Reward settlement method, electronic equipment and computer storage medium

Abstract

The invention discloses a reward settlement method, electronic equipment and a computer storage medium, and the method comprises the steps: obtaining real-time behavior data and historical behavior data of a first user executing a sharing operation in response to the execution of the sharing operation of an activity interface in a preset application program; verifying the real-time behavior data and the historical behavior data to obtain a verification result; outputting an auditing decision according to the verification result; and if the audit decision is passed, reward settlement of the first user is executed. According to the method, verification on the authenticity of the behavior of the first user is introduced, so that the problem of high scalping risk caused by only tracking the invited user in a traditional method is solved. By obtaining and cross-validating the real-time and historical behavior data of the first user, cheating is identified from the source, and low-efficiency manual auditing is replaced. Finally, real-time decision making and settlement are carried out based on an automatic verification result, the award issuing period is shortened, and the settlement efficiency and the user experience are greatly improved while the anti-cheating capability is improved.

Description

Technical Field

[0001] This invention relates to the field of internet marketing risk control technology for battery swapping services, and in particular to a reward settlement method, electronic device, and computer storage medium. Background Technology

[0002] Currently, battery swapping service platforms often launch driver referral reward programs to attract new users and increase user activity. However, the existing reward settlement methods have two major flaws: Weak anti-fraud capabilities: Existing methods mainly rely on tracking shared links and the behavior of invited users, lacking verification of the authenticity of the behavior of the initiator of the sharing behavior—the driver themselves. This makes it impossible to effectively identify and prevent fraudulent activities such as order boosting through simulators and fake accounts, resulting in losses of marketing funds.

[0003] Low settlement efficiency: Due to insufficient risk control measures, the platform has to rely on manual verification of order authenticity, resulting in long commission settlement cycles, which severely dampens drivers' enthusiasm for participation, makes it impossible to provide immediate incentives, and affects the effectiveness of the campaign.

[0004] Therefore, there is an urgent need in this field for a technical solution that can automatically and accurately verify the authenticity of the sharing driver's behavior and achieve rapid settlement. Summary of the Invention

[0005] The purpose of this application is to provide a reward settlement method, an electronic device, and a computer storage medium. To achieve the above objectives: In a first aspect, embodiments of this application provide a reward settlement method, the method comprising: In response to performing a sharing operation on the activity interface in a preset application, real-time behavior data and historical behavior data of the first user performing the sharing operation are obtained; The real-time behavior data and the historical behavior data are verified to obtain the verification results; Output an audit decision based on the verification results; If the review decision is approved, the reward settlement for the first user will be executed.

[0006] In one embodiment, the real-time behavioral data includes at least one of the following: the source of the activity interface, the sharing timestamp, the geographic location information at the time of sharing, the network protocol address used at the time of sharing, and the fingerprint of the terminal device used at the time of sharing; The historical behavior data includes at least one of the following: the first user's historical order records, the locations of frequently visited service stations, and the vehicle's historical driving trajectory data.

[0007] In one embodiment, obtaining the real-time behavior data and historical behavior data of the first user performing the sharing operation includes: Obtain behavioral data of the second user introduced through the sharing operation; The verification of the real-time behavior data and the historical behavior data includes: The behavioral data of the second user is verified.

[0008] In one embodiment, verifying the behavioral data of the second user includes: Verify whether the terminal device or network protocol address used by the second user is associated with the corresponding information of the first user, and / or, Verify whether the second user performed a preset preparatory operation before placing the order.

[0009] In one embodiment, the verification of the real-time behavior data and the historical behavior data includes at least one of the following: Obtain the account activity status from the real-time behavior data and the historical service usage records from the historical behavior data, and verify whether the account activity status and the historical service usage records meet the preset standards; Obtain the current location information from the real-time behavior data, and the historical frequently visited site location information and historical driving trajectory data from the historical behavior data, and verify whether the current location information matches the historical frequently visited site location information, and / or the historical driving trajectory data; Obtain current device and environment information from the real-time behavior data and historical device and environment information from the historical behavior data, and verify whether the current device and environment information and the historical device and environment information meet preset conditions.

[0010] In one embodiment, the step of outputting an audit decision based on the verification result includes: A credibility score is generated based on the verification results; Based on the comparison between the credibility score and the preset threshold, the audit decision is output as pass, rejection, or manual review required.

[0011] In one embodiment, the step of outputting a review decision (pass, reject, or requiring manual review) based on a comparison of the credibility score with a preset threshold includes: When the credibility score is greater than a preset first threshold, a pass review decision is output. When the credibility score is less than a preset second threshold, a rejection decision is output. When the credibility score is greater than the second threshold and less than the first threshold, an audit decision requiring manual review is output. After the output of the review decision that requires manual review, a review interface is generated, and the abnormal dimension information that caused the decision is marked in the review interface.

[0012] In one embodiment, after outputting an audit decision based on the verification result, the method further includes: If the review decision is to reject, the behavioral data and verification results related to this sharing operation will be used as case materials, and the case materials will be added to the material training set. The rules or models used in subsequent verification processes are optimized based on the training set of the materials.

[0013] Secondly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the reward settlement method described above.

[0014] Thirdly, embodiments of this application provide a computer storage medium storing a computer program, which, when executed by a processor, implements the steps of the reward settlement method described above.

[0015] This application addresses the high risk of fraudulent transactions inherent in traditional methods that only track invited users by introducing verification of the authenticity of the first user's own behavior. By acquiring and cross-validating the first user's real-time and historical behavioral data, it identifies fraud at the source, replacing inefficient manual review. Ultimately, real-time decision-making and settlement are based on the automated verification results, shortening the reward distribution cycle and significantly improving settlement efficiency and user experience while enhancing anti-fraud capabilities. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a reward settlement method provided in an embodiment of the present invention.

[0017] Figure 2 This is a schematic diagram of a reward settlement system provided in an embodiment of the present invention.

[0018] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0019] Explanation of reference numerals in the attached figures: 10. Sharing trigger module; 20. Data verification module; 30. Audit decision module; 40. Automatic settlement module; 310. Processor; 311. Memory; 312. Network interface; 313. Bus system. Detailed Implementation

[0020] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0021] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0022] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, this information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, can be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" as used herein are to be interpreted as inclusive, or mean any one or any combination thereof. Therefore, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A, B, and C". Exceptions to this definition will only occur if the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0023] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0024] It should be noted that step designations such as S1 and S2 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S2 first and then S1, etc., but these should all be within the protection scope of this application.

[0025] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0026] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustration and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0027] First Embodiment Please refer to Figure 1 , Figure 1 A flowchart illustrating a reward settlement method is shown, the method including: S1. In response to the sharing operation performed on the activity interface of the preset application, the system acquires the real-time and historical behavior data of the first user performing the sharing operation. Specifically, in this embodiment, when the first user clicks the "Share" button in the preset application, the system is triggered and immediately begins to acquire two types of data from the first user: the first type is the real-time behavior data generated at the moment of sharing, and the second type is the first user's past behavior records on the platform, i.e., historical behavior data. In this way, the focus of risk control shifts from the traditional "who clicked" to "who is sharing," providing sufficient data evidence for this purpose. By integrating real-time snapshots and historical entity behavior data that is difficult to forge, a solid data foundation is laid for subsequent identification of abnormal behavior, expanding the dimensions and depth of anti-fraud measures from the source. Among them, the first user is preferably a driver, and the preset application is preferably an application related to battery swapping.

[0028] S2. Verify real-time behavior data and historical behavior data to obtain verification results. Specifically, in this embodiment, the system compares the data collected in step S1 with a preset rule model to check the consistency of behavior, the authenticity of the device and environment, and the reliability of the identity. For example, it compares the real-time GPS at the time of sharing with the user's historically frequented battery swapping station locations. In this way, the cross-validation mode can effectively identify abnormal patterns such as "suddenly appearing in an unfamiliar area geographically" and "sharing using an unfamiliar device." It can accurately distinguish between the high-frequency, stable behavioral characteristics of real users and the isolated, abnormal characteristics of cheating behavior, thereby filtering out fraudulent behaviors such as machine-generated orders and group cheating, greatly improving the accuracy of identification.

[0029] S3. Output review decision based on verification results. Specifically, in this embodiment, based on the verification results obtained in step S2, the system automatically outputs a review decision of "pass," "reject," or "manual review required" in ambiguous cases. Thus, this embodiment replaces the traditional, subjective, and inefficient manual review method, transforming the review decision from a time-consuming manual process into an instant system output, creating a prerequisite for subsequent rapid settlement.

[0030] S4. If the review decision is approved, the reward settlement for the first user will be executed. Specifically, in this embodiment, when the system outputs that the review decision is approved, the automatic settlement module will immediately issue the activity commission, i.e., the reward, to the first user's platform account and notify the user. This solves the core pain point of the long settlement cycle in traditional methods, shortening reward feedback from days or even weeks to minutes. This immediacy provides drivers with a strong positive incentive, greatly increasing their willingness to participate and their enthusiasm for sharing, thus truly achieving the design goals of activating activity and attracting new users.

[0031] By executing steps S1-S4, the high risk of fraudulent transactions caused by traditional methods that only track invited users is resolved. By acquiring and cross-validating the real-time and historical behavioral data of the first user, fraud is identified at the source, replacing inefficient manual review. Finally, real-time decision-making and settlement are based on the automated verification results, shortening the reward distribution cycle. While improving anti-fraud capabilities, this significantly improves settlement efficiency and user experience, fundamentally solving the two major shortcomings of traditional sharing reward activities mentioned in the background technology.

[0032] Optionally, the real-time behavioral data includes at least one of the following: The source of the activity interface is used to determine whether the context of the sharing behavior is normal.

[0033] The sharing timestamp is used to analyze whether the sharing behavior occurs during normal activity periods (such as daytime, not late at night), which helps to identify abnormal human behavior (such as machine scripts sharing in batches in the early morning) or abnormal operation paths.

[0034] The geolocation information at the time of sharing is used to determine the real-time geographical location of the first user when the sharing operation occurs.

[0035] The network protocol address used during sharing is used to determine the legitimacy of the geographical location and whether a proxy or VPN is used. It can detect cheating behaviors such as using proxy IP pools and VPNs to hide the real location, and check whether the IP of the sharer is associated with the IP of the new user who places an order (to prevent self-fraud).

[0036] The fingerprint of the terminal device used for sharing, that is, the digital fingerprint generated by the device model, operating system, unique identification code (such as IMEI) and other information, is used to uniquely identify the device, effectively identifying and preventing one person from controlling multiple devices to commit fraud.

[0037] Historical behavioral data includes at least one of the following: The first user's historical order records, that is, the first user's past battery swapping service orders on the battery swapping platform, including time, location, amount, etc., are used to verify whether they are active and genuine service users.

[0038] The locations of frequently visited service stations in history, extracted by analyzing historical order data, form the geographical baseline of the driver's most frequently visited service stations.

[0039] Historical vehicle driving trajectory data, uploaded through devices such as the in-vehicle T-BOX, reflects the vehicle's long-term driving routes and activity range.

[0040] Understandably, this embodiment examines sharing behavior within a three-dimensional grid composed of time, space, device, network, and historical behavior patterns. In this way, while cheaters may be able to forge a single dimension, such as using fake location, it is extremely difficult to forge all dimensions simultaneously, in batches, and continuously, especially entity data that requires long-term accumulation, such as vehicle driving trajectories. This greatly increases the technical threshold and cost of cheating.

[0041] Optionally, obtaining the real-time and historical behavior data of the first user who performed the sharing operation in step S1 includes obtaining the behavior data of the second user introduced through the sharing operation. Specifically, in this embodiment, the second user refers to a new user who enters the platform through the first user's sharing link and completes registration, order placement, and other behaviors. When tracking the sharing link, the system not only records who shared it but also collects information on who used it. The behavior data of the second user also includes their device fingerprint, IP address, browsing behavior before placing an order (such as page dwell time and price comparison), and the order placement operation itself.

[0042] Furthermore, real-time and historical behavioral data are verified, including the behavioral data of the second user. Specifically, the aforementioned scheme aims to verify whether the first user's behavioral characteristics involve cheating, primarily to prevent cheaters from impersonating drivers to share cheating information. In this embodiment, based on the first line of defense checking the trustworthiness of the sharer, i.e., the first user, a second line of defense is constructed. This second line of defense checks the authenticity of the brought-in user, i.e., the second user. Thus, any anomaly detected at any line of defense can trigger a risk alert, effectively preventing drivers from hiring cheaters or cheaters from impersonating drivers to cheat, greatly improving the robustness of the overall anti-cheating system.

[0043] Optionally, verifying the behavior data of the second user as described in the above steps includes verifying whether the terminal device or network protocol address used by the second user is associated with the corresponding information of the first user. Specifically, in this embodiment, the system performs association verification based on hard data at the physical and network layers. By checking whether the device, IP, and other information of the second user have an unreasonable strong association with the first user, such as identical device IDs or being on the same local area network, the system can identify self-fraudulent order-taking. Thus, when the system finds that the device fingerprints or IP addresses of the sharing driver and multiple newly placed users highly overlap, it can determine it as high-risk self-fraudulent or group fraudulent order-taking behavior, thereby intercepting it before settlement.

[0044] Furthermore, the verification of the second user's behavioral data mentioned in the above steps also includes verifying whether the second user performed a preset preparatory operation before placing the order. Specifically, in this embodiment, the system performs behavioral authenticity verification based on a soft mode at the application and behavioral layers to determine whether the second user's ordering behavior conforms to the characteristics of a normal new user. For example, a real user typically goes through a process of browsing, understanding, and making a decision, while a fraudulent account may simply click a link and quickly place an order, lacking any prior interactive behavior. In this way, the system can effectively distinguish between fake accounts controlled by machine scripts and real human users. Even if cheaters can forge some behavioral data of the first user, they will find it extremely difficult to perfectly simulate a large number of normal, random second user behaviors in batch operations, thus exposing their deception.

[0045] Understandably, this set of technical features concretizes the abstract verification of a second user into two executable and detectable steps: "checking associations" and "verifying behavior." Working together, these two steps can accurately identify fraudulent accounts controlled by the same entity and fake traffic driven by machine scripts, thereby ensuring that every new user introduced through shared links is genuine and valid, safeguarding the security and value of the platform's marketing funds.

[0046] Optionally, the verification of real-time behavior data and historical behavior data in step S2 includes at least one of the following: 1) Obtain account activity status from real-time behavioral data and historical service usage records from historical behavioral data to verify whether the account activity status and historical service usage records meet preset standards. Specifically, in this embodiment, account activity status refers to whether the first user's account is currently logged in and in use normally, rather than being dormant, banned, or an abnormal account. Historical service usage records refer to retrieving the first user's past core business records on the platform, such as the frequency, amount, and time distribution of historical battery swapping orders. The system will determine whether the above data meets the preset standards for genuine active users, such as: at least 3 valid battery swapping orders in the past 30 days, account registration time exceeding 3 months, etc. In this way, it ensures that rewards are only issued to core service users of the platform, rather than temporarily registered aliases or zombie accounts. In order to pass this test, cheaters must first cultivate an account with stable consumption records, which greatly increases the time and financial costs of cheating, filters out low-quality cheating attempts from the source, and ensures that the marketing activities are aimed at genuine service users.

[0047] 2) Obtain the current location information from real-time behavior data, and the historical frequently visited site location information and historical driving trajectory data from historical behavior data, and verify whether the current location information matches the historical frequently visited site location information and / or the historical driving trajectory data. Specifically, in this embodiment, the current location information is the precise latitude and longitude information obtained by the terminal GPS when the sharing operation occurs. The historical frequently visited sites are a list of the first user's most frequently visited battery swapping stations derived from data analysis. The historical driving trajectory data is a continuous location record uploaded by the vehicle's T-BOX. The system will compare the real-time location at the time of sharing with the geographical location of the historically frequently visited sites and the area covered by the vehicle's historical trajectory. For example, it will determine whether the real-time location is within 1 kilometer of a frequently visited site, or whether it is in the main urban area covered by its historical driving trajectory. Among them, the vehicle's movement trajectory and frequently visited locations are high-strength trust data that has been formed over a long period of time and is strongly associated with the physical world, making it extremely difficult to be forged in batches. If a sharing behavior occurs in a place that the driver has never been, the system can immediately identify it as abnormal. In this way, the online virtual sharing action is effectively linked to the offline driving behavior, which can accurately identify cheating behavior using fake location software.

[0048] 3) Obtain current device and environment information from real-time behavior data and historical device and environment information from historical behavior data, and verify whether the current device and environment information and historical device and environment information meet preset conditions. Specifically, in this embodiment, the current device and environment information includes the device fingerprint used in this sharing, such as mobile phone model, IMEI, etc., and the network environment such as IP address. Historical device and environment information refers to the devices and IP addresses that the first user frequently used when logging in, placing orders, or sharing in the past. The system automatically checks whether the device used this time is a frequently used device and whether the location of the IP address this time is consistent with its frequently used activity city. Preset conditions may be, for example, that the device fingerprint this time is consistent with the device most frequently used in the past 7 days, and that the geographical city of the IP address this time matches the historical frequently used city, etc. It is understandable that a real user usually uses a familiar mobile phone and operates in a familiar network environment. If the system detects frequent changes of devices, or that the IP address crosses multiple impossible cities in a short period of time, it is highly likely that the account is being used by multiple people to engage in fraudulent transactions, or that proxy IPs or other technologies are being used for spoofing. This layer of verification effectively prevents behaviors such as using one account for multiple purposes and simultaneous cheating in different locations, and increases the technical difficulty of cheating.

[0049] Optionally, the step S3, which involves outputting an audit decision based on the verification results, includes generating a credibility score based on the verification results. Specifically, in this embodiment, the system does not simply treat each verification dimension as pass or fail, but rather assigns weights to each dimension and calculates a comprehensive, quantifiable score. For example, a device verification pass scores 30 points, a high match in historical trajectory scores 50 points, and an abnormal IP address deducts 20 points. Finally, the scores of all dimensions are summed to form a numerical score representing the overall credibility of the sharing behavior.

[0050] Furthermore, based on a comparison between the credibility score and a preset threshold, the system outputs an approval, rejection, or manual review decision. Specifically, in this embodiment, the system presets at least two thresholds, forming a decision interval. The system outputs an approval, rejection, or manual review decision based on the decision interval in which the feasibility score falls. Thus, for cases with obvious high-risk characteristics and normal characteristics, the system can process them quickly and automatically, ensuring overall efficiency. For intermediate cases with ambiguous risk characteristics, contradictions, or those in a critical state, the system does not make a decision on its own but leaves the final decision to a human. This prevents misjudging genuine users as cheaters and also prevents advanced cheating from being overlooked due to rigid rules, achieving a balance between automation efficiency and risk control accuracy.

[0051] Optionally, the step described above, which compares the credibility score with a preset threshold and outputs a review decision (pass, reject, or requiring manual review), includes: outputting a pass decision when the credibility score is greater than a preset first threshold; outputting a reject decision when the credibility score is less than a preset second threshold; and outputting a review decision requiring manual review when the credibility score is greater than the second threshold and less than the first threshold. Specifically, in this embodiment, the system sets two key thresholds to divide the credibility score into three distinct intervals, each corresponding to a distinct decision path, where the first threshold is greater than the second threshold. When the credibility score is greater than the first threshold, the behavior is excellent and without question, and the system automatically passes. When the credibility score is less than the second threshold, the behavior exhibits obvious abnormal characteristics and extremely high risk, and the system automatically rejects. When the credibility score is between the two thresholds, the behavior is in a gray area, exhibiting both credible characteristics and risk points, and the system marks it as "requiring manual review" without making a final judgment. In this way, the system can quickly and automatically process more than 80% of cases with high certainty, clearly providing a pass or reject decision, thereby ensuring high efficiency of the overall process. At the same time, it intelligently filters out the most complex and ambiguous cases that require human experience and contextual judgment, and hands them over to human processing, thereby greatly reducing the misjudgment rate and ensuring the accuracy of risk control.

[0052] Furthermore, after outputting the review decision requiring manual review, a review interface is generated, and the abnormal dimension information that caused the decision is marked in the review interface. Specifically, in this embodiment, when the decision enters the state requiring manual review, the system will automatically generate a dedicated review interface. The system will highlight on this review interface which specific verification dimensions (such as abnormal device fingerprints, GPS positioning not matching historical trajectory) caused the current score to fall into the middle range, in order to assist manual judgment quickly. Understandably, compared with the inefficient mode of traditional manual review that requires screening from scratch and blindly searching for suspicious points, in this invention, when the reviewer opens the review interface, the system can directly point out the suspicious points, allowing the reviewer to immediately focus on the core contradictions, such as: why does a commonly used device appear under an unfamiliar IP? This reduces the review time from minutes to seconds, significantly reducing the workload and professional skill requirements of the reviewers.

[0053] Optionally, after outputting the review decision based on the verification result in step S3, the method further includes: if the review decision is rejection, then the behavioral data and verification result related to this sharing operation are used as case material, and the case material is added to the material training set. Specifically, in this embodiment, when the system automatically determines that the sharing operation is rejected, the complete process of this event is packaged and saved as a chain of evidence, including behavioral data such as the driver's real-time GPS, device fingerprint, and IP address when sharing, as well as the system's specific judgment results and credibility scores (verification results) in various dimensions such as identity, behavioral consistency, and device. All the above information constitutes an anti-fraud case and is added to the material training set. This material training set is essentially a continuously growing database composed of real fraud behavior data.

[0054] Furthermore, the rules or models used in subsequent verification processes are optimized based on the training set. Specifically, in this embodiment, the system periodically or irregularly uses the training set to iteratively upgrade the rules or models used in subsequent verification processes, which can be achieved in two ways: Optimize rules: After analyzing a large number of cases and discovering new cheating patterns, add or adjust verification rules manually or automatically. For example, if a batch of cheating cases are found to have used a specific model of simulator, add that device feature to the blacklist or increase its risk weight.

[0055] Model optimization: If the system uses a machine learning model for credibility scoring, then this training set becomes the sample for training / retraining the model, enabling the model to learn the latest cheating features and thus make more accurate predictions in the future.

[0056] Understandably, traditional risk control systems heavily rely on risk control experts manually analyzing data, summarizing patterns, and then manually updating rules, which is costly and slow. The aforementioned technical features enable a shift from manual-driven optimization to data-driven self-optimization. The system can automatically complete most of the work of case collection and model training, greatly reducing reliance on manual analysis and enabling faster and lower-cost updates and iterations of risk control strategies.

[0057] Second Embodiment Please refer to Figure 2 , Figure 2 A schematic diagram of a reward settlement system is shown. The system includes: The sharing trigger module 10 is used to respond to a sharing operation performed on the activity interface of a preset application, and to obtain the real-time and historical behavior data of the first user performing the sharing operation. Specifically, in one embodiment, when the driver clicks the "Share" button in the APP, the sharing trigger module 10 is activated, generates a sharing poster with unique tracking parameters, collects the driver's real-time data for this sharing (time, GPS, IP, device number), and requests the driver's historical data (orders in the last 30 days, list of frequently used battery swapping stations, recent vehicle driving trajectory, etc.) from the server.

[0058] The data verification module 20 is used to verify real-time behavior data and historical behavior data to obtain verification results. Specifically, in one embodiment, the data verification module 20 is used to verify real-time behavior data and historical behavior data to obtain verification results. For example, the verification logic can be: if the driver's real-time GPS matches the range of their historically frequently used battery swapping stations, and the sharing device is a frequently used device and the IP address is a frequently used location, then the behavior authenticity is marked as "high"; if a new user who places an order through a shared link has a device IMEI and IP address that are different from the driver's device IMEI and IP address, and the new user has a normal page browsing time, then the new user authenticity is marked as "high".

[0059] The review decision module 30 is used to output a review decision based on the verification results. Specifically, in one embodiment, the review decision module 30 integrates all the flags and outputs a review decision based on the verification results. If the result is determined to be "high," a "pass" review decision is generated; if the result is determined to be "low," a "reject" review decision is generated; and if the result is determined to be "medium," a "manual review required" review decision is generated.

[0060] The automatic settlement module 40 is used to execute reward settlement for the first user when the review decision is approved. Specifically, in one embodiment, after receiving the approval instruction sent by the review decision module 30, the automatic settlement module 40 immediately allocates the corresponding commission from the activity budget to the driver's account and calls the message notification interface to send a prompt message to the driver's battery swapping APP.

[0061] It is understandable that when the reward settlement system is running, it can achieve the same beneficial effects as the reward settlement method described above, so it will not be elaborated here.

[0062] Based on the same inventive concept as the foregoing embodiments, this invention provides an electronic device, such as... Figure 3 As shown, the device includes: a processor 310 and a memory 311 storing a computer program; wherein, Figure 3 The processor 310 shown in the diagram does not indicate that there is only one processor 310, but only indicates the positional relationship of the processor 310 relative to other devices. In practical applications, there can be one or more processors 310; similarly, Figure 3 The memory 311 illustrated herein has the same meaning, that is, it is only used to indicate the positional relationship of memory 311 relative to other devices. In practical applications, there can be one or more memories 311. When the processor 310 runs the computer program, the method applied to the above-mentioned device is implemented.

[0063] The device may also include at least one network interface 312. The various components of the device are coupled together via a bus system 313. It is understood that the bus system 313 is used to implement communication between these components. In addition to a data bus, the bus system 313 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 3 The general designated all buses as Bus System 313.

[0064] The memory 311 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 311 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0065] The memory 311 in this embodiment of the invention is used to store various types of data to support the operation of the device. Examples of this data include: any computer programs used to operate on the device, such as operating systems and applications; contact data; phonebook data; messages; pictures; videos, etc. The operating system includes various system programs, such as the framework layer, core library layer, driver layer, etc., used to implement various basic services and handle hardware-based tasks. Applications can include various applications, such as media players, browsers, etc., used to implement various application services. Here, the program implementing the method of this embodiment of the invention can be included in the application.

[0066] Based on the same inventive concept as the foregoing embodiments, this embodiment also provides a computer-readable storage medium storing a computer program. The computer-readable storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it can also be various devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc. When the computer program stored in the computer-readable storage medium is run by a processor, it implements the above method. For the specific steps implemented when the computer program is executed by the processor, please refer to [link to relevant documentation]. Figure 1 The description of the illustrated embodiments will not be repeated here.

[0067] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0068] In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, which includes not only the elements listed but also other elements not expressly listed.

[0069] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A reward settlement method, characterized in that, The method includes: In response to performing a sharing operation on the activity interface in a preset application, real-time behavior data and historical behavior data of the first user performing the sharing operation are obtained; The real-time behavior data and the historical behavior data are verified to obtain the verification results; Output an audit decision based on the verification results; If the review decision is approved, the reward settlement for the first user will be executed.

2. The method according to claim 1, characterized in that, The real-time behavioral data includes at least one of the following: the source of the activity interface, the sharing timestamp, the geographic location information at the time of sharing, the network protocol address used at the time of sharing, and the fingerprint of the terminal device used at the time of sharing; The historical behavior data includes at least one of the following: the first user's historical order records, the locations of frequently visited service stations, and the vehicle's historical driving trajectory data.

3. The method according to any one of claims 1 or 2, characterized in that, The step of obtaining the real-time and historical behavior data of the first user who performed the sharing operation includes: Obtain behavioral data of the second user introduced through the sharing operation; The verification of the real-time behavior data and the historical behavior data includes: The behavioral data of the second user is verified.

4. The method according to claim 1, characterized in that, The verification of the behavioral data of the second user includes: Verify whether the terminal device or network protocol address used by the second user is associated with the corresponding information of the first user, and / or, Verify whether the second user performed a preset preparatory operation before placing the order.

5. The method according to claim 1, characterized in that, The verification of the real-time behavior data and the historical behavior data includes at least one of the following: Obtain the account activity status from the real-time behavior data and the historical service usage records from the historical behavior data, and verify whether the account activity status and the historical service usage records meet the preset standards; Obtain the current location information from the real-time behavior data, and the historical frequently visited site location information and historical driving trajectory data from the historical behavior data, and verify whether the current location information matches the historical frequently visited site location information, and / or the historical driving trajectory data; Obtain current device and environment information from the real-time behavior data and historical device and environment information from the historical behavior data, and verify whether the current device and environment information and the historical device and environment information meet preset conditions.

6. The method according to claim 1, characterized in that, The step of outputting an audit decision based on the verification result includes: A credibility score is generated based on the verification results; Based on the comparison between the credibility score and the preset threshold, the audit decision is output as pass, rejection, or manual review required.

7. The method according to claim 6, characterized in that, The process of comparing the credibility score with a preset threshold and outputting a review decision (pass, reject, or requiring manual review) includes: When the credibility score is greater than a preset first threshold, a pass review decision is output. When the credibility score is less than a preset second threshold, a rejection decision is output. When the credibility score is greater than the second threshold and less than the first threshold, an audit decision requiring manual review is output. After the output of the review decision that requires manual review, a review interface is generated, and the abnormal dimension information that caused the decision is marked in the review interface.

8. The method according to claim 1, characterized in that, After outputting the audit decision based on the verification result, the method further includes: If the review decision is to reject, the behavioral data and verification results related to this sharing operation will be used as case materials, and the case materials will be added to the material training set. The rules or models used in subsequent verification processes are optimized based on the training set of the materials.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the reward settlement method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the reward settlement method steps as described in any one of claims 1 to 8.

Images