Method and device for determining whether resource flow has risk

Abstract

The embodiment of the present invention provides a method and device for determining whether a resource flow direction has a risk, including: obtaining resource records within a historical time range to obtain a resource record set; constructing a resource flow direction network according to each resource record in the resource record set; determining a target resource flow direction in the resource flow direction network, and determining a risk value of the target resource flow direction; determining whether the target resource flow direction has a risk according to the risk value. The present invention solves the problem of risk misreporting caused by the inability to accurately identify risk points in related technologies, thereby achieving the effect of improving the accuracy of risk identification.

Description

Technical Field

[0001] The embodiments of the present invention relate to the computer field, and in particular, to a method and device for determining whether there is a risk in resource flow. Background Art

[0002] With the development of financial technology, financial institutions are facing more challenges in risk prevention and control, especially in quickly and accurately identifying potential risk points in massive data and generating detailed investigation conclusion reports. Traditional manual investigation methods often rely on preset rules and static indicators, lacking sufficient adaptability and flexibility in identifying complex and changeable risk characteristics, and are difficult to accurately identify risk points hidden in large amounts of data, resulting in the omission of important risk points, leading to underreporting and false reporting of risks, affecting the accuracy and efficiency of investigation. Moreover, risk identification through manual review is time-consuming and inefficient, and is difficult to meet the needs of the current financial industry.

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

[0004] The embodiments of the present invention provide a method and device for determining whether there is a risk in resource flow, so as to at least solve the problem in the related art that the risk point cannot be accurately identified, resulting in risk misreporting.

[0005] According to one embodiment of the present invention, a method for determining whether a resource flow is at risk is provided, comprising: acquiring resource records within a historical time range to obtain a resource record set; constructing a resource flow network based on each resource record in the resource record set; determining a target resource flow in the resource flow network, and determining a risk value of the target resource flow; and determining whether the target resource flow is at risk based on the risk value.

[0006] In an exemplary embodiment, determining the risk value of the target resource flow includes: determining a resource record of the target resource flow in the resource record set to obtain a target resource record; determining a risk characteristic of the target resource flow based on the target resource record; and determining the risk value of the target resource flow based on the risk characteristic.

[0007] In an exemplary embodiment, the risk characteristics of the target resource flow are determined based on the target resource record, including: determining the target resource amount, the target resource outflow party, the target resource inflow party, and the resource flow time of the target resource flow in the target resource record; generating an inquiry text based on the target resource amount, the resource outflow party, the resource inflow party, and the resource flow time; and determining the risk characteristics of the target resource flow through the inquiry text.

[0008] In an exemplary embodiment, the risk characteristics of the target resource flow are determined through the inquiry text, including: collecting voice information of the target resource outflow party through the inquiry text; converting the voice information into text to obtain text information; inputting the text information into a preset model to extract risk characteristics to obtain the risk characteristics of the target resource flow.

[0009] In an exemplary embodiment, the target resource flow satisfies at least one of the following conditions: the resource flow time is within a first preset time range; the target resource quantity is greater than or equal to a preset resource quantity threshold; within a second preset time range, the number of resource flows between the target resource outflow and the target resource inflow is greater than or equal to a preset quantity threshold.

[0010] In an exemplary embodiment, a resource flow network is constructed based on each of the resource records in the resource record set, including: determining a first resource quantity, a first resource outflow party, and a first resource inflow party in a first resource record, wherein the first resource record is any resource record in the resource record set; constructing a first resource flow direction of the first resource record based on the first resource quantity, the first resource outflow party, and the first resource inflow party, wherein the resource flow network includes multiple resource flows, the multiple resource flows include the first resource flow, the first resource outflow party is the starting point of the first resource flow, the first resource inflow party is the end point of the first resource flow, and the first resource quantity is the resource quantity flowing between the first resource outflow party and the first resource inflow party.

[0011] According to another embodiment of the present invention, there is provided a device for determining whether a resource flow is at risk, comprising: an acquisition module for acquiring resource records within a historical time range to obtain a resource record set; a construction module for constructing a resource flow network according to each resource record in the resource record set; a first determination module for determining a target resource flow in the resource flow network and determining a risk value of the target resource flow; and a second determination module for determining whether the target resource flow is at risk according to the risk value.

[0012] According to yet another embodiment of the present invention, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program implements the steps of any of the above methods when executed by a processor.

[0013] According to yet another embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0014] According to yet another embodiment of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0015] Through the present invention, all resource records within the historical time range are obtained, and a resource flow network is constructed based on each resource record, so as to determine the target resource flow and the risk value of the target resource flow in the resource flow network, and determine whether the target resource flow has risks based on the risk value.

[0016] By outlining the complete resource chain and clearly showing the relationship between the time, amount and object of resource flow, it is possible to analyze and track the resource flow from a global perspective, identify risk points hidden in a large amount of data more efficiently, comprehensively and accurately, and reduce false positives and omissions. Therefore, it can solve the problem of false positives caused by the inability to accurately identify risk points in related technologies, and achieve the effect of improving the accuracy of risk identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a hardware structure block diagram of a mobile terminal according to a method for determining whether a resource flow has a risk according to an embodiment of the present invention;

[0018] Figure 2 is a flow chart of a method for determining whether a resource flow has a risk according to an embodiment of the present invention;

[0019] Figure 3 is a flow chart of risk identification according to an embodiment of the present invention;

[0020] Figure 4 It is a structural block diagram of an apparatus for determining whether a resource flow has a risk according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and in combination with the embodiments.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0023] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for determining whether a resource flow is at risk according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0024] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for determining whether there is a risk in the flow of resources in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0025] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0026] In this embodiment, a method for determining whether there is a risk in resource flow is provided, which runs on the above mobile terminal or network architecture. Figure 2 is a flow chart of a method for determining whether a resource flow has a risk according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0027] Step S202, obtaining resource records within a historical time range to obtain a resource record set;

[0028] The above-mentioned resource records may be the user's personal basic information, relevant transaction records, etc., wherein the user's personal basic information may be name, place of origin, age, work unit, etc., and the relevant transaction records may be account opening time, number of transactions, transaction amount, etc.; obtain all resource records within the bank or financial institution within the historical time range, that is, the personal basic information and relevant transaction records of all users, etc., to obtain a resource record set, wherein the specific historical time range can be set according to actual conditions, such as the past three months, the past six months, the past year, etc.

[0029] Step S204, constructing a resource flow network according to each of the resource records in the resource record set;

[0030] The resource flow network mentioned above may be a capital link network, wherein the network includes multiple capital links, each of which represents a transaction or capital flow; according to each resource record in the resource record set, the specific data in the resource record is cleaned and standardized, and a capital link network is constructed based on the processed data, thereby improving data quality by removing irrelevant information, filling missing values, detecting anomalies, and other steps, thereby ensuring the accuracy of subsequent data analysis.

[0031] Optionally, a resource flow network is constructed according to each resource record in the resource record set, including: determining a first resource quantity, a first resource outflow party, and a first resource inflow party in a first resource record, wherein the first resource record is any resource record in the resource record set; constructing a first resource flow direction of the first resource record according to the first resource quantity, the first resource outflow party, and the first resource inflow party, wherein the resource flow network includes multiple resource flows, the multiple resource flows include the first resource flow direction, the first resource outflow party is the starting point of the first resource flow, the first resource inflow party is the end point of the first resource flow, and the first resource quantity is the resource quantity flowing between the first resource outflow party and the first resource inflow party.

[0032] The above-mentioned first resource record can be any resource record in multiple resource records in a resource record set; the above-mentioned first resource quantity, first resource outflow party, and first resource inflow party can be multiple data recorded in the first resource record, wherein the first resource outflow party can be the party that outputs resources in the resource record, such as the sender of the transfer, etc., the first resource inflow party can be the party that receives resources in the resource record, such as the receiver of the transfer, etc., and the first resource quantity can be the specific resource quantity flowing between the resource output and receiving parties, such as the transfer amount, etc.; the first resource quantity, the first resource outflow party, and the first resource inflow party are determined in the first resource record, and based on the first resource quantity, the first resource outflow party, and the first resource inflow party, the first resource outflow party and the first resource inflow party are respectively used as two nodes, and the specific first resource quantity between the two is used as the connection between the nodes, thereby constructing a resource flow network.

[0033] By constructing a resource flow network (or capital link network), the resource flow of all users in the organization can be clearly displayed, which helps to better understand the source and destination of resources and their usage in different links. From a global perspective, the relationship between multiple resource flows can be deeply analyzed, and hidden resource flows between nodes can be identified. This allows for more efficient and comprehensive monitoring of suspicious resource flows, an outline of the complete suspicious resource flow process, and tracking of resource flows, effectively improving the efficiency and accuracy of identifying resource flow risks.

[0034] Optionally, for online transaction records, that is, online transfers or transactions between two accounts, personal accounts or corporate accounts, or actual controllers of corporate accounts can be used as nodes, and the actual transaction amount between the accounts can be used as the connection between the two nodes, thereby building a capital link network.

[0035] Optionally, for offline transactions, that is, two accounts make deposits and withdrawals separately, and realize fund circulation through offline currency transactions, a fund link between the two accounts can be established through the currency number on the currency (that is, each currency has its own number), thereby constructing a fund link network to avoid the break of the fund tracking chain caused by the lack of continuity of transactions due to the use of currency transactions.

[0036] Optionally, it is also possible to cooperate with other platforms or institutions to achieve information and data sharing, build a more complete capital chain network, make up for the chain breaks caused by data silos or data dispersion, improve the transparency and stability of the capital chain network, and improve the accuracy and comprehensiveness of capital chain risk identification.

[0037] Step S206, determining a target resource flow in the resource flow network, and determining a risk value of the target resource flow;

[0038] The above-mentioned target resource flow may be a resource flow that may be at risk, and the resource flow that may be at risk may be a resource flow with a large amount of resources flowing, or a resource flow with an unconventional resource flow time; the above-mentioned risk value may be a risk score of the resource flow, and the risk value may be used to determine the possibility of risk in the resource flow, wherein the risk value is correlated to the possibility of risk; the target resource flow that may be at risk is identified in the resource flow network, and the risk value of the target resource flow is determined, so as to finally determine whether the target resource flow is at risk based on the risk value, thereby realizing intelligent and automatic identification and tracking of the flow path of suspicious resources through in-depth analysis of the relationship between multiple transaction events, thereby increasing the accuracy and reliability of resource flow risk identification and ensuring the safety and stability of resource flows.

[0039] Optionally, the target resource flow satisfies at least one of the following conditions: the resource flow time is within a first preset time range; the target resource quantity is greater than or equal to a preset resource quantity threshold; within a second preset time range, the number of resource flows between the target resource outflow and the target resource inflow is greater than or equal to a preset quantity threshold.

[0040] The resource flow time mentioned above can be the actual occurrence time of the target resource flow, such as the time of transfer or transaction. When the resource flow time of the resource flow is within the first preset time range, it is determined that the resource flow may be at risk, that is, the target resource flow, wherein the first preset time range can be set according to actual conditions, such as non-routine activity times such as 2:00-4:00 in the morning; the target resource amount can be the specific amount of resources transferred by the target resource flow, such as the actual amount of transfer or transaction. When the actual amount of resources transferred by the resource flow is greater than or equal to the preset resource amount threshold, it is determined that the resource flow may be at risk. Risk, that is, the target resource flow, wherein the preset resource amount threshold can be set according to the actual situation, such as a larger resource amount such as 20w; the number of the above-mentioned resource flows can be the number of actual resource flows between the target resource outflow party and the target resource inflow party, such as the number of transfers or transactions between user A and user B. Within the second preset time range, if resource flows occur multiple times between the same account and there is a resource flow, it is determined that the resource flow between the two users may be at risk, that is, the target resource flow, wherein the second preset time range can be set according to the actual situation, such as 10 minutes, 30 minutes, 1 hour, etc.

[0041] Step S208: determining whether there is a risk in the flow of the target resource according to the risk value.

[0042] Optionally, when the risk value is greater than or equal to a preset threshold, it is determined that the target resource flow has a risk; otherwise, the target resource flow has no risk, wherein the preset threshold can be set according to actual conditions.

[0043] Optionally, the executor of the above steps may be a background processor, or other devices with similar processing capabilities, or a machine that integrates at least an image acquisition device and a data processing device, wherein the image acquisition device may include a graphics acquisition module such as a camera, and the data processing device may include a computer, a mobile phone or other terminal, but is not limited thereto.

[0044] Through the above steps, all resource records within the historical time range are obtained, and a resource flow network is constructed based on each resource record, so as to determine the target resource flow and the risk value of the target resource flow in the resource flow network, and determine whether the target resource flow is risky based on the risk value. By outlining the complete resource chain, the relationship between the time, resource volume and object of resource flow is clearly displayed, so as to analyze and track the resource flow from a global perspective, identify risk points hidden in a large amount of data more efficiently, comprehensively and accurately, and reduce false positives and omissions. In addition, by combining artificial intelligence technology to automatically and intelligently identify the flow of risk resources, it reduces dependence on human resources, improves work efficiency, and thus reduces overall operating costs. It solves the problem of risk false positives caused by the inability to accurately identify risk points in related technologies, and improves the accuracy and comprehensiveness of risk identification.

[0045] As an optional implementation, determining the risk value of the target resource flow includes: determining the resource record of the target resource flow in the resource record set to obtain the target resource record; determining the risk characteristics of the target resource flow based on the target resource record; and determining the risk value of the target resource flow based on the risk characteristics.

[0046] The above-mentioned target resource record can be a resource record of the target resource flow; the above-mentioned risk feature can be a potential loss or threat in the resource flow, and the risk feature can help identify and manage potential risks in the resource flow; after identifying the target resource flow that may be risky in the resource flow network, the resource record of the target resource flow is determined in the resource record set, and the risk feature of the target resource flow is determined based on the resource record, so as to calculate the risk value of the target resource flow based on the risk feature, which is conducive to formulating corresponding risk management measures. At the same time, regularly evaluating and monitoring the risks of the target resource flow, and adjusting the risk management measures in time, help ensure the security and stability of the resource flow network.

[0047] As an optional implementation, the risk characteristics of the target resource flow are determined based on the target resource record, including: determining the target resource quantity, target resource outflow party, target resource inflow party, and resource flow time of the target resource flow in the target resource record; generating an inquiry text based on the target resource quantity, the resource outflow party, the resource inflow party, and the resource flow time; and determining the risk characteristics of the target resource flow through the inquiry text.

[0048] The target resource outflow party may be the party that outputs resources in the resource record, such as the sender of a transfer; the target resource inflow party may be the party that receives resources in the resource record, such as the recipient of a transfer; the target resource quantity may be the specific resource quantity transferred between the resource output and receiving parties, such as a transfer amount; the resource flow time may be the actual time when the resource flow occurs, such as a transfer time; the inquiry text may be a question text that simulates a manual telephone inquiry. Through the inquiry text, the system can automatically communicate with the user by phone based on the actual situation of the resource flow, and further confirm and understand the content in the resource record to ensure the accuracy and transparency of the resource flow; according to the specific content in the resource record corresponding to the target resource flow, the inquiry text is automatically generated to communicate with the user, thereby generating an accurate inquiry text without human intervention, avoiding the increase in errors and inconsistencies caused by different emphases and questioning methods during manual communication, and at the same time, eliminating the need for manual phone calls, greatly improving communication efficiency.

[0049] Optionally, the risk characteristics of the target resource flow are determined through the inquiry text, including: collecting voice information of the target resource outflow party through the inquiry text; converting the voice information into text to obtain text information; inputting the text information into a preset model to extract risk characteristics to obtain the risk characteristics of the target resource flow.

[0050] The language model is used to perform further natural language processing analysis on the collected conversation text (i.e., text information) to extract key risk features and potential abnormal behaviors, so that risks can be identified through these risk features without the need for a large amount of manpower. This ensures the accuracy and consistency of risk identification, reduces multiple interruptions to customers, and improves customer satisfaction.

[0051] As an optional implementation, Figure 3 is a flow chart of risk identification according to an embodiment of the present invention. Figure 3 As shown, the specific process is as follows:

[0052] S1, Data collection and compilation:

[0053] Collect and organize resource records within the historical time range, such as user personal information, transaction records, risk warnings and other data, to provide a basis for subsequent analysis. Data sources include but are not limited to user information stored in the database, online transaction records, etc.

[0054] S2, data preprocessing:

[0055] By removing irrelevant information, filling missing values, detecting anomalies and other steps, the original data (i.e., resource records) is cleaned and standardized to ensure the accuracy of data analysis and improve data quality.

[0056] S3, risk feature extraction:

[0057] S31, build a transaction network based on nodes and edges (i.e. resource flow network) to track the flow of funds (i.e. resource flow): by building a network between the "transaction subject" (i.e. the target resource outflow party) and the "transaction counterparty" (i.e. the target resource inflow party), each account (node) in the transaction chain (i.e. resource flow) and its corresponding transaction relationship (edge) are presented in a structured manner, thereby creating a complete transaction network. This helps financial institutions track the flow of funds from a global perspective, not only discovering current suspicious transactions, but also discovering hidden connection points and capital flow patterns in the transaction network.

[0058] In addition, the information of related persons and actual controllers (actual controllers) of corporate transactions can be extracted in an automated manner, and the transaction information can be linked together to avoid interruptions in the transaction chain due to different subject structures. For example, in some complex transaction records, funds may be secretly transferred through the flow of funds between personal accounts and corporate accounts. The model can capture these key connection points, track the complete flow of funds, and ensure the continuity of the transaction chain.

[0059] Optionally, the information of currency transactions can be further introduced, and currency-related transactions can be linked together by analyzing the serial numbers (currency unique identifiers) in cash withdrawal and deposit transactions, so as to avoid the break in the fund tracking chain caused by the lack of continuity of currency transactions in the monitoring system.

[0060] Alternatively, since the flow of funds in the financial system often involves transactions between multiple financial institutions or different banking platforms, the model can also use its powerful data integration capabilities to uniformly analyze scattered transaction data across multiple platforms, thereby identifying the complete capital chain (i.e., resource flow). For example, when a certain amount of funds is transferred between different banks, the model can obtain relevant transaction information from the interbank transaction interface, or integrate all the involved capital flows through transaction data provided by the regulatory agency. This breaks through the limitations of traditional monitoring systems, especially when the capital chain is long, and makes up for the chain breaks that may be caused by data islands or data dispersion in traditional tracking methods, and realizes comprehensive tracking of complex capital flows.

[0061] S32, using the pattern recognition capability of the large language model to monitor suspicious capital chains (i.e. resource flows) and outline the complete suspicious transaction data chain (i.e. resource flow network);

[0062] Optionally, by analyzing the relationship between the time (i.e., resource flow time), amount (i.e., target resource volume) and transaction objects (i.e., target resource outflow party, target resource inflow party) of multiple transactions, suspicious capital chains can be identified: by analyzing the time intervals between multiple transaction events, the size of the transaction amounts, and the relationship between the related transaction objects, it is possible to identify whether there is a related capital chain. For example, when multiple accounts transfer similar amounts in a short period of time, the model can identify whether these transactions are related to each other and whether there is a hidden capital flow network between these accounts. If these accounts have some connection with each other, the model can quickly outline the transaction network behind this chain.

[0063] S33 automatically identifies all suspicious transactions of customers (i.e. the flow of target resources) and generates accurate inquiry texts without human intervention. The inquiry content is based on the transaction background and transaction rules, ensuring the uniformity and professionalism of each inquiry and avoiding problems caused by human subjective differences. Subsequently, the system can initiate inquiries to customers through speech synthesis and automatic dialing technology, and when communicating with customers, it uses speech recognition technology to convert the conversation content into text records in real time, eliminating the need for manual dialing and greatly improving communication efficiency.

[0064] S34, further natural language processing analysis is performed on the collected conversation text to extract key risk features and potential abnormal behaviors.

[0065] S4, Risk Assessment:

[0066] Based on risk characteristics, a large language model is used for deep learning to quantitatively assess the degree of risk. The probability and impact of risk occurrence are learned in combination with historical cases to generate risk scores.

[0067] S5, report automatic generation:

[0068] Integrate risk assessment results and generate a clear and detailed risk investigation conclusion report through a large language model, including basic customer information, risk point overview, risk level and recommended measures.

[0069] S6, Decision Support:

[0070] Based on the generated risk reports, an intuitive visual interface is provided to assist decision makers in quickly formulating response strategies, and an early warning mechanism can be triggered based on the risk situation.

[0071] S7, output results.

[0072] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0073] In this embodiment, a device for determining whether there is a risk in the flow of resources is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0074] Figure 4 is a structural block diagram of an apparatus for determining whether a resource flow has a risk according to an embodiment of the present invention. Figure 4 As shown, the device includes: an acquisition module 402, used to acquire resource records within a historical time range to obtain a resource record set; a construction module 404, used to construct a resource flow network according to each resource record in the resource record set; a first determination module 406, used to determine the target resource flow in the resource flow network, and determine the risk value of the target resource flow; a second determination module 408, used to determine whether the target resource flow has a risk according to the risk value.

[0075] In an exemplary embodiment, the device is also used to determine the resource record of the target resource flow in the resource record set to obtain the target resource record; determine the risk characteristics of the target resource flow based on the target resource record; and determine the risk value of the target resource flow based on the risk characteristics.

[0076] In an exemplary embodiment, the device is also used to determine the target resource quantity, target resource outflow party, target resource inflow party, and resource flow time of the target resource flow in the target resource record; generate an inquiry text based on the target resource quantity, the resource outflow party, the resource inflow party, and the resource flow time; and determine the risk characteristics of the target resource flow through the inquiry text.

[0077] In an exemplary embodiment, the device is also used to collect voice information of the target resource outflow party through the inquiry text; convert the voice information into text to obtain text information; input the text information into a preset model to extract risk characteristics to obtain the risk characteristics of the target resource flow.

[0078] In an exemplary embodiment, the target resource flow satisfies at least one of the following conditions: the resource flow time is within a first preset time range; the target resource quantity is greater than or equal to a preset resource quantity threshold; within a second preset time range, the number of resource flows between the target resource outflow and the target resource inflow is greater than or equal to a preset quantity threshold.

[0079] In an exemplary embodiment, the device is also used to determine a first resource quantity, a first resource outflow party, and a first resource inflow party in a first resource record, wherein the first resource record is any resource record in the resource record set; based on the first resource quantity, the first resource outflow party, and the first resource inflow party, a first resource flow direction of the first resource record is constructed, wherein the resource flow direction network includes multiple resource flows, the multiple resource flows include the first resource flow direction, the first resource outflow party is the starting point of the first resource flow, the first resource inflow party is the end point of the first resource flow, and the first resource quantity is the resource quantity flowing between the first resource outflow party and the first resource inflow party.

[0080] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0081] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0082] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0083] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0084] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0085] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the steps of the method described in each embodiment of the present application when executed by a processor.

[0086] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0087] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0088] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for determining whether there is a risk in the flow of resources, characterized in that: include: Get resource records within the historical time range and obtain a resource record set; Constructing a resource flow network according to each of the resource records in the resource record set; Determining a target resource flow in the resource flow network, and determining a risk value of the target resource flow; Determine whether the target resource flow has a risk based on the risk value.

2. The method according to claim 1, characterized in that Determine the risk value of the target resource flow, including: Determine the resource record of the target resource flow direction in the resource record set to obtain the target resource record; Determining risk characteristics of the target resource flow according to the target resource record; A risk value of the target resource flow is determined based on the risk characteristics.

3. The method according to claim 2, characterized in that Determining the risk characteristics of the target resource flow according to the target resource record includes: Determining the target resource amount, the target resource outflow party, the target resource inflow party, and the resource flow time of the target resource flow direction in the target resource record; Generate an inquiry text according to the target resource amount, the resource outflow party, the resource inflow party, and the resource flow time; The risk characteristics of the target resource flow are determined through the query text.

4. The method according to claim 3, characterized in that Determine the risk characteristics of the target resource flow through the query text, including: Collecting voice information of the target resource outflow party through the inquiry text; Converting the voice information into text to obtain text information; The text information is input into a preset model to extract risk features, thereby obtaining risk features of the target resource flow.

5. The method according to claim 3, characterized in that: The target resource flow direction satisfies at least one of the following conditions: The resource transfer time is within a first preset time range; The target resource amount is greater than or equal to a preset resource amount threshold; Within a second preset time range, the number of resource flows between the target resource outflow party and the target resource inflow party is greater than or equal to a preset number threshold.

6. The method according to claim 1, characterized in that Constructing a resource flow network according to each of the resource records in the resource record set, including: Determine a first resource amount, a first resource outflow party, and a first resource inflow party in a first resource record, wherein the first resource record is any resource record in the resource record set; A first resource flow of the first resource record is constructed according to the first resource quantity, the first resource outflow party, and the first resource inflow party, wherein the resource flow network includes multiple resource flows, the multiple resource flows include the first resource flow, the first resource outflow party is the starting point of the first resource flow, the first resource inflow party is the end point of the first resource flow, and the first resource quantity is the resource quantity flowing between the first resource outflow party and the first resource inflow party.

7. A device for determining whether there is a risk in the flow of resources, characterized in that: include: The acquisition module is used to acquire resource records within a historical time range and obtain a resource record set; A construction module, used for constructing a resource flow network according to each resource record in the resource record set; A first determination module, configured to determine a target resource flow in the resource flow network, and determine a risk value of the target resource flow; The second determination module is used to determine whether there is a risk in the flow of the target resource according to the risk value.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 6 when executed by a processor.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

Images