Account identification method and device, storage medium and electronic equipment

Abstract

The invention discloses an account identification method and device, a storage medium and electronic equipment. The method comprises the steps that a serial number identifier, requested to be processed by a target account, of a to-be-recognized object is acquired, the serial number identifier is used for indicating the printing batch of the to-be-recognized object, and the serial number identifier is the unique identity identifier of the to-be-recognized object; according to the serial number identifier, determining a transaction path and a serial number overlap ratio of the object to be identified, the serial number overlap ratio being used for indicating a probability that different accounts use the same object to be identified; determining an account which satisfies a preset relationship with the target account in the transaction path as an associated account; and inputting the serial number overlap ratio and the transaction flow data into a target identification model to obtain a risk level of the associated account, the target identification model being obtained by training sample transaction flow data corresponding to a sample account with a high risk level in advance. According to the method and the device, the technical problem of relatively low identification accuracy of the risk account is solved.

Description

Technical Field

[0001] The present application relates to the field of computers, and more specifically, to an account identification method and device, a storage medium, and an electronic device. Background Art

[0002] In related technologies, item transactions have become a major challenge in identifying risky accounts due to the lack of effective digital tracking methods. Traditional risk assessment methods often rely on information such as transaction amount, frequency and time. However, since transaction data is very limited, when it comes to complex item transactions between multiple accounts, it is difficult to accurately capture abnormal behavior patterns based on the above information alone, resulting in a low accuracy rate in identifying risky accounts.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide an account identification method and device, a storage medium, and an electronic device to at least solve the technical problem of low identification accuracy of risky accounts.

[0005] According to one aspect of an embodiment of the present application, there is provided an account identification method, comprising: obtaining a crown number identifier of an object to be identified that is requested to be processed by a target account, wherein the crown number identifier is used to indicate a printing batch of the object to be identified, and the crown number identifier is a unique identity identifier of the object to be identified; determining a transaction path and a crown number overlap of the object to be identified based on the crown number identifier, wherein the crown number overlap is used to indicate a probability of using the same object to be identified between different accounts; determining an account in the transaction path that satisfies a preset relationship with the target account as an associated account; inputting the crown number overlap and transaction flow data into a target identification model to obtain a risk level of the associated account, wherein the target identification model is pre-trained with sample transaction flow data corresponding to sample accounts with high risk levels.

[0006] According to another aspect of an embodiment of the present application, an account identification device is also provided, including: an acquisition module, used to obtain a crown number identifier of an object to be identified that is requested to be processed by a target account, wherein the crown number identifier is used to indicate a printing batch of the object to be identified, and the crown number identifier is a unique identity identifier of the object to be identified; a first determination module, used to determine a transaction path and a crown number overlap of the object to be identified based on the crown number identifier, wherein the crown number overlap is used to indicate a probability of using the same object to be identified between different accounts; a second determination module, used to determine an account in the transaction path that satisfies a preset relationship with the target account as an associated account; an identification module, used to input the crown number overlap and transaction flow data into a target recognition model to obtain a risk level of the associated account, wherein the target recognition model is pre-trained with sample transaction flow data corresponding to sample accounts with high risk levels.

[0007] Optionally, the device is used to determine the transaction path and the degree of overlap of the serial number of the object to be identified according to the serial number identifier in the following manner: determine the source account of the object to be identified according to the serial number identifier; obtain first transaction data of the source account when using the object to be identified to conduct a transaction, and obtain second transaction data indicated by the transaction flow data of the target account; determine the ratio of the first transaction data to the second transaction data as the degree of overlap of the serial number.

[0008] Optionally, the device is used to determine the transaction path of the object to be identified according to the serial number identifier in the following manner: determine the transaction record according to the serial number identifier; determine a group of accounts that use the object to be identified for transactions, and transaction flow data between the accounts according to the transaction record, wherein the group of accounts includes the target account, and the transaction flow data is used to indicate the flow order and flow time of the object to be identified; generate the transaction path according to the group of accounts and the transaction flow data.

[0009] Optionally, the device is used to determine an account in the transaction path that satisfies a preset relationship with the target account as an associated account in the following manner: when the object to be identified flows from the first account to the target account, the first account is determined as the associated account; when the object to be identified flows from the target account to the second account, the second account is determined as the associated account.

[0010] Optionally, the device is also used for: in response to the target account acquiring the object to be identified for the first transaction from a cash machine or a counter, determining the target account as the starting account in the transaction path, wherein the object to be identified has not been acquired by other accounts before being acquired by the target account; determining M accounts after the starting account in the transaction path as the second account, wherein M is a positive integer and the value of M is related to the current transaction time of the object to be identified.

[0011] Optionally, the device is also used to: in response to the target account obtaining the object to be identified which is not the first transaction from other accounts and requesting to deposit the object to be identified, determine the target account as an intermediate account in the transaction path; determine N accounts before the intermediate account in the transaction path as the first account, wherein N is a positive integer and the value of N is related to the current transaction time of the object to be identified.

[0012] Optionally, the device is used to input the serial number overlap and the transaction flow data of the associated account into a target recognition model to determine the risk level of the associated account in the following manner: determine the transaction time, transaction frequency and transaction amount of the object to be identified based on the transaction flow data of the associated account; input the serial number overlap, the transaction time, the transaction frequency and the transaction amount into the target recognition model to determine the risk level.

[0013] Optionally, the device is also used to: obtain the serial number identification; determine the source account of the object to be identified according to the serial number identification; obtain first transaction data of the source account when using the object to be identified to conduct transactions, and obtain second transaction data indicated by the transaction flow data of the target account; determine the ratio of the first transaction data to the second transaction data as the serial number overlap, wherein the serial number overlap is used to indicate the probability of using the same object to be identified between different accounts; determine transaction records according to the serial number identification, and determine a group of accounts that use the object to be identified to conduct transactions and transaction flow data between the accounts according to the transaction records; generate the transaction path according to the group of accounts and the transaction flow data; in response to the target account obtaining the object to be identified that is not the first transaction from other accounts and requesting to deposit the object to be identified, determine the target account as an intermediate account in the transaction path; determine N accounts that are before the intermediate account in the transaction path as a first account number, wherein N is a positive integer, and the value of N is related to the current transaction time of the object to be identified; in the case where the object to be identified is transferred from the first account number to the target account number, the first account number is determined as the associated account number; in response to the object to be identified obtaining the first transaction from the cash machine or the counter by the target account number, the target account number is determined as the starting account number in the transaction path; M accounts after the starting account number in the transaction path are determined as second accounts, wherein M is a positive integer, and the value of M is related to the current transaction time of the object to be identified; in the case where the object to be identified is transferred from the target account number to the second account number, the second account number is determined as the associated account number; the transaction time, transaction frequency and transaction amount of the object to be identified are determined based on the transaction flow data of the associated account number; the overlap degree of the serial number, the transaction time, the transaction frequency and the transaction amount are input into the target recognition model to determine the risk level of the associated account number.

[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned account identification method when running.

[0015] According to another aspect of the embodiments of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the above account identification method.

[0016] According to another aspect of the embodiments of the present application, there is further provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the account identification method through the computer program.

[0017] In an embodiment of the present application, a target account is requested to obtain a serial number identifier of an object to be identified, wherein the serial number identifier is used to indicate a printing batch of the object to be identified, and the serial number identifier is a unique identity identifier of the object to be identified; a transaction path and a serial number overlap of the object to be identified are determined based on the serial number identifier, wherein the serial number overlap is used to indicate the probability of using the same object to be identified between different accounts; an account in the transaction path that satisfies a preset relationship with the target account is determined as an associated account; the serial number overlap and the transaction flow data are input into a target recognition model to obtain a risk level of the associated account, wherein the target recognition model is pre-trained with sample transaction flow data corresponding to sample accounts with high risk levels, thereby achieving the purpose of improving the accuracy of risk account identification, thereby achieving a more accurate risk assessment and early warning technical effect, and further solving the technical problem of low risk account identification accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a schematic diagram of an application environment of an optional account identification method according to an embodiment of the present application;

[0020] Figure 2 is a flowchart of an optional account identification method according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of an optional account identification method according to an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of the structure of an optional account identification device according to an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of the structure of an optional account identification product according to an embodiment of the present application;

[0024] Figure 6 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] The present application is described below in conjunction with embodiments:

[0028] According to one aspect of an embodiment of the present application, an account identification method is provided. Optionally, in this embodiment, the account identification method can be applied to Figure 1 In the hardware environment composed of the server 101 and the terminal device 103 shown in FIG. Figure 1As shown, the server 101 is connected to the terminal 103 via a network, and can be used to provide services for the terminal device or an application 107 installed on the terminal device. The application can be a video application, an instant messaging application, a browser application, an educational application, a game application, etc. A database 105 may be set up on the server or independently of the server to provide data storage services for the server 101, for example, a game data storage server. The above-mentioned network may include, but is not limited to, a wired network and a wireless network, wherein the wired network includes, for example, a local area network, a metropolitan area network, and a wide area network; the wireless network includes, for example, Bluetooth, WIFI, and other networks that implement wireless communication; the terminal device 103 may be a terminal configured with an application program, and may include, but is not limited to, at least one of the following: a mobile phone (such as an Android phone, an iOS phone, etc.), a laptop computer, a tablet computer, a PDA, a MID (Mobile Internet Devices), a PAD, a desktop computer, a smart TV, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, an aircraft, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a mixed reality (MR) terminal, and other computer devices; the above-mentioned server may be a single server, a server cluster consisting of multiple servers, or a cloud server.

[0029] Combination Figure 1 As shown, the above account identification method can be executed by an electronic device, which can be a terminal device or a server. The above account identification method can be implemented by the terminal device or the server respectively, or by the terminal device and the server together.

[0030] The above is only an example and is not specifically limited in this embodiment.

[0031] Optionally, as an optional implementation, as Figure 2 As shown, the above account identification method includes:

[0032] S202, obtaining a serial number identifier of the object to be identified that the target account requests to process, wherein the serial number identifier is used to indicate a printing batch of the object to be identified, and the serial number identifier is a unique identity identifier of the object to be identified;

[0033] Optionally, in the embodiment of the present application, the process of obtaining the serial number identification of the object to be identified requested by the target account refers to the system automatically reading and recording the serial number on each currency in the cash transaction conducted from the target account to track the circulation history and source information of the currency. The serial number identification is a unique code assigned by the printing factory to each batch of currency. It not only contains detailed information about the printing batch, but also can serve as a unique identity identification for each currency, ensuring that in a large-scale cash circulation environment, the circulation path and transaction records of each currency can be accurately tracked, including but not limited to automatic collection of serial number data through cash processing equipment (such as ATM machines, cash counting machines, etc.), or manual input of serial numbers into the system by bank staff when handling cash, to ensure the comprehensiveness and accuracy of the data.

[0034] It should be noted that the method for obtaining the serial number identification of the object to be identified requested by the target account can be diverse, which can be automatic reading through cash processing equipment, manual entry during manual operation, or indirect acquisition through the serial number data interface provided by a third-party organization.

[0035] In addition, there are many possibilities for storing and managing the serial number identification, such as storing it in a local database, cloud storage service, or using blockchain technology to ensure that it cannot be tampered with and is highly secure. This application does not limit this.

[0036] S204, determining the transaction path and the degree of overlap of the serial number of the object to be identified according to the serial number identifier, wherein the degree of overlap of the serial number is used to indicate the probability of using the same object to be identified between different accounts;

[0037] Optionally, in an embodiment of the present application, the above-mentioned determination of the transaction path of the object to be identified based on the serial number identification means that the system, based on the collected serial number data, traces back and constructs the entire process path of the object to be identified from printing, circulation to the current transaction through algorithm analysis. This path records in detail all the accounts passed by the object to be identified, as well as information such as the time, place and amount of each transaction. The serial number overlap degree quantifies the potential connection between different accounts caused by the use of the same object to be identified in this process, and indicates the probability of capital flow association between different accounts by counting and analyzing the frequency and proportion of repeated occurrence of serial numbers between multiple accounts, including but not limited to comparing transaction records between different accounts, calculating the repetition rate of serial numbers, or using more complex statistical methods, such as Bayesian estimation, to determine the serial number overlap degree.

[0038] It should be noted that there are many ways to determine the transaction path. The system can use time series analysis, graph database technology, etc. to efficiently track and organize the circulation history of the serial number identification.

[0039] There are also many possibilities for calculating the overlap of serial numbers. In addition to basic frequency comparison, you can also combine multi-dimensional data such as transaction amount, transaction frequency, and geographic location information, and use machine learning models to predict the strength of association between accounts.

[0040] In addition, the transaction path and serial number overlap analysis can be performed on a single currency, or can be extended to a group of currencies or currencies of a specific amount to meet data processing requirements of different scales. This application does not limit this.

[0041] S206, determining an account in the transaction path that satisfies a preset relationship with the target account as an associated account;

[0042] Optionally, in the embodiment of the present application, the above-mentioned determination of the account in the transaction path that satisfies the preset relationship with the target account as the associated account means that the system screens out other accounts that have a specific relationship with the target account in time and space based on the determined transaction path, and this preset relationship can be a rule set based on parameters such as time interval, geographical location, transaction amount or overlap of serial numbers, etc. Including but not limited to, determining an account that frequently receives or sends the same serial number currency as the target account in a short period of time, or an account that has conducted multiple transactions with the target account at the same location as the candidate for the associated account.

[0043] It should be noted that the conditions for satisfying the preset relationship can be flexibly set to meet the needs of different scenarios and risk levels. For example, the preset relationship can be a direct predecessor or successor of an account in a transaction path, or an indirect contact account associated through multi-hop transactions.

[0044] In addition, the preset relationship can also be comprehensively judged based on factors such as the size of the transaction amount, the frequency of transactions, the overlap of the serial numbers, etc. In actual applications, the system can dynamically adjust the parameters of these preset relationships based on real-time transaction data and historical risk cases to more accurately identify potential associated risk accounts, which is not limited in this application.

[0045] S208, inputting the serial number overlap and the transaction flow data into the target recognition model to obtain the risk level of the associated account, wherein the target recognition model is pre-trained with sample transaction flow data corresponding to sample accounts of high risk level.

[0046] Optionally, in the embodiment of the present application, the input of the serial number overlap and transaction flow data into the target recognition model refers to a model established using machine learning or deep learning technology, which uses the analyzed serial number overlap data and specific transaction flow information (such as transaction time, amount, location, etc.) as input features to evaluate the risk level of the associated account. The target recognition model can automatically identify the characteristic patterns of potential risk accounts by learning the transaction behavior and serial number flow patterns of known high-risk sample accounts, including but not limited to using the serial number overlap as a quantitative indicator for evaluating the relationship between accounts, and combining the specific details of the transaction flow to perform risk scoring or classification on the associated accounts.

[0047] It should be noted that the training and application methods of the above-mentioned target recognition model can be diversified. The model may adopt supervised learning, unsupervised learning or semi-supervised learning strategies. At the same time, the model architecture can also be a rule-based system, decision tree, support vector machine, neural network, etc. The specific choice depends on the data characteristics and model performance requirements of the actual application scenario.

[0048] In addition, the data input to the model can be further feature engineered, for example, smoothing the time series data, normalizing the crown number overlap data, or converting the geographic location information into distance or area codes to enhance the generalization ability and prediction accuracy of the model. This application does not limit this.

[0049] In an exemplary embodiment, taking the application scenario of cash transaction monitoring of a commercial bank as an example, the implementation process of the account identification method in this application is specifically demonstrated:

[0050] S1, obtaining the serial number identification: When the target account deposits and withdraws cash at a bank branch or ATM, the cash processing equipment (such as a cash counter, sorter or ATM) will automatically read and record the serial number identification on each banknote, and these data will be uploaded to the bank's backend system. The system further binds these serial number identifications with the target account's transaction flow data to form a serial number-transaction flow association record, providing basic data for subsequent analysis.

[0051] S2, Determination of the overlap between transaction paths and serial numbers: The backend system constructs a graph containing all transactions based on the uploaded serial number identifiers and transaction records, where nodes represent account numbers and edges represent the flow of serial numbers. The system uses graph analysis algorithms (such as breadth-first search, depth-first search, or graph database query) to track the transaction paths of the objects to be identified (i.e., banknotes with specific serial numbers), and calculates the overlap between serial numbers in different accounts, that is, to evaluate the degree of fund flow association that may exist between different accounts due to the use of the same banknotes.

[0052] S3, Determination of associated accounts: Based on the results of transaction path analysis and the preset relationship threshold (such as time window, geographic location range or transaction amount threshold), the system determines which accounts have direct or indirect connections with the target account in the transaction path. Accounts that meet the preset relationship are considered to be associated accounts of the target account, and these accounts are further included in the scope of risk assessment.

[0053] S4, risk level assessment: Finally, the system takes the serial number overlap data and transaction flow data of the identified associated account as input and sends them to the pre-trained target recognition model. The model is trained based on historical high-risk account samples and their transaction flow data, and can learn the key features of identifying risky accounts from the circulation rules and transaction patterns of serial numbers. The result of the model output is the risk level score of the associated account, which indicates the possibility of the account participating in malicious operations or fraudulent behavior, thereby providing the bank with a quantitative basis for risk warning and management.

[0054] Through the embodiments of the present application, a target account is obtained to request the identification of a crown number of an object to be identified, wherein the crown number is used to indicate a printing batch of the object to be identified, and is a unique identity identifier of the object to be identified; a transaction path and a crown number overlap of the object to be identified are determined according to the crown number, wherein the crown number overlap is used to indicate the probability of using the same object to be identified between different accounts; an account in the transaction path that satisfies a preset relationship with the target account is determined as an associated account; the crown number overlap and the transaction flow data are input into a target recognition model to obtain a risk level of the associated account, wherein the target recognition model is pre-trained with sample transaction flow data corresponding to sample accounts of high risk levels, thereby achieving the purpose of improving the accuracy of risk account identification, thereby achieving a more accurate risk assessment and early warning technical effect, and further solving the technical problem of low risk account identification accuracy.

[0055] As an optional scheme, the above-mentioned determination of the transaction path and the degree of overlap of the serial number of the object to be identified based on the serial number identification includes: determining the source account of the object to be identified based on the serial number identification; obtaining first transaction data of the source account when using the object to be identified to conduct a transaction, and obtaining second transaction data indicated by the transaction flow data of the target account; and determining the ratio of the first transaction data to the second transaction data as the degree of overlap of the serial number.

[0056] Optionally, in an embodiment of the present application, determining the transaction path of the object to be identified based on the serial number identification means tracing the entire process path of the object to be identified from printing, circulation to the current transaction through the serial number data, thereby confirming the source account of the object to be identified. Acquiring the first transaction data of the source account and the second transaction data of the target account means that the system extracts transaction details associated with the object to be identified from the transaction records, including information such as transaction time, transaction amount, and transaction location. Determining the ratio of the first transaction data to the second transaction data as the serial number overlap is to quantify the possibility of association between the two accounts due to the use of the same currency by comparing the transaction data of the source account and the target account when using the same object to be identified, which is used for subsequent risk assessment.

[0057] It should be noted that the data comparison and overlap calculation methods in this process can be diversified, including but not limited to directly calculating the overlap ratio of transaction amounts, the proximity of transaction times or the overlapping areas of geographical locations, and conducting a comprehensive evaluation in combination with other transaction features such as transaction frequency, transaction type, etc. This application does not limit this.

[0058] In an exemplary embodiment, taking the processing of a cash deposit transaction as an example, the system first reads and records the serial number of the deposited cash, and then uses the serial number data tracing function to determine the source account of the cash, that is, the account that has recently used the same serial number to withdraw. Then, the system extracts the withdrawal transaction data (first transaction data) of the source account and the deposit transaction data (second transaction data) of the target account, calculates the ratio of the two sets of data in terms of amount and time, and obtains the serial number overlap.

[0059] Through the embodiments of the present application, a method combining serial number data tracking with transaction data analysis is adopted to achieve accurate identification of potential account associations and risky behaviors in cash transactions, thereby achieving the purpose of enhancing the malicious operation and anti-fraud capabilities of financial institutions and effectively improving the level of financial security.

[0060] As an optional scheme, the above-mentioned determination of the transaction path of the above-mentioned object to be identified based on the above-mentioned serial number identification includes: determining the transaction record according to the above-mentioned serial number identification; determining a group of accounts that use the above-mentioned object to be identified for transactions, and transaction flow data between the accounts based on the above-mentioned transaction records, wherein the above-mentioned group of accounts includes the above-mentioned target account, and the above-mentioned transaction flow data is used to indicate the flow order and flow time of the above-mentioned object to be identified; and generating the above-mentioned transaction path based on the above-mentioned group of accounts and the above-mentioned transaction flow data.

[0061] Optionally, in an embodiment of the present application, the above-mentioned serial number identification refers to a unique serial number on each banknote, which is used to distinguish and track different batches of currency. Transaction records refer to detailed information on each cash transaction stored in the banking system, including but not limited to the transaction amount, transaction time, location, and account numbers involved. A group of accounts refers to multiple bank accounts that are identified in the transaction record as using the same serial number identification to conduct transactions with the object to be identified. These accounts are associated with each other through the transaction flow data of the object to be identified, showing the circulation path of the currency. The transaction flow data records in detail the flow order and flow time of the object to be identified between a group of accounts, and is key information for constructing a transaction path.

[0062] It should be noted that there are various ways to determine transaction records and generate transaction paths. For example, transaction records can be automatically collected through serial number recognition equipment or manually checked and entered. The generation of transaction paths may rely on complex data matching and sorting algorithms to ensure that the circulation trajectory of the object to be identified can be accurately tracked. In addition, transaction flow data may also include information such as transaction amount and transaction type to provide a more comprehensive transaction background, which is not limited in this application.

[0063] In an exemplary embodiment, the system first filters out relevant transaction records by serial number identification. Assume that the target account A deposits a sum of cash containing a specific serial number identification on a certain day. The system will automatically search for all historical transaction records containing the serial number identification and determine a group of accounts, that is, a set of accounts that use the same serial number identification for transactions. Subsequently, the system reconstructs the circulation order and timeline of the objects to be identified between these accounts based on the timestamps and transaction sequences in the transaction records, and generates a transaction path. For example, account B withdraws part of the cash from account C within two hours before the target account A deposits, and the withdrawn cash contains the same serial number identification. The system will identify account B as one of a group of accounts related to the target account A, and reflect this circulation relationship in the transaction path.

[0064] Through the embodiments of the present application, a method combining serial number identification and transaction flow data is adopted to achieve accurate tracking of the currency circulation path in cash transactions, improve the ability to identify potential risk associations between accounts, achieve the purpose of enhancing risk prevention and control and effectively identifying fraudulent behavior, and provide financial institutions with a powerful security tool.

[0065] As an optional solution, the above-mentioned determining the account in the above-mentioned transaction path that satisfies a preset relationship with the above-mentioned target account as the associated account includes: when the above-mentioned object to be identified flows from the first account to the above-mentioned target account, determining the above-mentioned first account as the above-mentioned associated account; when the above-mentioned object to be identified flows from the above-mentioned target account to the second account, determining the above-mentioned second account as the above-mentioned associated account.

[0066] Optionally, in the embodiment of the present application, the transaction path refers to the currency circulation track obtained by tracking the serial number identification, which reveals the whole process of currency transfer from one account to another, including but not limited to the order and time of currency transfer. The target account is the bank account currently being monitored or analyzed, and the first account and the second account refer to the account located at the previous transaction node and the next transaction node of the target account in the transaction path, respectively, and they are directly associated with the currency flow between the target account through the specific serial number identification.

[0067] It should be noted that the setting of the preset relationship can be flexible and diverse. In addition to the direct predecessor and successor accounts, it can also include accounts that have multiple transactions with the target account with the same serial number within a certain time window, or accounts that are indirectly related through multi-hop transactions. In addition, the judgment criteria of the preset relationship may also include factors such as the size of the transaction amount and the degree of serial number overlap, which are not limited in this application.

[0068] In an exemplary embodiment, it is assumed that the object to be identified with the serial number X is initially withdrawn from account A. Subsequently, X circulates in a series of transactions and eventually flows into target account Y. In this process, account B is the last account that has used X in the transaction directly before X circulates to target account Y. Based on this, the system will automatically determine account B as one of the associated accounts of target account Y, that is, the first account. Similarly, if X is deposited into account C after target account Y uses X for transactions, the system will also identify account C as an associated account of target account Y, that is, the second account. This process ensures that the system can accurately identify the predecessor and successor accounts directly related to the target account, providing accurate data support for subsequent risk assessment.

[0069] Through the embodiments of the present application, a method combining serial number identification tracking and account preset relationship determination is adopted to achieve accurate identification of direct connections between accounts in a cash transaction network, enhance the ability to quickly locate risky accounts, and achieve the purpose of improving the efficiency and accuracy of risk prevention and control of financial institutions in the fields of malicious operations and anti-fraud, thereby promoting the security and stability of the financial environment.

[0070] As an optional solution, the method further includes: in response to the target account obtaining the object to be identified for the first transaction from a cash machine or a counter, determining the target account as the starting account in the transaction path, wherein the object to be identified has not been obtained by other accounts before being obtained by the target account; determining M accounts after the starting account in the transaction path as the second account, wherein M is a positive integer, and the value of M is related to the current transaction time of the object to be identified.

[0071] Optionally, in an embodiment of the present application, the target account refers to a bank account currently being monitored or analyzed by the system, which plays the role of a starting point in the transaction path. The object to be identified refers to cash with a specific serial number identification, which can track the circulation history of the cash. The first transaction refers to the first transaction between the target account and the specific object to be identified, which usually means that the target account is the account that first appears in the serial number identification record, that is, the cash has not been used by any other account before. The transaction path is the entire cash flow process tracked and recorded according to the serial number identification, which includes all accounts related to the object to be identified and their transaction details. The starting account is the first account in the transaction path that has a transaction with the object to be identified, and the M accounts refer to the M consecutive transaction accounts after the starting account in the transaction path, which are related to the first transaction time and subsequent circulation of the object to be identified.

[0072] It should be noted that the value of M can be set according to different strategies, such as the interval between the first transaction time of the object to be identified and the current time, or a preset fixed value. This depends on the specific needs and risk assessment strategies of the financial institution. At the same time, the transaction path between the target account as the starting account and the M second accounts may present a variety of complex forms, including linear, branching or circular paths, etc., which are not limited in this application.

[0073] In an exemplary embodiment, assume that the object to be identified with a serial number of 12345678 is withdrawn from a cash machine for the first time by target account A. At this time, the system marks account A as the starting account in the transaction path. Subsequently, the system tracks the circulation of the serial number and finds that it has flowed through accounts B, C, and D, and account D is the account that has recently transacted with the object to be identified before the current time point. If M is set to 2, the system will determine accounts B and C as the associated accounts of target account A, that is, the second account, because they are located at the two transaction nodes after the starting account A in the transaction path.

[0074] Through the embodiments of the present application, a method is adopted to track the objects to be identified in the first transaction of the target account and determine that the subsequent M transaction accounts are associated accounts, thereby achieving accurate positioning of potential risk accounts in cash transactions, improving the real-time and effectiveness of risk assessment, and achieving the purpose of enhancing the risk prevention and control capabilities of financial institutions, timely discovering and preventing illegal activities, and effectively improving the security and stability of the financial system.

[0075] As an optional solution, the method further includes: in response to the target account obtaining the object to be identified which is not the first transaction from other accounts and requesting to deposit the object to be identified, determining the target account as an intermediate account in the transaction path; determining N accounts before the intermediate account in the transaction path as the first account, wherein N is a positive integer and the value of N is related to the current transaction time of the object to be identified.

[0076] Optionally, in an embodiment of the present application, an intermediate account refers to a bank account that is neither the starting account nor the final holding account in the circulation path identified by the serial number, but is located between the two. The object to be identified in a non-first transaction means that the cash identified by the specific serial number has not appeared for the first time in the transaction record of the current account, indicating that the cash has been used by other accounts in previous transactions. The transaction path is a cash flow trajectory obtained by tracking the serial number, which includes all accounts that have traded with the object to be identified and their transaction sequence. N accounts refer to N consecutive transaction accounts located before the intermediate account in the transaction path. These accounts have a direct or indirect relationship with the current transaction time of the object to be identified. The setting of N depends on the specific risk assessment strategy.

[0077] It should be noted that the value of N and the method of determining the first account can be diversified. For example, the size of N can be dynamically adjusted based on the difference between the current transaction time and the first transaction time of the object to be identified, or determined according to a preset fixed value. At the same time, the determination of the first account can be based on the most recent transaction time, or can be based on a comprehensive consideration of factors such as transaction frequency and transaction amount, and this application does not limit this.

[0078] In an exemplary embodiment, cash with a serial number Z is deposited in a target account C for a non-first time. The system identifies the transaction records that have circulated before Z through serial number tracking technology, and marks account C as an intermediate account in the transaction path. Assume that N is set to 4, which means that the system needs to determine the four transaction accounts before account C, namely the first account. By analyzing the transaction records, the system finds that Z flows through accounts D, E, F, and G in sequence, and account G is the deposit account immediately before account C, while account D is the withdrawal account for the first transaction with Z. Therefore, accounts D, E, F, and G are determined as the first accounts related to this deposit transaction, which are used for subsequent association analysis and risk assessment.

[0079] Through the embodiments of the present application, a method for determining intermediate accounts and first accounts based on the circulation path identified by the serial number is adopted, which realizes the accurate positioning of risky accounts in the cash transaction network, enhances the analysis depth of financial institutions when monitoring cash flow, achieves the purpose of improving risk prevention and control capabilities, and effectively identifies potential malicious operations or fraudulent behaviors, and provides a strong technical guarantee for maintaining financial security.

[0080] As an optional solution, the above-mentioned serial number overlap and the transaction flow data of the above-mentioned associated account are input into the target recognition model to determine the risk level of the above-mentioned associated account, including: determining the transaction time, transaction frequency and transaction amount of the above-mentioned object to be identified based on the transaction flow data of the above-mentioned associated account; inputting the above-mentioned serial number overlap, the above-mentioned transaction time, the above-mentioned transaction frequency and the above-mentioned transaction amount into the above-mentioned target recognition model to determine the above-mentioned risk level.

[0081] Optionally, in an embodiment of the present application, the above-mentioned overlap of serial numbers refers to an indicator that quantifies the potential fund association between accounts by analyzing the repeated occurrence of serial number identifiers between different accounts, including but not limited to the number of overlaps, the frequency of overlaps, and the probability of overlaps. The above-mentioned transaction flow data covers detailed records of all transactions of the account, including but not limited to information such as transaction time, transaction frequency, and transaction amount. These data are used to describe the transaction behavior characteristics of the account. The above-mentioned target recognition model is a model constructed using machine learning technology, which is used to evaluate and predict the risk level of an account based on the input feature data. The training data of the model may come from historical high-risk account cases and normal account cases to learn the characteristic patterns that distinguish risky accounts from ordinary accounts.

[0082] It should be noted that the analysis methods of transaction time, transaction frequency and transaction amount can be diversified. For example, transaction time analysis can consider the specific time when the transaction occurs, or divide a day into multiple time periods for statistics; transaction frequency can be measured according to the number of transactions in a specific time, which may involve daily, weekly or monthly frequency statistics; transaction amount analysis can be the size of a single transaction amount, or the total transaction amount or average transaction amount in a certain period. In addition, the target recognition model can use a variety of machine learning algorithms, such as support vector machines, decision trees, neural networks, etc., which are not limited in this application.

[0083] In an exemplary embodiment, it is assumed that the object to be identified with the serial number X has overlapping transactions between the target account A and account B. The system first determines the characteristics of X such as transaction time, transaction frequency and transaction amount based on the transaction flow data of accounts A and B. For example, X appears in the withdrawal transaction of account A on Monday morning, while account B has deposit transactions containing X on Tuesday afternoon and Wednesday morning respectively. The system will count the transaction frequency of X in account B as two times, and the transaction amounts are 200 yuan and 150 yuan respectively. Subsequently, these feature data are input into the target recognition model together with the degree of overlap of the serial number (assuming the overlap is 0.5). After calculation and evaluation, the model outputs that the risk level of account B is medium, indicating that the account may have certain malicious operations or fraud risks, and further monitoring and review are required.

[0084] Through the embodiments of the present application, a risk assessment method based on the overlap of serial numbers and transaction flow data characteristics is adopted to achieve intelligent identification and classification of potential risk accounts, improve the efficiency and accuracy of financial institutions in malicious operations and anti-fraud risk prevention and control, achieve the purpose of timely warning and effective response to illegal activities, and provide strong technical support for maintaining financial order and security.

[0085] As an optional solution, the above method also includes:

[0086] Obtain the above serial number identification;

[0087] Determine the source account number of the above-mentioned object to be identified according to the above-mentioned serial number identification;

[0088] Acquire first transaction data of the source account when using the object to be identified to conduct transactions, and acquire second transaction data indicated by transaction flow data of the target account;

[0089] Determine the ratio of the first transaction data to the second transaction data as the serial number coincidence degree, wherein the serial number coincidence degree is used to indicate the probability that the same object to be identified is used between different accounts;

[0090] Determine the transaction record according to the serial number identification, and determine a group of accounts that use the object to be identified to conduct transactions, as well as transaction flow data between the accounts, based on the transaction record;

[0091] Generate the transaction path according to the set of accounts and the transaction flow data;

[0092] In response to the target account acquiring the object to be identified which is not the first transaction from other accounts and requesting to deposit the object to be identified, the target account is determined as an intermediate account in the transaction path; N accounts before the intermediate account in the transaction path are determined as the first account, wherein N is a positive integer and the value of N is related to the current transaction time of the object to be identified;

[0093] In the case where the object to be identified is transferred from the first account to the target account, determining the first account as the associated account;

[0094] In response to the target account number obtaining the object to be identified for the first transaction from a cash machine or a counter, the target account number is determined as a starting account number in the transaction path; M accounts after the starting account number in the transaction path are determined as second accounts, wherein M is a positive integer and the value of M is related to the current transaction time of the object to be identified;

[0095] In the case where the object to be identified is transferred from the target account to the second account, determining the second account as the associated account;

[0096] Determine the transaction time, transaction frequency and transaction amount of the object to be identified based on the transaction flow data of the associated account;

[0097] The overlap of the serial numbers, the transaction time, the transaction frequency, and the transaction amount are input into the target recognition model to determine the risk level of the associated account.

[0098] In an exemplary embodiment, the account identification method proposed in the present application can be used to achieve the purpose of identifying risky accounts through a machine learning model using serial number data.

[0099] First, the nouns appearing in the embodiments of the present application are explained as follows:

[0100] Serial number: Serial number refers to the combination of letters and numbers printed on banknotes to mark the printing batch. Specifically, "Serial number" refers to the two or three letters printed on banknotes to mark the printing batch, which are arranged and printed by the banknote printing factory according to a certain pattern. "Serial number" refers to the seven or eight Arabic numeral serial number following the serial number. The serial number of each genuine banknote is unique, which makes each banknote have its own unique identity.

[0101] Machine learning model: A machine learning model is an algorithmic model that can automatically learn and improve from data to complete specific tasks. This model does not require human programming to specify each step of the operation, but instead uses algorithms to parse data, extract features from it, learn patterns, and then use the learned knowledge to predict new unknown data or make decisions.

[0102] Considering the existing technology, it is difficult to identify the risks of cash transactions: due to the physical characteristics of cash transactions, it cannot leave clear records like electronic transactions, which makes the risk identification method based on traditional data analysis ineffective when dealing with cash transactions; insufficient use of serial number data: the serial number is the unique identifier of the banknote and can provide information on the circulation of banknotes, but the current financial security system does not make full use of this, especially in associating accounts and assessing potential risks; the accuracy of account correlation identification is not high: traditional risk management models may not be able to accurately identify the connection between accounts through transaction patterns, especially when cash transactions are frequent and highly concealed; insufficient ability to identify high-risk accounts: due to the particularity of cash transactions, existing risk identification models find it difficult to capture behavioral characteristics related to financial crimes such as malicious operations and fraud.

[0103] Therefore, the embodiments of the present application are intended to address the limitations of traditional financial risk identification methods when processing cash transactions, especially the deficiencies in identifying financial crime activities such as malicious operations and fraud. Traditional methods often rely on non-physical information such as transaction amounts, frequencies, and times for analysis, while the embodiments of the present application introduce serial number data into the machine learning model, and identify the duplication of serial numbers between accounts by tracking and analyzing serial numbers in cash transactions. Not only does it improve the accuracy of identifying the correlation between accounts, but it also helps to more effectively detect and evaluate high-risk accounts involving malicious operations and fraud, thereby enhancing the security of the financial system. In this way, the present invention improves the ability to identify account risks, strengthens the financial security system, and reduces the occurrence of malicious operations and fraud.

[0104] For example, Figure 3 is a schematic diagram of an optional account identification method according to an embodiment of the present application, such as Figure 3As shown, by analyzing and comparing the cash transaction behaviors between different bank accounts and the overlap of serial numbers involved in these transactions, the risk level of bank accounts can be identified and assessed, including but not limited to:

[0105] S1, serial number data acquisition and processing: collect and organize serial number data generated during cash transactions. This process includes data recording of cash withdrawal and cash deposit transactions, and automatically reading and recording serial number information of banknotes in cash transactions through machines such as banknote counters, sorting machines, and self-service teller machines to ensure that the serial number of currency banknotes in each transaction is accurately recorded. These data are then transmitted to the central database through a secure network for centralized management and processing.

[0106] S2, analysis of serial number overlap: first, data preprocessing is performed to clean the collected serial number data, eliminate non-standard formats and erroneous data, and ensure the accuracy of subsequent analysis; secondly, according to the cleaned serial number data and the logical order of withdrawal and then deposit, the serial number overlap between different accounts is quickly matched; finally, data such as the time interval between transactions of different accounts, the number and frequency of serial number overlap are obtained.

[0107] S3, machine learning model training: extract key features from multiple dimensions such as serial number overlap, transaction time, transaction frequency, transaction amount, etc. obtained in step 2), use historical data and known high-risk accounts (such as accounts involved in malicious operations or accounts controlled by fraudsters, etc.) as black samples to train machine learning models (such as neural networks, etc.) to determine the risk level of associated accounts.

[0108] S4, Identification of associated risk accounts: Extract key features from multiple dimensions such as serial number data and transaction data and input them into the model to predict the risk level of associated accounts and generate a risk assessment report.

[0109] S5. Establish a risk account database: regularly maintain and update high-risk accounts, include accounts that are clearly involved in cases or malicious operations in existing accounts, and continuously include newly discovered risk accounts.

[0110] In general, the embodiments of the present application obtain serial number data through cash transaction records, including serial number information in cash withdrawal and cash deposit transactions, as the basis for subsequent analysis; analyze cash transactions between different accounts, identify the overlap of serial numbers involved, and quantify the strength of association between accounts; design and train a machine learning model, and based on the overlap of serial numbers and the analysis results of the machine learning model, determine whether there is a risk association between accounts for malicious operations or fraudulent behaviors, and its severity, so as to judge the potential risk level of the account; also establish a high-risk account library containing known malicious operations, frauds, etc., for model training and reference for risk assessment of new accounts; through the adaptive ability of the machine learning model and the dynamically updated high-risk account library, a risk account assessment method that can be continuously updated and optimized is formed, which systematically solves the problem of risk account identification in the financial field.

[0111] Through the embodiments of the present application, the ability to identify potential high-risk accounts such as malicious operations and fraud is effectively improved, missed judgments and misjudgments are reduced, the identification process of risky accounts is accelerated, and work efficiency is effectively improved. At the same time, human resources are reduced and risks that may be caused by human errors are reduced, and the level of early warning and prevention of unknown risk accounts is improved.

[0112] In other words, by making deeper use of the serial number data, the accuracy and efficiency of risk account identification are effectively improved. Compared with the prior art, the embodiment of the present application uses an advanced machine learning model that can not only capture complex account association patterns, but also achieve rapid response in actual operations. Specifically, by automatically tracking and analyzing the overlap of serial numbers between different accounts, the correlation between accounts can be more accurately evaluated, thereby identifying high-risk accounts such as potential malicious operations and fraud.

[0113] In addition, combined with the existing risk account data, the present invention can predict and warn of related risks that may arise in the future through reasoning methods, significantly enhancing the risk prediction capability.

[0114] In general, the present invention provides financial institutions with more powerful and flexible risk management tools through efficient data analysis and intelligent risk identification strategies, which helps to build a safer and more transparent financial environment, can more effectively monitor and control financial risks, and protect the legitimate financial order from being damaged.

[0115] It is understandable that in the specific implementation of this application, related data such as user information is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0116] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0117] According to another aspect of the embodiments of the present application, an account identification device for implementing the above account identification method is also provided. Figure 4 As shown, the device comprises:

[0118] An acquisition module 402 is used to acquire a serial number identifier of an object to be identified that is requested to be processed by a target account, wherein the serial number identifier is used to indicate a printing batch of the object to be identified, and the serial number identifier is a unique identification identifier of the object to be identified;

[0119] The first determination module 404 is used to determine the transaction path and the overlap degree of the serial number of the object to be identified according to the serial number identifier, wherein the overlap degree of the serial number is used to indicate the probability of using the same object to be identified between different accounts;

[0120] A second determination module 406, configured to determine an account in the transaction path that satisfies a preset relationship with the target account as an associated account;

[0121] The identification module 408 is used to input the serial number overlap and transaction flow data into the target identification model to obtain the risk level of the associated account, wherein the target identification model is pre-trained with sample transaction flow data corresponding to sample accounts with high risk levels.

[0122] As an optional solution, the above-mentioned device is used to determine the transaction path and the degree of overlap of the serial number of the above-mentioned object to be identified according to the above-mentioned serial number identification in the following manner: determine the source account of the above-mentioned object to be identified according to the above-mentioned serial number identification; obtain the first transaction data of the above-mentioned source account when using the above-mentioned object to be identified to conduct a transaction, and obtain the second transaction data indicated by the transaction flow data of the above-mentioned target account; determine the ratio of the above-mentioned first transaction data to the above-mentioned second transaction data as the degree of overlap of the above-mentioned serial number.

[0123] As an optional solution, the above-mentioned device is used to determine the transaction path of the above-mentioned object to be identified according to the above-mentioned serial number identification in the following manner: determine the transaction record according to the above-mentioned serial number identification; determine a group of accounts that use the above-mentioned object to be identified for transactions, and transaction flow data between the accounts based on the above-mentioned transaction records, wherein the above-mentioned group of accounts includes the above-mentioned target account, and the above-mentioned transaction flow data is used to indicate the flow order and flow time of the above-mentioned object to be identified; generate the above-mentioned transaction path based on the above-mentioned group of accounts and the above-mentioned transaction flow data.

[0124] As an optional solution, the above-mentioned device is used to determine the account in the above-mentioned transaction path that satisfies a preset relationship with the above-mentioned target account as an associated account in the following manner: when the above-mentioned object to be identified flows from the first account to the above-mentioned target account, the above-mentioned first account is determined as the above-mentioned associated account; when the above-mentioned object to be identified flows from the above-mentioned target account to the second account, the above-mentioned second account is determined as the above-mentioned associated account.

[0125] As an optional solution, the above-mentioned device is also used to: in response to the above-mentioned target account obtaining the above-mentioned object to be identified for the first transaction from a cash machine or a counter, determine the above-mentioned target account as the starting account in the above-mentioned transaction path, wherein the above-mentioned object to be identified has not been obtained by other accounts before being obtained by the above-mentioned target account; determine the M accounts after the above-mentioned starting account in the above-mentioned transaction path as the above-mentioned second account, wherein the above-mentioned M is a positive integer, and the value of the above-mentioned M is related to the current transaction time of the above-mentioned object to be identified.

[0126] As an optional solution, the above-mentioned device is also used to: in response to the above-mentioned target account obtaining the above-mentioned object to be identified which is not the first transaction from other accounts and requesting to deposit the above-mentioned object to be identified, determine the above-mentioned target account as the intermediate account in the above-mentioned transaction path; determine the N accounts before the above-mentioned intermediate account in the above-mentioned transaction path as the above-mentioned first account, wherein the above-mentioned N is a positive integer, and the value of the above-mentioned N is related to the current transaction time of the above-mentioned object to be identified.

[0127] As an optional solution, the above-mentioned device is used to input the above-mentioned serial number overlap and the transaction flow data of the above-mentioned associated account into the target recognition model in the following manner to determine the risk level of the above-mentioned associated account: determine the transaction time, transaction frequency and transaction amount of the above-mentioned object to be identified based on the transaction flow data of the above-mentioned associated account; input the above-mentioned serial number overlap, the above-mentioned transaction time, the above-mentioned transaction frequency and the above-mentioned transaction amount into the above-mentioned target recognition model to determine the above-mentioned risk level.

[0128] As an optional solution, the above-mentioned device is also used to: obtain the above-mentioned serial number identification; determine the source account of the above-mentioned object to be identified according to the above-mentioned serial number identification; obtain the first transaction data of the above-mentioned source account when using the above-mentioned object to be identified to conduct transactions, and obtain the second transaction data indicated by the transaction flow data of the above-mentioned target account; determine the ratio of the above-mentioned first transaction data to the above-mentioned second transaction data as the above-mentioned serial number overlap, wherein the above-mentioned serial number overlap is used to indicate the probability of using the same above-mentioned object to be identified between different accounts; determine the transaction record according to the above-mentioned serial number identification, and determine a group of accounts that use the above-mentioned object to be identified to conduct transactions according to the above-mentioned transaction record, as well as the transaction flow data between the accounts; generate the above-mentioned transaction path according to the above-mentioned group of accounts and the above-mentioned transaction flow data; in response to the above-mentioned target account obtaining the above-mentioned object to be identified that is not the first transaction from other accounts and requesting to deposit the above-mentioned object to be identified, determine the above-mentioned target account as an intermediate account in the above-mentioned transaction path; and determine the N accounts that are before the above-mentioned intermediate account in the above-mentioned transaction path. Determine as the first account, wherein N is a positive integer, and the value of N is related to the current transaction time of the object to be identified; in the case where the object to be identified is transferred from the first account to the target account, the first account is determined as the associated account; in response to the object to be identified obtaining the first transaction from the cash machine or the counter by the target account, the target account is determined as the starting account in the transaction path; M accounts after the starting account in the transaction path are determined as the second account, wherein M is a positive integer, and the value of M is related to the current transaction time of the object to be identified; in the case where the object to be identified is transferred from the target account to the second account, the second account is determined as the associated account; the transaction time, transaction frequency and transaction amount of the object to be identified are determined based on the transaction flow data of the associated account; the overlap of the serial number, the transaction time, the transaction frequency and the transaction amount are input into the target recognition model to determine the risk level of the associated account.

[0129] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0130] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0131] According to one aspect of the present application, a computer program product is provided. The computer program product includes a computer program.

[0132] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0133] Figure 5 The structure block diagram of a computer system for implementing an electronic device according to an embodiment of the present application is schematically shown.

[0134] It should be noted that Figure 5 The computer system 500 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0135] like Figure 5 As shown, the computer system 500 includes a central processing unit 501 (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory 502 (ROM) or the program loaded from the storage part 508 to the random access memory 503 (RAM). Various programs and data required for system operation are also stored in the random access memory 503. The central processing unit 501, the read-only memory 502 and the random access memory 503 are connected to each other through a bus 504. The input / output interface 505 (Input / Output interface, i.e., I / O interface) is also connected to the bus 504.

[0136] The following components are connected to the input / output interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a local area network card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0137] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processor 501, various functions defined in the system of the present application are executed.

[0138] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processor 501, various functions provided by the embodiment of the present application are performed.

[0139] According to another aspect of the embodiment of the present application, an electronic device for implementing the above account identification method is also provided. The electronic device may be Figure 1 The terminal device or server shown in the figure. This embodiment is described by taking the electronic device as a terminal device as an example. Figure 6 As shown, the electronic device includes a memory 602 and a processor 604. The memory 602 stores a computer program, and the processor 604 is configured to execute the steps in any of the above method embodiments through the computer program.

[0140] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0141] Optionally, in this embodiment, the above-mentioned processor can be configured to execute the methods in each embodiment of the present application through a computer program.

[0142] Alternatively, a person skilled in the art may understand that: Figure 6 The structure shown is for illustration only. Figure 6 The structure of the electronic device is not limited. Figure 6 More or fewer components (such as network interfaces, etc.) as shown in, or with Figure 6 Different configurations are shown.

[0143] Among them, the memory 602 can be used to store software programs and modules, such as the program instructions / modules corresponding to the account identification method and device in the embodiments of the present application. The processor 604 executes various functional applications and data processing by running the software programs and modules stored in the memory 602, that is, to implement the above-mentioned account identification method. The memory 602 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 instances, the memory 602 may further include a memory remotely located relative to the processor 604, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 602 can be specifically, but not limited to, used to store information such as information of the object to be identified. As an example, such as Figure 6 As shown, the memory 602 may include but is not limited to the acquisition module 402, the first determination module 404, the second determination module 406 and the identification module 408 in the account identification device. In addition, it may also include but is not limited to other module units in the account identification device, which will not be repeated in this example.

[0144] Optionally, the transmission device 606 is used to receive or send data via a network. Specific examples of the network may include a wired network and a wireless network. In one example, the transmission device 606 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 606 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0145] In addition, the electronic device further includes: a display 608 for displaying the risk account; and a connection bus 610 for connecting various module components in the electronic device.

[0146] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. The nodes may form a peer-to-peer network, and any form of computing device, such as a server, terminal or other electronic device, may become a node in the blockchain system by joining the peer-to-peer network.

[0147] According to one aspect of the present application, a computer-readable storage medium is provided, and a processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the account identification method provided in various optional implementations of the above-mentioned account identification aspects.

[0148] Optionally, in this embodiment, the above-mentioned computer-readable storage medium can be configured to store data for executing the methods in various embodiments of the present application.

[0149] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0150] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0151] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for one or more electronic devices to execute all or part of the steps of the methods described in each embodiment of the present application.

[0152] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed application can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0156] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An account identification method, characterized in that: include: Obtaining a serial number identifier of an object to be identified that is requested to be processed by the target account, wherein the serial number identifier is used to indicate a printing batch of the object to be identified, and the serial number identifier is a unique identity identifier of the object to be identified; Determine the transaction path and the degree of overlap of the serial number of the object to be identified according to the serial number identifier, wherein the degree of overlap of the serial number is used to indicate the probability of using the same object to be identified between different accounts; Determining an account in the transaction path that satisfies a preset relationship with the target account as an associated account; The serial number overlap and transaction flow data are input into a target recognition model to obtain the risk level of the associated account, wherein the target recognition model is pre-trained with sample transaction flow data corresponding to sample accounts with high risk levels.

2. The method according to claim 1, characterized in that The step of determining the overlap between the transaction path and the serial number of the object to be identified according to the serial number identifier includes: Determine the source account number of the object to be identified according to the serial number identifier; Acquire first transaction data of the source account when using the object to be identified to conduct transactions, and acquire second transaction data indicated by transaction flow data of the target account; The ratio of the first transaction data to the second transaction data is determined as the serial number coincidence degree.

3. The method according to claim 1, characterized in that The step of determining the transaction path of the object to be identified according to the serial number identifier includes: Determine the transaction record according to the serial number identification; Determine, according to the transaction record, a group of accounts that use the object to be identified for transactions, and transaction flow data between the accounts, wherein the group of accounts includes the target account, and the transaction flow data is used to indicate the flow sequence and flow time of the object to be identified; The transaction path is generated according to the group of accounts and the transaction flow data.

4. The method according to claim 1, characterized in that The determining an account in the transaction path that satisfies a preset relationship with the target account as a related account includes: In the case where the object to be identified is transferred from the first account to the target account, determining the first account as the associated account; In the case where the object to be identified is transferred from the target account to a second account, the second account is determined as the associated account.

5. The method according to claim 4, characterized in that The method further comprises: In response to the target account acquiring the object to be identified for the first transaction from a cash machine or a counter, the target account is determined as the starting account in the transaction path, wherein the object to be identified has not been acquired by other accounts before being acquired by the target account; The M accounts after the starting account in the transaction path are determined as the second account, wherein M is a positive integer, and the value of M is related to the current transaction time of the object to be identified.

6. The method according to claim 4, characterized in that The method further comprises: In response to the target account acquiring the object to be identified of a non-first transaction from another account and requesting to deposit the object to be identified, determining the target account as an intermediate account in the transaction path; The N accounts before the intermediate account in the transaction path are determined as the first account, wherein N is a positive integer, and the value of N is related to the current transaction time of the object to be identified.

7. The method according to claim 1, characterized in that The step of inputting the serial number overlap degree and the transaction flow data of the associated account into a target recognition model to determine the risk level of the associated account includes: Determine the transaction time, transaction frequency and transaction amount of the object to be identified based on the transaction flow data of the associated account; The overlap of the serial numbers, the transaction time, the transaction frequency, and the transaction amount are input into the target recognition model to determine the risk level.

8. The method according to claim 1, characterized in that: The method further comprises: Obtain the serial number identification; Determine the source account number of the object to be identified according to the serial number identifier; Acquire first transaction data of the source account when using the object to be identified to conduct transactions, and acquire second transaction data indicated by transaction flow data of the target account; Determine the ratio of the first transaction data to the second transaction data as the serial number coincidence degree, wherein the serial number coincidence degree is used to indicate the probability of using the same object to be identified between different accounts; Determine the transaction record according to the serial number identification, and determine a group of accounts that use the object to be identified for transactions, and transaction flow data between the accounts according to the transaction record; generating the transaction path according to the set of accounts and the transaction flow data; In response to the target account acquiring the object to be identified which is not the first transaction from other accounts and requesting to deposit the object to be identified, the target account is determined as an intermediate account in the transaction path; N accounts before the intermediate account in the transaction path are determined as the first account, wherein N is a positive integer and the value of N is related to the current transaction time of the object to be identified; In a case where the object to be identified is transferred from the first account to the target account, determining the first account as the associated account; In response to the target account number obtaining the object to be identified for the first transaction from a cash machine or a counter, the target account number is determined as a starting account number in the transaction path; M accounts after the starting account number in the transaction path are determined as second accounts, wherein M is a positive integer and the value of M is related to the current transaction time of the object to be identified; In a case where the object to be identified is transferred from the target account to the second account, determining the second account as the associated account; Determine the transaction time, transaction frequency and transaction amount of the object to be identified based on the transaction flow data of the associated account; The overlap of the serial numbers, the transaction time, the transaction frequency, and the transaction amount are input into the target recognition model to determine the risk level of the associated account.

9. An account identification device, characterized in that: include: An acquisition module, used for acquiring a serial number identifier of an object to be identified that is requested to be processed by a target account, wherein the serial number identifier is used to indicate a printing batch of the object to be identified, and the serial number identifier is a unique identity identifier of the object to be identified; A first determination module is used to determine the transaction path and the degree of overlap of the serial number of the object to be identified according to the serial number identifier, wherein the degree of overlap of the serial number is used to indicate the probability of using the same object to be identified between different accounts; A second determination module, configured to determine an account in the transaction path that satisfies a preset relationship with the target account as an associated account; The identification module is used to input the serial number overlap and transaction flow data into a target recognition model to obtain the risk level of the associated account, wherein the target recognition model is pre-trained with sample transaction flow data corresponding to sample accounts with high risk levels.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein the computer program can be executed by an electronic device to perform the method described in any one of claims 1 to 8.

11. 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 8 are implemented.

12. 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 execute the method according to any one of claims 1 to 8 through the computer program.

Images