Refund method and device, nonvolatile storage medium and computer device

Abstract

The application discloses a refund method and device, a nonvolatile storage medium and a computer device. The method comprises the following steps: obtaining a refund order corresponding to a target object and historical data of the refund order corresponding to the refund order; determining a refund risk corresponding to the refund order based on the historical data of the refund order; and refunding the target object under the condition that the refund risk is not greater than a predetermined threshold. The application solves the technical problem of the risk of financing and refunding when a platform receives a large number of refund orders.

Description

Technical Field

[0001] This invention relates to the field of machine learning, and more specifically, to a refund method, apparatus, non-volatile storage medium, and computer device. Background Technology

[0002] After booking tickets on a ticketing platform, users may need to request a refund. The platform communicates with users downstream and ticket agents upstream, needing to decide whether to issue a refund. If the agent hasn't yet processed the refund, the platform faces a choice: continue waiting for the agent to issue the refund before issuing one, or advance the refund funds to the agent and wait for the agent's funds to arrive. Clearly, if the platform always waits for the agent to issue a refund before issuing one, users may experience long wait times and a poor refund experience; if the platform advances the refund funds to the agent and then refunds the user, the platform faces financial risk.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a refund method, apparatus, non-volatile storage medium, and computer device to at least address the technical problem of the risk of fund advance refunds when a platform receives a large number of refund orders.

[0005] According to one aspect of the present invention, a refund method is provided, comprising: obtaining a refund order corresponding to a target object and historical data of the refund order corresponding to the refund order; determining the refund risk corresponding to the refund order based on the historical data of the refund order; and refunding the target object if the refund risk is not greater than a predetermined threshold.

[0006] Optionally, determining the refund risk corresponding to the refund order based on the historical refund order data includes: determining at least one risk control filter based on the historical refund order data, wherein the risk control filter calculates the refund risk corresponding to the refund order based on a predetermined risk calculation rule; inputting the historical refund order data into the risk control filter to calculate the refund risk corresponding to the refund order.

[0007] Optionally, determining at least one risk control filter based on the refund order history data includes: determining a general filter, wherein the risk control filter includes the general filter; and determining an optional filter corresponding to the refund order based on the refund order history data, wherein the risk control filter includes the optional filter.

[0008] Optionally, determining the refund risk corresponding to the refund order further includes: generating an estimated refund time for the refund order based on the historical data of the refund order, wherein the estimated refund time is the estimated time for the agent corresponding to the refund order to complete the refund; obtaining the current refund waiting time for the refund order; and determining the refund risk corresponding to the refund order if the refund waiting time is greater than the estimated refund time.

[0009] Optionally, if the refund waiting time is greater than the expected refund time, determining the refund risk corresponding to the refund order includes: reducing the number of optional filters based on the difference between the refund waiting time and the expected refund time; and invoking the risk control filter, which includes the general filter and the optional filters, to determine the refund risk corresponding to the refund order.

[0010] Optionally, obtaining the refund orders corresponding to the target object and the historical data of the refund orders corresponding to the refund orders includes: obtaining the current data processing capability to determine the refund risk corresponding to the refund order based on the historical data of the refund orders; determining the target number of the refund orders to be obtained based on the data processing capability; and obtaining the target number of refund orders and the historical data of the refund orders corresponding to the target number of refund orders.

[0011] Optionally, the refund order history data includes: the historical data of the target object and the historical data of the agent corresponding to the refund order.

[0012] According to another aspect of the present invention, a refund device is also provided, comprising: an acquisition module, configured to acquire a refund order corresponding to a target object and historical data of the refund order corresponding to the refund order; a determination module, configured to determine the refund risk corresponding to the refund order based on the historical data of the refund order; and a refund module, configured to refund the target object if the refund risk is not greater than a predetermined threshold.

[0013] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is executed, it controls the device where the non-volatile storage medium is located to perform any of the above-described refund methods.

[0014] According to another aspect of the present invention, a computer device is also provided, the computer device including a processor for running a program, wherein the program executes any of the above-described refund methods when it runs.

[0015] In this embodiment of the invention, a risk quantification method for refund orders is adopted. This involves obtaining the refund orders corresponding to the target object and the historical data of the refund orders; determining the refund risk corresponding to the refund order based on the historical data; and refunding the target object if the refund risk is not greater than a predetermined threshold. This achieves the purpose of quantifying the risk of refunding a single refund order initiated by a user, thereby reducing the technical effect of reducing the risk of the platform providing advance refunds to users. It also solves the technical problem of the risk of advance refunds when the platform receives a large number of refund orders. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a computer terminal for implementing a refund method is shown;

[0018] Figure 2 This is a flowchart illustrating a refund method provided according to an embodiment of the present invention;

[0019] Figure 3 This is a schematic diagram of the flight ticket order process provided by an optional embodiment of the present invention;

[0020] Figure 4 This is an architecture diagram of a platform refund system provided according to an optional embodiment of the present invention;

[0021] Figure 5 This is a structural block diagram of a refund device provided according to an embodiment of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] According to an embodiment of the present invention, an image annotation method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a refund method is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0026] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be implemented wholly or partially as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be wholly or partially integrated into any other element in the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0027] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the refund method in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the above-mentioned refund method of the application. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0028] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0029] Figure 2 This is a flowchart illustrating the refund method provided according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0030] Step S202: Obtain the refund order corresponding to the target object and the historical data of the refund order corresponding to the refund order.

[0031] Optionally, in an exemplary application scenario, the target object can be a user who initiates a refund request to the platform, such as an ordinary consumer. After placing an order and paying the fee on the platform, the user wants to cancel the order and submits a refund request to the platform. At this time, the platform can generate a refund order based on the user's refund request, and further retrieve historical refund order data related to the refund order from the big data, so as to estimate the risk of refunding the user in the future.

[0032] Step S204: Based on historical refund order data, determine the refund risk corresponding to each refund order. In this step, the refund risk corresponding to a refund order can be a quantifiable number, where refund risk represents the risk that the platform bears when providing advance payment for refunds to the target recipient.

[0033] It should be noted that the platform's advance payment risk may come from two aspects: user risk and agent risk.

[0034] Step S206: If the refund risk is not greater than a predetermined threshold, refund the target object.

[0035] Through the above steps, the risk of refunding a single refund order initiated by a user is quantified, thereby reducing the technical risk of the platform providing advance refunds to users and solving the technical problem of the risk of advance refunds when the platform receives a large number of refund orders.

[0036] As an optional implementation, the refund order history data may include the target object's historical data and the historical data of the agent corresponding to the refund order. The target object's historical data may include the target object's previous consumption data, number of refunds, refund reasons, etc. The agent corresponding to the refund order may be the channel provider through which the target object placed the order; that is, the order for which the target object requested a refund was previously placed through that agent's channel. The agent's historical data may include data related to the agent's previous processing of refund orders, such as the processing time for each refund, whether refunds were accepted for users, and the amount refunded to users.

[0037] Figure 3 This is a schematic diagram of the flight ticket order process provided by an optional embodiment of the present invention, to help understand the relationship between users, agents, and airlines. Figure 3 As shown, when a user books a flight ticket on the platform, the user can place a combined order. This order can include the flight ticket itself, as well as services provided by multiple suppliers, such as hotels, insurance, and co-sold products. Based on the user's flight ticket, the platform forwards the order to the corresponding agent, such as the airline's own store, flagship store, agency platform, OTA agent, and distributor. The agent then provides the flight ticket order to the airline, which sells the ticket, completing a successful order.

[0038] As an optional embodiment, to determine the refund risk corresponding to a refund order based on historical refund order data, at least one risk control filter can be determined first based on the historical refund order data. The risk control filter calculates the refund risk corresponding to the refund order based on a predetermined risk calculation rule. Then, the historical refund order data is input into the risk control filter to calculate the refund risk corresponding to the refund order.

[0039] The risk control filter described in this embodiment can calculate the risk level of the platform's advance payment for a refund order based on historical refund order data. The risk of advance payment for refunds comes from two aspects: firstly, the user applying for a refund (i.e., the target) may maliciously request a refund, or the refund may be initiated by a cyber attacker who hijacks the user, thus harming the platform's interests; secondly, the risk may come from the agent, for example, the agent may refuse to refund the user, resulting in the platform's advance payment not being repaid, or the agent may be slow to refund, causing cash flow pressure on the platform. The risk control filter can, based on historical refund order data, properly assess the characteristics of the historical behavior of both the user and the agent in this refund order, as well as the risks from both aspects, and then calculate the risk of the platform's advance payment for the refund order. Optionally, the platform can only refund the user when the refund risk is 0, to maximize the protection of the platform's own interests.

[0040] As an optional implementation, risk control filters may include general filters and optional filters. Based on historical refund order data, determining at least one risk control filter can begin by identifying a general filter, and then by identifying optional filters corresponding to specific refund orders based on the historical refund order data. It should be noted that a general filter is one that requires inputting historical refund order data to calculate risk for any given refund order, while optional filters are more targeted. Optional filters are not activated when performing risk assessments on every refund order, but are only enabled in specific scenarios related to the optional filter. For example, a general filter may include a blacklist filter, which can identify users on the platform's blacklist as having a high refund risk. Additionally, a general filter may include a domain filter; for example, for refund requests originating from sensitive domains that may be highly associated with fraud, the domain filter can output a high risk value, guiding the platform to refuse to advance refund funds for that refund order. Optional filters may include interface blacklist filters, refund timeout filters, special event filters, and omnichannel blocking filters, etc. No single optional filter is activated when performing risk assessments on every refund order, but rather risk assessments are only initiated for certain types of refund orders. For example, the special event filter will only be activated to conduct a risk assessment of a refund order if the refund order is found to be related to a special event based on the historical data of the refund order.

[0041] Optionally, when the risk control filter includes multiple general filters and multiple optional filters, each risk control filter can output a risk value, and then the multiple risk values ​​can be summed or summed according to weights to obtain the total risk of the refund order.

[0042] As an optional embodiment, determining the refund risk corresponding to a refund order further includes the following steps: generating an estimated refund time for the refund order based on historical data of the refund order, wherein the estimated refund time is the estimated time for the agent corresponding to the refund order to complete the refund; obtaining the current refund waiting time for the refund order; and determining the refund risk corresponding to the refund order if the refund waiting time is greater than the estimated refund time.

[0043] Based on the method provided in this embodiment, if the waiting time for the target object to initiate a refund is less than the estimated time for the agent's refund, the platform may not initiate the risk assessment calculation for advance payment and may not simultaneously provide advance payment refunds to the target object. The estimated refund time for the agent's refund can be predicted by analyzing agent-related data in the historical data of refund orders.

[0044] Furthermore, the platform can display a visible refund time to the target user who initiates the refund request. This visible refund time is displayed on the target user's app interface, indicating approximately how long the platform will need to process the refund. Specifically, the visible refund time can be obtained by adding a risk period to the agent's estimated refund time. The risk period is determined based on the level of risk associated with providing a refund on behalf of the target user. For target users with low risk of receiving a refund on behalf of the target user, a shorter risk period can be generated, resulting in a shorter visible refund time. If the target user's waiting time for the refund exceeds the visible refund time, the platform can prioritize processing the refund. Conversely, for target users with higher risk of electronic refunds, a longer risk period can be generated, resulting in a longer visible refund time. During this longer visible refund time, the platform can assess the risk of refunding the user as much as possible, aiming to reduce the risk before processing the refund or refusing to process it.

[0045] As an optional implementation, when the refund waiting time is longer than the expected refund time, the refund risk corresponding to the refund order can be determined by reducing the number of optional filters based on the difference between the refund waiting time and the expected refund time; and by calling a risk control filter that includes general filters and optional filters to determine the refund risk corresponding to the refund order.

[0046] In this optional embodiment, the platform can provide flexible services to the target audience, avoiding prolonged waiting that could lead to a poor user experience or direct complaints. When the target audience is a user who has placed an order, as the waiting time for a refund application increases, the platform's risk control system can gradually reduce the number of optional filters used to assess the user's refund application. This means the review process for the refund application is relaxed, and the platform no longer strictly requires the refund order to pass the risk assessment of each risk control filter. It should be noted that the general filter will not be abandoned as the waiting time increases; only the optional filters will be gradually reduced in use. In extreme cases, if the user's waiting time is too long, all optional filters can be abandoned, and only the general filter can be used to assess the risk of the refund order. If the risk values ​​output by multiple general filters are low, the platform can advance the refund for the user.

[0047] As an optional embodiment, the processing speed of refund orders can also be controlled based on the capacity of the platform's risk control system. Obtaining the refund orders corresponding to the target object and the corresponding historical data of refund orders may include the following steps: acquiring the current data processing capacity to determine the refund risk corresponding to the refund order based on the historical data; determining the target number of refund orders to be acquired based on the data processing capacity; acquiring the target number of refund orders and the corresponding historical data of refund orders. This optional embodiment can solve the problem of the risk control system being overwhelmed by a large number of refund orders received in a short period, improving the flexibility of the entire refund system.

[0048] Figure 4 This is an architecture diagram of a platform refund system provided by an optional embodiment of the present invention, such as... Figure 4 As shown, after receiving a large number of refund orders from users, the platform's refund system first retrieves historical data related to each refund order to predict the refund period for each order and estimate the refund cycle for the agent. During this process, factors such as the airline, business line, flight cycle, seasonality, reason for refund, and whether there is an epidemic in the travel area can all affect the agent's refund time. After estimating the refund cycle for each order, the platform's refund prediction module can tag the orders and store them in the refund driver. The refund driver then retrieves the refund orders to be processed and sends them to the risk control filter based on the tagging results. A rate control module can be used between the refund driver and the risk control filter to control the data retrieval speed of the refund driver. This is to avoid the risk control filter's limited data processing speed being overloaded and crashing due to the refund driver's excessively fast data retrieval speed. The risk control filter can assess the risk of the platform covering the refund for a given order based on the order and its related historical data. If the risk is too high, the platform is prohibited from refunding the user corresponding to that order. If the risk is below the risk threshold, the platform can be allowed to refund the order and push it into the refund executor. Similarly, a rate control module can control the data retrieval speed between the refund executor and the risk control filter to prevent the risk control filter from inputting too many orders into the refund executor, causing the executor to crash due to excessive data load.

[0049] According to an embodiment of the present invention, a refund apparatus for implementing the above-described refund method is also provided. Figure 5 This is a structural block diagram of a refund device provided according to an embodiment of the present invention, such as... Figure 5 As shown, the refund device includes: an acquisition module 52, a determination module 54, and a refund module 56. The refund device will be described below.

[0050] Module 52 is used to obtain the refund orders corresponding to the target object and the historical data of the refund orders corresponding to the refund orders;

[0051] The determination module 54, connected to the acquisition module 52, is used to determine the refund risk corresponding to a refund order based on historical refund order data.

[0052] The refund module 56, connected to the aforementioned determination module 54, is used to refund the target object when the refund risk does not exceed a predetermined threshold.

[0053] It should be noted that the acquisition module 52, the determination module 54, and the refund module 56 mentioned above correspond to steps S202 to S206 in the embodiments. The three modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of the device, can run in the computer terminal 10 provided in the embodiments.

[0054] Embodiments of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0055] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the refund method and apparatus in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned refund method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0056] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: obtain the refund order corresponding to the target object and the historical data of the refund order; determine the refund risk corresponding to the refund order based on the historical data of the refund order; and refund the target object if the refund risk is not greater than a predetermined threshold.

[0057] Optionally, the processor can also invoke information and applications stored in the memory via a transmission device to perform the following steps: determining the refund risk corresponding to a refund order based on historical refund order data, including: determining at least one risk control filter based on historical refund order data, wherein the risk control filter calculates the refund risk corresponding to the refund order based on a predetermined risk calculation rule; inputting historical refund order data into the risk control filter to calculate the refund risk corresponding to the refund order.

[0058] Optionally, the processor can also invoke information and applications stored in the memory via a transmission device to perform the following steps: determining at least one risk control filter based on historical refund order data, including: determining a general filter, wherein the risk control filter includes a general filter; and determining an optional filter corresponding to a refund order based on historical refund order data, wherein the risk control filter includes an optional filter.

[0059] Optionally, the processor can also invoke information and applications stored in the memory via a transmission device to perform the following steps: determining the refund risk corresponding to a refund order, further including: generating an estimated refund time for the refund order based on historical data of the refund order, wherein the estimated refund time is the estimated time for the agent corresponding to the refund order to complete the refund; obtaining the current refund waiting time for the refund order; and determining the refund risk corresponding to the refund order if the refund waiting time is greater than the estimated refund time.

[0060] Optionally, the processor can also invoke information and applications stored in the memory via the transmission device to perform the following steps: determining the refund risk corresponding to the refund order when the refund waiting time is longer than the expected refund time, including: reducing the number of optional filters based on the difference between the refund waiting time and the expected refund time; and invoking a risk control filter that includes general filters and optional filters to determine the refund risk corresponding to the refund order.

[0061] Optionally, the processor can also invoke information and applications stored in the memory via a transmission device to perform the following steps: obtaining refund orders corresponding to the target object and historical refund order data corresponding to the refund orders, including: obtaining the current data processing capability to determine the refund risk corresponding to the refund order based on the historical refund order data; determining the target number of refund orders to be obtained based on the data processing capability; obtaining the target number of refund orders and the historical refund order data corresponding to the target number of refund orders.

[0062] Optionally, the processor can also invoke information and applications stored in the memory via a transmission device to perform the following steps: refund order history data, including: historical data of the target object and historical data of the agent corresponding to the refund order.

[0063] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

[0064] Embodiments of the present invention also provide a non-volatile storage medium. Optionally, in this embodiment, the aforementioned non-volatile storage medium can be used to store the program code executed by the refund method provided in the above embodiments.

[0065] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0066] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: obtaining the refund order corresponding to the target object and the historical data of the refund order; determining the refund risk corresponding to the refund order based on the historical data of the refund order; and refunding the target object if the refund risk is not greater than a predetermined threshold.

[0067] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining the refund risk corresponding to a refund order based on historical refund order data, including: determining at least one risk control filter based on historical refund order data, wherein the risk control filter calculates the refund risk corresponding to the refund order based on a predetermined risk calculation rule; inputting historical refund order data into the risk control filter to calculate the refund risk corresponding to the refund order.

[0068] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining at least one risk control filter based on historical refund order data, including: determining a general filter, wherein the risk control filter includes a general filter; and determining an optional filter corresponding to a refund order based on historical refund order data, wherein the risk control filter includes an optional filter.

[0069] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining the refund risk corresponding to a refund order, further including: generating an estimated refund time corresponding to the refund order based on historical data of the refund order, wherein the estimated refund time is the estimated time for the agent corresponding to the refund order to complete the refund; obtaining the current refund waiting time of the refund order; and determining the refund risk corresponding to the refund order if the refund waiting time is greater than the estimated refund time.

[0070] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining the refund risk corresponding to the refund order when the refund waiting time is greater than the expected refund time, including: reducing the number of optional filters based on the difference between the refund waiting time and the expected refund time; and calling a risk control filter including a general filter and optional filters to determine the refund risk corresponding to the refund order.

[0071] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: obtaining refund orders corresponding to the target object and historical data of refund orders corresponding to the refund orders, including: obtaining the current data processing capability to determine the refund risk corresponding to the refund order based on the historical data of the refund orders; determining the target number of refund orders to be obtained based on the data processing capability; obtaining the target number of refund orders and the historical data of refund orders corresponding to the target number of refund orders.

[0072] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: refund order history data, including: historical data of the target object and historical data of the agent corresponding to the refund order.

[0073] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0074] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0075] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0076] The units described as separate components may or may not be physically separate. 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0078] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0079] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A refund method, characterized in that, include: Obtain the refund order corresponding to the target object and the historical data of the refund order corresponding to the refund order, wherein the historical data of the refund order includes the historical data of the target object and the historical data of the agent corresponding to the refund order, and the agent is the channel partner when the target object placed the order; Based on the historical data of the refund orders, the refund risk corresponding to the refund orders is determined, wherein the refund risk is the risk that the platform will advance funds for the refund orders, and the platform is the intermediary platform between the target and the agent; If the refund risk is not greater than a predetermined threshold, a refund will be issued to the target object; The step of determining the refund risk corresponding to a refund order based on the historical data of the refund orders includes: determining at least one risk control filter based on the historical data of the refund orders, wherein the risk control filter calculates the refund risk corresponding to the refund order based on a predetermined risk calculation rule; inputting the historical data of the refund orders into the risk control filter to calculate the refund risk corresponding to the refund order, wherein the risk control filter includes a general filter and an optional filter, the general filter is used for each refund order, and the optional filter is determined based on the scenario corresponding to the refund order; The method further includes: reducing the number of optional filters used based on the increase in the user's waiting time in the refund order, and determining the refund risk corresponding to the refund order based on the general filter.

2. The method according to claim 1, characterized in that, The determination of at least one risk control filter based on the historical refund order data includes: A general-purpose filter is determined, wherein the risk control filter includes the general-purpose filter; Based on the historical data of the refund orders, an optional filter corresponding to the refund order is determined, wherein the risk control filter includes the optional filter.

3. The method according to any one of claims 1 to 2, characterized in that, The determination of the refund risk corresponding to the refund order also includes: Based on the historical data of the refund orders, an estimated refund time is generated for the corresponding refund order, wherein the estimated refund time is the estimated time for the agent corresponding to the refund order to complete the refund; Get the current refund waiting time for the refund order; If the refund waiting time is longer than the estimated refund time, the refund risk corresponding to the refund order is determined.

4. The method according to claim 3, characterized in that, If the refund waiting time is longer than the estimated refund time, the refund risk corresponding to the refund order is determined, including: Based on the difference between the refund waiting time and the estimated refund time, the number of optional filters is reduced; The risk control filter, which includes the general filter and the optional filter, is invoked to determine the refund risk corresponding to the refund order.

5. The method according to claim 1, characterized in that, The step of obtaining the refund order corresponding to the target object and the historical data of the refund order corresponding to the refund order includes: The ability to obtain data processing capabilities to determine the refund risk corresponding to the refund order based on the historical data of the refund order; Based on the data processing capabilities, determine the target number of the obtained refund orders; Obtain the target number of refund orders and the historical data of the refund orders corresponding to the target number of refund orders.

6. The method according to claim 1, characterized in that, The refund order history data includes: the historical data of the target object and the historical data of the agent corresponding to the refund order.

7. A refund device, characterized in that, include: The acquisition module is used to acquire the refund order corresponding to the target object and the historical data of the refund order corresponding to the refund order. The historical data of the refund order includes the historical data of the target object and the historical data of the agent corresponding to the refund order. The agent is the channel partner when the target object placed the order. The determination module is used to determine the refund risk corresponding to the refund order based on the historical data of the refund order, wherein the refund risk is the risk that the platform will advance funds for the refund order, and the platform is an intermediary platform between the target object and the agent; The refund module is used to refund the target object if the refund risk is not greater than a predetermined threshold. The determining module is further configured to determine at least one risk control filter based on the historical data of the refund orders, wherein the risk control filter calculates the refund risk corresponding to the refund order based on a predetermined risk calculation rule; inputting the historical data of the refund orders into the risk control filter to calculate the refund risk corresponding to the refund order, wherein the risk control filter includes a general filter and an optional filter, the general filter is used for each refund order, and the optional filter is determined based on the scenario corresponding to the refund order; The device is also used to reduce the number of optional filters used based on the increase in the user's waiting time in the refund order, and to determine the refund risk corresponding to the refund order based on the general filter.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the non-volatile storage medium to perform the refund method according to any one of claims 1 to 6.

9. A computer device, characterized in that, The computer device includes a processor for running a program, wherein the program, when running, performs the refund method according to any one of claims 1 to 6.

Images