Method, device and equipment for monitoring data and computer readable medium

Abstract

The invention discloses a data monitoring method, device and equipment and a computer readable medium, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: identifying default historical parameters of a repayment liability by adopting historical asset data and historical liability data of an enterprise; determining default preliminary screening characteristics in the historical business data according to business operation, and screening out default secondary screening characteristics from the default preliminary screening characteristics based on a preset model; the default re-screening features are combined with the default historical parameters and the default actual parameters to construct a risk threshold model, and a risk threshold is determined according to deviation distribution of the default historical parameters and the default actual parameters and the risk threshold model; and monitoring business data of the enterprise by using a default current parameter of the enterprise and the risk threshold. According to the embodiment, the change of the service data can be known in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and in particular, to a method, device and equipment for monitoring data and a computer readable medium. BACKGROUND

[0002] Supply chain financial service refers to a series of financial services provided for upstream and downstream enterprises in a supply chain to reduce financial cost and improve operation efficiency of the enterprises. A financial institution can provide digital supervision services for upstream or downstream merchants and carrier customers in the supply chain to improve the effectiveness of business data.

[0003] In the process of implementing the present application, the inventors have found that at least the following problem exists in the prior art: the change of business data cannot be learned in time. SUMMARY

[0004] Therefore, the embodiments of the present application provide a method, device and equipment for monitoring data and a computer readable medium, which can learn the change of business data in time.

[0005] To achieve the above object, according to one aspect of the embodiments of the present application, a method for monitoring data is provided, comprising:

[0006] adopting historical asset data of an enterprise and historical liability data of the enterprise to identify a default history parameter of a liability payment;

[0007] determining a default preliminary screening feature in historical business data according to business operation, and screening a default re-screening feature in the default preliminary screening feature based on a preset model;

[0008] combining the default history parameter and a default actual parameter with the default re-screening feature to construct a risk threshold model, and determining a risk threshold based on a deviation distribution of the default history parameter and the default actual parameter and the risk threshold model;

[0009] monitoring business data of the enterprise by using a default current parameter of the enterprise and the risk threshold.

[0010] The determination of the default preliminary screening feature in the historical business data according to the business operation, and the screening of the default re-screening feature in the default preliminary screening feature based on the preset model, comprises:

[0011] acquiring an identifier of default business data in historical business data, and determining a default preliminary screening feature according to an identifier of business operation;

[0012] establishing a decision tree model as the preset model based on the default preliminary screening feature and a default result of the historical business data, and screening a default re-screening feature in the default preliminary screening feature based on the preset model.

[0013] The identifier of the default business data is obtained from the historical business data, and the default preliminary screening feature is determined according to the identifier of the business operation.

[0014] The identifier of the default business data is obtained from the historical business data, and the default business feature is determined according to the identifier of the default business operation.

[0015] The default business feature and the default adjustment feature are used as the default preliminary screening feature, and the default adjustment feature is determined by analyzing the defaulted result of the historical business data.

[0016] The default re-screening feature is combined with the default historical parameter and the default actual parameter to construct a risk threshold model, and the risk threshold model includes:

[0017] The risk threshold model is constructed on the basis of the default re-screening feature, the default historical parameter and the default actual parameter, and the risk threshold model includes the bias of the default historical parameter and the default actual parameter.

[0018] The weight parameter of the default re-screening feature in the risk threshold model is adjusted to make the bias of the default historical parameter and the default actual parameter conform to a preset probability distribution.

[0019] The risk threshold is determined according to the bias distribution of the default historical parameter and the default actual parameter and the risk threshold model, and the risk threshold model includes:

[0020] Random data is determined according to the bias distribution of the default historical parameter and the default actual parameter, and the random data is input into the risk threshold model to obtain a default prediction parameter.

[0021] The plurality of default prediction parameters are arranged from large to small, and the default prediction parameter of a preset quantile is used as the risk threshold.

[0022] The business data of the enterprise is monitored by using the default current parameter of the enterprise and the risk threshold, and the business data of the enterprise is monitored by using the default current parameter of the enterprise and the risk threshold.

[0023] The sum of the default current parameters of all enterprises is compared with the risk threshold, and a monitoring result of monitoring the business data of the enterprise is sent according to the comparison result.

[0024] The method further includes:

[0025] The monitoring reminder instruction of the enterprise is sent by using the default current parameter of the enterprise, the current asset data of the enterprise and the liability threshold.

[0026] According to a second aspect of an embodiment of the present application, a device for monitoring data is provided, which includes:

[0027] The identification module is configured to identify a default history parameter of a payment liability by using historical asset data of the enterprise and historical liability data of the enterprise.

[0028] The screening module is configured to determine a default preliminary screening feature according to business operations in the historical business data, and screen a default secondary screening feature from the default preliminary screening feature based on a preset model.

[0029] The establishment module is configured to construct a risk threshold model by combining the default secondary screening feature, the default history parameter and a default actual parameter, and determine a risk threshold based on a deviation distribution of the default history parameter and the default actual parameter and the risk threshold model.

[0030] The monitoring module is configured to monitor the business data of the enterprise by using a default current parameter of the enterprise and the risk threshold.

[0031] According to a third aspect of the embodiments of the present application, an electronic device for monitoring data is provided, which comprises:

[0032] one or more processors;

[0033] a storage device configured to store one or more programs,

[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0035] According to a fourth aspect of the embodiments of the present application, a computer readable medium having a computer program stored thereon is provided, and the program is executed by a processor to implement the method as described above.

[0036] An embodiment of the above application has the following advantages or beneficial effects: the default history parameter of the payment liability is identified by using the historical asset data of the enterprise and the historical liability data of the enterprise; the default preliminary screening feature is determined according to the business operations in the historical business data, and the default secondary screening feature is screened from the default preliminary screening feature based on the preset model; the risk threshold model is constructed by combining the default secondary screening feature, the default history parameter and the default actual parameter, and the risk threshold is determined based on the deviation distribution of the default history parameter and the default actual parameter and the risk threshold model; and the business data of the enterprise is monitored by using the default current parameter of the enterprise and the risk threshold. The risk threshold is used as the basis for monitoring the data, and the change of the business data can be learned in time based on the default current parameter of the enterprise.

[0037] The further effects of the above non-conventional optional mode will be described in the following combined with the specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0038] The accompanying drawings are used to better understand the present application and do not constitute undue limitations on the present application. Among them:

[0039] Figure 1 is a main flow diagram of a method for monitoring data according to an embodiment of the present application;

[0040] Figure 2 is a flow diagram of screening out default re-screening features according to an embodiment of the present application;

[0041] Figure 3 is a flow diagram of determining default preliminary screening features according to an embodiment of the present application according to the identification of business operations;

[0042] Figure 4 is a flow diagram of constructing a risk threshold model according to an embodiment of the present application;

[0043] Figure 5 is a flow diagram of determining a risk threshold according to an embodiment of the present application according to the deviation distribution of default historical parameters and default actual parameters and the risk threshold model;

[0044] Figure 6 is a main structure diagram of a device for monitoring data according to an embodiment of the present application;

[0045] Figure 7 is an exemplary system architecture diagram to which an embodiment of the present application can be applied;

[0046] Figure 8 is a structure diagram of a computer system of a terminal device or a server suitable for implementing an embodiment of the present application. DETAILED DESCRIPTION

[0047] The exemplary embodiments of the present application are described below with reference to the accompanying drawings, including various details of the embodiments of the present application to help understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Also, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0048] Taking the business data related to the movable financing business as an example, as a financing core enterprise, the financial institution provides financing services to upstream merchants, and uses the movable property or the value of the merchant as a mortgage combined with risk control means to help the financial institution to implement credit granting business, and at the same time, bears a certain responsibility for the credit granting result. If the risk control method is too aggressive, there is a risk of being responsible for bad debts, and if the risk control method is too conservative, it affects the loan amount and reduces business income.

[0049] Currently, the enterprise solvency evaluation in the supply chain movable property financing business includes: verifying and monitoring the value of the enterprise in the warehouse collateral, and issuing a control instruction to limit the warehouse out of the financing enterprise's collateral when detecting that the value is lower than the financing arrears, so as to achieve risk control.

[0050] Small and medium-sized enterprises often have unstable operation and non-transparent financial status, so the credit risk of loans only depends on the value of the collateral. When the control instruction is issued when the value of the collateral is lower than the arrears, subsequent credit losses are often inevitable. In addition, the influence of economic environment is not considered, and the default correlation between enterprises is not considered.

[0051] Business data reflects the solvency of the enterprise, and changes in business data cannot be learned in time.

[0052] In order to solve the problem that the changes in business data cannot be learned in time, the technical solutions in the embodiments of the present application can be used.

[0053] Referring to Figure 1 , Figure 1 The method for monitoring data according to the embodiments of the present application mainly includes the following steps. Figure 1 That is, 100 is specifically shown as follows:

[0054] S101, using historical asset data and historical liability data, identifying default historical parameters of solvency liabilities.

[0055] In the embodiments of the present application, the monitoring data includes business data of the enterprise. The business data of the enterprise is the data involved in the operation process of the enterprise. As an example, the business data includes one or more of the following: investment rate, return rate, inventory age and turnover days.

[0056] In order to monitor the business data of the enterprise, the basis for monitoring the business data can be determined from the historical data of the enterprise. The historical data of the enterprise includes historical asset data and historical liability data. As an example, the historical asset data includes the amount involved in the enterprise's collateral. The historical liability data includes the amount of the enterprise's liabilities. The difference between the historical asset data (A) and the historical liability data (L) can be used as the debt historical parameter (E). That is, E=A-L. If the debt historical parameter is greater than zero, it is judged that the enterprise is profitable; if the debt historical parameter is less than zero, it is judged that the enterprise is loss-making.

[0057] For the re-screening data, the debt term T is involved. After the debt term T, if the historical asset data (A) is higher than the historical liability data (L), the enterprise does not have the default possibility; if the historical asset data (A) is lower than or equal to the historical liability data (L), the enterprise has the default possibility. T E T is the historical liability parameter after the debt term T, i.e. T E

[0058] In an embodiment of the present application, the historical asset data of the enterprise and the historical liability data of the enterprise are used to identify the historical liability parameter of the liability according to the option pricing model.

[0059] In an embodiment of the present application, the historical liability data to be expired can be regarded as the behavior of obtaining the delivery of the underlying by paying the exercise price. Therefore, the historical liability parameter is equivalent to holding the call option with the historical liability data as the exercise price and the historical asset data as the underlying.

[0060] Therefore, the historical liability parameter can be determined according to the option. Specifically, the option pricing model is used for pricing. As an example, the option pricing model includes the Black-Scholes-Merton (BS) model. The BS model is a mathematical model for pricing financial derivatives such as options or warrants.

[0061] E T = AN (d1) - Le-rTN (d2) Formula 1

[0062]

[0063]

[0064] A is the historical asset data, L is the historical liability data, r is the risk-free rate, σ A is the historical asset data volatility, and T is the debt term. d2 is the distance to default, d2 is the default parameter, and 1-N (d2) is the default probability. Using Formula 1, E T , i.e. the historical liability parameter, can be obtained.

[0065] S102, determine the default preliminary screening features according to the business operations in the historical business data, and screen the default re-screening features based on the preset model in the default preliminary screening features.

[0066] For the default behavior of the enterprise, the default feature can be screened out from the historical business data to construct a risk threshold model using the default feature. The historical business data is the existing business data of the enterprise. As an example, the historical business data includes one or more of the following: historical delivery rate, historical return rate, historical inventory age, and historical turnover days.

[0067] In order to improve the pertinence and accuracy of the default feature, the default preliminary screening feature is determined according to the business operation in the historical business data, and the default re-screening feature is screened out from the default preliminary screening feature based on a preset model.

[0068] Referring to Figure 2 That is, 200, Figure 2 is a flowchart of screening out a default re-screening feature according to an embodiment of the present application. Specifically, it includes the following steps:

[0069] S201, obtaining the identification of default business data in the historical business data, and determining the default preliminary screening feature according to the identification of default business operation.

[0070] Obtain the historical business data of a plurality of enterprises from the database, and mark the historical business data with a default record as 1 and the historical business data without a default record as 0 according to the identification of the credit record of the enterprise.

[0071] Obtain the identification of default business data in the historical business data marked as 1. Then, determine the default preliminary screening feature according to the identification of default business operation. The identification of default business data is preset. As an example, the identification of default business data includes the identification of logistics transportation. Determining the default preliminary screening feature according to the identification of logistics transportation includes: historical delivery rate.

[0072] Referring to Figure 3 That is, 300, Figure 3 is a flowchart of determining a default preliminary screening feature according to the identification of business operation according to an embodiment of the present application. Specifically, it includes the following steps:

[0073] S301, obtaining the identification of default business data in the historical business data, and determining the default business feature according to the identification of business operation.

[0074] Similar to S201, the default business feature is determined according to the identification of default business data in the historical business data according to the identification of business operation.

[0075] S302, taking the default business feature and the default adjustment feature as the default preliminary screening feature, and the default adjustment feature is determined by analyzing the default result of the historical business data.

[0076] In the embodiments of the present application, in order to consider other factors affecting default, a default adjustment feature can be added on the basis of the default business feature, and the default business feature and the default adjustment feature are taken as the default preliminary screening feature. The default adjustment feature is determined according to the defaulted results of the historical business data. As an example, the defaulted results of the historical business data, i.e., the historical business data marked as 1, are analyzed according to the economic development, and the historical turnover days are screened out as the default adjustment feature.

[0077] In Figure 3 the embodiments of the present application, the default business feature is first determined according to the identification of the default business data, and then the default adjustment is supplemented to finally determine the default preliminary screening feature. The default preliminary screening feature is the first feature screened out on the basis of the historical business data.

[0078] S202, a decision tree model is established as a preset model based on the default preliminary screening feature and the defaulted results of the historical business data, and a default re-screening feature is screened out from the default preliminary screening feature based on the preset model.

[0079] In the embodiments of the present application, the default preliminary screening feature and the defaulted results of the historical business data are taken as the training data on the basis of the decision tree model to train the preset model. The defaulted results of the historical business data include the historical business data marked as 1 with defaulted records and the historical business data marked as 0 without defaulted records.

[0080] Most of the data of S201 is taken as the training data, and the remaining data is taken as the verification data. After the preset model is trained on the basis of the training data, the verification data is input into the preset model to obtain the judgment result of the verification data. By comparing the judgment result of the verification data with the marked result of the verification data, a confusion matrix is obtained.

[0081] Each column of the confusion matrix represents a prediction category, the total number of each column represents the number of data predicted as the category, the total number of data in each row represents the number of data instances of the category, and the value in each column represents the number of true data predicted as the category. The prediction efficiency of the preset model can be intuitively reflected by calculating the precision, recall and F1 value reflected by the confusion matrix. It can be understood that the prediction efficiency can be determined by using the above-mentioned precision, recall and F1 value.

[0082] It can be understood that in the case where the prediction efficiency of the preset model does not meet the requirements, the preset model can be trained again by adjusting the default preliminary screening feature. The default feature in the preset model that meets the requirements is taken as the default re-screening feature according to the above-mentioned manner. The requirements include the precision, recall and F1.

[0083] As an example, the default preliminary screening features include feature 1, feature 2, feature 3, feature 4, and feature 5. After the preset model is established, the prediction efficiency of the preset model does not meet the requirements. The default preliminary screening is adjusted to: feature 1, feature 2, feature 3, and feature 4. After the preset model is established, the prediction efficiency of the preset model meets the requirements, and the default rescreening features include feature 1, feature 2, feature 3, and feature 4.

[0084] In Figure 2 In an embodiment, the default preliminary screening features embody default features of historical business data, and the default rescreening features represent actual features that affect default.

[0085] S103, the default rescreening features combine the default historical parameters and the default actual parameters to construct a risk threshold model, and determine the risk threshold based on the deviation distribution of the default historical parameters and the default actual parameters and the risk threshold model.

[0086] The default historical parameters represent the repayment willingness of the enterprise. The default actual parameters represent the repayment behavior of the enterprise. The default rescreening features combine the default historical parameters and the default actual parameters to construct a risk threshold model, and further determine the risk threshold, so as to realize monitoring of the business data based on the risk threshold.

[0087] Referring to Figure 4 That is, 400, Figure 4 is a flowchart of constructing a risk threshold model according to an embodiment of the present application. Specifically, the following steps are included:

[0088] S401, based on the default rescreening features, the default historical parameters, and the default actual parameters, a risk threshold model is constructed on the basis of a logistic regression model, and the risk threshold model includes the deviation of the default historical parameters and the default actual parameters.

[0089] Based on the default rescreening features, the default historical parameters, and the default actual parameters, a risk threshold model is constructed on the basis of a logistic regression model.

[0090] d2=a F1+b ln F2+c 1 / F3+…+Δ Formula 3

[0091] Wherein, d2 is a default parameter, i.e. a default distance, F is a default rescreening feature, and Δ is a deviation of the default historical parameters and the default actual parameters. a, b, and c are weight parameters corresponding to the default rescreening features.

[0092] S402, the weight parameters of the default rescreening features in the risk threshold model are adjusted to make the deviation of the default historical parameters and the default actual parameters conform to a preset probability distribution.

[0093] For Δ, a probability distribution needs to be met to eliminate the trend factor. Therefore, the deviation of the default historical parameter and the default actual parameter can be adjusted to meet a preset probability distribution by adjusting the weight parameter of the default rescreening feature in the risk threshold model. The preset probability distribution includes a normal distribution or a lognormal distribution.

[0094] As an example, the correlation between Δ and the weight parameter of the default rescreening feature is analyzed. The weight parameter with high correlation is determined in the weight parameter of the default rescreening feature. Then, the deviation of the default historical parameter and the default actual parameter is adjusted to meet the preset probability distribution by adjusting the weight parameter with high correlation.

[0095] In Figure 4 In an embodiment, the risk threshold model is constructed based on the default rescreening feature, the default historical parameter and the default actual parameter.

[0096] In an embodiment of the present application, after the risk threshold model is determined, the risk threshold can be determined based on the deviation distribution of the default historical parameter and the default actual parameter, i.e., Δ distribution.

[0097] Referring to Figure 5 That is, 500, Figure 5 is a flowchart for determining the risk threshold based on the deviation distribution of the default historical parameter and the default actual parameter and the risk threshold model according to an embodiment of the present application. Specifically, the following steps are included:

[0098] S501, determining random data according to the deviation distribution of the default historical parameter and the default actual parameter, so as to input the random data into the risk threshold model to obtain a default prediction parameter.

[0099] In an embodiment of the present application, the random data can be determined according to the deviation distribution of the default historical parameter and the default actual parameter. As an example, the Δ distribution is a normal distribution N(μ,σ), and the deviation distribution of the default historical parameter and the default actual parameter is N(μ,σ), where μ=0 and σ=1. Based on the above normal distribution (0,1), the random data is determined.

[0100] The random data is input into the risk threshold model, i.e., formula 3, to obtain a default prediction parameter. Each random data has a corresponding default prediction parameter.

[0101] S502, arranging a plurality of default prediction parameters from large to small, and taking the default prediction parameter of a preset quantile as the risk threshold.

[0102] In an embodiment of the present application, in order to obtain the risk threshold value, and monitor the business data of the enterprise with the risk threshold value, a plurality of default prediction parameters need to be obtained. Then, a plurality of random data can be determined, and the random data is input into the risk threshold value model to obtain corresponding default prediction parameters. As an example, the number of random data is greater than 1000.

[0103] After obtaining the plurality of default prediction parameters, the plurality of default prediction parameters are arranged in descending order of value, and the default prediction parameter of a preset quantile is taken as the risk threshold value. As an example, the preset quantile includes 5%.

[0104] The default prediction parameter represents the risk loss, and the risk loss is adjusted by the preset quantile. As an example, the preset quantile is 5%, that is, the default prediction parameter of the 5% quantile is the maximum risk loss. Denoted as: 95% (Value at risk, VaR).

[0105] In an embodiment of the present application, the risk threshold value is preset according to the skew distribution. Figure 5

[0106] S104, monitoring the business data of the enterprise by using the default current parameter of the enterprise and the risk threshold value.

[0107] The current asset data of the enterprise and the current load data of the enterprise are used to obtain the default current parameter of the enterprise according to the d2 of formula 2. For a plurality of enterprises, the default current parameter of each enterprise can be obtained. Further, the business data of the enterprise is monitored by using the default current parameter of the enterprise and the risk threshold value.

[0108] In an embodiment of the present application, the sum of the default current parameters of all enterprises is compared with the risk threshold value, and the monitoring result of the business data of the enterprise is sent according to the comparison result.

[0109] The risk threshold value is the maximum risk loss identified from the perspective of all enterprises. Therefore, the monitoring is realized by comparing the sum of the default current parameters of all enterprises with the risk threshold value.

[0110] As an example, the comparison result includes the sum of the default current parameters of all enterprises, which is greater than the risk threshold value, indicating that the repayment risk loss of all enterprises has exceeded the maximum risk loss, and therefore the monitoring result of the business data of the enterprise includes: the repayment risk of the enterprise is large.

[0111] As another example, the comparison result includes the sum of the default current parameters of all enterprises, which is less than or equal to the risk threshold value, indicating that the repayment risk loss of all enterprises has not exceeded the maximum risk loss, and therefore the monitoring result of the business data of the enterprise includes: the repayment risk of the enterprise is small.

[0112] ​In the above embodiment, the monitoring result of the business data of the enterprise by the risk threshold is used to determine the repayment risk of all the enterprises as a whole.

[0113] In an embodiment of the present application, the monitoring reminder instruction of the enterprise is sent by the debt current parameter of the enterprise, the current asset data of the enterprise and the liability threshold.

[0114] The debt current parameter of the enterprise can be calculated according to formula 1, which represents the current repayment willingness of the enterprise. The current asset parameter of the enterprise is A in formula 2. The ratio of the debt current parameter of the enterprise to the current asset parameter of the enterprise represents the repayment possibility of the enterprise under the current load parameter. If the ratio of the debt current parameter of the enterprise to the current asset parameter of the enterprise is greater than or equal to the liability threshold, it means that the possibility of the enterprise repaying on time is small; if the ratio of the debt current parameter of the enterprise to the current asset parameter of the enterprise is less than the liability threshold, it means that the possibility of the enterprise repaying on time is large.

[0115] The reminder is sent by sending the monitoring reminder instruction of the enterprise. The monitoring reminder instruction includes the identification of the enterprise and the possibility of the enterprise repaying on time. In addition, the monitoring of the enterprise can be adjusted by adjusting the liability threshold.

[0116] In the above embodiment, the historical asset data of the enterprise and the historical liability data of the enterprise are used to identify the default history parameter of the liability payment; the default preliminary screening feature is determined according to the business operation in the historical business data, and the default rescreening feature is screened based on the preset model in the default preliminary screening feature; the default rescreening feature combines the default history parameter and the default actual parameter to construct a risk threshold model, and the deviation distribution of the default history parameter and the default actual parameter and the risk threshold model are used to determine the risk threshold; the business data of the enterprise is monitored by using the default current parameter of the enterprise and the risk threshold. The risk threshold is used as the basis for monitoring data, and the change of the business data can be known in time on the basis of the default current parameter of the enterprise. The risk is preposed before the real default occurs.

[0117] In specific applications, the movable property financing business feedback movable property financing business default rate reaches 6% within one year of the quarter-end business group, which causes a credit loss of 1.45 million.

[0118] By using the technical solution in the embodiment of the present application on the existing loan dataset, when the 95% VaR is 145 million, the collateral value required per 100 million arrears is calculated according to the current market interest rate of 3% and the average volatility of the value of goods of 0.3. The collateral value level in the embodiment of the present application is always lower than that of the prior art, and the occupation time of the collateral goods is much lower than the total value of the required occupation time of the prior art. Therefore, under the premise of keeping the same risk control level, the embodiment of the present application reduces the customer's cost of funds and improves the business income, and is a very effective risk control method.

[0119] In addition, if the risk degree reflected by the VaR exceeds the controllable range, the final risk level can be adjusted by adjusting the liability threshold. When the liability threshold is 9, the required collateral value level in the embodiment of the present application is lower than that of the prior art before the debt expiration time is 0.485 years. The total value of the collateral goods occupied by the embodiment of the present application is equivalent to that of the prior art. Therefore, the embodiment of the present application realizes the reduction of the risk level under the premise of keeping the total value of the collateral goods occupied unchanged, and has actual risk control value.

[0120] Referring to Figure 6 , Figure 6 is the main structure diagram of the monitoring data device according to the embodiment of the present application. The monitoring data device can realize the monitoring data method, such as Figure 6 As shown in 600, the monitoring data device specifically comprises:

[0121] The identification module 601 is configured to identify the default history parameters of the paid liabilities by using the historical asset data of the enterprise and the historical liability data of the enterprise.

[0122] The screening module 602 is configured to determine the default preliminary screening features in the historical business data according to the business operation, and screen the default re-screening features based on a preset model in the default preliminary screening features.

[0123] The establishment module 603 is configured to combine the default re-screening features with the default history parameters and the default actual parameters to construct a risk threshold model, and determine a risk threshold based on the deviation distribution of the default history parameters and the default actual parameters and the risk threshold model.

[0124] The monitoring module 604 is configured to monitor the business data of the enterprise by using the default current parameters of the enterprise and the risk threshold.

[0125] In an embodiment of the present application, the screening module 602 is specifically configured to obtain the identification of the default business data in the historical business data, and determine the default preliminary screening features according to the identification of the business operation.

[0126] The default screening feature and the default result of the historical business data are used to establish a decision tree model as the preset model, and the default screening feature is screened out based on the preset model.

[0127] In an embodiment of the present application, the screening module 602 is specifically configured to obtain the identification of the default business data from the historical business data, and determine the default business feature according to the identification of the default business operation.

[0128] The default business feature and the default adjustment feature are used as the default screening feature, and the default adjustment feature is determined by analyzing the historical business data with the default result.

[0129] In an embodiment of the present application, the establishing module 603 is specifically configured to establish a risk threshold model based on a logistic regression model by using the default screening feature, the default historical parameter and the default actual parameter, and the risk threshold model includes the deviation of the default historical parameter and the default actual parameter.

[0130] The weight parameter of the default screening feature in the risk threshold model is adjusted so that the deviation of the default historical parameter and the default actual parameter conforms to a preset probability distribution.

[0131] In an embodiment of the present application, the establishing module 603 is specifically configured to determine random data according to the deviation distribution of the default historical parameter and the default actual parameter, and input the random data into the risk threshold model to obtain a default prediction parameter.

[0132] The plurality of default prediction parameters are arranged in descending order, and the default prediction parameter with a preset quantile is used as the risk threshold.

[0133] In an embodiment of the present application, the monitoring module 604 is specifically configured to compare the default current parameter of all enterprises with the risk threshold, and send a monitoring result of monitoring the business data of the enterprise according to the comparison result.

[0134] In an embodiment of the present application, the monitoring module 604 is specifically configured to send a monitoring reminder instruction of the enterprise by using the default current parameter of the enterprise, the current asset data of the enterprise and the liability threshold.

[0135] Figure 7 An exemplary system architecture 700 of the method for monitoring data or the device for monitoring data to which the embodiments of the present application can be applied is shown.

[0136] As Figure 7As shown, the system architecture 700 can include terminal devices 701, 702, 703, a network 704 and a server 705. The network 704 is a medium for providing communication links between the terminal devices 701, 702, 703 and the server 705. The network 704 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0137] The users can use the terminal devices 701, 702, 703 to interact with the server 705 through the network 704 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 701, 702, 703, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0138] The terminal devices 701, 702, 703 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers and desktop computers, etc.

[0139] The server 705 can be a server providing various services, such as a background management server supporting shopping websites browsed by users using the terminal devices 701, 702, 703 (only as an example). The background management server can analyze and process received product information query requests and other data, and feed back the processing results (such as target push information, product information - only as examples) to the terminal devices.

[0140] It should be noted that the method for monitoring data provided by the embodiments of the present application is generally executed by the server 705, and accordingly, the device for monitoring data is generally provided in the server 705.

[0141] It should be understood that, Figure 7 The number of terminal devices, networks and servers in the system architecture 700 is only illustrative. According to the needs of implementation, there can be any number of terminal devices, networks and servers.

[0142] Reference is made below to Figure 8 which shows a structural schematic diagram of a computer system 800 of a terminal device suitable for implementing the embodiments of the present application. Figure 8 The terminal device shown is only an example and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0143] As Figure 8As shown, the computer system 800 includes a central processing unit (CPU) 801 which can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 802 or loaded into a random access memory (RAM) 803 from a storage section 808. In the RAM 803, various programs and data required for the operation of the system 800 are also stored. The CPU 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0144] Connected to the I / O interface 805 are an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as necessary. A removable recording medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 810 as necessary, so that a computer program read therefrom is installed into the storage section 808 as necessary.

[0145] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 809, and / or installed from the removable recording medium 811. When the computer program is executed by the central processing unit (CPU) 801, the above-described functions defined in the system of the present disclosure are performed.

[0146] It should be noted that the computer-readable medium shown in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component. In the present application, the computer-readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or component. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0147] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code containing one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different order than that shown in the drawings. For example, two blocks that are shown in succession can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0148] The modules described in the embodiments of the present application can be implemented in software or hardware. The modules described can also be arranged in a processor, for example, a processor can be described as comprising an identification module, a screening module, an establishment module and a monitoring module. In some cases, the names of the modules do not constitute a limitation of the modules themselves, for example, the identification module can also be described as "a module configured to identify a default history parameter of a payment liability by using historical asset data and historical liability data of an enterprise".

[0149] As another aspect, the present application also provides a computer readable medium, which can be included in the device described in the above embodiments or exist independently without being assembled into the device. The computer readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0150] identify a default history parameter of a payment liability by using historical asset data and historical liability data of an enterprise;

[0151] determine a default preliminary screening feature in historical business data according to business operations, and screen a default re-screening feature from the default preliminary screening feature based on a preset model;

[0152] combine the default history parameter and a default actual parameter with the default re-screening feature to construct a risk threshold model, and determine a risk threshold based on a deviation distribution of the default history parameter and the default actual parameter and the risk threshold model;

[0153] monitor business data of the enterprise by using a default current parameter of the enterprise and the risk threshold.

[0154] According to the technical solution of the embodiments of the present application, a default history parameter of a payment liability is identified by using historical asset data and historical liability data of an enterprise, a default preliminary screening feature is determined in historical business data according to business operations, a default re-screening feature is screened from the default preliminary screening feature based on a preset model, the default re-screening feature is combined with the default history parameter and a default actual parameter to construct a risk threshold model, a risk threshold is determined based on a deviation distribution of the default history parameter and the default actual parameter and the risk threshold model, and business data of the enterprise is monitored by using a default current parameter of the enterprise and the risk threshold. The risk threshold is used as a basis for monitoring data, and changes in business data can be learned in a timely manner based on a default current parameter of the enterprise.

[0155] The above detailed description does not limit the scope of the application. It is to be understood that various modifications and examples can be made without departing from the spirit and scope of the application. Any modification, equivalent replacement, and improvement made within the spirit and principle of the application shall fall within the scope of the application. It should be noted that the acquisition, storage, and application of user personal information in the technical solutions of the present disclosure comply with relevant laws and regulations and do not violate public order and good customs.

Claims

1. A method for monitoring data, characterized in that, include: By using the company's historical asset data and historical liability data, historical default parameters for liability repayment are identified; Determine the initial screening features of default based on business operations in historical business data, and then select the secondary screening features of default based on a preset model from the initial screening features of default. The default rescreening features combine the default historical parameters and the default actual parameters to construct a risk threshold model, and the risk threshold is determined by the deviation distribution of the default historical parameters and the default actual parameters and the risk threshold model. The company's business data is monitored using the company's current default parameters and the risk threshold.

2. The method for monitoring data according to claim 1, characterized in that, The process of determining initial default screening features based on business operations in historical business data, and then selecting secondary default screening features from these initial default screening features based on a preset model, includes: Obtain the identifiers of defaulted business data from historical business data, and determine the initial screening characteristics of defaults based on the identifiers of business operations; Based on the default screening features and the default results of historical business data, a decision tree model is established as the preset model, and default rescreening features are selected from the default screening features based on the preset model.

3. The method for monitoring data according to claim 2, characterized in that, The step of obtaining the identifier of default business data from historical business data and determining the initial screening characteristics of default based on the identifier of business operation includes: Obtain the identifiers of defaulted business data from historical business data, and determine the characteristics of defaulted business based on the identifiers of defaulted business operations; The default business characteristics and default adjustment characteristics are used as the initial default screening characteristics, and the default adjustment characteristics are determined by analyzing the default results of the historical business data.

4. The method for monitoring data according to claim 1, characterized in that, The default rescreening features, combined with the historical default parameters and the actual default parameters, construct a risk threshold model, including: Based on the default rescreening features, the default history parameters, and the default actual parameters, a risk threshold model is constructed on the basis of a logistic regression model. The risk threshold model includes the deviation between the default history parameters and the default actual parameters. Adjust the weight parameters of the default rescreening features in the risk threshold model so that the deviation between the historical default parameters and the actual default parameters conforms to a preset probability distribution.

5. The method for monitoring data according to claim 1, characterized in that, The determination of the risk threshold using the deviation distribution of historical default parameters and actual default parameters, and the risk threshold model, includes: Random data is determined based on the deviation distribution between historical default parameters and actual default parameters, and the random data is input into the risk threshold model to obtain default prediction parameters; Multiple default prediction parameters are arranged from largest to smallest, and the default prediction parameter with a preset quantile is used as the risk threshold.

6. The method for monitoring data according to claim 1, characterized in that, The monitoring of the enterprise's business data using the enterprise's current default parameters and the risk threshold includes: The sum of the current default parameters of all enterprises is compared with the risk threshold, and the monitoring results of the business data of the monitored enterprises are sent according to the comparison results.

7. The method for monitoring data according to claim 1 or 6, characterized in that, The method further includes: Based on the company's current default parameters, current asset data, and liability threshold, a monitoring alert instruction is sent to the company.

8. A device for monitoring data, characterized in that, include: The identification module is used to identify historical default parameters for debt repayment by using the company's historical asset data and historical liability data. The filtering module is used to determine the initial screening features of default based on business operations in historical business data, and to filter out the secondary screening features of default based on a preset model from the initial screening features of default. A module is established to construct a risk threshold model by combining the default rescreening features with the default history parameters and the default actual parameters, and to determine the risk threshold by the deviation distribution of the default history parameters and the default actual parameters and the risk threshold model; The monitoring module is used to monitor the company's business data using the company's current default parameters and the risk threshold.

9. An electronic device for monitoring data, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images