Riding management method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a riding management method and device, electronic equipment and a storage medium, and belongs to the technical field of public transportation. The method comprises the following steps: calling a long-term risk assessment sub-model of a pre-trained risk assessment model to carry out long-term risk assessment on a balance fare ratio, an equipment risk probability and a long-term payment failure probability to obtain a long-term payment risk score; calling a short-term risk assessment sub-model of a pre-trained risk assessment model to perform short-term risk assessment on the code scanning time interval sequence and the short-term payment failure probability to obtain a short-term payment risk score; determining a target payment risk score according to a preset weight coefficient, the long-term payment risk score and the short-term payment risk score; and performing risk level mapping on the target payment risk score according to a preset risk level mapping table to obtain a target risk level of the target object, and performing riding management on the target object according to the target risk level. According to the embodiment of the invention, the riding management accuracy of the user can be improved.

Description

Technical Field

[0001] The present application relates to the field of public transportation technology, and in particular to a method and device for managing a ride, an electronic device, and a storage medium. Background Art

[0002] In the development of modern cities, QR code payment has become the mainstream payment method due to its convenience, efficiency, and security. For example, in the public transportation sector, QR code payment, as a form of QR code payment, is gradually replacing credit card payment and becoming the preferred method for travel due to its convenience of not requiring pre-purchased cards.

[0003] In scenarios where ride-hailing codes are widely used, operators often need to address the risk of user arrears. For example, due to insufficient account balances or malicious arrears, ride-hailing code payment deductions may fail, resulting in financial losses for operators and potentially causing credit issues. Credit issues often increase user payment risks, making it difficult for operators to accurately predict users' payment capabilities, increasing operational uncertainty and potential losses. Therefore, operators need to conduct payment risk assessments on users and then implement appropriate ride management based on the results to ensure operational efficiency and user experience.

[0004] However, in the existing technology, the accuracy of payment risk assessment is low, resulting in reduced accuracy in user ride management. Summary of the Invention

[0005] The main purpose of the embodiments of the present application is to propose a ride management method and device, electronic equipment and storage medium, aiming to improve the accuracy of ride management for users.

[0006] To achieve the above objectives, a first aspect of an embodiment of the present application provides a ride management method, the method comprising: In response to a target subject's ride payment operation, obtaining the target subject's balance fare ratio at the current time, obtaining the target subject's code scanning time interval sequence and short-term payment failure probability within a first time interval before the current time, and obtaining the target subject's device risk probability and long-term payment failure probability within a second time interval before the current time; wherein the second time interval is greater than the first time interval; Calling the long-term risk assessment sub-model of the pre-trained risk assessment model to perform a long-term risk assessment on the balance-to-fare ratio, the device risk probability, and the long-term payment failure probability to obtain a long-term payment risk score; Calling the short-term risk assessment sub-model of the pre-trained risk assessment model to perform a short-term risk assessment on the code scanning time interval sequence and the short-term payment failure probability to obtain a short-term payment risk score; Determine the target payment risk score of the target object according to a preset weight coefficient, the long-term payment risk score and the short-term payment risk score; The target payment risk score is mapped to a risk level according to a preset risk level mapping table to obtain the target risk level of the target object, and the target object is managed for riding according to the target risk level; wherein the preset risk level mapping table is used to indicate the mapping relationship between risk level and payment risk score.

[0007] In some embodiments, managing the target object's ride based on the target risk level includes: If the target risk level is a low risk level, controlling the target object's ride payment data to be in normal use; If the target risk level is a medium risk level, sending reminder data to the target subject according to a preset reminder method, and / or controlling the target subject's ride payment data to be in a quota usage state; If the target risk level is a high risk level, the ride payment data of the target object is controlled to be in a restricted use state.

[0008] In some embodiments, after performing ride management on the target object according to the target risk level, the method further includes: If the target risk level is the high risk level, obtaining the actual payment risk score of the target object at the current time, and constructing training sample data based on the actual payment risk score, the scan time interval sequence, the short-term payment failure probability, the device risk probability, and the long-term payment failure probability; The risk assessment model is optimized and trained according to the training sample data to obtain an optimized and trained risk assessment model.

[0009] In some embodiments, determining the target payment risk score of the target object according to a preset weight coefficient, the long-term payment risk score, and the short-term payment risk score includes: constructing current long-term risk data based on the balance-to-fare ratio, the device risk probability, and the long-term payment failure probability, obtaining historical long-term risk data of the target object, and performing a stability assessment on the current long-term risk data based on the historical long-term risk data to obtain a long-term stability score; Constructing current short-term risk data based on the scan time interval sequence and the short-term payment failure probability, obtaining historical short-term risk data of the target object, and performing a stability assessment on the current short-term risk data based on the historical short-term risk data to obtain a short-term stability score; Determining a first sub-weight coefficient corresponding to the long-term payment risk score and a second sub-weight coefficient corresponding to the short-term payment risk score based on the long-term stability score, the short-term stability score, and the preset weight coefficient; wherein the preset weight is used to indicate the sum of the first sub-weight coefficient and the second sub-weight coefficient; The target payment risk score of the target object is determined according to the long-term payment risk score, the first sub-weight coefficient, the short-term payment risk score, and the second sub-weight coefficient.

[0010] In some embodiments, determining the first sub-weight coefficient corresponding to the long-term payment risk score and the second sub-weight coefficient corresponding to the short-term payment risk score based on the long-term stability score, the short-term stability score, and the preset weight coefficient includes: Determining a total stability score based on the sum of the long-term stability score and the short-term stability score, and determining a weight adjustment factor for the long-term payment risk score based on a ratio of the long-term stability score to the total stability score; Adjust the parameters of the preset weight coefficient based on the weight adjustment factor to obtain a first sub-weight coefficient corresponding to the long-term payment risk score; A second sub-weight coefficient corresponding to the short-term payment risk score is determined based on the preset weight coefficient and the first sub-weight coefficient.

[0011] In some embodiments, performing risk level mapping on the target payment risk score according to a preset risk level mapping table to obtain the target risk level of the target object includes: Get the system security status at the current time; If the system security state is an attacked state, adjusting parameters of the preset risk level mapping table according to a first adjustment range to obtain a first adjusted risk level mapping table; wherein the maximum risk score corresponding to each risk level in the first adjusted risk level mapping table is less than the maximum risk score of the corresponding risk level in the preset risk level mapping table; The target payment risk score is mapped to a risk level according to the first adjusted risk level mapping table to obtain the target risk level of the target object.

[0012] In some embodiments, performing risk level mapping on the target payment risk score according to a preset risk level mapping table to obtain the target risk level of the target object further includes: If the system security status is normal, obtaining the geographic location information of the target object at the current time; If the geographic location information is within a preset high-risk area, adjusting parameters of the preset risk level mapping table according to a second adjustment range to obtain a second adjusted risk level mapping table; wherein the maximum risk score corresponding to each risk level in the second adjusted risk level mapping table is less than the maximum risk score of the corresponding risk level in the preset risk level mapping table; and the second adjustment range is less than the first adjustment range; The target payment risk score is mapped to a risk level according to the second adjusted risk level mapping table to obtain the target risk level of the target object.

[0013] In some embodiments, performing risk level mapping on the target payment risk score according to a preset risk level mapping table to obtain the target risk level of the target object further includes: If the geographic location information is outside the preset high-risk area and the current time is within the preset peak period, the parameters of the preset risk level mapping table are adjusted according to a third adjustment range to obtain a third adjusted risk level mapping table; wherein the maximum risk score corresponding to each risk level in the third adjusted risk level mapping table is greater than the maximum risk score of the corresponding risk level in the preset risk level mapping table; and the third adjustment range is less than the second adjustment range; The target payment risk score is mapped to a risk level according to the third adjusted risk level mapping table to obtain the target risk level of the target object.

[0014] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a ride management device, the device comprising: a data acquisition unit configured to, in response to a target subject's payment operation for a ride, acquire the target subject's current balance fare ratio, acquire the target subject's code scanning time interval sequence and short-term payment failure probability within a first time interval prior to the current time, and acquire the target subject's device risk probability and long-term payment failure probability within a second time interval prior to the current time; wherein the second time interval is greater than the first time interval; a long-term risk assessment unit, configured to call a long-term risk assessment sub-model of a pre-trained risk assessment model to perform a long-term risk assessment on the balance-to-fare ratio, the device risk probability, and the long-term payment failure probability, to obtain a long-term payment risk score; a short-term risk assessment unit, configured to call a short-term risk assessment sub-model of a pre-trained risk assessment model to perform a short-term risk assessment on the code scanning time interval sequence and the short-term payment failure probability to obtain a short-term payment risk score; a risk scoring unit, configured to determine a target payment risk score for the target object based on a preset weight coefficient, the long-term payment risk score, and the short-term payment risk score; A ride management unit is used to perform risk level mapping on the target payment risk score according to a preset risk level mapping table, obtain the target risk level of the target object, and perform ride management on the target object according to the target risk level; wherein the preset risk level mapping table is used to indicate the mapping relationship between risk level and payment risk score.

[0015] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0016] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect.

[0017] The ride management method and device, electronic device, and storage medium proposed in this application, in response to a target subject's ride payment operation, obtain the target subject's current balance fare ratio, obtain the target subject's scan code time interval sequence and short-term payment failure probability in a first time interval before the current time, and obtain the target subject's device risk probability and long-term payment failure probability in a second time interval before the current time. Then, the long-term risk assessment submodel of a pre-trained risk assessment model is invoked to perform a long-term risk assessment on the balance fare ratio, device risk probability, and long-term payment failure probability to obtain a long-term payment risk score. Furthermore, the short-term risk assessment submodel of the pre-trained risk assessment model is invoked to perform a short-term risk assessment on the scan code time interval sequence and short-term payment failure probability to obtain a short-term payment risk score. Furthermore, a target payment risk score for the target subject is determined based on a preset weight coefficient, the long-term payment risk score, and the short-term payment risk score. Finally, the target payment risk score is mapped to a risk level according to a preset risk level mapping table to obtain the target subject's target risk level, and ride management is performed on the target subject based on the target risk level.

[0018] This application calls the long-term risk assessment sub-model of the trained risk assessment model to perform a long-term risk assessment on the device risk probability, the long-term payment failure probability, and the current time balance fare ratio in the second time interval to obtain the long-term payment risk score of the target object, and calls the short-term risk assessment sub-model of the trained risk assessment model to perform a short-term risk assessment on the scanning time interval sequence and the short-term payment failure probability in the first time interval to obtain the short-term payment risk score of the target object, and then determines the target payment risk score based on the long-term payment risk score, the short-term payment risk score, and the preset weight coefficient. Finally, the target payment risk score is mapped to a risk level according to the preset risk level mapping table to obtain the target risk level of the target object, thereby managing the target object's ride according to the target risk level. In this way, it is possible to achieve a comprehensive analysis of the multi-dimensional data of the target object through two different models, reduce the problem of insufficient data utilization that may be caused by single-dimensional data, and avoid the problem that a single model may not be able to simultaneously predict short-term payment risk and long-term payment risk, thereby improving the accuracy of payment risk assessment, and then making it possible to refer to a more accurate payment risk score when determining the target risk level of the target object, that is, this application can improve the accuracy of user ride management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of the ride management method provided by an embodiment of the present application; Figure 2 This is a flowchart of the first method of determining a target risk level provided by an embodiment of the present application; Figure 3 This is a flow chart of the second method of determining target risk level provided in an embodiment of the present application; Figure 4 This is a flowchart of the third method of determining the target risk level provided in an embodiment of the present application; Figure 5 It is a structural diagram of the ride management device provided in an embodiment of the present application; Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0021] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0023] First, let’s analyze some of the terms used in this application: A neural network model is a computational model inspired by biological neural networks and used in machine learning and artificial intelligence. It consists of a hierarchy of neurons, each connected to the neurons in the next layer. These connections have weights, and through these weights and activation functions, the neural network can learn complex patterns and relationships in the input data.

[0024] A QR code is a credential used to board public transportation. Users can generate it through an app and display it to an on-board scanner for scanning. The QR code contains the user's identity, account information, and ride history. By connecting to public transportation payment systems, it enables fast fare deductions, making travel more convenient.

[0025] The widespread application of ride management methods has provided technical support for public transportation operations, effectively improving operational efficiency and user experience. However, existing ride management methods still have shortcomings when assessing user payment risk, significantly impacting the accuracy of ride management and reducing the user experience. For example, related technologies often use fixed rules (such as account balance thresholds and historical arrears) to control user arrears risk. However, this approach cannot dynamically assess user payment risk in real time, potentially leading to misjudgments (such as high-credit users being blocked due to temporary insufficient balances) or missed judgments (such as frequently arrears users not being blocked). Alternatively, related technologies use manual review to assess payment risk. However, this approach is inefficient, struggles to cope with high-concurrency scenarios, and degrades the user experience. Alternatively, related technologies use simple rule engines to integrate limited user data. However, this approach fails to effectively leverage multi-dimensional data for comprehensive analysis, resulting in an incomplete risk assessment, which in turn reduces the accuracy of payment risk assessment and, consequently, ride management. Based on this, the embodiments of the present application provide a ride management method and device, an electronic device and a storage medium, which aim to improve the accuracy of payment risk assessment, thereby improving the accuracy of user ride management, and further improving the user experience.

[0026] The ride management method provided in the embodiment of the present application relates to the field of public transportation technology. The ride management method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the ride management method, etc., but is not limited to the above forms.

[0027] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0028] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0029] Figure 1 This is an optional flowchart of the ride management method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S105: Step S101: In response to a ride payment operation by a target subject, the target subject's current balance fare ratio is obtained, along with a sequence of scanned QR code time intervals and a short-term payment failure probability within a first time interval prior to the current time, and the target subject's device risk probability and long-term payment failure probability within a second time interval prior to the current time. Step S102: Calling the long-term risk assessment sub-model of the pre-trained risk assessment model to perform a long-term risk assessment on the balance-to-fare ratio, the device risk probability, and the long-term payment failure probability to obtain a long-term payment risk score; Step S103: Calling the short-term risk assessment sub-model of the pre-trained risk assessment model to perform a short-term risk assessment on the scan time interval sequence and the short-term payment failure probability to obtain a short-term payment risk score; Step S104, determining the target payment risk score of the target object based on the preset weight coefficient, the long-term payment risk score and the short-term payment risk score; Step S105 , mapping the target payment risk score to a risk level according to a preset risk level mapping table to obtain a target risk level of the target object, and performing travel management on the target object according to the target risk level.

[0030] In steps S101 to S105 shown in the embodiment of the present application, a long-term risk assessment is performed on the device risk probability, the long-term payment failure probability and the current balance fare ratio within the second time interval by calling the long-term risk assessment sub-model of the trained risk assessment model to obtain the long-term payment risk score of the target object, and a short-term risk assessment sub-model of the trained risk assessment model is called to perform a short-term risk assessment on the scanning time interval sequence and the short-term payment failure probability within the first time interval to obtain the short-term payment risk score of the target object, and then the target payment risk score is determined based on the long-term payment risk score, the short-term payment risk score and the preset weight coefficient, and finally the target payment risk score is mapped to the risk level according to the preset risk level mapping table to obtain the target risk level of the target object, so as to manage the target object according to the target risk level. In this way, it is possible to conduct a comprehensive analysis of the multi-dimensional data of the target object through two different models, reduce the problem of insufficient data utilization that may be caused by single-dimensional data, and avoid the problem that a single model may not be able to simultaneously predict short-term payment risks and long-term payment risks, thereby improving the accuracy of payment risk assessment, and then making it possible to refer to a more accurate payment risk score when determining the target risk level of the target object, that is, this application can improve the accuracy of user ride management.

[0031] In step S101 of some embodiments, the target object may refer to an object requiring a payment risk assessment, and a corresponding risk level may be determined based on the payment risk assessment results. For example, the target object may be a user who needs to take public transportation. The ride payment operation may refer to the target object's action of controlling a public transportation-related application to generate a ride code. The current time may refer to the time at which the target object controls the public transportation-related application to generate the ride code. For example, if the target object performs a ride payment operation at 8:00, the current time is 8:00. The balance fare ratio may refer to the ratio of the target object's account balance at the current time to the estimated fare. For example, if the target object's account balance at the current time is 20 yuan and the estimated fare is 5 yuan, the balance fare ratio is 4; alternatively, if the target object's account balance at the current time is 1 yuan and the estimated fare is 2 yuan, the balance fare ratio is 0.5. It should be noted that the estimated fare may refer to the fare calculated based on a comprehensive assessment of the target object's historical ride records (e.g., historical ride routes, historical fares, etc.). For example, if the fare of the public transportation that the target subject usually takes is 2 yuan, the expected fare can be estimated as 2 yuan.

[0032] The first time interval can refer to a specific time range before the current time. For example, if the current time is 8:00 AM, the first time interval can refer to the one-hour period from 7:00 AM to 8:00 AM; or, if the current time is March 6th, the first time interval can refer to the one-day period from March 5th to March 6th. It is understood that the length of the first time interval can be adjusted based on actual needs. The scan time interval sequence can refer to the sequence of time intervals corresponding to when the target subject uses the ride code to scan the code within the first time interval. For example, if the first time interval is one hour from 7:00 AM to 8:00 AM, the scan time interval sequence can be the interval between each scan operation within that hour, such as [5s, 4s, 300s]. The short-term payment failure probability can refer to the ratio of the number of payment failures to the total number of payments made by the target subject using the ride code to scan the code within the first time interval. For example, if the first time interval is one hour from 7:00 AM to 8:00 AM, and the target subject makes four payments within that hour, two of which fail, then the short-term payment failure probability is 0.5.

[0033] The second time interval can refer to another specific time range before the current time. For example, if the current time is September, the second time interval can refer to the one-month period from August to September. Alternatively, if the current time is the eighth week, the second time interval can refer to the five weeks from the eighth week to the third week. It is understood that the length of the second time interval can be adjusted based on actual needs, but it must be longer than the first time interval. The device risk probability can refer to a risk value derived from a comprehensive assessment of the target subject's terminal device (e.g., mobile phone) usage during the second time interval. For example, if the target subject frequently changes terminal devices or the device's IP address changes abnormally during the second time interval, the device risk probability can be set to a higher value, such as 0.8. Alternatively, if the target subject uses the same terminal device and its IP address remains stable during the second time interval, the device risk probability can be set to a lower value, such as 0.1. It is understood that the device risk probability assessment method can be adjusted based on actual needs. The long-term payment failure probability can refer to the ratio of the number of payment failures after the target subject scans the ride code to the total number of payments made during the second time interval. For example, if the second time interval is one month from August to September, and the target object makes 80 payments in total within one month, of which 20 payments fail, then the long-term payment failure probability is 0.25.

[0034] In step S102 of some embodiments, the pre-trained risk assessment model may refer to a trained deep learning model with payment risk assessment capabilities. The risk assessment model includes a long-term risk assessment sub-model. The long-term risk assessment sub-model may refer to a model component in the risk assessment model used to assess long-term payment risk. For example, the long-term risk assessment sub-model may be a Random Forest model (RF) or a Gradient Boosting Decision Tree (GBDT), without specific limitation. Long-term risk assessment may refer to the process of calling the long-term risk assessment sub-model to conduct a comprehensive analysis of the balance-to-fare ratio, device risk probability, and long-term payment failure probability to predict the long-term payment risk score of the target object. The long-term payment risk score may refer to the numerical value used to quantify the long-term payment risk of the target object after calling the long-term risk assessment sub-model to perform a long-term risk assessment on the balance-to-fare ratio, device risk probability, and long-term payment failure probability.

[0035] In step S103 of some embodiments, the risk assessment model includes a short-term risk assessment sub-model. The short-term risk assessment sub-model may refer to a model component in the risk assessment model used to assess short-term payment risks. For example, the short-term risk assessment sub-model may be a Long Short-Term Memory model (LSTM) or a Gated Recurrent Unit model (GRU), without specific limitation. Short-term risk assessment may refer to the process of calling the short-term risk assessment sub-model to conduct a comprehensive analysis of the scan code time interval sequence and the short-term payment failure probability to predict the short-term payment risk score of the target object. The short-term payment risk score may refer to the numerical value used to quantify the short-term payment risk of the target object after calling the short-term risk assessment sub-model to conduct a short-term risk assessment on the scan code time interval sequence and the short-term payment failure probability.

[0036] In step S104 of some embodiments, the preset weight coefficient refers to a pre-set weight value, including the weights corresponding to the long-term payment risk score and the short-term payment risk score, respectively. For example, if the preset weight coefficient can be expressed as 1, and the importance of the long-term payment risk score is higher and the importance of the short-term payment risk score is lower, then the weight of the long-term payment risk score can be set to 0.7 and the weight of the short-term payment risk score can be set to 0.3; or, if the importance of the short-term payment risk score is higher and the importance of the long-term payment risk score is lower, then the weight of the short-term payment risk score can be set to 0.6 and the weight of the long-term payment risk score can be set to 0.4. The target payment risk score can refer to a comprehensive score obtained by weighting the long-term payment risk score and the short-term payment risk score according to the preset weight coefficient. For example, if the long-term payment risk score is 0.8 and the short-term payment risk score is 0.5, the weight of the long-term payment risk score is set to 0.7 and the weight of the short-term payment risk score is set to 0.3, then the target payment risk score is 0.7×0.8 + 0.3×0.5 = 0.61; or, if the long-term payment risk score is 0.5 and the short-term payment risk score is 0.2, the weight of the long-term payment risk score is set to 0.4 and the weight of the short-term payment risk score is set to 0.6, then the target payment risk score is 0.4×0.5 + 0.6×0.2 = 0.32.

[0037] In step S105 of some embodiments, risk level mapping may refer to the process of mapping a target payment risk score to a corresponding risk level according to a preset risk level mapping table. The preset risk level mapping table may refer to a predefined table that indicates the mapping relationship between risk levels and payment risk scores. For example, as shown in Table 1, Table 1 is an example of a preset risk level mapping table provided in an embodiment of the present application, in which the payment risk score is divided into three intervals: 0-0.4 corresponds to low risk, 0.4-0.7 corresponds to medium risk, and greater than 0.7 corresponds to high risk. The target risk level may refer to the level indicating the payment risk level of the target object obtained by mapping the target payment risk score to a risk level according to the preset risk level mapping table. For example, if the target payment risk score is 0.6, then according to the preset risk level mapping table in Table 1, this score falls within the interval of 0.4-0.7 and corresponds to a medium risk level. Alternatively, if the target payment risk score is 0.8, then according to the preset risk level mapping table in Table 1, this score is greater than 0.7 and corresponds to a high risk level.

[0038]

[0039] Ride management refers to the process of taking appropriate management measures based on the target risk level of the target user to control and reduce payment risks in public transportation operations. For example, for low-risk users, they can be allowed to use the ride code normally; for medium-risk users, their ride amount or number of rides can be restricted; for high-risk users, their ride service can be suspended or they can be required to top up in advance to ensure payment ability.

[0040] In some embodiments, determining a target payment risk score of a target object based on a preset weight coefficient, a long-term payment risk score, and a short-term payment risk score includes: Build current long-term risk data based on the balance-to-fare ratio, device risk probability, and long-term payment failure probability, obtain historical long-term risk data of the target object, and perform stability assessment on current long-term risk data based on historical long-term risk data to obtain a long-term stability score. Build current short-term risk data based on the scan time interval sequence and the short-term payment failure probability, obtain the historical short-term risk data of the target object, and perform a stability assessment on the current short-term risk data based on the historical short-term risk data to obtain a short-term stability score. Determining a first sub-weight coefficient corresponding to the long-term payment risk score and a second sub-weight coefficient corresponding to the short-term payment risk score based on the long-term stability score, the short-term stability score, and a preset weight coefficient; wherein the preset weight is used to indicate the sum of the first sub-weight coefficient and the second sub-weight coefficient; The target payment risk score of the target object is determined based on the long-term payment risk score, the first sub-weight coefficient, the short-term payment risk score, and the second sub-weight coefficient.

[0041] In the embodiments of the present application, current long-term risk data may refer to a data set constructed based on the balance-to-fare ratio, device risk probability, and long-term payment failure probability, used to reflect the current long-term payment risk status of the target object. Historical long-term risk data may refer to a data set constructed based on the historical balance-to-fare ratio, historical device risk probability, and historical long-term payment failure probability of the target object, used to reflect the historical long-term payment risk status of the target object. It should be noted that the historical long-term risk data and the current long-term risk data contain the same type of data, and the reference time length when obtaining the required data is also the same, to ensure consistency and comparability between the two when performing stability assessments. Stability assessment may refer to the process of comparing the balance-to-fare ratio, device risk probability, and long-term payment failure probability included in the current long-term risk data with the historical balance-to-fare ratio, historical device risk probability, and historical long-term payment failure probability included in the historical long-term risk data one by one to assess data consistency and fluctuations. The long-term stability score may refer to a quantitative score obtained after performing a stability assessment on the current long-term risk data based on the historical long-term risk data, used to indicate the stability of the target object's long-term payment risk.

[0042] Current short-term risk data may refer to a data set constructed based on the scan time interval sequence and the short-term payment failure probability, which is used to reflect the current short-term payment risk status of the target object. Historical short-term risk data may refer to a data set constructed based on the historical scan time interval sequence and the historical short-term payment failure probability of the target object, which is used to reflect the historical short-term payment risk status of the target object. It should be noted that the historical short-term risk data and the current short-term risk data contain the same type of data, and the reference time length when obtaining the required data is also the same, to ensure the consistency and comparability of the two when conducting stability assessments. Stability assessment may refer to the process of comparing the scan time interval sequence and short-term payment failure probability in the current short-term risk data with the corresponding historical scan time interval sequence and historical short-term payment failure probability in the historical short-term risk data one by one to evaluate data consistency and fluctuations. Short-term stability score may refer to a quantitative score obtained after stability assessment, which is used to indicate the stability of the target object's short-term payment risk.

[0043] The first sub-weight coefficient and the second sub-weight coefficient can be comprehensively determined based on the long-term stability score, the short-term stability score and the preset weight coefficient. Among them, the preset weight can refer to a pre-set weight ratio used to indicate the sum of the first sub-weight coefficient and the second sub-weight coefficient. For example, if the long-term stability score is 0.9, the short-term stability score is 0.6, and the preset weight coefficient is 1, it can be considered that the stability of the long-term payment risk score is relatively high, and the first sub-weight coefficient can be determined to be 0.7, and the second sub-weight coefficient can be determined to be 0.3. Alternatively, if the long-term stability score is 0.6, the short-term stability score is 0.8, and the preset weight coefficient is 1, it can be considered that the stability of the short-term payment risk score is relatively high, and the first sub-weight coefficient can be determined to be 0.4, and the second sub-weight coefficient can be determined to be 0.6.

[0044] The target payment risk score can be the combined score obtained by multiplying the long-term payment risk score by the first sub-weighting coefficient, plus the short-term payment risk score by the second sub-weighting coefficient. For example, if the long-term payment risk score is 0.8, the first sub-weighting coefficient is 0.7, the short-term payment risk score is 0.5, and the second sub-weighting coefficient is 0.3, then the target payment risk score is 0.8×0.7+0.5×0.3=0.61.

[0045] It can be understood that this application performs a stability assessment on the current long-term risk data constructed based on the balance fare ratio, device risk probability and long-term payment failure probability and the corresponding historical long-term risk data to obtain a long-term stability score. At the same time, the application performs a stability assessment on the current short-term risk data constructed based on the scan code time interval sequence and the short-term payment failure probability and the corresponding historical short-term risk data to obtain a short-term stability score. The first sub-weight coefficient corresponding to the long-term payment risk score and the second sub-weight coefficient corresponding to the short-term payment risk score are determined based on the long-term stability score, the short-term stability score and the preset weight coefficient. In this way, the target payment risk score can be obtained by weighted calculation based on the long-term payment risk score and the short-term payment risk score and their respective weight coefficients, reducing the deviation that may be caused by the pre-assigned weights, reducing the impact of unstable data in payment risk prediction, improving the accuracy of payment risk assessment, and thus improving the accuracy of ride management.

[0046] In some embodiments, determining a first sub-weight coefficient corresponding to the long-term payment risk score and a second sub-weight coefficient corresponding to the short-term payment risk score based on the long-term stability score, the short-term stability score, and a preset weight coefficient includes: The total stability score is determined based on the sum of the long-term stability score and the short-term stability score, and the weight adjustment factor of the long-term payment risk score is determined based on the ratio of the long-term stability score to the total stability score; Adjust the parameters of the preset weight coefficient based on the weight adjustment factor to obtain the first sub-weight coefficient corresponding to the long-term payment risk score; The second sub-weight coefficient corresponding to the short-term payment risk score is determined based on the preset weight coefficient and the first sub-weight coefficient.

[0047] In the embodiments of the present application, the total stability score may refer to the sum of the long-term stability score and the short-term stability score. For example, if the long-term stability score is 0.7 and the short-term stability score is 0.3, the total stability score is 1.0. The weight adjustment factor may refer to the ratio of the long-term stability score to the total stability score, which is used to measure the relative contribution of the long-term payment risk score to the overall stability. For example, if the long-term stability score is 0.7 and the total stability score is 1.0, the weight adjustment factor is 0.7 / 1.0 = 0.7. Parameter adjustment may refer to the process of adjusting the preset weight coefficient according to the weight adjustment factor to determine the first sub-weight coefficient. The first sub-weight coefficient may refer to the weight value corresponding to the long-term payment risk score obtained after parameter adjustment of the preset weight coefficient based on the weight adjustment factor. For example, if the weight adjustment factor is 0.7 and the preset weight coefficient is 1, the first sub-weight coefficient may be 0.7×1=0.7. The second sub-weight coefficient may refer to the weight value corresponding to the short-term payment risk score determined based on the preset weight coefficient and the first sub-weight coefficient. For example, if the preset weight coefficient is 1, the first sub-weight coefficient is 0.7, and the second sub-weight coefficient is 0.3.

[0048] It is understandable that the present application determines the total stability score by the sum of the long-term stability score and the short-term stability score, and determines the weight adjustment factor of the long-term payment risk score based on the ratio of the long-term stability score to the total stability score, and then determines the first sub-weight coefficient of the long-term payment risk score based on the weight adjustment factor and the preset weight coefficient, and finally determines the second sub-weight coefficient corresponding to the short-term payment risk score based on the first sub-weight coefficient and the preset weight coefficient. In this way, the weight values ​​corresponding to the long-term payment risk score and the short-term payment risk score can be automatically adjusted, making the weight distribution more flexible and accurate, reducing manual intervention, and improving the efficiency of payment risk assessment, thereby improving the efficiency of ride management.

[0049] It should be noted that in order to reduce the computing resources required to calculate the weight values ​​corresponding to the long-term payment risk score and the short-term payment risk score, the embodiment of the present application can also pre-set a stability score threshold, such as 0.8. When the long-term stability score or the short-term stability score is higher than the stability score threshold, the corresponding weight coefficient can be directly determined to be a preset value, such as 0.7, and then another weight coefficient can be determined based on the preset weight coefficient. When the long-term stability score and the short-term stability score are both higher or lower than the stability score threshold, the corresponding weight coefficients can be directly determined to be another preset value, such as 0.5. The size of the stability score threshold and the preset weight value can be freely adjusted according to actual needs.

[0050] In some embodiments, risk level mapping is performed on the target payment risk score according to a preset risk level mapping table to obtain the target risk level of the target object, including: Get the system security status at the current time; If the system security state is an attacked state, adjusting the parameters of the preset risk level mapping table according to the first adjustment range to obtain a first adjusted risk level mapping table; The target payment risk score is mapped to a risk level according to the first adjusted risk level mapping table to obtain a target risk level for the target object.

[0051] In an embodiment of the present application, the system security status may refer to the security status of the system at the current time. The system security status includes an attacked state and a normal state. Among them, the attacked state may refer to the system being under security threats or attacks at the current time. The normal state may refer to the system being not under security threats and operating stably at the current time. The first adjustment range may refer to a pre-set parameter for adjusting the maximum payment risk score in the preset risk level mapping table. For example, the first adjustment range may be 0.5 or 0.4, and is not specifically limited. Parameter adjustment may refer to the process of changing the maximum risk score corresponding to each risk level in the preset risk level mapping table according to the first adjustment range. The first adjusted risk level mapping table may refer to the risk level mapping table obtained after the parameters of the preset risk level mapping table are adjusted according to the first adjustment range.

[0052] It is understandable that the maximum risk score corresponding to each risk level in the first adjusted risk level mapping table is less than the maximum risk score of the corresponding risk level in the preset risk level mapping table. For example, as shown in Table 2, Table 2 is an example of a first adjusted risk level mapping table provided in an embodiment of the present application. This table is obtained by adjusting the parameters of the preset risk level mapping table shown in Table 1 when the first adjustment range is 0.5. The payment risk score is divided into three intervals: 0-0.2 corresponds to low risk, 0.2-0.35 corresponds to medium risk, and greater than 0.35 corresponds to high risk.

[0053]

[0054] The target risk level may refer to a level indicating the payment risk level of the target object obtained by mapping the target payment risk score to a risk level according to the first adjustment risk level mapping table. For example, see Figure 2 , Figure 2 The first flow chart for determining the target risk level provided in the embodiment of the present application specifically includes: first, obtaining the system security status at the current time. Then, determining whether the system security status is in an attacked state. If the system security status is in an attacked state, the parameters of the preset risk level mapping table are adjusted according to the first adjustment range to obtain a first adjusted risk level mapping table, and finally, the target payment risk score is risk-level mapped according to the first adjusted risk level mapping table to obtain the target risk level of the target object; if the system security status is not in an attacked state (i.e., a normal state), the target payment risk score is risk-level mapped according to the preset risk level mapping table to obtain the target risk level of the target object.

[0055] It is understood that the embodiments of this application dynamically adjust the preset risk level mapping table based on the current system security status. This allows for timely improvement in the stringency of risk assessments when the system is under attack, reducing the likelihood of missing potential risks when assessing user payment risks, improving the accuracy of payment risk assessments, and ultimately, improving the accuracy of ride management.

[0056] In some embodiments, performing risk level mapping on the target payment risk score according to a preset risk level mapping table to obtain the target risk level of the target object further includes: If the system security status is normal, obtain the target object's geographic location information at the current time; If the geographical location information is within the preset high-risk area, adjusting the parameters of the preset risk level mapping table according to the second adjustment range to obtain a second adjusted risk level mapping table; The target payment risk score is mapped to a risk level according to the second adjusted risk level mapping table to obtain the target risk level of the target object.

[0057] In embodiments of the present application, geographic location information may refer to the geographic location of the target object at the current time. For example, the geographic location information may be the latitude and longitude coordinates of the target object; alternatively, the geographic location information may be a combination of the city and street name where the target object is located, without limitation. The preset high-risk area may refer to a pre-defined high-risk geographical area. When the geographic location information is within the preset high-risk area, the parameters of the preset risk level mapping table may be adjusted according to a second adjustment range to obtain a second adjusted risk level mapping table. The second adjustment range may refer to a pre-set parameter for adjusting the maximum payment risk score in the preset risk level mapping table. For example, the second adjustment range may be 0.2 or 0.3. It is understood that the second adjustment range can be freely adjusted based on actual needs, but must be less than the first adjustment range. Parameter adjustment may refer to the process of changing the maximum risk score corresponding to each risk level in the preset risk level mapping table according to the second adjustment range. The second adjusted risk level mapping table may refer to the risk level mapping table obtained after the parameters of the preset risk level mapping table are adjusted according to the second adjustment range.

[0058] It is understandable that the maximum risk score corresponding to each risk level in the second adjusted risk level mapping table is less than the maximum risk score of the corresponding risk level in the preset risk level mapping table. For example, as shown in Table 3, Table 3 is an example of a second adjusted risk level mapping table provided in an embodiment of the present application. The table is obtained by adjusting the parameters of the preset risk level mapping table shown in Table 1 when the second adjustment range is 0.2. The payment risk score is divided into three intervals: 0-0.32 corresponds to low risk, 0.32-0.56 corresponds to medium risk, and greater than 0.56 corresponds to high risk.

[0059]

[0060] The target risk level may refer to a level indicating the payment risk level of the target object obtained by mapping the target payment risk score to a risk level according to the second adjustment risk level mapping table. For example, see Figure 3 , Figure 3The second flow chart for determining a target risk level provided in an embodiment of the present application specifically includes the following steps: first, obtaining the current system security status. Then, determining whether the system security status is in an attacked state. If the system security status is in an attacked state, adjusting the parameters of a preset risk level mapping table according to a first adjustment range to obtain a first adjusted risk level mapping table. Finally, risk level mapping is performed on the target payment risk score according to the first adjusted risk level mapping table to obtain the target risk level of the target object. If the system security status is not in an attacked state (i.e., a normal state), obtaining the geographic location information of the target object at the current time. Further, determining whether the geographic location information is within a preset high-risk area. If the geographic location information is within the preset high-risk area, adjusting the parameters of the preset risk level mapping table according to a second adjustment range to obtain a second adjusted risk level mapping table. Finally, risk level mapping is performed on the target payment risk score according to the second adjusted risk level mapping table to obtain the target risk level of the target object. If the geographic location information is not within the preset high-risk area, risk level mapping is performed on the target payment risk score according to the preset risk level mapping table to obtain the target risk level of the target object.

[0061] It is understood that, in embodiments of the present application, when the system security status is normal, the preset risk level mapping table can be dynamically adjusted based on the target subject's current geographic location information. This allows for a moderately increased level of stringency in risk assessments when the system is normal but the target subject is located in a high-risk area, reducing potential risks missed due to geographic location, improving the accuracy of payment risk assessments, and ultimately, enhancing the accuracy of ride management.

[0062] In some embodiments, performing risk level mapping on the target payment risk score according to a preset risk level mapping table to obtain the target risk level of the target object further includes: If the geographical location information is outside the preset high-risk area and the current time is within the preset peak period, the parameters of the preset risk level mapping table are adjusted according to the third adjustment range to obtain a third adjusted risk level mapping table; The target payment risk score is mapped to a risk level according to the third adjusted risk level mapping table to obtain the target risk level of the target object.

[0063] In an embodiment of the present application, the preset peak hours may refer to preset time periods with high public transportation usage. For example, the preset peak hours may be 7:00 AM to 9:00 AM or 5:00 PM to 7:00 PM, without limitation. When the target subject's geographic location information is outside the preset high-risk area and the current time is within the preset peak hours, the preset risk level mapping table may be parameter-adjusted according to a third adjustment range to obtain a third adjusted risk level mapping table. The third adjustment range may refer to a preset parameter used to adjust the maximum payment risk score in the preset risk level mapping table. For example, the third adjustment range may be 0.05 or 0.1. It is understood that the third adjustment range can be freely adjusted based on actual needs, but must be less than the second adjustment range. Parameter adjustment may refer to the process of changing the maximum risk score corresponding to each risk level in the preset risk level mapping table according to the third adjustment range. The third adjusted risk level mapping table may refer to the risk level mapping table obtained after the parameters of the preset risk level mapping table are adjusted according to the third adjustment range.

[0064] It is understandable that the maximum risk score corresponding to each risk level in the third adjusted risk level mapping table is greater than the maximum risk score of the corresponding risk level in the preset risk level mapping table. For example, as shown in Table 4, Table 4 is an example of a third adjusted risk level mapping table provided in an embodiment of the present application. This table is obtained by adjusting the parameters of the preset risk level mapping table shown in Table 1 when the third adjustment range is 0.1. The payment risk score is divided into three intervals: 0-0.32 corresponds to low risk, 0.32-0.56 corresponds to medium risk, and greater than 0.56 corresponds to high risk.

[0065]

[0066] The target risk level may refer to a level indicating the payment risk level of the target object obtained by mapping the target payment risk score to a risk level according to the third adjustment risk level mapping table. For example, see Figure 4 , Figure 4The third flow chart for determining the target risk level provided in the embodiment of the present application specifically includes the following steps: first, obtaining the system security status at the current time. Then, determining whether the system security status is in an attacked state. If the system security status is in an attacked state, adjusting the parameters of the preset risk level mapping table according to a first adjustment range to obtain a first adjusted risk level mapping table. Finally, risk level mapping is performed on the target payment risk score according to the first adjusted risk level mapping table to obtain the target risk level of the target object. If the system security status is not in an attacked state (i.e., a normal state), obtaining the geographic location information of the target object at the current time. Further, determining whether the geographic location information is within a preset high-risk area. If the geographic location information is within the preset high-risk area, adjusting the parameters of the preset risk level mapping table according to a second adjustment range to obtain a second adjusted risk level mapping table. Finally, risk level mapping is performed on the target payment risk score according to the second adjusted risk level mapping table to obtain the target risk level of the target object. If the geographic location information is not within the preset high-risk area, further determining whether the current time is within a preset peak period. If the current time is within the preset peak period, the preset risk level mapping table is adjusted according to the third adjustment range to obtain a third adjusted risk level mapping table, and the target payment risk score is risk-level mapped according to the third adjusted risk level mapping table to obtain the target risk level of the target object. If the current time is not within the preset peak period, the target payment risk score is risk-level mapped according to the preset risk level mapping table to obtain the target risk level of the target object.

[0067] It is understood that, in embodiments of the present application, when the system security status is normal and the current geographic location information is not within a preset high-risk area, the preset risk level mapping table can be dynamically adjusted based on the current time and the preset peak hours. This allows for moderate relaxation of payment risk assessment criteria when the user is in a non-high-risk area and during peak hours, reducing payment restrictions on users and improving the user experience.

[0068] It should be noted that the embodiment of the present application can also determine the adjustment range of the preset risk level mapping table based on the current time, the system security status at the current time, and the geographic location information of the target object at the current time, and then adjust the parameters of the preset risk level mapping table according to the adjustment range. Finally, the target payment risk score is mapped to the risk level according to the adjusted preset risk level mapping table to obtain the target risk level of the target object. For example, if the system security status is an attacked state, the geographic location information is within the preset high-risk area, and the current time is within the preset peak period. At the same time, the first adjustment range is 0.5, the second adjustment range is 0.2, and the third adjustment range is 0.1. The final adjustment range can be 0.5+0.2-0.1=0.6, and the maximum risk score corresponding to each risk level in the preset risk level mapping table can be reduced according to the adjustment range.

[0069] In some embodiments, managing the target subject's ride based on the target risk level includes: If the target risk level is low, the ride payment data of the target object is controlled to be in normal use; If the target risk level is medium, a reminder is sent to the target according to a preset reminder method, and / or the target's ride payment data is controlled to a limit usage state; If the target risk level is a high risk level, the ride payment data of the target object is controlled to be in a restricted use state.

[0070] In the embodiment of the present application, ride payment data may refer to data generated when the target object uses the ride code to make a payment. For example, the ride payment data may be the generation time of the ride code, the payment amount, the number of payments, or the payment method, etc., without specific limitation. The normal usage status may refer to the normal use of the payment function of the ride code. For example, the normal usage status may be to generate the ride code at any time; or, the normal usage status may also refer to completing the payment according to the regular payment process; or, the normal usage status may also be not limiting the number of payments and the payment amount. The preset reminder method may refer to a method of sending notifications to the target object through various communication channels. For example, the preset reminder method may be to send a notification via SMS; or, the preset reminder method may also be to send a notification via application push, without specific limitation. Reminder data may refer to risk warning information including the risk level of the target object and the corresponding ride management method. The limited usage status may refer to limiting the payment amount of the ride code, the number of rides, or the generation time of the ride code. For example, the limited usage status can be to limit the payment amount for a single ride to no more than 5 yuan; or, the limited usage status can also be to limit the number of rides per day to no more than 3 times; or, the limited usage status can also be to limit the generation of ride codes during peak hours, without specific limitations. The limited usage status can refer to stopping the payment function of the ride code. For example, the limited usage status can be to permanently stop the payment function of the ride code; or, the limited usage status can be to temporarily stop the payment function of the ride code, without specific limitations.

[0071] It should be noted that in order to better manage the ride of high-risk target objects, the embodiment of the present application can also set a payment risk score threshold (such as 0.9). When the target payment risk score of the target object exceeds the payment risk score threshold, the payment function of the target object's ride code is directly and permanently suspended. When the target payment risk score of the target object does not exceed the payment risk score threshold, the payment function of the target object's ride code is only temporarily suspended, such as restricting the target object from using the ride code payment function for one week after the current time. If the target object needs to continue to use it at the current time, a credit recovery mechanism can also be established to apply for credit restoration after paying the unpaid fare, thereby reducing the risk level.

[0072] It is understood that the embodiments of the present application can adopt corresponding ride management methods based on the risk level of the target object. When the risk level of the target object is high, a preset reminder method can be used to send reminder data containing the risk level and the corresponding ride management method, and at the same time, the ride payment data can be controlled to a limited usage state; when the risk level of the target object is extremely high, the payment function of the ride code can be directly restricted. In this way, dynamic management of target objects of different risk levels can be achieved, avoiding the potential risks brought about by high-risk target objects' arbitrary use of the ride code, reducing risk events in the ride payment process, thereby protecting the operator's operational efficiency and improving the user experience.

[0073] In some embodiments, after managing the target object's ride according to the target risk level, the method further includes: If the target risk level is high, obtain the target object's actual payment risk score at the current time, and construct training sample data based on the actual payment risk score, the scan time interval sequence, the short-term payment failure probability, the device risk probability, and the long-term payment failure probability; The risk assessment model is optimized and trained according to the training sample data to obtain the optimized and trained risk assessment model.

[0074] In the embodiments of the present application, the real payment risk score may refer to the actual risk level of the target object. It is understandable that the real payment risk score can be obtained based on manual evaluation; alternatively, the real payment risk score can also be obtained by automatic system evaluation, without specific limitation. The training sample data may refer to a data set formed by constructing training sample data in combination with the real payment risk score, the scan code time interval sequence, the short-term payment failure probability, the device risk probability, and the long-term payment failure probability. The training sample data can be used to train and optimize the risk assessment model. Optimization training may refer to the process of further training the risk assessment model using the constructed training sample data to improve the model performance. The risk assessment model after optimized training may refer to a risk assessment model with higher performance obtained after optimizing the risk assessment model based on the training sample data.

[0075] It is understood that embodiments of the present application can obtain the target object's actual payment risk score at the current time, construct training sample data based on this score, and then optimize and train the risk assessment model based on the training sample data. In this way, when encountering a new high-risk target object, the model can be incrementally learned using the constructed training sample data, avoiding the need to update the risk assessment model as a whole, thereby improving the efficiency and accuracy of model updates and enhancing the model's ability to identify high-risk characteristics.

[0076] See also Figure 5The present application also provides a vehicle management device that can implement the above-mentioned vehicle management method. The device includes: Data acquisition unit 501 is configured to, in response to a target subject's payment operation for a ride, acquire the target subject's current balance fare ratio, acquire the target subject's code scanning time interval sequence and short-term payment failure probability within a first time interval prior to the current time, and acquire the target subject's device risk probability and long-term payment failure probability within a second time interval prior to the current time, wherein the second time interval is greater than the first time interval; The long-term risk assessment unit 502 is configured to call a long-term risk assessment sub-model of a pre-trained risk assessment model to perform a long-term risk assessment on the balance-to-fare ratio, the device risk probability, and the long-term payment failure probability to obtain a long-term payment risk score; A short-term risk assessment unit 503 is configured to call a short-term risk assessment sub-model of a pre-trained risk assessment model to perform a short-term risk assessment on the scan time interval sequence and the short-term payment failure probability to obtain a short-term payment risk score; The risk scoring unit 504 is configured to determine a target payment risk score of the target object based on a preset weight coefficient, a long-term payment risk score, and a short-term payment risk score; The ride management unit 505 is used to map the target payment risk score to a risk level according to a preset risk level mapping table, obtain the target risk level of the target object, and manage the ride of the target object according to the target risk level; wherein the preset risk level mapping table is used to indicate the mapping relationship between the risk level and the payment risk score.

[0077] The specific implementation of the ride management device is basically the same as the specific embodiment of the above-mentioned ride management method, and will not be repeated here.

[0078] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned boarding management method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, an in-vehicle computer, or the like.

[0079] See also Figure 6 , Figure 6 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes: The processor 601 may be implemented as a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application. The memory 602 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 602 and is called by the processor 601 to execute the ride management method of the embodiments of this application. Input / output interface 603, used to implement information input and output; Communication interface 604, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.); Bus 605 , which transmits information between various components of the device (e.g., processor 601 , memory 602 , input / output interface 603 , and communication interface 604 ); The processor 601 , the memory 602 , the input / output interface 603 and the communication interface 604 are connected to each other in communication within the device via a bus 605 .

[0080] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned ride management method is implemented.

[0081] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0082] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0083] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0084] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0085] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0086] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0087] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0089] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0091] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0092] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A method for managing a ride, characterized in that: The method comprises: In response to a target subject's ride payment operation, obtaining the target subject's balance fare ratio at the current time, obtaining the target subject's code scanning time interval sequence and short-term payment failure probability within a first time interval before the current time, and obtaining the target subject's device risk probability and long-term payment failure probability within a second time interval before the current time; wherein the second time interval is greater than the first time interval; Calling the long-term risk assessment sub-model of the pre-trained risk assessment model to perform a long-term risk assessment on the balance-to-fare ratio, the device risk probability, and the long-term payment failure probability to obtain a long-term payment risk score; Calling the short-term risk assessment sub-model of the pre-trained risk assessment model to perform a short-term risk assessment on the code scanning time interval sequence and the short-term payment failure probability to obtain a short-term payment risk score; Determine the target payment risk score of the target object according to a preset weight coefficient, the long-term payment risk score and the short-term payment risk score; The target payment risk score is mapped to a risk level according to a preset risk level mapping table to obtain the target risk level of the target object, and the target object is managed for riding according to the target risk level; wherein the preset risk level mapping table is used to indicate the mapping relationship between risk level and payment risk score.

2. The method according to claim 1, characterized in that The performing ride management on the target object according to the target risk level includes: If the target risk level is a low risk level, controlling the target object's ride payment data to be in normal use; If the target risk level is a medium risk level, sending reminder data to the target subject according to a preset reminder method, and / or controlling the target subject's ride payment data to be in a quota usage state; If the target risk level is a high risk level, the ride payment data of the target object is controlled to be in a restricted use state.

3. The method according to claim 2, characterized in that After the target object is managed according to the target risk level, the method further includes: If the target risk level is the high risk level, obtaining the actual payment risk score of the target object at the current time, and constructing training sample data based on the actual payment risk score, the scan time interval sequence, the short-term payment failure probability, the device risk probability, and the long-term payment failure probability; The risk assessment model is optimized and trained according to the training sample data to obtain an optimized and trained risk assessment model.

4. The method according to claim 1, wherein The determining of the target payment risk score of the target object according to the preset weight coefficient, the long-term payment risk score, and the short-term payment risk score includes: constructing current long-term risk data based on the balance-to-fare ratio, the device risk probability, and the long-term payment failure probability, obtaining historical long-term risk data of the target object, and performing a stability assessment on the current long-term risk data based on the historical long-term risk data to obtain a long-term stability score; Constructing current short-term risk data based on the scan time interval sequence and the short-term payment failure probability, obtaining historical short-term risk data of the target object, and performing a stability assessment on the current short-term risk data based on the historical short-term risk data to obtain a short-term stability score; Determining a first sub-weight coefficient corresponding to the long-term payment risk score and a second sub-weight coefficient corresponding to the short-term payment risk score based on the long-term stability score, the short-term stability score, and the preset weight coefficient; wherein the preset weight is used to indicate the sum of the first sub-weight coefficient and the second sub-weight coefficient; The target payment risk score of the target object is determined according to the long-term payment risk score, the first sub-weight coefficient, the short-term payment risk score, and the second sub-weight coefficient.

5. The method according to claim 4, characterized in that The determining, according to the long-term stability score, the short-term stability score, and the preset weight coefficient, of the first sub-weight coefficient corresponding to the long-term payment risk score and the second sub-weight coefficient corresponding to the short-term payment risk score includes: Determining a total stability score based on the sum of the long-term stability score and the short-term stability score, and determining a weight adjustment factor for the long-term payment risk score based on a ratio of the long-term stability score to the total stability score; Adjust the parameters of the preset weight coefficient based on the weight adjustment factor to obtain a first sub-weight coefficient corresponding to the long-term payment risk score; A second sub-weight coefficient corresponding to the short-term payment risk score is determined based on the preset weight coefficient and the first sub-weight coefficient.

6. The method according to claim 1, characterized in that The step of performing risk level mapping on the target payment risk score according to a preset risk level mapping table to obtain the target risk level of the target object includes: Get the system security status at the current time; If the system security state is an attacked state, adjusting parameters of the preset risk level mapping table according to a first adjustment range to obtain a first adjusted risk level mapping table; wherein the maximum risk score corresponding to each risk level in the first adjusted risk level mapping table is less than the maximum risk score of the corresponding risk level in the preset risk level mapping table; The target payment risk score is mapped to a risk level according to the first adjusted risk level mapping table to obtain the target risk level of the target object.

7. The method according to claim 6, characterized in that The target payment risk score is mapped to a risk level according to a preset risk level mapping table to obtain a target risk level of the target object, further comprising: If the system security status is normal, obtaining the geographic location information of the target object at the current time; If the geographic location information is within a preset high-risk area, adjusting parameters of the preset risk level mapping table according to a second adjustment range to obtain a second adjusted risk level mapping table; wherein the maximum risk score corresponding to each risk level in the second adjusted risk level mapping table is less than the maximum risk score of the corresponding risk level in the preset risk level mapping table; and the second adjustment range is less than the first adjustment range; The target payment risk score is mapped to a risk level according to the second adjusted risk level mapping table to obtain the target risk level of the target object.

8. The method according to claim 7, characterized in that The target payment risk score is mapped to a risk level according to a preset risk level mapping table to obtain a target risk level of the target object, further comprising: If the geographic location information is outside the preset high-risk area and the current time is within the preset peak period, the parameters of the preset risk level mapping table are adjusted according to a third adjustment range to obtain a third adjusted risk level mapping table; wherein the maximum risk score corresponding to each risk level in the third adjusted risk level mapping table is greater than the maximum risk score of the corresponding risk level in the preset risk level mapping table; and the third adjustment range is less than the second adjustment range; The target payment risk score is mapped to a risk level according to the third adjusted risk level mapping table to obtain the target risk level of the target object.

9. A ride management device, characterized in that: The device comprises: a data acquisition unit configured to, in response to a target subject's payment operation for a ride, acquire the target subject's current balance fare ratio, acquire the target subject's code scanning time interval sequence and short-term payment failure probability within a first time interval prior to the current time, and acquire the target subject's device risk probability and long-term payment failure probability within a second time interval prior to the current time; wherein the second time interval is greater than the first time interval; a long-term risk assessment unit, configured to call a long-term risk assessment sub-model of a pre-trained risk assessment model to perform a long-term risk assessment on the balance-to-fare ratio, the device risk probability, and the long-term payment failure probability, to obtain a long-term payment risk score; a short-term risk assessment unit, configured to call a short-term risk assessment sub-model of a pre-trained risk assessment model to perform a short-term risk assessment on the code scanning time interval sequence and the short-term payment failure probability to obtain a short-term payment risk score; a risk scoring unit, configured to determine a target payment risk score for the target object based on a preset weight coefficient, the long-term payment risk score, and the short-term payment risk score; A ride management unit is used to perform risk level mapping on the target payment risk score according to a preset risk level mapping table, obtain the target risk level of the target object, and perform ride management on the target object according to the target risk level; wherein the preset risk level mapping table is used to indicate the mapping relationship between risk level and payment risk score.

10. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the ride management method according to any one of claims 1 to 8 when executing the computer program.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the boarding management method according to any one of claims 1 to 8 is implemented.

Images