Branch service parameter determination method and device, equipment, medium and product

Abstract

The invention provides a branch mechanism business parameter determination method and device, equipment, a medium and a product, and relates to the technical field of finance. The method comprises the steps of obtaining multiple pieces of transaction information which are processed by a branch mechanism within a preset duration and meet transaction conditions of a preset transaction model, wherein the transaction information comprises transaction parameters corresponding to at least one transaction factor; according to the number of at least one transaction factor in the transaction information, determining a transaction model type of a preset transaction model, the transaction model type including a single-factor transaction model and a multi-factor transaction model; according to the transaction model type and a transaction parameter corresponding to at least one transaction factor in the plurality of transaction information, determining a branch business parameter corresponding to the branch; wherein the branch business parameters are used for representing transaction risk degrees of multiple pieces of transaction information processed by the branch. The method can improve the efficiency of determining the business parameters of the branch mechanism.

Description

Technical Field

[0001] This application relates to the field of financial technology, and in particular to a method, apparatus, equipment, medium and product for determining the business parameters of a branch office. Background Technology

[0002] With the development of financial technology, the amount of transaction information processed by branches (e.g., branches) is also increasing. In order to ensure the security of the transaction information processed by the branch, it is necessary to determine the degree of transaction risk of the transaction information processed by the branch.

[0003] In related technologies, firstly, multiple transaction information entries from branch offices that meet the transaction conditions are manually inspected. Then, these multiple transaction entries are manually reviewed to determine the degree of transaction risk associated with the transactions processed by the branch offices.

[0004] However, the inventors have found at least the following technical problems in the prior art: manually detecting and reviewing transaction information is time-consuming and laborious, resulting in low efficiency in determining the degree of transaction risk. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, medium, and product for determining business parameters of branch offices, in order to solve the technical problem of low efficiency in generating interface change information in the prior art.

[0006] Firstly, this application provides a method for determining the business parameters of a branch office, including:

[0007] Obtain multiple transaction information items processed by branch offices within a preset time period that meet the transaction conditions of a preset transaction model. The transaction information items include transaction parameters corresponding to at least one transaction factor.

[0008] Based on the number of at least one trading factor in the trading information, the trading model type of the preset trading model is determined, wherein the trading model type includes a single-factor trading model and a multi-factor trading model;

[0009] Based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among the multiple transaction information, the branch office business parameters are determined; wherein, the branch office business parameters are used to represent the transaction risk level of the multiple transaction information processed by the branch office.

[0010] Secondly, this application provides a device for determining the business parameters of a branch office, comprising:

[0011] The acquisition module is used to acquire multiple transaction information of a branch office within a preset time period that meets the transaction conditions of a preset transaction model. The transaction information includes transaction parameters corresponding to at least one transaction factor.

[0012] The first determining module is used to determine the trading model type of the preset trading model based on the number of at least one trading factor in the trading information, wherein the trading model type includes a single-factor trading model and a multi-factor trading model.

[0013] The second determining module is used to determine the branch office business parameters corresponding to the branch office based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among the multiple transaction information; wherein, the branch office business parameters are used to represent the transaction risk level of the multiple transaction information processed by the branch office.

[0014] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0015] The memory stores the instructions that the computer executes;

[0016] The processor executes computer execution instructions stored in memory, causing the processor to perform the implementation method described in the first aspect above.

[0017] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the embodiments described in the first aspect above.

[0018] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, is used to implement the embodiments described in the first aspect above.

[0019] This application provides a method, apparatus, device, medium, and product for determining branch office business parameters. The method includes: acquiring multiple transaction information items processed by a branch office within a preset time period that meet the transaction conditions of a preset transaction model, wherein the transaction information includes transaction parameters corresponding to at least one transaction factor; determining the transaction model type of the preset transaction model based on the number of at least one transaction factor in the transaction information, wherein the transaction model type includes a single-factor transaction model and a multi-factor transaction model; and determining the branch office business parameters corresponding to the branch office based on the transaction model type and the transaction parameters corresponding to at least one transaction factor in the multiple transaction information items; wherein the branch office business parameters are used to represent the transaction risk level of the multiple transaction information items processed by the branch office. In this embodiment, firstly, multiple transaction information items processed by the branch office that meet the transaction conditions are screened through a preset transaction model; then, the branch office business parameters are determined through the transaction model type and the transaction parameters corresponding to at least one transaction factor in the multiple transaction information items. Compared with manually determining the branch office business parameters, this improves the efficiency of determining the branch office business parameters. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0021] Figure 1 A schematic diagram illustrating an application scenario for a method for determining business parameters of a branch office provided in this application embodiment;

[0022] Figure 2 The flowchart of a method for determining branch office business parameters provided in this application embodiment Figure 1 ;

[0023] Figure 3 A schematic diagram of a method for determining branch office business parameters provided in this application embodiment. Figure 1 ;

[0024] Figure 4 This application provides an illustration of scoring information for model weight parameters. Figure 1 ;

[0025] Figure 5 A schematic diagram of the structure of a device for determining business parameters of a branch office provided in an embodiment of this application;

[0026] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0027] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0028] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0029] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse.

[0030] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0031] It should be noted that the methods, devices, equipment, media and products for determining branch office business parameters provided in this application can be used in the field of financial technology, or in any field other than financial technology. The application fields of the methods, devices, equipment, media and products for determining branch office business parameters in this application are not limited.

[0032] With the development of financial technology, the amount of transaction information processed by branches (e.g., branches) is also increasing. In order to ensure the security of the transaction information processed by the branch, it is necessary to determine the degree of transaction risk of the transaction information processed by the branch.

[0033] In related technologies, firstly, multiple transaction information entries from branch offices that meet the transaction conditions are manually inspected. Then, these multiple transaction entries are manually reviewed to determine the level of transaction risk for the information processed by the branch office. However, manually inspecting and reviewing transaction information is time-consuming and labor-intensive, resulting in low efficiency in determining the level of transaction risk.

[0034] Therefore, determining the efficiency of the transaction risk level of transaction information processed by branch offices is a technical problem that urgently needs to be solved.

[0035] To solve the above-mentioned technical problems, the inventor's technical concept is as follows: by pre-setting the transaction model type of the transaction model and the transaction parameters corresponding to the transaction factors in the transaction information, the degree of transaction risk of the transaction information processed by the branch office is determined.

[0036] Accordingly, the specific steps may include: First, acquiring multiple transaction information items processed by the branch within a preset time period that meet the transaction conditions of a preset transaction model, wherein the transaction information includes transaction parameters corresponding to at least one transaction factor. Then, determining the transaction model type of the preset transaction model based on the number of at least one transaction factor in the transaction information, wherein the transaction model type includes single-factor transaction models and multi-factor transaction models. Finally, determining the branch business parameters corresponding to the branch based on the transaction model type and the transaction parameters corresponding to at least one transaction factor in the multiple transaction information; wherein the branch business parameters are used to represent the transaction risk level of the multiple transaction information items processed by the branch.

[0037] In this technical solution, firstly, multiple transaction information that meets the transaction conditions and is processed by the branch office is screened through a preset transaction model. Then, the business parameters of the branch office are determined by the transaction model type and the transaction parameters corresponding to at least one transaction factor among the multiple transaction information. Compared with manually determining the business parameters of the branch office, this improves the efficiency of determining the business parameters of the branch office.

[0038] Figure 1 This is a schematic diagram illustrating an application scenario for a method for determining branch office business parameters provided in an embodiment of this application. For example... Figure 1 As shown, terminal 101 and server 102 are connected via a network. A user can send a request to server 102 to detect branch office business parameters via terminal 101. Server 102 receives the request from terminal 101, determines the branch office business parameters corresponding to the branch office using the method provided in this application, and returns the corresponding branch office business parameters to terminal 101 for display.

[0039] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0040] Figure 2 The flowchart of a method for determining branch office business parameters provided in this application embodiment Figure 1 ,like Figure 2 As shown, the method includes:

[0041] S201. Obtain multiple transaction information items processed by the branch within a preset time period that meet the transaction conditions of the preset transaction model. The transaction information items include transaction parameters corresponding to at least one transaction factor.

[0042] In this embodiment of the disclosure, the value of the preset duration is not specifically limited, and the preset duration can be 1 week, 1 month, 1 quarter, etc.

[0043] Optionally, preset transaction conditions in the transaction model are used to filter transaction information used to determine the business parameters of branch offices. These preset transaction conditions can be any type of transaction condition. Examples include: "abnormal transfer after order cancellation," "counter deposit exceeding a preset amount," and "counter withdrawal exceeding a preset amount."

[0044] Optionally, the transaction factor can be any attribute information from the transaction information. For example, transaction amount, number of overdue days, transaction frequency, etc.

[0045] S202. Based on the number of at least one trading factor in the trading information, determine the trading model type of the preset trading model, wherein the trading model type includes single-factor trading model and multi-factor trading model.

[0046] In this embodiment of the disclosure, if the number of at least one trading factor in the trading information is one, then the trading model type of the preset trading model is determined to be a single-factor trading model; if the number of at least one trading factor in the trading information is multiple, then the trading model type of the preset trading model is determined to be a multi-factor trading model.

[0047] It should be noted that the method for determining branch office business parameters varies depending on the number of transaction factors.

[0048] S203. Based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among multiple transaction information, determine the branch office business parameters corresponding to the branch office; wherein, the branch office business parameters are used to represent the transaction risk level of multiple transaction information processed by the branch office.

[0049] In some embodiments, the transaction model type is a single-factor transaction model, and the branch office business parameters corresponding to the branch office can be determined by normalizing the transaction parameters corresponding to the transaction factors. Accordingly, determining the branch office business parameters corresponding to the branch office based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among multiple transaction information includes: if the preset transaction model type is a single-factor transaction model, then normalizing the transaction parameters corresponding to the transaction factors in each transaction information according to the transaction parameters corresponding to the transaction factors among multiple transaction information to obtain normalized parameters corresponding to each transaction information; determining the average value of the normalized parameters corresponding to multiple transaction information based on the normalized parameters corresponding to each transaction information; and determining the average value of the normalized parameters corresponding to multiple transaction information as the branch office business parameters corresponding to the branch office.

[0050] Optionally, based on the trading parameters corresponding to the trading factors in multiple trading information, the trading parameters corresponding to the trading factors in each trading information are normalized to obtain the normalized parameters corresponding to each trading information, including:

[0051] Based on the trading parameters corresponding to the trading factors in multiple trading information, determine the mean and standard deviation of the trading parameters corresponding to the trading factors; for the trading parameters corresponding to the trading factors in each trading information, determine the difference between the trading parameters and the mean; based on the ratio of the difference to the standard deviation, determine the normalization parameter corresponding to the trading information.

[0052] For example, the number of multiple transaction information items that meet the transaction conditions of the preset transaction model processed by a branch within a preset time period is n; the transaction parameters corresponding to the transaction factors in the multiple transaction information items can be represented as N1, N2, N3, ..., N n The average value N of the trading parameters corresponding to the trading factor. mean The standard deviation can be expressed as N. std .

[0053] In this embodiment of the disclosure, since the quantification of the trading parameters corresponding to each trading factor is different, the trading parameters corresponding to the trading factors in each trading information are normalized according to the trading parameters corresponding to the trading factors in multiple trading information, so that the quantification can be uniform.

[0054] Optionally, for the nth transaction information, the normalization parameter corresponding to the transaction information is determined as D based on the ratio of the difference to the standard deviation. n =(N n -N mean ) / N std .

[0055] Accordingly, the average value of the normalized parameters corresponding to multiple transaction information is determined as the branch office business parameter for the branch office: E = (D1 + D2 + ... + D...) n ) / n.

[0056] In other embodiments, the trading model is a multi-factor trading model, which treats multiple risk factors as a multi-dimensional space. Each piece of detailed data, after normalization, corresponds to the coordinates of a point in this space. The Euclidean distance from each point to the origin is calculated, and the average of these distances is used as the branch office's business parameter. Furthermore, different weights can be assigned to different factors when calculating the Euclidean distance; using weighted Euclidean distance offers greater flexibility and accuracy.

[0057] In some embodiments, in order to meet the requirements of horizontal quantitative comparison of the risk levels of different business areas and business links, this application first calculates the weighted Euclidean distance to find a few transactions that differ from most transactions. Among them, the closer the weighted Euclidean distance is to the mean, the lower the risk score; the further the weighted Euclidean distance deviates from the mean, the higher the risk score. Then, the calculation result (weighted Euclidean distance) is normalized to a value between 0 and 1, and the kinetic value is output for each monitoring result in combination with historical monthly data. This kinetic value can be used as a business parameter reflecting the current risk level. Accordingly, based on the transaction model type and the transaction parameters corresponding to at least one transaction factor in multiple transaction information, the branch business parameters corresponding to the branch are determined, including the following steps (1) to (3):

[0058] (1) If the trading model type of the preset trading model is a multi-factor trading model, then the weight parameter corresponding to each trading factor in the trading information is determined according to the trading parameters corresponding to each trading factor in the multiple trading information.

[0059] Optionally, the sum of a large number of independent random variables tends to a normal distribution; therefore, the normal distribution is often used to describe the distribution of random variables. Normal random data should follow a normal distribution; the more data anomalies there are, the greater the difference from a normal distribution. In this application, the smaller the difference between the trading parameter distribution and the normal distribution, the smaller the weight of the trading factor; the larger the difference, the larger the weight of the trading factor.

[0060] Accordingly, based on the trading parameters corresponding to each trading factor in multiple trading information, the weight parameters corresponding to each trading factor in the trading information are determined, including: determining the distribution information of the trading parameters corresponding to each trading factor in the trading information based on the trading parameters corresponding to each trading factor in multiple trading information; determining the difference parameter between the distribution information of the trading parameters and the normal distribution information for each trading factor; normalizing the difference parameter corresponding to each trading factor to obtain the normalized difference parameter, and determining the normalized difference parameter as the weight parameter corresponding to the trading factor.

[0061] Alternatively, the Anderson test can be used to calculate the difference between the risk factor distribution and the normal distribution. The basic principle of this test is to calculate a statistic that involves the cumulative distribution function of the sample dataset and the cumulative distribution function of a specific distribution (usually the normal distribution). If the calculated statistic exceeds the corresponding critical value, the null hypothesis is rejected, meaning that the sample dataset is considered significantly different from the normal distribution.

[0062] For example, multiple trading factors include: X, Y, ..., M. The following explanation uses the determination of the weight parameters corresponding to trading factor X as an example. The trading parameters corresponding to trading factor X in n trading information are: x1, x2, x3, ..., x... n Sort these data in ascending order to get x. (1) x (2) x (3) , ..., x (n) At this point, the statistic for the trading factor X can be determined using Formula 1:

[0063] Formula 1:

[0064] Where F(x) (i) ) represents the cumulative distribution function of the sample in x. (i) The value at the specified location, where n is the number of transaction parameters.

[0065] The statistics S of different trading factors are normalized and used as the weights of those factors. Optionally, a 5% significance level critical value is used as a comparison value for rejecting or accepting the normal distribution hypothesis. In this case, this critical value c can be used as the minimum value of the statistics for statistical normalization calculation. Accordingly, the weights of the trading factors can be determined using Formula 2:

[0066] Formula 2:

[0067] Among them, w i S is the weight parameter of the i-th trading factor. i Let S be the statistic for the i-th trading factor, c be the minimum value of the statistic, and S be the minimum value of the statistic. max This represents the maximum value of the statistic.

[0068] It should be noted that if the Anderson validation results indicate that the data does not conform to a normal distribution, the weight parameters of the trading factors can be determined using a pre-defined weight model. This pre-defined weight model can be a value-iterative reinforcement learning model. This model takes the trading factor as input and outputs its weight parameters.

[0069] (2) For each transaction information, determine the transaction business parameters corresponding to the transaction information based on the transaction parameters and weight parameters corresponding to each transaction factor in the transaction information.

[0070] Optionally, the transaction parameters corresponding to the transaction information can be determined using weighted Euclidean distance. Accordingly, this step may include: for each piece of transaction information, determining the normalized transaction parameters corresponding to each transaction factor based on the transaction parameters corresponding to each transaction factor in the transaction information; and determining the transaction business parameters corresponding to the transaction information based on the normalized transaction parameters and weight parameters corresponding to each transaction factor.

[0071] Euclidean distance is the distance between two points in Euclidean space, commonly used to calculate the distance between points in space. Euclidean distance is calculated as the square root of the sum of the squares of the differences between each coordinate component. Weighted Euclidean distance calculates the distance between two points by weighting the differences along each coordinate axis before summing them.

[0072] For example, the coordinates formed by the trading parameters of the M trading factors in the nth trading information are (Xn, Yn, ..., Mn). The coordinate values ​​of each dimension are normalized to obtain the final coordinates (Xn', Yn', ..., Mn'). Meanwhile, the weight parameters determined using the Anderson test for each trading factor are (w1, w2, ..., w...). M Finally, the weighted Euclidean distance from the point to the origin is calculated, and this weighted Euclidean distance is determined as the transaction business parameter corresponding to the nth transaction information, denoted as Dn:

[0073]

[0074] (3) Determine the normalized transaction business parameters corresponding to each transaction information, and determine the average value of the normalized transaction business parameters corresponding to multiple transaction information as the branch business parameters corresponding to the branch.

[0075] For example, the normalized transaction business parameter corresponding to the transaction business parameter for each transaction information is determined as D. n '=D n / D max The branch office business parameters are as follows:

[0076] In this embodiment of the disclosure, since the weighted Euclidean distance takes into account the weight differences between different trading factors, it can more accurately reflect the overall contribution of each trading factor and more fully consider the interrelationship between each trading factor, expanding from the perspective of a single trading factor to a multi-dimensional comprehensive analysis, thus improving the accuracy of determining the business parameters of branch offices.

[0077] This application provides a method for determining branch office business parameters: First, multiple transaction information items processed by the branch office within a preset time period that meet the transaction conditions of a preset transaction model are acquired. Each transaction information item includes transaction parameters corresponding to at least one transaction factor. Then, based on the number of at least one transaction factor in the transaction information, the transaction model type of the preset transaction model is determined. The transaction model type includes single-factor transaction models and multi-factor transaction models. Finally, based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among the multiple transaction information items, the branch office business parameters are determined. These branch office business parameters represent the transaction risk level of the multiple transaction information items processed by the branch office. In this embodiment, by filtering multiple transaction information items processed by the branch office that meet the transaction conditions using a preset transaction model, and determining the branch office business parameters based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among the multiple transaction information items, the efficiency of determining branch office business parameters is improved compared to manual determination.

[0078] In some embodiments, this application may further determine the branch office weight parameters corresponding to each branch office, and generate ranking information of business parameters corresponding to multiple branches offices based on the branch office weight parameters and branch office business parameters. Accordingly, such as Figure 3 As shown, the method also includes:

[0079] S301. Based on the number of transactions of multiple transaction information that meet the transaction conditions of the preset transaction model and have been processed by multiple branches within a preset time period, determine the branch weight parameter corresponding to each branch.

[0080] Optionally, the branch office weight parameter is related to the transaction volume. Branch offices are divided into buckets and weighted according to their transaction volume. The weight is multiplied by the branch office's business parameter to obtain the final adjusted business parameter for that branch office. Accordingly, this step includes the following steps (1) to (4):

[0081] (1) Sort the branches in ascending order of the corresponding transaction volume.

[0082] (2) Use the interquartile range (IQR) of the data to determine the bin width.

[0083] Alternatively, the bin width can be determined using the interquartile range (IQR) of the data, using the following formula: The calculation formula is:

[0084] Where h is the bin width, IQR is the interquartile range of the data, and n is the total number of data points. The number of bins k is obtained by dividing the data range by h.

[0085] Optionally, after sorting the transaction quantities, calculate the values ​​of Q1 (25%) and Q3 (75%), and calculate the interquartile range (IQR) based on the result of Q3-Q1. The value at position Q1 is: P 25 =0.25×(n+1), the value at position Q3 is: P 75 =0.75×(n+1); where n is the number of branches.

[0086] It should be noted that if the calculated quantile position is an integer, then the quantile represents the number of transactions corresponding to that branch. If the calculated quantile position is not an integer, then linear interpolation is performed on the position.

[0087] In this embodiment of the disclosure, linear interpolation is used to determine the quantile values:

[0088]

[0089] in, This represents the number of transactions at the branch office at position Q1 after rounding up.

[0090] In this embodiment of the disclosure, the interquartile range is the difference between the upper quartile (Q3) and the lower quartile (Q1). The interquartile range takes into account the dispersion of the data and is suitable for datasets containing outliers. Furthermore, by automatically adjusting the bin width according to the total number of data points to adapt to the actual distribution of the data, the accuracy of binning can be improved.

[0091] (3) Determine the number of buckets k based on the maximum and minimum transaction quantities and the bucket width.

[0092]

[0093] Where Max(X) is the maximum number of transactions and Min(X) is the minimum number of transactions.

[0094] (4) Calculate the bucket number corresponding to each branch office x based on the bucket width and the minimum business volume.

[0095]

[0096] (5) Determine the weight parameters corresponding to branch x based on the bucket number corresponding to branch x.

[0097]

[0098] S302. For each branch, determine the corresponding modified business parameters based on the branch business parameters and branch weight parameters.

[0099] For example, the branch offices include branch office 1, branch office 2, branch office 3 and branch office 4; wherein, the modified business parameter corresponding to branch office 1 is 0.0301, the modified business parameter corresponding to branch office 2 is 0.0288, the modified business parameter corresponding to branch office 3 is 0.0175 and the modified business parameter corresponding to branch office 4 is 0.0146.

[0100] S303. Based on the modified business parameters corresponding to each branch, generate ranking information of business parameters for multiple branches.

[0101] For example, multiple branch offices include branch office 1, branch office 2, branch office 3, and branch office 4; the ranking information of the business parameters corresponding to the multiple branch offices is shown in the table below:

[0102] Organization Name kinetic energy Ranking Branch Office 1 0.0301 1 Branch Office 2 0.0288 2 Branch Office 3 0.0175 3 Branch Office 4 0.0146 4

[0103] It's important to note that in the original algorithm, branches with low workload but high business parameters might be ranked higher, potentially leading to incorrect focus on these branches. However, the bucketing weighting algorithm ensures that the ranking based on business parameters more accurately reflects reality, avoiding excessive focus on branches with low workload but high business parameters.

[0104] It should be noted that the aforementioned branches can be branch banks, banking operations, bank customers, etc. The method for determining the risk ranking of branches described above is also applicable to determining the risk ranking of operations and customers, thus enabling risk analysis from multiple dimensions, including institutions, operations, and customers.

[0105] In this embodiment of the disclosure, when there are multiple preset transaction models, in order to reflect the differences between different models, each model is assigned a certain weight, and the comprehensive business parameters of the branch are determined based on the product of the modified business parameters of each model and the model weight.

[0106] In some embodiments, the weights of preset transactions can be determined based on dimensions such as business attributes, data attributes, and risk attributes of the preset transaction model. Optionally, such as Figure 4As shown, business attributes are used to represent the scope of influence of the preset transaction model. Business attributes include: employee count rating information, institution count rating information, and business volume rating information. For example, employee count rating information is: 90 for the hundred level, 100 for the thousand level, 100 for the ten thousand level, and cannot be estimated. Institution count rating information is: 90 for the hundred level, 100 for the thousand level, 100 for the ten thousand level, and cannot be estimated. Business volume rating information is: 50 for below 100, 100-10,000, and above 10,000. Data attributes include: update rate rating information is: 100 for monthly, 90 for quarterly, 80 for semi-annually, and 70 for annually. Risk attributes include: risk level rating information, verification accuracy rate rating information, and number of problems found rating information. For example, risk level rating information is: 100 for high, 80 for medium, and 50 for low. Verification accuracy score: Verification accuracy × 100. Number of problems found score: 0-0, 1-5-80, 5 or more in the tens of thousands -100.

[0107] Taking the preset transaction model "Daily cumulative limit and transaction amount mismatch (transaction condition)" as an example, this model involves 1583 business transactions, corresponding to a score of 100; 609 customers, corresponding to a score of 90; 449 institutions, corresponding to a score of 90; monthly update frequency, corresponding to a score of 100; low model risk level, corresponding to a score of 50; 80% model verification accuracy, corresponding to a score of 80; and fewer than 5 problems found, corresponding to a score of 80. In this case, the model's weighted score is: 90+90+100+100+50+80+80=590, and the model weight is 590 / 700=0.84.

[0108] It should be noted that, in this embodiment, different models can be linked and merged according to certain business logic, time sequence, and consistent behavioral characteristics to generate new models. Optionally, they can be classified according to four elements: business domain, business line, business process, and risk point, forming a business logic chain, which can support flexible integration between different models.

[0109] Figure 5 A schematic diagram of the structure of a branch office business parameter determination device provided in this application embodiment. Figure 1 ,like Figure 5 As shown, the device includes:

[0110] The acquisition module 501 is used to acquire multiple transaction information of the branch office within a preset time period that meets the transaction conditions of the preset transaction model. The transaction information includes transaction parameters corresponding to at least one transaction factor.

[0111] The first determining module 502 is used to determine the trading model type of the preset trading model based on the number of at least one trading factor in the trading information, wherein the trading model type includes a single-factor trading model and a multi-factor trading model.

[0112] The second determining module 503 is used to determine the branch office business parameters corresponding to the branch office based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among multiple transaction information; wherein, the branch office business parameters are used to represent the transaction risk level of multiple transaction information processed by the branch office.

[0113] In one possible implementation, the first determining module 502 determines the branch office business parameters corresponding to the branch office based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among the plurality of transaction information, including: if the transaction model type of the preset transaction model is a single-factor transaction model, then normalize the transaction parameters corresponding to the transaction factors in each transaction information according to the transaction parameters corresponding to the transaction factors among the plurality of transaction information to obtain normalized parameters corresponding to each transaction information; determine the average value of the normalized parameters corresponding to the plurality of transaction information according to the normalized parameters corresponding to each transaction information; and determine the average value of the normalized parameters corresponding to the plurality of transaction information as the branch office business parameters corresponding to the branch office.

[0114] In one possible implementation, the first determining module 502 normalizes the trading parameters corresponding to the trading factors in each of the plurality of trading information based on the trading parameters corresponding to the trading factors in the plurality of trading information, to obtain normalized parameters corresponding to each trading information, including: determining the average value and standard deviation of the trading parameters corresponding to the trading factors in the plurality of trading information based on the trading parameters corresponding to the trading factors in the plurality of trading information; determining the difference between the trading parameters and the average value for each trading parameter corresponding to the trading factors in the plurality of trading information; and determining the normalized parameters corresponding to the trading information based on the ratio of the difference to the standard deviation.

[0115] In one possible implementation, the first determining module 502 determines the branch office business parameters corresponding to the branch office based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among the plurality of transaction information, including: if the transaction model type of the preset transaction model is a multi-factor transaction model, then determining the weight parameter corresponding to each transaction factor in the transaction information based on the transaction parameters corresponding to each transaction factor in the plurality of transaction information; for each transaction information, determining the transaction business parameters corresponding to the transaction information based on the transaction parameters and weight parameters corresponding to each transaction factor in the transaction information; determining the normalized transaction business parameters corresponding to the transaction business parameters corresponding to each transaction information, and determining the average value of the normalized transaction business parameters corresponding to the plurality of transaction information as the branch office business parameters corresponding to the branch office.

[0116] In one possible implementation, the first determining module 502 determines the weight parameter corresponding to each trading factor in the plurality of trading information based on the trading parameters corresponding to each trading factor in the plurality of trading information, including: determining the distribution information of the trading parameters corresponding to each of the trading factors in the plurality of trading information based on the trading parameters corresponding to each of the trading factors in the plurality of trading information; determining the difference parameter between the distribution information of the trading parameters and the normal distribution information for each trading factor; normalizing the difference parameter corresponding to each trading factor to obtain a normalized difference parameter, and determining the normalized difference parameter as the weight parameter corresponding to the trading factor.

[0117] In one possible implementation, the first determining module 502 determines the transaction business parameters corresponding to each transaction information based on the transaction parameters and weight parameters corresponding to each transaction factor in the transaction information, including: determining the normalized transaction parameters corresponding to each transaction factor based on the transaction parameters corresponding to each transaction factor in the transaction information; and determining the transaction business parameters corresponding to the transaction information based on the normalized transaction parameters and weight parameters corresponding to each transaction factor.

[0118] In one possible implementation, the second determining module 503 is further configured to determine the branch weight parameter corresponding to each branch based on the number of transactions of multiple transaction information that meet the transaction conditions of a preset transaction model that have been processed by multiple branches within a preset time period; for each branch, determine the corresponding modified business parameter based on the branch business parameter and the branch weight parameter; and generate business parameter ranking information corresponding to the multiple branches based on the modified business parameter corresponding to each branch.

[0119] This application provides a device for determining branch office business parameters. By filtering multiple transaction information that meets the transaction conditions processed by the branch office through a preset transaction model, and determining the branch office business parameters by using the transaction model type and the transaction parameters corresponding to at least one transaction factor among the multiple transaction information, the efficiency of determining branch office business parameters is improved compared with manual determination.

[0120] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 600 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the device 600 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0121] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.

[0122] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0123] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0124] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0125] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0126] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0127] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0128] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0129] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0130] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0131] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0132] It should be noted that the terms "first," "second," etc., in the claims, specification, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, products, or apparatus.

[0133] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0134] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0135] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0136] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0137] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0138] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0139] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for determining business parameters of a branch office, characterized in that, The method includes: Obtain multiple transaction information items processed by branch offices within a preset time period that meet the transaction conditions of a preset transaction model. The transaction information items include transaction parameters corresponding to at least one transaction factor. Based on the number of at least one trading factor in the trading information, the trading model type of the preset trading model is determined, wherein the trading model type includes a single-factor trading model and a multi-factor trading model; Based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among the multiple transaction information, the branch office business parameters are determined; wherein, the branch office business parameters are used to represent the transaction risk level of the multiple transaction information processed by the branch office.

2. The determination method according to claim 1, characterized in that, The step of determining the branch office business parameters corresponding to the branch office based on the transaction parameters corresponding to at least one transaction factor among the multiple transaction information includes: If the trading model type of the preset trading model is a single-factor trading model, then the trading parameters corresponding to the trading factors in each trading information are normalized according to the trading parameters corresponding to the trading factors in the multiple trading information to obtain the normalized parameters corresponding to each trading information. Based on the normalization parameter corresponding to each transaction information, determine the average value of the normalization parameter corresponding to multiple transaction information. The average value of the normalized parameters corresponding to the multiple transaction information is determined as the branch office business parameter corresponding to the branch office.

3. The determination method according to claim 2, characterized in that, The step of normalizing the trading parameters corresponding to the trading factors in each of the multiple trading information entries to obtain normalized parameters for each trading information entry includes: Based on the trading parameters corresponding to the trading factors in the multiple trading information, determine the average value and standard deviation of the trading parameters corresponding to the trading factors; For each transaction information, the difference between the transaction parameter and the average value is determined for the transaction parameter corresponding to the transaction factor. The normalization parameter corresponding to the transaction information is determined based on the ratio of the difference to the standard deviation.

4. The determination method according to claim 1, characterized in that, The step of determining the branch office business parameters corresponding to the branch office based on the transaction parameters corresponding to at least one transaction factor among the multiple transaction information includes: If the trading model type of the preset trading model is a multi-factor trading model, then the weight parameter corresponding to each trading factor in the multiple trading information is determined according to the trading parameters corresponding to each trading factor in the multiple trading information. For each transaction information, the transaction business parameters corresponding to the transaction information are determined based on the transaction parameters and weight parameters corresponding to each transaction factor in the transaction information. Determine the normalized transaction business parameters corresponding to each transaction information, and use the average value of the normalized transaction business parameters corresponding to multiple transaction information as the branch business parameters corresponding to the branch.

5. The determination method according to claim 4, characterized in that, The step of determining the weight parameter corresponding to each trading factor in the multiple trading information based on the trading parameters corresponding to each trading factor in the multiple trading information includes: Based on the trading parameters corresponding to each trading factor in the multiple trading information, determine the distribution information of the trading parameters corresponding to each of the multiple trading factors in the trading information; For each trading factor, determine the difference parameter between the trading parameter distribution information and the normal distribution information; The difference parameters corresponding to each trading factor are normalized to obtain normalized difference parameters, and the normalized difference parameters are determined as the weight parameters corresponding to the trading factor.

6. The determination method according to claim 4, characterized in that, For each piece of transaction information, determining the corresponding transaction business parameters based on the transaction parameters and weight parameters corresponding to each transaction factor in the transaction information includes: For each transaction information, the normalized transaction parameters corresponding to each transaction factor are determined based on the transaction parameters corresponding to each transaction factor in the transaction information. Based on the normalized trading parameters and weight parameters corresponding to each trading factor, the trading business parameters corresponding to the trading information are determined.

7. The determination method according to any one of claims 1-6, characterized in that, The method further includes: Based on the number of transactions that meet the transaction conditions of the preset transaction model and have been processed by multiple branches within a preset time period, determine the branch weight parameters corresponding to each branch. For each branch, the corresponding modified business parameters are determined based on the branch business parameters and branch weight parameters. Based on the modified business parameters corresponding to each branch, generate business parameter ranking information for the multiple branches.

8. A device for determining business parameters of a branch office, characterized in that, The device includes: The acquisition module is used to acquire multiple transaction information of a branch office within a preset time period that meets the transaction conditions of a preset transaction model. The transaction information includes transaction parameters corresponding to at least one transaction factor. The first determining module is used to determine the trading model type of the preset trading model based on the number of at least one trading factor in the trading information, wherein the trading model type includes a single-factor trading model and a multi-factor trading model. The second determining module is used to determine the branch office business parameters corresponding to the branch office based on the transaction model type and the transaction parameters corresponding to at least one transaction factor among the multiple transaction information; wherein, the branch office business parameters are used to represent the transaction risk level of the multiple transaction information processed by the branch office.

9. An electronic device, characterized in that, The electronic device includes: a memory and a processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method for determining branch office business parameters as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for determining branch office business parameters as described in any one of claims 1-7.

11. A computer program product comprising a computer program that, when executed by a processor, implements the method for determining branch office business parameters as described in any one of claims 1-7.

Images