization learning mechanism.

[0050] In one optional specific embodiment, step 1021 performs data processing on the multi-dimensional vehicle network data to obtain at least one vehicle network feature data, including: When the multi-dimensional vehicle network data includes the first location and the second location, the distance difference between the first location and the second location is calculated, and the vehicle network feature data includes the distance difference.

[0051] Specifically, if the multi-dimensional vehicle-to-everything (V2X) data includes a first location (GPS_Lat, GPS_Lng) and a second location (GPS_Lat_H, GPS_Lng_H), then the distance difference between the first and second locations, DistanceToHistoricLogoff, is calculated. This distance difference is the V2X feature data. The lower the distance difference, the more fixed the user's location is, and the less likely they are to move.

[0052] In one optional specific embodiment, step 1021 performs data processing on the multi-dimensional vehicle network data to obtain at least one vehicle network feature data, including: When the multi-dimensional vehicle network data includes the first identifier, if the first identifier indicates that the vehicle is charging, then the charging probability value of the vehicle is determined based on the first identifier, and the vehicle network feature data includes the charging probability value. If the first identifier indicates that the vehicle is not charging, then the charging probability value of the vehicle is calculated based on the second identifier, the operating status of the target application, the distance difference, the first speed, the second speed, and the time difference between the current time and the timestamp.

[0053] Specifically, the vehicle charging probability value ranges from 0 to 1. If the multi-dimensional vehicle network data includes a first identifier, and the first identifier is 1, it indicates that the vehicle is currently charging. In this case, the vehicle charging probability value, VehicleChargeConfidence (VCC), is equal to 1, and the charging probability value is the vehicle network feature data.

[0054] If the first identifier is 0, it means that the vehicle is not charging at the current time. Then, the charging probability value of the vehicle is calculated based on the second identifier of whether the charging page of the target application was entered during the first time period, the running status of the target application, the distance difference, the first speed of the vehicle, the second speed of the electronic device, and the time difference between the current time and the timestamp of the last operation of the target application before the current time.

[0055] In an optional specific embodiment, the step of calculating the charging probability value of the vehicle based on the second identifier, the operating status of the target application, the distance difference, the first speed, the second speed, and the time difference between the current time and the timestamp specifically includes: The distance difference is compared with the distance threshold to obtain a first comparison result; The first speed is compared with the first speed threshold to obtain a second comparison result; The second speed is compared with the second speed threshold to obtain the third comparison result; The time difference is compared with the time threshold to obtain the fourth comparison result; Based on the second identifier, the running status of the target application, the first comparison result, the second comparison result, the third comparison result, and the fourth comparison result, the charging probability value of the vehicle is calculated.

[0056] Specifically, the charging probability value of the aforementioned vehicles can be calculated using the following formula:

[0057] in, The probability value for charging the vehicle; This is an indicator function, and the corresponding condition is that the second flag is 1. If the condition is true, then... The value is 1 if the condition is not met. 0 is 0; 0.5 is the weighting coefficient corresponding to the second identifier; This is an indicator function, and the corresponding condition is that the target application is running in the foreground. If the condition is true, then... The value is 1 if the condition is not met. 0 is 0; 0.1 is the weight coefficient corresponding to the running state of the target application. This is an indicator function, and the corresponding condition is that the second comparison result is that the first velocity is less than the first velocity threshold (e.g., 5 m / s). If the condition is met, then... The value is 1 if the condition is not met. The value is 0; 0.1 is the weighting coefficient corresponding to the second comparison result. This is an indicator function, and the corresponding condition is that the third comparison result is that the second velocity is less than the second velocity threshold (e.g., 5 m / s). If the condition is met, then... The value is 1 if the condition is not met. A value of 0 indicates a negative result; 0.1 represents the weighting coefficient for the third comparison result. This is an indicator function, and the corresponding condition is that the first comparison result is a distance difference less than a distance threshold (e.g., 20 meters). If the condition is met, then... The value is 1 if the condition is not met. A value of 0 indicates a negative result; 0.1 represents the weighting coefficient corresponding to the first comparison result. This is an indicator function, and the corresponding condition is that the fourth comparison result is that the time difference between the current time and the timestamp of the last operation on the target application before the current time is greater than a time threshold (e.g., 10 minutes). If the condition is true, then... The value is 1 if the condition is not met. The value is 0; 0.1 is the weighting coefficient corresponding to the fourth comparison result.

[0058] In one optional specific embodiment, step 1021 performs data processing on the multi-dimensional vehicle network data to obtain at least one vehicle network feature data, including: When the multi-dimensional vehicle network data includes the number of switching operations and the number of operations for each operation on each page, the user operation activity is calculated based on the number of operations for each operation on each page and the corresponding first weight coefficient, the number of switching operations and the corresponding second weight coefficient, and the vehicle network feature data includes the user operation activity.

[0059] Specifically, if the multi-dimensional vehicle-to-everything (V2X) data includes the number of foreground / background switching operations of the target application and the number of operations performed on each page, then the number of operations performed on each page is multiplied by its corresponding first weight coefficient, and the number of switching operations of the target application is multiplied by its corresponding second weight coefficient. The products are then summed, and the resulting score is the Operational Activity Score (OAS). This OAS score is a V2X feature data measure of user interaction activity within the target application. The sum of the first and second weight coefficients for each operation on each page is 1.

[0060] For example: During the second time period, the user interacted with pages A and B of the target application and switched between foreground and background. The product of the click operation on page A and its corresponding first weight coefficient, the product of the swipe operation on page A and its corresponding first weight coefficient, the product of the click operation on page B and its corresponding first weight coefficient, the product of the swipe operation on page B and its corresponding first weight coefficient, and the product of the number of foreground / background switches in the target application and its corresponding second weight coefficient are calculated. The sum of these products is the user's activity level.

[0061] It should be noted that the first weight coefficient corresponding to the click operation on page A, the first weight coefficient corresponding to the swipe operation on page A, the first weight coefficient corresponding to the click operation on page B, and the first weight coefficient corresponding to the swipe operation on page B can be the same or different, and can be set as needed.

[0062] In an optional specific embodiment, step 1021 processes the multi-dimensional vehicle network data to obtain at least one vehicle network feature data, including but not limited to at least one of the following three: The first item: When the multi-dimensional vehicle network data includes the online duration and the average of the historical online duration, calculate the online duration outlier based on the absolute value of the first difference between the online duration and the average of the historical online duration and a first tolerance.

[0063] Specifically, if the multi-dimensional vehicle network data includes online duration and the average of historical online duration, the OnlineDurationAnomaly (ODA) can be calculated using the following formula:

[0064] in, These are outliers in online duration, which are characteristic data of the Internet of Vehicles (IoV) used to calculate the degree to which their behavior deviates from normal. Online time; This represents the average historical online time. The absolute value of the first difference; The first tolerance level can be a preset value or the standard deviation of historical online time.

[0065] The second item: When the multi-dimensional vehicle network data includes the online time and the average of the historical online times, if the abnormal value of the online duration is greater than a preset value, the abnormal value of the online time is calculated based on the absolute value of the second difference between the online time and the average of the historical online times and the second tolerance.

[0066] Specifically, if the multi-dimensional vehicle-to-everything (V2X) data includes both the online time and the historical average of online times, then the LoginTimeAnomaly (LTA) can be calculated using the following formula:

[0067] in, These are outlier values ​​for online time, and are only valid when ODA > a preset value (e.g., 0). Outlier values ​​for online time are characteristic data of the Internet of Vehicles, used to calculate the degree to which they deviate from normal behavior. This refers to the launch date; This is the average historical launch time; The absolute value of the second difference; The second tolerance level can be a preset value or the standard deviation of the historical online time.

[0068] Thirdly: When the multi-dimensional vehicle network data includes the average value of the order acceptance interval time and the average value of the historical order acceptance interval time, if the abnormal value of the online duration is greater than a preset value, then the abnormal value of the order acceptance interval is calculated based on the absolute value of the third difference between the average value of the order acceptance interval time and the average value of the historical order acceptance interval time, and the third tolerance.

[0069] Specifically, if the multi-dimensional vehicle network data includes the average order interval time and the historical average order interval time, the order interval anomaly (OIA) can be calculated using the following formula:

[0070] in, The order acceptance interval is an abnormal value, which is only valid when ODA > preset value (e.g., 0). The order acceptance interval abnormal value is the vehicle network characteristic data, which is used to calculate the degree of deviation from normal behavior. This represents the average order acceptance interval. This is the average historical order interval. The absolute value of the third difference; The third tolerance level can be a preset value or the standard deviation of historical order intervals.

[0071] In an optional specific embodiment, step 1022, which inputs the at least one vehicle-to-everything (V2X) feature data into an anomaly assessment model to obtain an assessment value indicating that the online state is an anomaly, includes: When the at least one vehicle-to-everything (V2X) characteristic data includes at least one of distance difference, user operation activity, abnormal online duration, abnormal online time, abnormal order acceptance interval, and charging probability value, the at least one of the distance difference, user operation activity, abnormal online duration, abnormal online time, and abnormal order acceptance interval is input into the anomaly assessment model. The distance difference, user operation activity, abnormal online duration, abnormal online time, and abnormal order acceptance interval are then normalized to obtain at least one of the following: normalized distance difference, normalized user operation activity, normalized online duration, normalized online time, and normalized order acceptance interval. Based on at least one of the following: the product of the normalized distance difference and the corresponding third weight coefficient; the product of the normalized user operation activity and the corresponding fourth weight coefficient; the product of the normalized online duration anomaly and the corresponding fifth weight coefficient; the product of the normalized online time anomaly and the corresponding sixth weight coefficient; the product of the normalized order acceptance interval anomaly and the corresponding seventh weight coefficient; the product of the charging probability value and the corresponding eighth weight coefficient; and the evaluation threshold, an evaluation value for the online state being an abnormal state is obtained.

[0072] Specifically, if at least one of the vehicle-to-everything (V2X) characteristic data includes not only at least one of the following: distance difference, user activity level, outlier online duration, outlier online time, and outlier order acceptance interval, but also a charging probability value, then the evaluation value can be calculated using the following formula:

[0073] in, This is the evaluation value; This represents the probability of charging. This represents the eighth weighting coefficient corresponding to the charging probability value, for example: greater than or equal to 0.5 and less than 1; express The weighting coefficients corresponding to the vehicle-to-everything (V2X) feature data (or the i-th normalized V2X feature data); This represents the normalized vehicle network feature data corresponding to the i-th vehicle network feature data.

[0074] The normalization process for various vehicle-to-everything (V2X) feature data is explained below:

[0075] in, This indicates an outlier in online duration; Indicates outliers in normalized online duration; This represents the scaling factor corresponding to outlier online durations, in order to... Scale to the range [0, 1].

[0076]

[0077] in, This is an outlier in the online time. This is to normalize outliers in the online time; This is the scaling factor corresponding to the outlier in the online time, in order to... Scaled to [0, 1], only counted if ODA is less than or equal to the online duration threshold Critical_ODA (e.g., 1.5).

[0078]

[0079] in, This indicates an abnormal value in the order acceptance interval. This represents outliers in the normalized order acceptance interval. This is the scaling factor corresponding to the abnormal value of the order interval, in order to... Scaled to [0, 1], only counted if ODA is less than or equal to the online duration threshold Critical_ODA (e.g., 1.5).

[0080]

[0081] in, To measure user activity; To normalize user activity levels, the lower the normalized user activity level, the greater the contribution. The scaling factor corresponding to user activity level, in order to... Scale to the range [0, 1].

[0082]

[0083] in, This represents the distance difference. This is the normalized distance difference; the higher the normalized distance difference, the smaller the contribution. This is the scaling factor corresponding to the distance difference, in order to... Scale to the range [0, 1].

[0084] In summary, this embodiment constructs a comprehensive user status profile through cross-validation of multi-dimensional vehicle network data, particularly by adding vehicle charging data, thus reducing the false positive rate of users forgetting to log off. Furthermore, the first, second, and third tolerance levels are dynamic values, which, through dynamic data and feedback learning mechanisms, can adapt to the individual habits of different users, resulting in higher accuracy over time. Moreover, the use of a machine learning model for real-time evaluation value calculation results in a response speed far faster than a fixed timeout mechanism, improving the efficiency of anomaly assessment. These embodiments fundamentally reduce invalid order dispatches and order cancellations caused by users forgetting to log off, improving the success rate of passenger ride-hailing experiences, optimizing the platform's capacity resource allocation, and reducing operating costs.

[0085] The vehicle online status assessment method provided in this application can be executed by a vehicle online status assessment device. This application uses an example of a vehicle online status assessment device executing the vehicle online status assessment method to illustrate the vehicle online status assessment device provided in this application.

[0086] like Figure 2 As shown in the figure, this application embodiment also provides a vehicle online status evaluation device 200, specifically including: The acquisition module 201 is used to acquire multi-dimensional vehicle network data corresponding to the current moment when the vehicle is online on the service platform; wherein, the multi-dimensional vehicle network data includes data of at least two of the following dimensions: the first state data of the vehicle, the second state data of the electronic device bound to the vehicle, the user interaction behavior data of the target application on the electronic device corresponding to the service platform, and the service operation data of the vehicle on the service platform. The processing module 202 is used to determine an evaluation value for the online status as an abnormal state based on the multi-dimensional vehicle network data, and to perform the corresponding target operation based on the evaluation value.

[0087] Optionally, when the processing module 202 determines the online status as an abnormal state based on the multi-dimensional vehicle network data, it is specifically used for: The multi-dimensional vehicle network data is processed to obtain at least one vehicle network feature data. The at least one vehicle-to-everything (V2X) feature data is input into the anomaly assessment model to obtain an assessment value indicating that the online state is an anomaly.

[0088] Optionally, when the multi-dimensional vehicle network data includes the first state data, the first state data includes at least one of the following: The vehicle's first speed; The first indicator of whether the vehicle is charging; When the multi-dimensional vehicle network data includes the second state data, the second state data includes at least one of the following: The second speed of the electronic device; The first position of the electronic device; The electronic device is located at a second position at a historical moment corresponding to the current moment; When the multi-dimensional vehicle network data includes the user interaction behavior data, the user interaction behavior data includes at least one of the following: The running status of the target application; The timestamp of the last operation on the target application before the current time; A second identifier indicating whether the target application's charging page is accessed within a first time period, wherein the first time period is the time period covered by a first duration traced backward from the current moment; The number of times the target application is switched between foreground and background during the second time period, and the number of times each operation is performed on each page of the target application. The second time period is the time period covered by the second duration tracing back from the current moment. When the multi-dimensional vehicle network data includes the service operation data, the service operation data includes at least one of the following: The current online time is the average of the online time of the current online time period and the historical online time corresponding to multiple historical online time periods, wherein the multiple historical online time periods are the historical online time periods corresponding to the current time. The online duration between the online time and the current time, and the average of the historical online durations corresponding to the multiple historical online time periods; The average order interval between each pair of adjacent orders within the third time period and the average historical order interval between each pair of adjacent orders within the corresponding historical time period, wherein the third time period is the time period covered by the third duration traced back from the current moment.

[0089] Optionally, when the processing module 202 processes the multi-dimensional vehicle network data to obtain at least one vehicle network feature data, it is specifically used for: When the multi-dimensional vehicle network data includes the first location and the second location, the distance difference between the first location and the second location is calculated, and the vehicle network feature data includes the distance difference.

[0090] Optionally, when the processing module 202 processes the multi-dimensional vehicle network data to obtain at least one vehicle network feature data, it is specifically used for: When the multi-dimensional vehicle network data includes the first identifier, if the first identifier indicates that the vehicle is charging, then the charging probability value of the vehicle is determined based on the first identifier, and the vehicle network feature data includes the charging probability value. If the first identifier indicates that the vehicle is not charging, then the charging probability value of the vehicle is calculated based on the second identifier, the operating status of the target application, the distance difference, the first speed, the second speed, and the time difference between the current time and the timestamp.

[0091] Optionally, when the processing module 202 calculates the charging probability value of the vehicle based on the second identifier, the running status of the target application, the distance difference, the first speed, the second speed, and the time difference between the current time and the timestamp, it is specifically used for: The distance difference is compared with the distance threshold to obtain a first comparison result; The first speed is compared with the first speed threshold to obtain a second comparison result; The second speed is compared with the second speed threshold to obtain the third comparison result; The time difference is compared with the time threshold to obtain the fourth comparison result; Based on the second identifier, the running status of the target application, the first comparison result, the second comparison result, the third comparison result, and the fourth comparison result, the charging probability value of the vehicle is calculated.

[0092] Optionally, when the processing module 202 processes the multi-dimensional vehicle network data to obtain at least one vehicle network feature data, it is specifically used for: When the multi-dimensional vehicle network data includes the number of switching operations and the number of operations for each operation on each page, the user operation activity is calculated based on the number of operations for each operation on each page and the corresponding first weight coefficient, the number of switching operations and the corresponding second weight coefficient, and the vehicle network feature data includes the user operation activity.

[0093] Optionally, when the processing module 202 processes the multi-dimensional vehicle network data to obtain at least one vehicle network feature data, it is specifically used for at least one of the following: When the multi-dimensional vehicle network data includes the online duration and the average of the historical online duration, anomalies in online duration are calculated based on the absolute value of the first difference between the online duration and the average of the historical online duration and a first tolerance. When the multi-dimensional vehicle network data includes the online time and the average of the historical online times, if the abnormal value of the online duration is greater than a preset value, the abnormal value of the online time is calculated based on the absolute value of the second difference between the online time and the average of the historical online times and the second tolerance. When the multi-dimensional vehicle network data includes the average value of the order acceptance interval time and the average value of the historical order acceptance interval time, if the abnormal value of the online duration is greater than a preset value, the abnormal value of the order acceptance interval is calculated based on the absolute value of the third difference between the average value of the order acceptance interval time and the average value of the historical order acceptance interval time, and the third tolerance.

[0094] Optionally, when the processing module 202 inputs the at least one vehicle-to-everything (V2X) feature data into the anomaly assessment model to obtain an assessment value indicating that the online state is an anomaly, it is specifically used for: When the at least one vehicle-to-everything (V2X) characteristic data includes at least one of distance difference, user operation activity, abnormal online duration, abnormal online time, abnormal order acceptance interval, and charging probability value, the at least one of the distance difference, user operation activity, abnormal online duration, abnormal online time, and abnormal order acceptance interval is input into the anomaly assessment model. The distance difference, user operation activity, abnormal online duration, abnormal online time, and abnormal order acceptance interval are then normalized to obtain at least one of the following: normalized distance difference, normalized user operation activity, normalized online duration, normalized online time, and normalized order acceptance interval. Based on at least one of the following: the product of the normalized distance difference and the corresponding third weight coefficient; the product of the normalized user operation activity and the corresponding fourth weight coefficient; the product of the normalized online duration anomaly and the corresponding fifth weight coefficient; the product of the normalized online time anomaly and the corresponding sixth weight coefficient; the product of the normalized order acceptance interval anomaly and the corresponding seventh weight coefficient; the product of the charging probability value and the corresponding eighth weight coefficient; and the evaluation threshold, an evaluation value for the online state being an abnormal state is obtained.

[0095] The vehicle online status assessment device in this application embodiment can be an electronic device or a component of an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.

[0096] The vehicle online status assessment device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0097] The vehicle online status evaluation device provided in this application embodiment can achieve Figure 1 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0098] Optionally, such as Figure 3As shown, this application embodiment also provides an electronic device 300, including a processor 301 and a memory 302. The memory 302 stores a program or instructions that can run on the processor 301. When the program or instructions are executed by the processor 301, they implement the various steps of the above-described vehicle online status evaluation method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0099] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0100] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described vehicle online status evaluation method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0101] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0102] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described vehicle online status evaluation method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0103] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0104] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described vehicle online status assessment method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0105] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0106] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0107] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for evaluating the online status of a vehicle, characterized in that, include: When a vehicle is online on the service platform, multi-dimensional vehicle network data corresponding to the current moment is acquired; wherein, the multi-dimensional vehicle network data includes data in at least two of the following dimensions: the first state data of the vehicle, the second state data of the electronic device bound to the vehicle, the user interaction behavior data of the target application on the electronic device corresponding to the service platform, and the service operation data of the vehicle on the service platform; Based on the multi-dimensional vehicle network data, an evaluation value is determined for the online status to be an abnormal state, and the corresponding target operation is executed based on the evaluation value.

2. The method according to claim 1, characterized in that, The evaluation value for determining the online status as abnormal based on the multi-dimensional vehicle network data includes: The multi-dimensional vehicle network data is processed to obtain at least one vehicle network feature data. The at least one vehicle-to-everything (V2X) feature data is input into the anomaly assessment model to obtain an assessment value for the online state being an anomaly.

3. The method according to claim 2, characterized in that, When the multi-dimensional vehicle network data includes the first state data, the first state data includes at least one of the following: The vehicle's first speed; The first indicator of whether the vehicle is charging; When the multi-dimensional vehicle network data includes the second state data, the second state data includes at least one of the following: The second speed of the electronic device; The first position of the electronic device; The electronic device is located at a second position at a historical moment corresponding to the current moment; When the multi-dimensional vehicle network data includes the user interaction behavior data, the user interaction behavior data includes at least one of the following: The running status of the target application; The timestamp of the last operation on the target application before the current time; A second identifier indicating whether the target application's charging page is accessed within a first time period, wherein the first time period is the time period covered by a first duration traced backward from the current moment; The number of times the target application is switched between foreground and background during the second time period, and the number of times each operation is performed on each page of the target application. The second time period is the time period covered by the second duration tracing back from the current moment. When the multi-dimensional vehicle network data includes the service operation data, the service operation data includes at least one of the following: The current online time is the average of the online time of the current online time period and the historical online time corresponding to multiple historical online time periods, wherein the multiple historical online time periods are the historical online time periods corresponding to the current time. The online duration between the online time and the current time, and the average of the historical online durations corresponding to the multiple historical online time periods; The average order interval between each pair of adjacent orders within the third time period and the average historical order interval between each pair of adjacent orders within the corresponding historical time period, wherein the third time period is the time period covered by the third duration traced back from the current moment.

4. The method according to claim 3, characterized in that, The data processing of the multi-dimensional vehicle network data to obtain at least one vehicle network feature data includes: When the multi-dimensional vehicle network data includes the first location and the second location, the distance difference between the first location and the second location is calculated, and the vehicle network feature data includes the distance difference.

5. The method according to claim 4, characterized in that, The data processing of the multi-dimensional vehicle network data to obtain at least one vehicle network feature data includes: When the multi-dimensional vehicle network data includes the first identifier, if the first identifier indicates that the vehicle is charging, then the charging probability value of the vehicle is determined based on the first identifier, and the vehicle network feature data includes the charging probability value. If the first identifier indicates that the vehicle is not charging, then the charging probability value of the vehicle is calculated based on the second identifier, the operating status of the target application, the distance difference, the first speed, the second speed, and the time difference between the current time and the timestamp.

6. The method according to claim 5, characterized in that, The calculation of the vehicle's charging probability value based on the second identifier, the target application's operating status, the distance difference, the first speed, the second speed, and the time difference between the current time and the timestamp includes: The distance difference is compared with the distance threshold to obtain a first comparison result; The first speed is compared with the first speed threshold to obtain a second comparison result; The second speed is compared with the second speed threshold to obtain a third comparison result; The time difference is compared with the time threshold to obtain the fourth comparison result; Based on the second identifier, the running status of the target application, the first comparison result, the second comparison result, the third comparison result, and the fourth comparison result, the charging probability value of the vehicle is calculated.

7. The method according to claim 3, characterized in that, The data processing of the multi-dimensional vehicle network data to obtain at least one vehicle network feature data includes: When the multi-dimensional vehicle network data includes the number of switching operations and the number of operations for each operation on each page, the user operation activity is calculated based on the number of operations for each operation on each page and the corresponding first weight coefficient, the number of switching operations and the corresponding second weight coefficient, and the vehicle network feature data includes the user operation activity.

8. The method according to claim 3, characterized in that, The data processing of the multi-dimensional vehicle network data to obtain at least one vehicle network feature data includes at least one of the following: When the multi-dimensional vehicle network data includes the online duration and the average of the historical online duration, anomalies in online duration are calculated based on the absolute value of the first difference between the online duration and the average of the historical online duration and a first tolerance. When the multi-dimensional vehicle network data includes the online time and the average of the historical online times, if the abnormal value of the online duration is greater than a preset value, the abnormal value of the online time is calculated based on the absolute value of the second difference between the online time and the average of the historical online times and the second tolerance. When the multi-dimensional vehicle network data includes the average value of the order acceptance interval time and the average value of the historical order acceptance interval time, if the abnormal value of the online duration is greater than a preset value, the abnormal value of the order acceptance interval is calculated based on the absolute value of the third difference between the average value of the order acceptance interval time and the average value of the historical order acceptance interval time, and the third tolerance.

9. The method according to claim 2, characterized in that, The step of inputting the at least one vehicle-to-everything (V2X) feature data into the anomaly assessment model to obtain an assessment value indicating that the online state is an anomaly includes: When the at least one vehicle-to-everything (V2X) characteristic data includes at least one of distance difference, user operation activity, abnormal online duration, abnormal online time, abnormal order acceptance interval, and charging probability value, the at least one of the distance difference, user operation activity, abnormal online duration, abnormal online time, and abnormal order acceptance interval is input into the anomaly assessment model. The distance difference, user operation activity, abnormal online duration, abnormal online time, and abnormal order acceptance interval are then normalized to obtain at least one of the following: normalized distance difference, normalized user operation activity, normalized online duration, normalized online time, and normalized order acceptance interval. Based on at least one of the following: the product of the normalized distance difference and the corresponding third weight coefficient; the product of the normalized user operation activity and the corresponding fourth weight coefficient; the product of the normalized online duration anomaly and the corresponding fifth weight coefficient; the product of the normalized online time anomaly and the corresponding sixth weight coefficient; the product of the normalized order acceptance interval anomaly and the corresponding seventh weight coefficient; the product of the charging probability value and the corresponding eighth weight coefficient; and the evaluation threshold, an evaluation value for the online state being an abnormal state is obtained.

10. A device for evaluating the online status of a vehicle, characterized in that, include: The acquisition module is used to acquire multi-dimensional vehicle network data corresponding to the current moment when the vehicle is online on the service platform; wherein, the multi-dimensional vehicle network data includes data of at least two of the following dimensions: the first state data of the vehicle, the second state data of the electronic device bound to the vehicle, the user interaction behavior data of the target application on the electronic device corresponding to the service platform, and the service operation data of the vehicle on the service platform; The processing module is used to determine an evaluation value for the online status as an abnormal state based on the multi-dimensional vehicle network data, and to perform the corresponding target operation based on the evaluation value.

11. An electronic device, characterized in that, It includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steps of the vehicle online status assessment method as described in any one of claims 1-9.

Images