Transaction data processing method and apparatus

Abstract

The application discloses a kind of transaction data processing method and device, it is related to transaction technical field, the method includes: receiving multiple pending transactions;Calculate the approval probability of each pending transaction;Calculate the expected cumulative value of each transaction counterparty;According to the real occurred library, determine the occurred value of each transaction counterparty;Receive the first approval result of first pending transaction;According to the first approval result, modify the approval probability of first pending transaction, update the expected cumulative value of first transaction counterparty;Wherein, when the first approval result is passed: from the pending transaction of first transaction counterparty, delete the pending transaction of first pending transaction with lower priority, according to the pending transaction of first transaction counterparty after deletion, update the expected cumulative value of first transaction counterparty;According to the occurred value and updated expected cumulative value, determine whether first pending transaction triggers major transaction.The application can improve the identification accuracy and efficiency of major transaction.

Description

Technical Field

[0001] The present invention relates to the field of transaction technology, and in particular to a transaction data processing method and device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] There are many types of transactions closely related to a company, such as routine commercial transactions, supply chain transactions, and financial services transactions. The party interacting with the other party in a transaction is called the counterparty. Significant transactions are those that have a significant impact on a company's financial condition, operating results, or business decisions. The management and disclosure of significant transactions are crucial components of corporate transaction management.

[0004] Prior art generally identifies significant transactions by monitoring the amount of a single transaction to determine whether it meets the significant transaction threshold. However, for more complex transactions, such as when multiple transactions occur simultaneously with the same counterparty, existing monitoring methods cannot accurately determine the status of all transactions with the same counterparty. In this case, manual monitoring and calculation are required for the same counterparty. By comparing the known counterparty's regulatory status, all transactions with the counterparty are screened using counterparty identifiers. Then, based on regulatory rules, transactions with amounts that meet the regulatory threshold are marked as significant transactions. However, manual processing has the following shortcomings: First, manually matching each transaction against the counterparty list requires significant manpower, resulting in low matching efficiency. Second, manual calculations are subject to information lags in transaction information being reviewed for approval. For example, incomplete information on the counterparty's regulatory status, the number of transactions, and the transaction approval status can easily lead to misjudgments regarding whether a transaction meets the significant transaction criteria, leading to missed or incorrect identification of significant transactions. Summary of the Invention

[0005] An embodiment of the present invention provides a transaction data processing method for reducing labor costs and improving the accuracy and efficiency of identifying major transactions. The method includes:

[0006] Receive multiple pending transactions; the pending transactions carry counterparty identification and transaction amount;

[0007] The probability of approval for each pending transaction is calculated using a preset probability calculation model. The preset probability calculation model is pre-trained using the approval results and counterparty credit information of multiple historical transactions to train a logistic regression model. The approval results include whether the approval was passed and the approval time point.

[0008] Based on the transaction amount and approval probability corresponding to the same counterparty ID, the estimated cumulative value of each counterparty is calculated; the estimated cumulative value reflects the total transaction amount expected to occur with the counterparty;

[0009] Determine the incurred value of each counterparty based on transactions obtained from a real incurred database; the incurred value reflects the total amount of transactions that have occurred with the counterparty; the real incurred database stores incurred transactions;

[0010] Receiving a first approval result of a first transaction to be approved; the first transaction to be approved carries an identifier of a first transaction counterparty;

[0011] Modifying the approval probability of the first pending transaction based on the first approval result, and updating the estimated cumulative value of the first transaction counterparty; wherein, when the first approval result is approval, updating the estimated cumulative value of the first transaction counterparty includes: deleting pending transactions with a lower priority than the first pending transaction from the first transaction counterparty's pending transactions, and updating the estimated cumulative value of the first transaction counterparty based on the transaction amount and transaction probability of all pending transactions of the first transaction counterparty after deletion; the priority reflects the business importance and approval time of the pending transaction;

[0012] Determine whether the first pending transaction triggers a major transaction based on the updated estimated cumulative value of the first transaction counterparty, the incurred value of the first transaction counterparty, and a preset cumulative threshold; the preset cumulative threshold is used to determine whether the total amount of all transactions with the transaction counterparty triggers a major transaction.

[0013] An embodiment of the present invention further provides a transaction data processing device for reducing labor costs and improving the accuracy and efficiency of identifying major transactions. The device includes:

[0014] A data receiving module is used to receive multiple pending transactions; the pending transactions carry a counterparty identifier and a transaction amount;

[0015] The approval probability prediction module is used to calculate the approval probability of each pending transaction using a preset probability calculation model. The preset probability calculation model is pre-trained using the approval results and counterparty credit information of multiple historical transactions to train a logistic regression model. The approval results include whether the approval was passed and the approval time point.

[0016] An estimated cumulative value calculation module is used to calculate the estimated cumulative value of each counterparty based on the transaction amount and approval probability corresponding to the same counterparty identifier; the estimated cumulative value reflects the total transaction amount expected to occur with the counterparty;

[0017] An occurred value calculation module is configured to determine an occurred value of each transaction counter according to transactions obtained from a real occurred database, wherein the occurred value reflects a total amount of accumulated occurred transactions of the transaction counter, and the real occurred database stores occurred transactions;

[0018] An expected cumulative value updating module is configured to receive a first approval result of a first to-be-approved transaction, wherein the first to-be-approved transaction carries an identity of a first transaction counter; modify an approval passing probability of the first to-be-approved transaction according to the first approval result; and update an expected cumulative value of the first transaction counter, wherein when the first approval result is passing, updating the expected cumulative value of the first transaction counter comprises: deleting to-be-approved transactions with lower priority than the first to-be-approved transaction from to-be-approved transactions of the first transaction counter; and updating the expected cumulative value of the first transaction counter according to transaction amounts and transaction occurrence probabilities of all to-be-approved transactions of the first transaction counter after the deletion, wherein the priority reflects business importance and approval duration of the to-be-approved transaction.

[0019] A trigger judgment module is configured to determine whether the first to-be-approved transaction triggers a major transaction according to the updated expected cumulative value of the first transaction counter, the occurred value of the first transaction counter and a preset cumulative threshold, wherein the preset cumulative threshold is used to determine whether a total amount of all transactions of the transaction counter triggers the major transaction.

[0020] The embodiment of the present application further provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor implements the transaction data processing method when executing the computer program.

[0021] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the transaction data processing method.

[0022] The embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the transaction data processing method.

[0023] In the embodiment of the present invention, the cumulative value of the expected transactions and the cumulative value of the actual transactions that have occurred for all pending transactions with the same counterparty are automatically counted, and the cumulative value of the statistics is automatically updated based on the real-time approval results. The preset cumulative threshold used to determine whether the approved transaction has triggered a major transaction is used to determine whether the approved transaction has triggered a major transaction. Compared with the technical solutions in the prior art, the embodiment of the present invention first avoids manual calculations, reduces a large amount of labor costs, and improves the efficiency of identifying major transactions. Secondly, in the case of multiple pending transactions at the same time, the expected transaction amount can be adjusted in real time based on the approval results of the transactions, thereby making the identification of major transactions more accurate and improving the accuracy of major transaction identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0025] Figure 1 Schematic diagram of the process of the transaction data processing method according to an embodiment of the present invention;

[0026] Figure 2 A diagram showing a specific example of a transaction data processing method according to an embodiment of the present invention;

[0027] Figure 3 FIG2 is another specific example diagram of the transaction data processing method in an embodiment of the present invention;

[0028] Figure 4 Schematic diagram of a transaction data processing device according to an embodiment of the present invention;

[0029] Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0031] The acquisition, transmission, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0032] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0033] Figure 1 FIG. 1 is a flow chart of a transaction data processing method according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0034] Step 101: Receive multiple pending transactions, each of which carries a counterparty identifier and a transaction amount.

[0035] Step 102: Calculate the approval probability of each pending transaction using a preset probability calculation model. The preset probability calculation model is pre-trained using the approval results and counterparty credit information of multiple historical transactions to train a logistic regression model. The approval results include whether the approval was passed and the approval time point.

[0036] Step 103: Calculate the estimated cumulative value for each counterparty based on the transaction amount and approval probability corresponding to the same counterparty identifier; the estimated cumulative value reflects the total transaction amount expected to occur with the counterparty;

[0037] Step 104: Determine the incurred value of each transaction counterparty based on the transactions obtained from the real incurred database; the incurred value reflects the total amount of transactions that have occurred with the transaction counterparty; the real incurred database stores the incurred transactions;

[0038] Step 105: Receive a first approval result of a first pending transaction; the first pending transaction carries an identifier of a first transaction counterparty;

[0039] Step 106: Modify the approval probability of the first pending transaction based on the first approval result, and update the estimated cumulative value of the first transaction counterparty. When the first approval result is approval, updating the estimated cumulative value of the first transaction counterparty includes: deleting pending transactions with a lower priority than the first pending transaction from the first transaction counterparty's pending transactions, and updating the estimated cumulative value of the first transaction counterparty based on the transaction amount and transaction probability of all pending transactions of the first transaction counterparty after deletion. The priority reflects the business importance and approval time of the pending transaction.

[0040] Step 107: Determine whether the first pending transaction triggers a major transaction based on the updated estimated cumulative value of the first transaction counterparty, the incurred value of the first transaction counterparty, and a preset cumulative threshold; the preset cumulative threshold is used to determine whether the total amount of all transactions with the transaction counterparty triggers a major transaction.

[0041] from Figure 1 As can be seen from the illustrated process, the embodiment of the present invention automatically calculates the cumulative value of the expected transactions and the cumulative value of the actual transactions that have occurred for all pending transactions with the same counterparty, and automatically updates the statistical cumulative value based on the real-time approval results. It then determines whether the approved transaction has triggered a major transaction based on the preset cumulative threshold used to determine whether the transaction has triggered a major transaction. Compared with the technical solutions in the prior art, the embodiment of the present invention first avoids manual calculations, reduces a large amount of labor costs, and improves the efficiency of identifying major transactions. Secondly, when there are multiple pending transactions at the same time, the expected transaction amount can be adjusted in real time based on the approval results of the transactions, thereby making the identification of major transactions more accurate and improving the accuracy of major transaction identification.

[0042] In the embodiment of the present invention, a trading system is established, which realizes Figure 1 In the method shown, the transaction system interacts with the business system and receives multiple pending transactions pushed by the business system, specifically including transaction information of each pending transaction. The transaction information includes but is not limited to transaction identifiers such as serial numbers, counterparty identifiers such as personal names of counterparties, corporate information of counterparties, transaction amounts, transaction types such as fixed assets, transportation costs, sales transactions, etc., descriptive information on transaction impacts, etc.

[0043] In one embodiment, the method described in the embodiment of the present invention is to process transactions of a specified type, such as establishing an expected change library and an actual occurred library for transactions of the same specified type, and performing corresponding processing. The transaction of the specified type can be a transaction with a special counterparty, in which the enterprise and its subsidiaries transfer resources, services, obligations or other interests with the special counterparty, and a designated regulatory department supervises the transaction of the specified type.

[0044] The transaction system can store multiple pending transactions received into the expected change database. The expected change database is mainly used to store transaction information of pending transactions.

[0045] In one embodiment, after receiving multiple transactions to be approved, the method may further include the following steps:

[0046] Step 1: Use a streaming architecture to obtain counterparty credit information and transaction data in real time. Credit information includes, but is not limited to, any one or any combination of the following: enterprise registration information, enterprise operating information, enterprise compliance and regulatory information, enterprise public opinion and market evaluation information, natural person credit information, natural person public affairs payment information, natural person tax information, and natural person public opinion information.

[0047] Step 2: Store multiple pending transactions and real-time credit information and transaction data in the expected change database; the expected change database stores pending and approved transactions in a graph structure, with pending transaction identifiers and counterparty identifiers as nodes, and transaction amounts, time information, credit information, and transaction data as node attributes.

[0048] In this example, in order to achieve faster and more efficient probability prediction, priority prediction, etc., the latest counterparty credit information and transaction data are obtained in real time, and the counterparty credit information and transaction data are stored as node attributes together with the pending transaction information.

[0049] During implementation, in order to quickly obtain pending transactions, counterparty credit information and transaction data can also be stored separately, that is, not placed in the expected change library, but stored in other databases, which can be stored in the form of a structure tree.

[0050] Credit information about the counterparty:

[0051] If the counterparty is a legal person, the counterparty's credit information may include: the industry to which the legal person belongs, the registered capital, the approval time of historical transactions that have been approved (if included), the legal person's operating status, the frequency of information changes on the legal person, utility bill records, and the institution's internal credit rating;

[0052] If the counterparty is a natural person, the counterparty credit information may include: the natural person's age, the natural person's social security record, the natural person's length of service, the nature of the natural person's work industry, the approval time of historical transactions that have passed approval (if included), the institution's internal credit rating, etc.

[0053] Transaction data of the counterparty: such as transaction frequency, transaction type, approval time information, etc., which will not be listed here one by one.

[0054] Afterwards, the preset probability calculation model is used to calculate the approval probability of each transaction to be approved.

[0055] In one embodiment, a preset probability calculation model is used to calculate the approval probability of each pending transaction, including: obtaining node information and node attribute information of the pending transaction from the expected change library; and calculating the approval probability of each pending transaction using the node information, node attribute information and the preset probability calculation model.

[0056] In one embodiment, the node information, node attribute information, and a preset probability calculation model are used to calculate the approval probability of each pending transaction, including:

[0057] Step 1: Perform data preprocessing on node information and node attribute information to obtain preprocessed data; data preprocessing includes natural language processing, data cleaning, and data conversion;

[0058] Step 2: Input the pre-processed data into the following preset probability calculation model to output the approval probability of each pending transaction:

[0059]

[0060] In the formula, p represents the probability value of approval, for example, approval is 1 and approval is 0; ψ represents the probability calculation function, which is used to judge the p-value result based on the probability result, b represents the sample deviation, and a n is the weight coefficient, x n is the nth preprocessed data, i.e., the independent variable of the constant term, and θ is the influencing factor, which is obtained based on the public opinion information related to the counterparty.

[0061] During implementation, the approval results and counterparty credit information of multiple historical transactions are used in advance to train, verify and test the logistic regression model to obtain the model parameters of the trained preset probability calculation model, such as weight coefficients and influencing factors.

[0062] Specifically, the p-value can be obtained by constructing a probability function of the transaction occurring (i.e., approval passing) and calculating the probability of the transaction occurring (i.e., approval passing) by using the characteristic parameters (e.g., a n and b), calculate the probability, and compare the resulting probability with a preset threshold (e.g., 50%) to determine the value of p for the corresponding single transaction in formula (1). For example, if the probability function calculation result is 60%, which is greater than 50%, then p is 1. The preset moment can be understood as the preset probability calculation model that needs to be updated in real time using historical data, and its characteristic parameters will change. Therefore, the characteristic parameters at the preset moment are obtained for calculation.

[0063] The p-value can be obtained as follows:

[0064] Step 1: For a pending transaction, extract the node features corresponding to each node and the edge features of each directed edge from the historical transactions of the counterparty of the pending transaction;

[0065] Step 2: Construct a probability function of the basic features and fit the basic probability function to obtain the basic features of the transaction occurrence probability function;

[0066] Step 3: Extract the basic features of the moment stage, construct a new function (logistic regression model) based on the basic features of the transaction probability function, and obtain the matrix required by the target.

[0067] When using a logistic regression model to predict the probability of approval, the specific steps are as follows:

[0068] Step 1: Data Preparation

[0069] Data collection: Collect historical transaction data, including but not limited to approval, failure, approval time information, etc.

[0070] Data cleaning: remove duplicate records, handle missing values ​​(delete or fill), detect and handle outliers.

[0071] Data transformation: Convert categorical variables to numerical representations, such as one-hot encoding; standardize or normalize continuous variables (such as transaction amounts) to facilitate model training.

[0072] Step 2: Feature Selection

[0073] Correlation analysis: Calculate the correlation between each feature and the target variable (approval result), and use methods such as correlation coefficient matrix or chi-square test to screen out important features.

[0074] Step 3: Model training

[0075] Divide the dataset into training and testing sets (ratio is 70% training, 30% testing).

[0076] Initialize the model: Use the logistic regression model and select the binary cross entropy loss function.

[0077] Parameter setting: Set regularization parameters (such as L1 or L2 regularization) to prevent overfitting; set the number of iterations and other hyperparameters.

[0078] Train Model: Fit a logistic regression model using the training set data.

[0079] Step 4: Model Evaluation

[0080] Evaluate model performance on the test set using metrics such as accuracy, precision, recall, and F1 score.

[0081] Step 5: Model maintenance and update

[0082] As more data accumulates, the model is retrained periodically to adapt to the new data distribution.

[0083] Formula (1) is obtained through the specific steps of the above logistic regression model.

[0084] The determination step of the influence factor θ is: (1) according to the counterparty credit information, collect and analyze public opinion by calling a large prophecy model; (2) the large language model analyzes the public opinion result of the counterparty, and obtains a public opinion prospect level (such as serious negative influence and negative influence, maintain the status quo, positive influence and optimistic positive influence); (3) the large language model feeds back the public opinion prospect level to the transaction system; (4) the transaction system converts the public opinion prospect level of the large language model into an influence factor (a numerical value) and adds it to formula (1) for calculation.

[0085] In step 103, the expected cumulative value of each counterparty is calculated according to the corresponding transaction amount and the approval probability of the same counterparty identifier; the expected cumulative value reflects the total amount of the transaction amount expected to occur by the counterparty.

[0086] In implementation, the expected cumulative value of each counterparty is calculated, for example, the transaction amount and the approval probability are multiplied, and then the product is accumulated.

[0087] At this time, in the process of accumulating the product, the p value of the to-be-approved transaction can be placed at the end, and the to-be-approved transaction with a p value of 0 can be sorted according to the time sequence to participate in the expected cumulative value calculation.

[0088] For example, there are n, n+1, n+2 and n+3 four transactions at the same time. According to the time sequence, n, n+1, n+2 and n+3, after calculating the approval probability, the result of n+1 is 0, then the sorting result is n, n+2, n+3 and n+1.

[0089] Considering that some to-be-approved transactions are executed and approved, the p value needs to be changed subsequently, and the to-be-approved transactions with different p values can be stored respectively in the embodiment of the application, for example, the data in the expected change library is structured and stored in batches according to the p value result, and two database tables are used to store the transactions with unchanged p value and the transactions with p value of 0.

[0090] In an embodiment, the expected cumulative value of each counterparty is calculated according to the corresponding transaction amount and the approval probability of the same counterparty identifier, which can include the following steps:

[0091] Step 1, using a preset linear regression model to calculate the priority of the to-be-approved transaction of the same counterparty, sorting the to-be-approved transaction of the same counterparty according to the priority to obtain a to-be-approved transaction sequence; the counterparty identifiers of any two to-be-approved transaction sequences are different; the preset linear regression model is obtained by training the linear regression model using historical transaction approval information, credit information and transaction data of multiple transaction counterparties; the transaction approval information includes the initiation approval time point, whether the approval is passed, and the approval time point;

[0092] Step 2: Based on the transaction amount, approval probability, and priority order of the pending transactions, calculate the estimated cumulative value for each counterparty using the following formula:

[0093] A 变 =P1×A1+P2×A2+P3×A3+……+P n ×A n (2);

[0094] Where A 变 Indicates the expected cumulative value, P n A represents the probability of approval of the nth pending transaction. n Indicates the transaction amount of the nth pending transaction. The priority of the n-1th pending transaction is higher than that of the nth pending transaction.

[0095] In this example, the priority of pending transactions is introduced. The priority can reflect the importance of the business and the length of the approval time, which is more in line with actual work needs.

[0096] Calculating the priority of pending transactions with the same counterparty using a preset linear regression model may include:

[0097] Step 1: Obtain the node information and node attribute information of pending transactions with the same counterparty from the expected change database;

[0098] Step 2: Calculate the priority of pending transactions with the same counterparty using the node information, node attribute information, and a preset linear regression model according to the following formula:

[0099] y′=(X×β+∈)×θ (3);

[0100] Where y' represents the priority; X is the input data; β is the model parameter matrix, which is obtained by least squares fitting; ∈ is the random error term; and θ is the impact factor, which is obtained based on the public opinion information related to the counterparty.

[0101] Specifically, the preset linear regression model is:

[0102]

[0103] Among them, x nnIs a constant term independent variable, that is, the independent variable of the constant term, which can be used as a vector feature for function construction of the relevant factors in historical transactions. The construction steps are as follows: take the nature of the counterparty (legal person and natural person) in the variable feature as the basic feature to select the influencing factors. If the nature of the counterparty is a legal person, the influencing factors selected are: the industry to which the legal person belongs, historical transaction amount, transaction frequency, the operating status of the legal person, the frequency of information changes of the legal person, water and electricity bill records, the credit rating within the institution, recent public opinion information of the legal person, the approval probability of historical transactions, etc.; If the nature of the counterparty is a natural person, the influencing factors selected are: the age of the natural person, the social security record of the natural person, the length of service of the natural person, the nature of the natural person's work industry, the credit rating within the institution, recent public opinion information of the natural person, historical transaction amount, transaction frequency, the approval probability of historical transactions, etc.; β n is a variable parameter obtained by function fitting, and θ is an influencing factor, which is usually a constant. The process of obtaining the influencing factor in the preset probability calculation model can be referred to.

[0104] For example, for the four specified types of transactions whose sorting results are n, n+2, n+3 and n+1, they are re-sorted according to the priority sorting results. If transaction n+3 is more important and has a shorter approval time, n is second, and n+2 is the longest, then the sorting results are updated to: n+3, n, n+2 and n+1.

[0105] In step 104, the incurred value of each transaction counterparty is determined based on the transactions obtained from the real incurred database; the incurred value reflects the total amount of transactions that have occurred with the transaction counterparty; the real incurred database stores the incurred transactions.

[0106] For example, the incurred value of each counterparty is determined based on transactions obtained from the actual incurred database using the following formula:

[0107] B 历 =k1×B1+k2×B2+k3×B3+……+k n ×B n (5);

[0108] Where B 历 Indicates the value that has occurred, k n Indicates the preset weight coefficient of the nth approved transaction, which is generally a business experience value and a constant. n Indicates the transaction amount. n , which can be understood as leaving room for change in calculations. For example, even if a transaction is approved, something unexpected may happen.

[0109] In summary, the calculation of the expected cumulative value and the incurred value for each counterparty has been completed.

[0110] When the transaction system receives the approval result of a pending transaction from the business system, it begins updating and modifying the estimated cumulative value. In step 105, the first approval result for a first pending transaction is received; the first pending transaction carries the identifier of the first transaction counterparty. The first pending transaction can be any pending transaction or any number of pending transactions.

[0111] In step 106, the approval probability of the first transaction to be approved is modified according to the first approval result, and the estimated accumulated value of the first transaction counterparty is updated.

[0112] When the first approval result is failure, the approval probability is modified according to the failure result, and formula (2) is modified at the same time, waiting for the approval processing of subsequent other transactions.

[0113] When the first approval result is passed, updating the expected cumulative value of the first transaction counterparty includes: deleting pending transactions with a lower priority than the first pending transaction from the pending transactions of the first transaction counterparty, and updating the expected cumulative value of the first transaction counterparty based on the transaction amount and transaction probability of all pending transactions of the first transaction counterparty after deletion.

[0114] For example, if the third transaction in formula (2) is approved, the estimated cumulative value of the first three transactions will be calculated.

[0115] Finally, in step 107 , it is determined whether the first transaction to be approved triggers a major transaction based on the updated estimated cumulative value of the first transaction counterparty, the incurred value of the first transaction counterparty, and the preset cumulative threshold.

[0116] In the embodiment of the present invention, significant transactions include transactions with transaction amounts exceeding a specified threshold, wherein the transaction amount includes a single transaction amount and a cumulative transaction amount of a single counterparty.

[0117] When implementing, it can be calculated according to the following formula:

[0118] Z 组合 =ψ(ω1×A 变 +ω2×B 历 ) (6);

[0119] Where Z 组合 Indicates whether a major transaction is triggered. For example, if it is a major transaction, Z 组合 Yes, not for major transactions, Z 组合 No; ψ() represents a judgment function. The data input to ψ() is subtracted from the preset cumulative threshold. If it is less than 0, it is not a major transaction. If it is greater than 0, it is a major transaction. ω1 and ω2 are variable parameters that can be obtained from business experience and regulatory requirements.

[0120] In an embodiment, a counterparty supervision flag is introduced, which is used to reflect whether the counterparty is still under supervision.

[0121] When the counterparty supervision flag is invalid, starting from the invalidation date of the counterparty, the expected occurrence amount in the expected change library after this time point is deducted in total. The cumulative occurred amount in the real occurred library to the last day of the validity period of the counterparty supervision flag is the calculation amount of the major transaction, and is stored in the history transaction of the transaction system.

[0122] When the validity period of the counterparty supervision flag is increased, if the supervision flag validity period is continuously increased on the original validity period, it is calculated according to the existing rules. If the counterparty supervision flag is re-activated within a period of time after invalidation, the major transaction is calculated according to the existing rules on the basis of the history transaction of the real occurred library.

[0123] In specific implementation, after the business system pushes the approval result to the transaction system, the transaction system receives the approval result text data, converts the text data into signal information, performs transaction information combination calculation according to formula (2), and after the counterparty supervision flag in the transaction system is changed, the supervision flag change information is converted into signal information, and transaction information combination calculation is performed. The basic features of the converted signal information are fed back in the change of P value. The vector eigenvalue change of P value under the preset time node is as follows.

[0124] The change of the approval result being approval is shown in Table 1.

[0125] Table 1

[0126]

[0127] The change of the approval result being disapproval is shown in Table 2.

[0128] Table 2

[0129]

[0130]

[0131] The change of the counterparty supervision flag is shown in Table 3.

[0132] Table 3

[0133]

[0134] In an embodiment, according to the updated first counterparty expected cumulative value, the first counterparty occurred value and the preset cumulative threshold, determining whether the first to-be-approved transaction triggers a major transaction can include:

[0135] comparing the sum of the updated projected cumulative value of the first counterparty and the incurred value of the first counterparty to a preset cumulative threshold;

[0136] When the total is greater than the preset cumulative threshold, it is determined that the first pending transaction triggers a major transaction; when the total is not greater than the preset cumulative threshold, it is determined that the first pending transaction does not trigger a major transaction.

[0137] In one embodiment, after determining that the first pending transaction triggers a major transaction, the process may further include: forwarding the first pending transaction to a high-level approval process for approval. The high-level approval process is used to approve major transactions. For example, senior management of the company may decide whether to approve the major transaction.

[0138] In one embodiment, after determining that the first pending transaction did not trigger a major transaction, it may also include: deleting the node corresponding to the first pending transaction from the expected change library, updating the expected cumulative value of the first transaction counterparty; storing the first pending transaction as a real transaction in the real occurred library, and updating the occurred value of the first transaction counterparty.

[0139] Similarly, after the advanced approval process determines that a significant transaction has not been triggered, the node corresponding to the first pending transaction will be deleted from the estimated change database, and the estimated cumulative value of the first counterparty will be updated. The first pending transaction will be stored as a real transaction in the actual transaction database, and the actual transaction value of the first counterparty will be updated. If the advanced approval process determines that a significant transaction has been triggered, the relevant regulations for significant transactions will be followed and will not be further elaborated here.

[0140] Figure 2 FIG. 1 is a specific example of a transaction data processing method according to an embodiment of the present invention. Figure 2 As shown, after determining the incurred value of each counterparty based on the transactions obtained from the real incurred database, it can also include:

[0141] Step 201: Use the trained time prediction model to predict the approval time point of each pending transaction; the time prediction model is pre-trained using the autoregressive integrated moving average (ARIMA) model using historical transaction approval information, counterparty credit information, and transaction data;

[0142] Step 202: Set the approval probability of each pending transaction to approved;

[0143] Step 203: Calculate the expected cumulative value and the actual value for each counterparty at the same approval time point in descending order of the approval time points of all pending transactions.

[0144] Step 204: Output the time point at which each trading counterparty reaches the preset cumulative threshold based on the preset cumulative threshold and the expected cumulative value and the actual value at the same approval time point for each trading counterparty.

[0145] In this example, at a preset time point, the future transaction trend of the counterparty is predicted. The predicted value is used to perform a combined calculation in formula (6). Based on the combined calculation results, a prediction is made as to whether a major transaction will be triggered. During implementation, historical data is first obtained. Secondly, a time series analysis function is constructed. The basic probability function is fitted using historical data to obtain the basic characteristics of the time series analysis function. Finally, based on the basic characteristics of the function, data is introduced to calculate the transaction value under the future time vector. The constructed functional relationship is:

[0146] Z 未来 ={ARIMA(v,d,q)}×θ (7);

[0147] Where Z 未来 represents the predicted cumulative value. Parameter v is the AR autoregressive model parameter, parameter d is the difference parameter, and parameter q is the MA moving average model parameter. All three parameters are obtained through model fitting. The model requires historical transaction data as a constant term independent variable. The independent variable of the constant term can be the relevant factors in historical transactions as vector features for function construction. The construction steps are as follows: The nature of the counterparty (legal person or natural person) in the variable special type is used as the basic feature to select influencing factors. If the counterparty is a legal person, the influencing factors selected are: the legal person's industry, historical transaction amount, transaction frequency, legal person's nature, legal person's operating status, frequency of changes in legal person supervisors, utility bill records, and recent legal person public opinion information. If the counterparty is a natural person, the influencing factors selected are: the natural person's age, social security record, length of service, historical transaction amount, and transaction frequency. θ is the influencing factor (generally a constant).

[0148] The calculated value Z at the preset time node 未来 Substitute it into formula (6) for calculation, and send a risk warning message of an upcoming major transaction to the business system based on the calculation result, so that the enterprise can prepare for the response in advance and improve the user experience.

[0149] In one embodiment, after outputting the time point at which each transaction counterparty reaches a preset cumulative threshold, the process may also include: counting the actual approval result and actual approval time information of each pending transaction, and obtaining the latest credit information and transaction data of the transaction counterparty; based on a principal component analysis algorithm, using the actual approval result, actual approval time information, the latest credit information and transaction data of each pending transaction, to update the model parameters of a time prediction model, a preset linear regression model, and a preset probability calculation model.

[0150] During implementation, each time a transaction is approved, the system uses the new approval time as a node, and uses the counterparty's credit data, transaction data, and other approval factors and results at that time as samples to incorporate into the training data for the new transaction time prediction model, the pre-set linear regression model, and the pre-set probability calculation model. Based on the training results, the trading system automatically adjusts the model parameters. Simultaneously, based on the new model parameters, the system adjusts the probability, ranking, and future transaction amount of pending transactions in real time, using the adjusted model. These adjusted results are then incorporated into the formula for calculating significant transactions.

[0151] Figure 3 FIG. 1 is another specific example of the transaction data processing method in an embodiment of the present invention, as shown in FIG. Figure 3 As shown in this method, the business system pushes pending transactions to the trading system, specifically pending transactions 1, 2, ..., N information. After receiving the pending transactions 1, 2, ..., N information, the trading system presses Figure 1 The method described in this article sequentially calculates the approval probability p, the expected cumulative value, and prioritizes the transaction. It then determines the actual transaction value for each counterparty based on the actual transaction database. It then receives approval information pushed by the business system in real time, updates the approval probability and expected cumulative value based on the latest approval information, and then, based on the real-time expected cumulative value and actual transaction value, determines whether the currently approved transaction has triggered a significant transaction for the counterparty. If a significant transaction has been triggered, the business system is prompted for further approval. If not, the transaction is deleted from the expected change database and the counterparty's transaction amount in the actual transaction database is updated.

[0152] In summary, the transaction data processing method in the embodiment of the present invention is based on the real-time detection of the transaction system, counterparty supervision flags, transaction status and cumulative transaction amount, and is more accurate in calculating major transactions, and has the following beneficial technical effects.

[0153] 1) The shift from manual matching to calculation by the trading system reduces a significant amount of labor costs. At the same time, real-time judgment can be made based on the validity period of the counterparty's regulatory mark, making the identification and calculation of major transactions more accurate.

[0154] 2) When there are multiple transactions at the same time, the proposed transaction amount can be adjusted in real time based on the approval results of the transactions, thereby making the identification of major transactions more accurate.

[0155] 3) In the case of multiple transactions, it can measure in real time whether a transaction constitutes a major transaction based on the approval results of the transaction, provide advance reminders for transactions that meet the major transaction standards, and conduct relevant approval processes to reduce compliance risks.

[0156] 4) In the case of multiple transactions, the algorithm effectively excludes unreasonable transactions from the calculation in advance, thereby improving the accuracy of major transactions.

[0157] 5) Predicting trading behaviors with counterparties in advance and responding promptly to transactions that may trigger major transactions improves business operation efficiency.

[0158] The present invention also provides a transaction data processing device, as described in the following embodiments. Since the principle of solving the problem of the device is similar to that of the transaction data processing method, the implementation of the device can refer to the implementation of the transaction data processing method, and the repeated parts will not be repeated.

[0159] Figure 4 FIG. 1 is a schematic diagram of a transaction data processing device according to an embodiment of the present invention. Figure 4 The transaction data processing device 400 includes:

[0160] The data receiving module 401 is used to receive multiple pending transactions; the pending transactions carry counterparty identification and transaction amount;

[0161] Approval Probability Prediction Module 402 is used to calculate the approval probability of each pending transaction using a preset probability calculation model. The preset probability calculation model is pre-trained using the approval results and counterparty credit information of multiple historical transactions to train a logistic regression model. The approval result includes whether the approval was passed and the approval time point.

[0162] The estimated cumulative value calculation module 403 is used to calculate the estimated cumulative value of each transaction counterparty based on the transaction amount and approval probability corresponding to the same transaction counterparty identifier; the estimated cumulative value reflects the total transaction amount expected to occur with the transaction counterparty;

[0163] The incurred value calculation module 404 is used to determine the incurred value of each transaction counterparty based on transactions obtained from the real incurred database; the incurred value reflects the total amount of transactions that have occurred with the transaction counterparty; the real incurred database stores incurred transactions;

[0164] The expected cumulative value updating module 405 is configured to receive a first examination result of a first to-be-examined transaction, the first to-be-examined transaction carrying an identifier of a first transaction counterparty; modify the examination pass probability of the first to-be-examined transaction according to the first examination result, and update the expected cumulative value of the first transaction counterparty; when the first examination result is pass, the updating of the expected cumulative value of the first transaction counterparty comprises: deleting, from the to-be-examined transactions of the first transaction counterparty, to-be-examined transactions with a priority lower than that of the first to-be-examined transaction, and updating the expected cumulative value of the first transaction counterparty according to the transaction amount and the transaction occurrence probability of all the to-be-examined transactions of the first transaction counterparty after the deletion; the priority reflects the business importance and the examination duration of the to-be-examined transaction.

[0165] The trigger judgment module 406 is configured to determine whether the first to-be-examined transaction triggers a major transaction according to the updated expected cumulative value of the first transaction counterparty, the occurred value of the first transaction counterparty, and a preset cumulative threshold value; the preset cumulative threshold value is used to determine whether the total transaction amount of all the transactions of the transaction counterparty triggers a major transaction.

[0166] In an embodiment, the apparatus 400 further comprises an expected fluctuation library processing module, which is configured to:

[0167] After the data receiving module 401 receives a plurality of to-be-examined transactions, the credit information and the transaction data of the transaction counterparty are acquired in real time through a streaming architecture; the credit information of the transaction counterparty comprises one or any combination of the following: enterprise registration information, enterprise operation information, enterprise compliance supervision information, enterprise public opinion and market evaluation information, natural person credit information, natural person public affairs payment information, natural person tax information, and natural person public opinion information.

[0168] The plurality of to-be-examined transactions and the credit information and the transaction data of the transaction counterparty acquired in real time are stored in an expected fluctuation library; the to-be-examined transactions and the examined transactions in the expected fluctuation library are stored in a graph structure, the to-be-examined transactions and the examined transactions being nodes, and the transaction amount, the time information, the credit information, and the transaction data being node attributes.

[0169] In an embodiment, the examination pass probability prediction module 402 is specifically configured to: acquire the node information and the node attribute information of the to-be-examined transactions from the expected fluctuation library; and calculate the examination pass probability of each to-be-examined transaction by using the node information, the node attribute information, and a preset probability calculation model.

[0170] In an embodiment, the examination pass probability prediction module 402 is specifically configured to:

[0171] The node information and the node attribute information are subjected to data preprocessing to obtain preprocessed data; the data preprocessing comprises natural language processing, data cleaning, and data conversion.

[0172] The pre-processed data is input into the following preset probability calculation model to output the approval probability of each pending transaction: the preset probability calculation model uses the binary cross entropy loss function;

[0173]

[0174] In the formula, p represents the probability of approval, ψ represents the probability calculation function, b represents the sample deviation, and a n is the weight coefficient, x n is the nth pre-processed data, and θ is the influence factor, which is obtained based on the public opinion information related to the counterparty.

[0175] In one embodiment, the estimated accumulated value calculation module 403 is specifically configured to:

[0176] A preset linear regression model is used to calculate the priority of pending transactions for the same counterparty, and the pending transactions for the same counterparty are sorted by priority to obtain a sequence of pending transactions. Any two sequences of pending transactions have different counterparty identifiers. The preset linear regression model is pre-trained using historical transaction approval information, credit information, and transaction data of multiple counterparties. The transaction approval information includes the time of initiation of approval, whether the approval is passed, and the time of approval.

[0177] Based on the transaction amount, approval probability, and priority order of transactions in the queue for approval, the estimated cumulative value of each counterparty is calculated using the following formula:

[0178] A 变 =P1×A1+P2×A2+P3×A3+……+P n ×A n ;

[0179] Where A 变 Indicates the expected cumulative value, P n A represents the probability of approval of the nth pending transaction. n Indicates the transaction amount of the nth pending transaction. The priority of the n-1th pending transaction is higher than that of the nth pending transaction.

[0180] In one embodiment, the estimated accumulated value calculation module 403 is specifically configured to:

[0181] Obtain node information and node attribute information of pending transactions with the same counterparty from the expected change database;

[0182] The priority of pending transactions with the same counterparty is calculated using the node information, node attribute information, and a preset linear regression model according to the following formula:

[0183] y'=(X×β+∈)×θ;

[0184] Where y' represents the priority; X is the input data; β is the model parameter matrix, which is obtained by least squares fitting; ∈ is the random error term; and θ is the impact factor, which is obtained based on the public opinion information related to the counterparty.

[0185] In one embodiment, the occurred value calculation module 404 is specifically configured to:

[0186] The incurred value of each counterparty is determined based on the transactions obtained from the real incurred database according to the following formula:

[0187] B 历 =k1×B1+k2×B2+k3×B3+……+k n ×B n ;

[0188] Where B 历 Indicates the value that has occurred, k n Indicates the preset weight coefficient of the nth approved transaction, B n Indicates the transaction amount.

[0189] In one embodiment, the trigger determination module 406 is specifically configured to:

[0190] comparing the sum of the updated projected cumulative value of the first counterparty and the incurred value of the first counterparty to a preset cumulative threshold;

[0191] When the total is greater than the preset cumulative threshold, the first pending transaction is determined to have triggered a major transaction;

[0192] When the total is not greater than the preset cumulative threshold, it is determined that the first pending transaction does not trigger a major transaction.

[0193] In one embodiment, the device 400 also includes: an advanced approval processing module, which is used to: after the trigger judgment module 406 determines that the first pending transaction triggers a major transaction, push the first pending transaction to the advanced approval process for approval, and the advanced approval process is used to approve major transactions.

[0194] In one embodiment, the device 400 also includes: a post-approval processing module, which is used to: after the trigger judgment module 406 determines that the first pending transaction does not trigger a major transaction, delete the node corresponding to the first pending transaction from the expected change library and update the expected cumulative value of the first transaction counterparty; store the first pending transaction as a real transaction in the real occurred library and update the occurred value of the first transaction counterparty.

[0195] In one embodiment, the apparatus 400 further includes a significant transaction advance prediction module, which is configured to:

[0196] After determining the actual value of each counterparty based on transactions obtained from the actual actual value database, the actual value calculation module 404 uses a trained time prediction model to predict the approval time of each pending transaction. The time prediction model is pre-trained using an autoregressive integrated moving average (ARIMA) model using historical transaction approval information, counterparty credit information, and transaction data.

[0197] Set the approval probability of each pending transaction to approved;

[0198] Calculate the expected cumulative value and actual value for each counterparty at the same approval time point, based on the approval time points of all pending transactions from earliest to latest.

[0199] Based on the preset cumulative threshold and the expected cumulative value and the actual value at the same approval time point for each counterparty, the time point at which each counterparty reaches the preset cumulative threshold is output.

[0200] In one embodiment, the apparatus 400 further includes a model iterative updating module, which is configured to:

[0201] After the major transaction advance prediction module outputs the time point when each transaction counterparty reaches the preset cumulative threshold, the actual approval results and actual approval time information of each pending transaction are counted to obtain the latest counterparty credit information and transaction data; based on the principal component analysis algorithm, the actual approval results, actual approval time information, latest counterparty credit information and transaction data of each pending transaction are used to update the model parameters of the time prediction model, the preset linear regression model, and the preset probability calculation model.

[0202] Figure 5 Schematic diagram of a computer device according to an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention further provides a computer device 500, including a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501, wherein the processor 501 implements the above-mentioned transaction data processing method when executing the computer program 503.

[0203] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned transaction data processing method is implemented.

[0204] The embodiment of the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the transaction data processing method.

[0205] In the embodiment of the present application, the expected occurrence transaction cumulative value and the real occurrence transaction cumulative value of all the to-be-approved transactions of the same transaction counterparty are automatically counted, and the counted cumulative values are automatically updated according to the real-time approval result, and whether the approved transaction triggers a major transaction is judged according to the preset cumulative threshold for judging the triggering of a major transaction. Compared with the prior art, the embodiment of the present application first avoids manual calculation, reduces a large amount of manual cost, and improves the identification efficiency of a major transaction, and second, in the case that multiple to-be-approved transactions exist at the same time, the expected occurrence amount of the transaction can be adjusted in real time according to the approval result of the transaction, so that the major transaction identification is more accurate, and the identification accuracy of the major transaction is improved.

[0206] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer usable program codes.

[0207] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks.

[0208] These computer program instructions can also be stored in a computer readable memory that can guide the computer or other programmable data processing devices to work in a specific way, so that the instructions stored in the computer readable memory produce a manufactured product including instruction devices that implement the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks.

[0209] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0210] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A transaction data processing method, characterized in that: include: Receive multiple pending transactions; the pending transactions carry counterparty identification and transaction amount; The probability of approval for each pending transaction is calculated using a preset probability calculation model. The preset probability calculation model is pre-trained using the approval results and counterparty credit information of multiple historical transactions to train a logistic regression model. The approval results include whether the approval was passed and the approval time point. Based on the transaction amount and approval probability corresponding to the same counterparty ID, the estimated cumulative value of each counterparty is calculated; the estimated cumulative value reflects the total transaction amount expected to occur with the counterparty; Determine the incurred value of each counterparty based on transactions obtained from the real incurred database; The actual value reflects the total amount of transactions that have occurred with the counterparty; the actual actual value stores transactions that have occurred; Receiving a first approval result of the first pending transaction; The first transaction to be approved carries an identifier of the first transaction counterparty; Modifying the approval probability of the first pending transaction based on the first approval result, and updating the estimated cumulative value of the first transaction counterparty; wherein, when the first approval result is approval, updating the estimated cumulative value of the first transaction counterparty includes: deleting pending transactions with a lower priority than the first pending transaction from the first transaction counterparty's pending transactions, and updating the estimated cumulative value of the first transaction counterparty based on the transaction amount and transaction probability of all pending transactions of the first transaction counterparty after deletion; the priority reflects the business importance and approval time of the pending transaction; Determining whether the first pending transaction triggers a major transaction based on the updated estimated cumulative value of the first transaction counterparty, the incurred value of the first transaction counterparty, and a preset cumulative threshold; the preset cumulative threshold is used to determine whether the total amount of all transactions with the transaction counterparty triggers a major transaction; After receiving multiple pending transactions, it also includes: Through a streaming architecture, real-time access to counterparty credit information and transaction data; such credit information includes any one or any combination of the following: enterprise registration information, enterprise operating information, enterprise compliance and regulatory information, enterprise public opinion and market evaluation information, natural person credit information, natural person public affairs payment information, natural person tax information, and natural person public opinion information; Multiple pending transactions and real-time credit information and transaction data are stored in the expected change database. The expected change database stores pending and approved transactions in a graph structure, with pending transaction IDs and counterparty IDs as nodes, and transaction amounts, time information, credit information, and transaction data as node attributes. The estimated cumulative value for each counterparty is calculated based on the transaction amount and approval probability corresponding to the same counterparty ID, including: A preset linear regression model is used to calculate the priority of pending transactions for the same counterparty, and the pending transactions for the same counterparty are sorted by priority to obtain a sequence of pending transactions. Any two sequences of pending transactions have different counterparty identifiers. The preset linear regression model is pre-trained using historical transaction approval information, credit information, and transaction data of multiple counterparties. The transaction approval information includes the time of initiation of approval, whether the approval is passed, and the time of approval. Based on the transaction amount, approval probability, and priority order of transactions in the queue for approval, the estimated cumulative value of each counterparty is calculated using the following formula: A 变 =P1×A1+P2×A2+P3×A3+......+P n ×A n ; Where A 变 Indicates the expected cumulative value, P n A represents the probability of approval of the nth pending transaction. n Indicates the transaction amount of the nth pending transaction. The priority of the n-1th pending transaction is higher than the nth pending transaction. The priority of pending transactions with the same counterparty is calculated using a preset linear regression model, including: Obtain node information and node attribute information of pending transactions with the same counterparty from the expected change database; The priority of pending transactions with the same counterparty is calculated using the node information, node attribute information, and a preset linear regression model according to the following formula: y'=(X×β+ )×θ; Where y' represents the priority; X is the input data; β is the model parameter matrix, which is obtained by least squares fitting; is the random error term; θ is the impact factor, which is obtained based on the public opinion information related to the counterparty.

2. The method according to claim 1, wherein The probability of approval for each pending transaction is calculated using a preset probability calculation model, including: Obtain the node information and node attribute information of the pending transaction from the expected change database; Utilize node information, node attribute information and preset probability calculation model to calculate the approval probability of each pending transaction.

3. The method according to claim 2, wherein Utilizing node information, node attribute information, and a preset probability calculation model, the approval probability of each pending transaction is calculated, including: Perform data preprocessing on node information and node attribute information to obtain preprocessed data; data preprocessing includes natural language processing, data cleaning, and data conversion; The pre-processed data is input into the following preset probability calculation model to output the approval probability of each pending transaction: the preset probability calculation model uses the binary cross entropy loss function; ； In the formula, p represents the probability of approval, ψ represents the probability calculation function, b represents the sample deviation, and a n is the weight coefficient, x n is the nth pre-processed data, and θ is the influence factor, which is obtained based on the public opinion information related to the counterparty.

4. The method according to claim 1, wherein Determine the incurred value of each counterparty based on transactions obtained from the real incurred database, including: The incurred value of each counterparty is determined based on the transactions obtained from the real incurred database according to the following formula: B 历 =k1×B1+k2×B2+k3×B3+......+k n ×B n ; Where B 历 Indicates the value that has occurred, k n Indicates the preset weight coefficient of the nth approved transaction, B n Indicates the transaction amount.

5. The method according to claim 1, wherein Determine whether the first pending transaction triggers a significant transaction based on the updated estimated cumulative value of the first transaction counterparty, the incurred value of the first transaction counterparty, and the preset cumulative threshold, including: comparing the sum of the updated projected cumulative value of the first counterparty and the incurred value of the first counterparty to a preset cumulative threshold; When the total is greater than the preset cumulative threshold, the first pending transaction is determined to have triggered a major transaction; When the total is not greater than the preset cumulative threshold, it is determined that the first pending transaction does not trigger a major transaction.

6. The method according to claim 5, wherein After determining that the first pending transaction triggers a major transaction, the following also applies: The first pending transaction is pushed to the advanced approval process for approval. The advanced approval process is used to approve major transactions.

7. The method according to claim 5, wherein After confirming that the first pending transaction does not trigger a major transaction, the following also applies: Deleting the node corresponding to the first pending transaction from the estimated change database and updating the estimated cumulative value of the first transaction counterparty; The first pending transaction is stored as a real transaction in the real transaction database, and the transaction value of the first transaction counterparty is updated.

8. The method according to claim 1, wherein After determining the incurred value of each counterparty based on the transactions obtained from the real incurred database, it also includes: Using a trained time prediction model, the approval time point of each pending transaction is predicted; the time prediction model is pre-trained using the autoregressive integrated moving average (ARIMA) model using historical transaction approval information, counterparty credit information, and transaction data; Set the approval probability of each pending transaction to approved; Calculate the expected cumulative value and actual value for each counterparty at the same approval time point, based on the approval time points of all pending transactions from earliest to latest. Based on the preset cumulative threshold and the expected cumulative value and the actual value at the same approval time point for each counterparty, the time point at which each counterparty reaches the preset cumulative threshold is output.

9. The method according to claim 8, wherein Outputs the time point at which each counterparty reaches the preset cumulative threshold, including: Collect statistics on the actual approval results and actual approval time of each pending transaction, and obtain the latest counterparty credit information and transaction data; Based on the principal component analysis algorithm, the model parameters of the time prediction model, the preset linear regression model, and the preset probability calculation model are updated using the actual approval results, actual approval time information, the latest counterparty credit information and transaction data of each pending transaction.

10. A transaction data processing device, characterized in that: include: A data receiving module is used to receive multiple pending transactions; the pending transactions carry a counterparty identifier and a transaction amount; The approval probability prediction module is used to calculate the approval probability of each pending transaction using a preset probability calculation model. The preset probability calculation model is pre-trained using the approval results and counterparty credit information of multiple historical transactions to train a logistic regression model. The approval results include whether the approval was passed and the approval time point. An estimated cumulative value calculation module is used to calculate the estimated cumulative value of each counterparty based on the transaction amount and approval probability corresponding to the same counterparty identifier; the estimated cumulative value reflects the total transaction amount expected to occur with the counterparty; The incurred value calculation module is used to determine the incurred value of each counterparty based on the transactions obtained from the real incurred database; The actual value reflects the total amount of transactions that have occurred with the counterparty; the actual actual value stores transactions that have occurred; an estimated cumulative value updating module, configured to receive a first approval result of a first transaction to be approved; The first pending transaction carries an identifier of the first transaction counterparty; the approval probability of the first pending transaction is modified based on the first approval result, and the estimated cumulative value of the first transaction counterparty is updated; wherein, when the first approval result is approval, updating the estimated cumulative value of the first transaction counterparty includes: deleting pending transactions with a lower priority than the first pending transaction from the first transaction counterparty's pending transactions, and updating the estimated cumulative value of the first transaction counterparty based on the transaction amount and transaction probability of all pending transactions of the first transaction counterparty after deletion; the priority reflects the business importance and approval time of the pending transaction; a trigger determination module, configured to determine whether the first pending transaction triggers a major transaction based on the updated estimated cumulative value of the first transaction counterparty, the incurred value of the first transaction counterparty, and a preset cumulative threshold; the preset cumulative threshold is used to determine whether the total amount of all transactions with the transaction counterparty triggers a major transaction; It also includes an expected change library processing module; the expected change library processing module is used to: after the data receiving module receives multiple pending transactions, obtain the credit information and transaction data of the counterparty in real time through a streaming architecture; the counterparty credit information includes one of the following or any combination: enterprise registration information, enterprise operation information, enterprise compliance and supervision information, enterprise public opinion and market evaluation information, natural person credit information, natural person public affairs payment information, natural person tax information, natural person public opinion information; multiple pending transactions and the credit information and transaction data of the counterparty obtained in real time are stored in the expected change library; the pending and under-approval transactions are stored in the expected change library in the form of a graph structure, in which the pending transaction identifier and the counterparty identifier are nodes, and the transaction amount, time information, credit information and transaction data are node attributes; The estimated cumulative value calculation module is specifically used for: A preset linear regression model is used to calculate the priority of pending transactions for the same counterparty, and the pending transactions for the same counterparty are sorted by priority to obtain a sequence of pending transactions. Any two sequences of pending transactions have different counterparty identifiers. The preset linear regression model is pre-trained using historical transaction approval information, credit information, and transaction data of multiple counterparties. The transaction approval information includes the time of initiation of approval, whether the approval is passed, and the time of approval. Based on the transaction amount, approval probability, and priority order of transactions in the queue for approval, the estimated cumulative value of each counterparty is calculated using the following formula: A 变 =P1×A1+P2×A2+P3×A3+......+P n ×A n ; Where A 变 Indicates the expected cumulative value, P n A represents the probability of approval of the nth pending transaction. n Indicates the transaction amount of the nth pending transaction. The priority of the n-1th pending transaction is higher than the nth pending transaction. The estimated cumulative value calculation module is specifically used for: Obtain node information and node attribute information of pending transactions with the same counterparty from the expected change database; The priority of pending transactions with the same counterparty is calculated using the node information, node attribute information, and a preset linear regression model according to the following formula: y'=(X×β+ )×θ; Where y' represents the priority; X is the input data; β is the model parameter matrix, which is obtained by least squares fitting; is the random error term; θ is the impact factor, which is obtained based on the public opinion information related to the counterparty.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images