Methods, devices, equipment, media, and products for limiting the amount of payment received by the party owning the goods.

Abstract

This invention discloses a method, apparatus, equipment, medium, and product for setting payment limits for the owner of goods. The invention relates to the field of financial risk technology. The method includes: acquiring first historical transaction details data of the owner of the goods; preprocessing the first historical transaction details data to obtain preprocessed data; performing spectral clustering based on the preprocessed data to obtain clustering results; and adjusting the payment limits for the owner of the goods based on the clustering results. The technical solution of this invention addresses the problem that regulatory agencies primarily rely on managers to comprehensively consider various information to adjust payment limits for the owner of goods. It achieves the technical effect of intelligently adjusting payment limits for the owner of goods.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of financial risk technology, and in particular to a method, apparatus, equipment, medium and product for limiting the amount of payment received by the owner of goods. Background Technology

[0002] In traditional risk control models, risk control of the owner of goods is mainly concentrated in the onboarding stage, lacking continuous monitoring of their operational risks. The judgment of whether the owner of goods poses a risk also primarily relies on analyzing the owner's own information. Because the cost of falsifying information is currently very low, a significant amount of manpower is needed to verify the owner's identity and the authenticity of the submitted materials.

[0003] Under current standard operating procedures, governing bodies primarily rely on management personnel to integrate information from various sources to adjust the payment limits for the ownership of goods. This approach may be subject to delays and could expose financial risks due to failure to adjust limits in a timely manner. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for determining the payment limit for the owner of goods, in order to solve the problem that the governing body mainly relies on management personnel to comprehensively consider various information to adjust the payment limit for the owner of goods.

[0005] In a first aspect, embodiments of the present invention provide a method for limiting the amount a party owns an item can receive, including:

[0006] Obtain the first historical transaction details of the party to whom the item belongs;

[0007] The first historical transaction details data is preprocessed to obtain preprocessed data;

[0008] Based on the preprocessed data, spectral clustering is performed to obtain the clustering results;

[0009] Based on the clustering results, adjust the payment limit for the party to whom the item belongs.

[0010] Secondly, embodiments of the present invention provide an apparatus for limiting the amount of money a party can receive from an item, comprising:

[0011] The first historical transaction details data acquisition module is used to acquire the first historical transaction details data of the owner of the item;

[0012] The preprocessed data acquisition module is used to preprocess the first historical transaction details data to obtain preprocessed data;

[0013] The clustering result acquisition module is used to perform spectral clustering to obtain clustering results based on the preprocessed data;

[0014] The payment limit adjustment module is used to adjust the payment limit of the item owner based on the clustering results.

[0015] Thirdly, embodiments of the present invention provide an electronic device for limiting the amount of payment received by the owner of an item, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for limiting the amount of payment received by the owner of an item as described in the first aspect.

[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for limiting the amount of payment to the owner of the goods as described in the first aspect.

[0017] Fifthly, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the method for limiting the amount of payment received by the owner of the goods as described in the first aspect.

[0018] In this embodiment of the invention, by acquiring the first historical transaction details data of the item's owner, preprocessing the first historical transaction details data to obtain preprocessed data, and performing spectral clustering based on the preprocessed data to obtain clustering results, the payment limit for the item's owner is adjusted according to the clustering results. This addresses the problem that governing bodies primarily rely on managers to comprehensively consider various information to adjust the payment limit for item owners. Through an intelligent prediction strategy based on spectral clustering, the adjustment of the payment limit for item owners is more timely and intelligent. While mitigating related financial risks, it optimizes the payment experience for item owners, improves the digital operation capabilities of governing bodies, and achieves the technical effect of intelligently adjusting the payment limit for item owners. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a method for limiting the amount a party can receive payment for goods, as provided in an embodiment of the present invention;

[0021] Figure 2 A flowchart illustrating another method for limiting the amount of payment received by the owner of goods, as provided in an embodiment of the present invention;

[0022] Figure 3A flowchart illustrating another method for limiting the amount of payment received by the owner of goods, as provided in an embodiment of the present invention;

[0023] Figure 4 A flowchart illustrating another method for limiting the amount of payment received by the owner of goods, as provided in an embodiment of the present invention;

[0024] Figure 5 A schematic diagram of a device for limiting the amount of payment received by the owner of an item, provided in an embodiment of the present invention;

[0025] Figure 6 This is a block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0027] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0028] Optionally, before introducing the various embodiments of the present invention, the situation regarding the payment limit for the item owner in the embodiments of the present invention will be described first. The management personnel of the governing body cannot have a comprehensive understanding of the item owner; if there are unnoticed business fluctuations, a lower payment limit will affect the payment experience of the item owner. A balance needs to be struck between optimizing the payment experience of the item owner and meeting the regulatory requirements for payment limits, and the digital operation capabilities of the governing body need to be improved. Furthermore, the estimation of payment limits by the management personnel of the governing body largely depends on the subjective personal assessment of the management personnel, and is highly subjective. Here, the governing body refers to the institution to which the management personnel belong; the management personnel have the right to enter the necessary information opened by the item owner and maintain relevant parameters according to business development needs. Payment limits refer to the various payment limit parameters maintained by the management personnel for an individual item owner based on anti-money laundering and other regulatory requirements. The governing body is, for example, a financial institution, which refers to a financial intermediary institution engaged in the financial services industry and is part of the financial system. For example, a financial institution includes a bank.

[0029] Figure 1This is a flowchart illustrating a method for limiting payment collection by the owner of goods, as provided in this embodiment of the invention. This embodiment is applicable to situations where payment collection by the owner of goods is limited. This method can be executed by a device for limiting payment collection by the owner of goods, as described in this embodiment of the invention. This device can be implemented using software and / or hardware. The device can be configured in an electronic device, such as a server or terminal device. Typical terminal devices include mobile terminals, specifically mobile phones, computers, or tablet computers. (Reference) Figure 1 The method includes:

[0030] S101. Obtain the first historical transaction details of the item's owner.

[0031] In this context, the owner of the goods refers to the organization that provides the goods or services, and the owner earns income by selling the goods or services. For example, a merchant could be the owner of the goods.

[0032] The first historical transaction details include historical transaction details for a selected period of time prior to the current day, week, or month, such as historical transaction details for a year or several years prior to the current day.

[0033] Different owners of goods exhibit different characteristics in terms of transaction fluctuations. In some industries, the ownership of goods experiences seasonal fluctuations in ownership transfer. For owners of goods experiencing seasonal ownership transfer fluctuations, the number of ownership transfers is higher and the fluctuations are greater during peak seasons. Conversely, the number of ownership transfers is lower and the fluctuations are smaller during off-seasons. Ownership transfers can include, for example, the sale or transaction of goods or services.

[0034] The owner of the goods may also experience fluctuations in ownership transfer due to discounts on ownership transfers. Typically, when a discount on ownership transfer occurs, the number of ownership transfers increases, and the fluctuations in ownership transfers increase. These discounts can be, for example, promotional activities.

[0035] S102. Preprocess the first historical transaction details data to obtain the preprocessed data.

[0036] For example, the preprocessing of the first historical transaction details data may include removing invalid data from the first historical transaction details data. Invalid data includes, for example, data on incomplete orders and data on invalid orders.

[0037] For example, the preprocessing of the first historical transaction details data may also include some basic classification of the order data information in the first historical transaction details data. For example, the order data information in the first historical transaction details data may be classified according to which terminals the order data is concentrated on, payment frequency, order counter enrichment pattern, and duplicate payment ratio.

[0038] For example, the preprocessing of the first historical transaction details data may also include standardization of order data within the first historical transaction details data, forming different types of data into a unified data format.

[0039] S103. Based on the preprocessed data, perform spectral clustering to obtain the clustering results.

[0040] Among them, the spectral clustering algorithm is based on spectral graph theory. Compared with traditional clustering algorithms, it has the advantages of being able to cluster on sample spaces of arbitrary shapes and converging to the global optimum. The algorithm first defines an affinity matrix describing the similarity of paired data points based on the given sample dataset, and calculates the eigenvalues ​​and eigenvectors of the matrix. Then, it selects appropriate eigenvectors to cluster different data points.

[0041] Order data for the item's owner is influenced by various factors, including the item's industry, location, price point, and the number of people acquiring the item. This results in a complex distribution, allowing for clustering of order data from all item owners to obtain clustering results. For example, the item acquirer could be a consumer.

[0042] For example, transactions involving a single item owner over a period of time typically share certain common characteristics. Spectral clustering can more efficiently and accurately extract the feature elements most directly related to fluctuations in transaction volume for that item owner over a given period. Item owners with the same type of feature elements tend to have similar risk profiles; therefore, spectral clustering analysis can extract the commonalities of a large number of feature elements corresponding to a large number of item owners. The clustering result includes at least one feature element.

[0043] S104. Based on the clustering results, adjust the payment limit for the item owner.

[0044] In this step, based on the clustering results, the owners of items at risk are identified, and their payment limits are adjusted. For example, payment limits for owners of items at risk may be suspended or lowered.

[0045] In this embodiment of the invention, by acquiring the first historical transaction details data of the item's owner, preprocessing the first historical transaction details data to obtain preprocessed data, and performing spectral clustering based on the preprocessed data to obtain clustering results, the payment limit for the item's owner is adjusted according to the clustering results. This addresses the problem that governing bodies primarily rely on managers to comprehensively consider various information to adjust the payment limit for item owners. Through an intelligent prediction strategy based on spectral clustering, the adjustment of the payment limit for item owners is more timely and intelligent. While mitigating related financial risks, it optimizes the payment experience for item owners, improves the digital operation capabilities of governing bodies, and achieves the technical effect of intelligently adjusting the payment limit for item owners.

[0046] Figure 2 This is a flowchart illustrating another method for limiting the amount of payment received by the owner of goods according to an embodiment of the present invention. This embodiment further optimizes the method for limiting the amount of payment received by the owner of goods based on the above embodiment. Accordingly, refer to... Figure 2 The method includes:

[0047] S201. Obtain the first historical transaction details of the item's owner.

[0048] S202. Preprocess the first historical transaction details data to obtain the preprocessed data.

[0049] S203. Extract the feature elements that have a significant impact on trading fluctuations from the preprocessed data.

[0050] Optionally, the feature elements include product acquisition behavior elements and product ownership transfer elements. Product acquisition behavior elements can be, for example, consumer behavior elements. These include the purchase time, payment behavior, payment method, and refund transactions of the product acquirer. Product ownership transfer elements can be, for example, marketing elements. These include product ownership transfer discounts, transaction amounts, number of transactions, and sales performance.

[0051] Situations where transaction fluctuations have a significant impact include, for example, concentrated consumption patterns, which are correlated to some extent with the transfer discounts on ownership of one or more types of goods.

[0052] For example, in a non-volatile scenario, there is a certain time interval between adjacent orders and a certain range of total orders. If the total number of orders exceeds this range, or if the time interval between adjacent orders exceeds this range, then the transaction volatility has a significant impact. The characteristic elements that indicate a significant transaction volatility impact are then extracted.

[0053] For example, a transfer-of-ownership discount may include a discount for the payment channel and / or a discount for the item's owner. A discount for the payment channel, for example, applies when paying via WeChat. This discount does not apply when paying via other payment channels. A discount for the item's owner may be a merchant's promotional discount, such as a minimum purchase amount, a fixed discount, or a minimum purchase quantity.

[0054] For example, withdrawals are required for cases of obvious intensive payments, cases of accumulation in a certain type of channel, or cases of coupon usage.

[0055] S204. Link the feature elements in the form of a graph to form a tree diagram.

[0056] Clustering methods are divided into hierarchical clustering and non-hierarchical clustering. Hierarchical clustering includes decomposition and dendrograms, while non-hierarchical clustering includes partitioning. Dendrograms describe the data classification process, which is helpful for manual analysis. The maximum number of calculations for each prediction does not exceed the depth of the dendrogram.

[0057] S205. Consider the n elements in the tree diagram as n classes, and merge the two classes with the most similar properties or the greatest degree of similarity into a new class to obtain n-1 classes.

[0058] Where n is a positive integer greater than 1. An element may include at least one feature.

[0059] Alternatively, the longest distance method can be used to merge two classes with the most similar properties or the highest degree of similarity into a new class. The longest distance method refers to using the longest distance between elements in the two classes to represent the inter-class distance, and then using the smallest distance to merge the two classes into a new class. The inter-class distance can be calculated using the Euclidean distance formula.

[0060] S206. From the n-1 classes, merge the two classes with the most similar properties or the greatest degree of similarity into a new class to obtain n-2 classes.

[0061] S207. Repeat the above merging process until all elements are in one category.

[0062] Following the above merging process, the two classes with the most similar properties or the greatest degree of similarity are successively merged into a new class. From class n-2, class n-3 is obtained, ..., from class 3, class 2 is obtained, and from class 2, class 1 is obtained.

[0063] In this embodiment of the invention, using the classification concept, the spectral clustering method first considers each element (sample or variable) as its own class, then clusters the most similar elements (those with the smallest distance or the largest similarity coefficient) into smaller classes, and then re-aggregates the already aggregated smaller classes according to their similarity (measured by inter-class distance). As the similarity decreases, finally all subclasses are aggregated into one large class, thereby obtaining the clustering result.

[0064] Figure 3 This is a flowchart illustrating another method for limiting the amount of payment received by the owner of goods according to an embodiment of the present invention. This embodiment further optimizes the method for limiting the amount of payment received by the owner of goods based on the above embodiment. Accordingly, refer to... Figure 3 The method includes:

[0065] S301. Obtain historical transaction details for the same period corresponding to the predicted transaction amount of the item's owner.

[0066] The predicted transaction amount for the owner of the goods is the transaction amount for a future period after today. The historical transaction details corresponding to the predicted transaction amount include not only the transaction amount, but also the purchase time, payment behavior, payment channel, refund transactions, ownership transfer discounts, transaction amount, number of transactions, and sales status.

[0067] For example, if the transaction volume to be predicted is the transaction volume for the quarter following today, then the historical transaction details for the same period in the quarter following today are obtained. That is, the transaction details for the same quarter in previous years of this year.

[0068] S302. Obtain historical fluctuation transaction details for the period when the transaction fluctuation of the item owner exceeds the threshold.

[0069] The periods during which transaction fluctuations exceed a threshold are considered periods of significant impact from transaction fluctuations. Historical transaction details for these periods, particularly those affecting the item's owner, are obtained. For example, periods of transaction fluctuations exceeding the threshold can be identified by factors such as the source of the transaction, whether it is concentrated in a short period, the amount involved, and the behavior of the item acquirer.

[0070] For example, if the fluctuation in the transfer of ownership of an item increases due to the discount on the transfer of ownership of the item during a period prior to the current day, then the historical fluctuation transaction details data for the period in which the transaction fluctuation of the item's owner exceeds the threshold are obtained.

[0071] Because the transfer of ownership of goods is highly random, in one implementation, only the transaction details of the same period in history can be obtained, without obtaining the transaction details of historical fluctuations.

[0072] S303. Split the first historical transaction details data according to the first preset time period.

[0073] The statistical time for different dimensions of information in the first historical transaction details data can be different statistical time units, so the first historical transaction details data can be split according to the first preset time period, thereby increasing the accuracy of the parameters representing the fluctuation degree of information in different dimensions.

[0074] For example, the first preset time period may include a single calendar day, multiple calendar days, or a single business day.

[0075] S304. Obtain the evaluation index values ​​of the first historical transaction details data within each first preset time period to form an attribute sample set.

[0076] After splitting the first historical transaction details data according to the first preset time period, the fluctuation degree characterization parameter is calculated based on the first historical transaction details data of multiple item owners under the same dimension. Then, an attribute sample set is formed based on the information of different dimensions in the first historical transaction details data and the fluctuation degree characterization parameter corresponding to the information of that dimension.

[0077] The evaluation index values ​​for the first historical transaction details data include parameters representing the degree of volatility. Multiple evaluation index values ​​for the first historical transaction details data within each first preset time period can be obtained, and then these multiple evaluation index values ​​can be merged together to form a single merged evaluation index value.

[0078] For example, several evaluation index values ​​are obtained for each first preset time period.

[0079] S305. Based on the attribute sample set, perform spectral clustering to obtain the clustering results.

[0080] S306. Based on the clustering results, adjust the payment limit for the item owner.

[0081] In this embodiment of the invention, historical transaction details for the same period and historical fluctuation transaction details for periods when transaction fluctuations exceed a threshold are obtained for the predicted transaction amount of the item owner. Data mining is then performed to analyze the historical data fluctuations of the item owner and to formulate a reasonable payment limit for the item owner.

[0082] Figure 4 This is a flowchart illustrating another method for limiting the amount of payment received by the owner of goods according to an embodiment of the present invention. This embodiment further optimizes the method for limiting the amount of payment received by the owner of goods based on the above embodiment. Accordingly, refer to... Figure 4 The method includes:

[0083] S401. Obtain the first historical transaction details of the item's owner.

[0084] S402. Preprocess the first historical transaction details data to obtain the preprocessed data.

[0085] S403. Based on the preprocessed data, perform spectral clustering to obtain the clustering results.

[0086] S404. Based on the anti-fraud model, heterogeneous data in the first historical transaction details are removed to form a corrected clustering result.

[0087] Qualitative data refers to transaction details resulting from sudden events, such as fraud or money laundering incidents. Heterogeneous data is characterized by its suddenness. Anti-fraud models are used to identify fraudulent activities including transaction fraud, online fraud, telephone fraud, and card / account theft. Anti-fraud models can identify fraudulent customers, and the transaction details resulting from such fraudulent transactions constitute heterogeneous data.

[0088] S405. Based on the clustering results, establish a prediction model based on knowledge reasoning.

[0089] Knowledge reasoning refers to the process of simulating human intelligent reasoning in computer or intelligent systems, and using formalized knowledge to perform machine thinking and solve problems based on reasoning control strategies.

[0090] This step may also include training the established prediction model and / or verifying the accuracy of the established prediction model. For example, the accuracy of the prediction model can be calculated by verifying the actual values ​​and predicted values ​​through regression.

[0091] S406. Obtain the second historical transaction details of the item owner for past time periods of the current day.

[0092] The second historical transaction details may or may not be included within the first historical transaction details. The size of the second historical transaction details may be smaller than that of the first historical transaction details.

[0093] The second set of historical transaction details includes historical transaction details for a selected period of time prior to the current day, week, or month, such as historical transaction details for a recent period prior to the current day.

[0094] S407. Input the second historical transaction details into the prediction model to obtain the predicted transaction amount corresponding to the transaction amount to be predicted.

[0095] The predictive model is used to predict future development trends based on historical data, thereby obtaining the predicted transaction amount for the time period in which the transaction amount to be predicted falls based on the input second historical transaction details data.

[0096] S408. Based on the predicted transaction amount and the historical transaction details data corresponding to the transaction amount to be predicted, obtain the risk coefficient of the item owner.

[0097] In this step, the predicted transaction amount is compared with the transaction amount in the historical transaction details data corresponding to the transaction amount to be predicted, in order to obtain the risk coefficient of the item owner.

[0098] For example, when the predicted transaction amount differs significantly from the transaction amount in the historical transaction details data corresponding to the transaction amount to be predicted, the risk coefficient of the owner of the goods is high; when the predicted transaction amount differs slightly from the transaction amount in the historical transaction details data corresponding to the transaction amount to be predicted, the risk coefficient of the owner of the goods is low.

[0099] For example, if there is a significant increase in transaction volume at a particular counter outside of peak sales seasons with cyclical fluctuations, this abnormal behavior carries a higher risk factor. Abnormal behavior could include, for instance, fraudulent order placement.

[0100] S409. When the risk coefficient is within the preset risk range, reduce the payment limit for the owner of the goods.

[0101] For example, the greater the difference between the predicted transaction amount and the transaction amount in the historical transaction details data corresponding to the transaction amount to be predicted, the greater the risk coefficient of the item owner. Therefore, it can be stipulated that when the risk coefficient is greater than a preset risk range, the payment limit for abnormal item owners should be reduced.

[0102] S410. When the risk factor exceeds the preset risk range, the payment limit for the owner of the goods shall not be reduced.

[0103] In this step, the payment limit for the party to whom the goods belong will not be lowered if the risk factor is not within the preset risk range. That is, the payment limit for the normal party to whom the goods belong will not be lowered.

[0104] In this embodiment of the invention, by eliminating heterogeneous data and correcting the clustering results, the impact of heterogeneous data on the prediction model can be avoided, thus improving the stability of the prediction model. It also predicts the recent payment situation of the item's owner and sets reasonable payment limits for them. While mitigating related financial risks, it optimizes the payment experience for the item's owner and improves the digital operational capabilities of the governing body.

[0105] This invention also provides a device for setting a payment limit for the owner of an item. Figure 5 This is a schematic diagram of a device for setting a payment limit for the owner of an item, provided in an embodiment of the present invention. (Refer to...) Figure 5The device includes a first historical transaction detail data acquisition module 110, a preprocessed data acquisition module 120, a clustering result acquisition module 130, and a payment limit adjustment module 140. The first historical transaction detail data acquisition module 110 acquires the first historical transaction detail data of the item's owner. The preprocessed data acquisition module 120 preprocesses the first historical transaction detail data to obtain preprocessed data. The clustering result acquisition module 130 performs spectral clustering based on the preprocessed data to obtain clustering results. The payment limit adjustment module 140 adjusts the payment limit of the item's owner based on the clustering results.

[0106] The device based on the payment limit of the item owner provided in the embodiments of the present invention can execute the method of payment limit of the item owner provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0107] This invention also provides an electronic device for limiting the amount a party can receive payment for an item. Figure 6 This is a block diagram of an electronic device provided in an embodiment of the present invention. Figure 6 The electronic device 60 shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. Figure 6 As shown, the electronic device 60 is presented in the form of a general-purpose computing device. The components of the electronic device 60 may include, but are not limited to: one or more processors 601, system memory 602, and bus 603 connecting different system components (including system memory 602 and processor 601).

[0108] Bus 603 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0109] Electronic device 60 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 60, including volatile and non-volatile media, removable and non-removable media.

[0110] System memory 602 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 604 and / or cache memory 605. Electronic device 60 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 606 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 603 via one or more data media interfaces. System memory 602 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0111] A program / utility 608 having a set (at least one) of program modules 607 may be stored, for example, in system memory 602. Such program modules 607 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 607 typically perform the functions and / or methods described in the embodiments of the present invention.

[0112] Electronic device 60 can also communicate with one or more external devices 609 (e.g., keyboard, pointing device, display 610, etc.), and with one or more devices that enable user interaction with the device, and / or with any device that enables electronic device 60 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 611. Furthermore, electronic device 60 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 612. Figure 6 As shown, network adapter 612 communicates with other modules of electronic device 60 via bus 603. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with electronic device 60, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0113] The processor 601 executes various functional applications and data processing by running programs stored in the system memory 602, such as implementing the method for limiting the amount of money received by the owner of the item provided in the embodiments of the present invention.

[0114] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, can implement the method for limiting the amount of payment received by the owner of the goods as described in the above embodiments.

[0115] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0116] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0117] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0118] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0119] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the method for limiting the amount of money received by the owner of goods as provided in any embodiment of this application.

[0120] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0121] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for limiting the amount of payment received by the owner of goods, characterized in that, include: Obtain the first historical transaction details of the party to whom the item belongs; The first historical transaction details data is preprocessed to obtain preprocessed data; Based on the preprocessed data, spectral clustering is performed to obtain the clustering results; Based on the clustering results, adjust the payment limit for the party to whom the item belongs; The step of performing spectral clustering to obtain clustering results based on the preprocessed data includes: Extract the feature elements that have a significant impact on transaction fluctuations from the preprocessed data; the feature elements include item acquisition behavior elements and item ownership transfer elements; The aforementioned feature elements are linked in a graph to form a tree diagram; the tree diagram is used to describe the data classification process. The n elements in the tree diagram are considered as n classes. The two classes with the most similar properties or the greatest degree of similarity are merged into a new class, resulting in n-1 classes. From the n-1 classes, the two classes with the most similar properties or the greatest degree of similarity are merged into a new class, resulting in n-2 classes; Repeat the above merging process until all elements are in one category; The method of merging two classes with the most similar properties or the highest degree of similarity into a new class includes: The longest distance method is used to merge two classes with the most similar properties or the greatest degree of similarity into a new class; Among them, the longest distance method refers to using the longest distance between elements in two classes to represent the distance between classes, and then using the smallest distance to merge the two classes into a new class.

2. The method according to claim 1, characterized in that, Obtain the first historical transaction details of the party to whom the item belongs, including: Obtain historical transaction details for the same period corresponding to the predicted transaction amount of the item's owner.

3. The method according to claim 2, characterized in that, Obtaining the first historical transaction details of the owner of the item also includes: Obtain historical fluctuation transaction details for the period during which the transaction fluctuation of the owner of the item exceeds the threshold.

4. The method according to claim 1, characterized in that, The first historical transaction details data are preprocessed to obtain preprocessed data, including: The first historical transaction details data is split according to the first preset time period; Obtain the evaluation index values ​​of the first historical transaction details data within each first preset time period to form an attribute sample set.

5. The method according to claim 1, characterized in that, Before adjusting the payment limit for the item's owner based on the clustering results, the method further includes: Based on the anti-fraud model, heterogeneous data in the first historical transaction details are removed to form a corrected clustering result.

6. The method according to claim 1, characterized in that, Based on the clustering results, adjust the payment limit for the item's owner, including: Based on the clustering results, a prediction model is established using knowledge reasoning. Obtain the second historical transaction details of the item's owner for the past period of the day; Input the second historical transaction details into the prediction model to obtain the predicted transaction amount corresponding to the transaction amount to be predicted. Based on the predicted transaction amount, the payment limit for the party to whom the item belongs is determined.

7. The method according to claim 6, characterized in that, Based on the predicted transaction amount, determine the payment limit for the party to whom the goods belong, including: Based on the predicted transaction amount and the historical transaction details data corresponding to the transaction amount to be predicted, the risk coefficient of the owner of the item is obtained. When the risk coefficient is within a preset risk range, the payment limit for the owner of the item is reduced.

8. A device for limiting the amount of payment received by the owner of an item, characterized in that, include: The first historical transaction details data acquisition module is used to acquire the first historical transaction details data of the owner of the item; The preprocessed data acquisition module is used to preprocess the first historical transaction details data to obtain preprocessed data; The clustering result acquisition module is used to perform spectral clustering to obtain clustering results based on the preprocessed data; The payment limit adjustment module is used to adjust the payment limit of the item owner based on the clustering results. The clustering result acquisition module is specifically used to extract the feature elements that have a significant impact on transaction fluctuations from the preprocessed data; the feature elements include item acquisition behavior elements and item ownership migration elements; the feature elements are associated in the form of a graph to form a tree diagram; the tree diagram is used to describe the data classification process; Consider the n elements in the tree diagram as n classes. Merge the two classes with the most similar properties or the highest degree of similarity into a new class, resulting in class n-1. From class n-1, merge the two classes with the most similar properties or the highest degree of similarity into a new class, resulting in class n-2. Repeat the above merging process until all elements are in one class. The method of merging two classes with the most similar properties or the greatest degree of similarity into a new class includes: using the longest distance method to merge two classes with the most similar properties or the greatest degree of similarity into a new class; wherein, the longest distance method refers to using the longest distance between each element in the two classes to represent the distance between the classes, and then using the smallest distance to merge the two classes into a new class.

9. An electronic device for limiting the amount of money a party can receive from the owner of an item, characterized in that, The invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements a method for the item owner receiving payment limit as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the method for limiting the amount of payment to the owner of the goods as described in any one of claims 1-7.

11. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method for limiting the amount of payment to the owner of the goods as described in any one of claims 1-7.

Images