Data processing method and device, equipment, storage medium and program product

Abstract

The invention provides a data processing method which can be applied to the technical field of big data and the technical field of financial science and technology. The data processing method comprises the following steps: in response to a data processing instruction sent by a terminal, obtaining multiple pieces of target transaction data corresponding to a target transaction object from a data prediction system; performing data expansion processing on the multiple pieces of target transaction data, and outputting multiple pieces of expanded transaction data; performing N times of data combination processing on the plurality of extended transaction data, and outputting N initial data processing results in one-to-one correspondence with the N times of data combination processing; a target data processing result which is sent by the data analysis system and corresponds to the target transaction object is received, and the target data processing result is generated by the data analysis system based on the N initial data processing results; and sending the target data processing result to a result display system. The invention further provides a data processing device, equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the fields of big data and financial technology, and specifically to a data processing method, device, equipment, storage medium and program product. Background Art

[0002] In order to ensure that trading business is carried out normally and stably, it is usually necessary to analyze trading behavior. In the process of realizing the concept of the present disclosure, the inventor found that there are at least the following problems in the relevant technology: the relevant trading analysis method usually only relies on historical data, technical analysis and professional knowledge, resulting in strong subjectivity of trading analysis results and large human errors, so the accuracy of the analysis results is low; and the analysis process is usually only performed by a single system, resulting in low analysis decision efficiency and response speed, and poor scalability. Summary of the invention

[0003] In view of the above problems, the present disclosure provides a data processing method, apparatus, device, storage medium and program product.

[0004] According to a first aspect of the present disclosure, a data processing method is provided, comprising: in response to a data processing instruction sent by a terminal, obtaining a plurality of target transaction data corresponding to a target transaction object from a data prediction system; performing data expansion processing on the plurality of target transaction data, and outputting a plurality of extended transaction data; performing N data combination processing on the plurality of extended transaction data, and outputting N initial data processing results corresponding one to one to the N data combination processing; receiving a target data processing result corresponding to the target transaction object sent by a data analysis system, wherein the target data processing result is generated by the data analysis system based on the N initial data processing results; and sending the target data processing result to a result presentation system.

[0005] According to an embodiment of the present disclosure, multiple extended transaction data include K extended transaction behavior data and L extended transaction risk data; the data combination processing includes: performing a first random extraction process on the K extended transaction behavior data to obtain multiple target extended transaction behavior data; performing a second random extraction process on the L extended transaction risk data to obtain multiple target extended transaction risk data; performing data combination processing on the multiple target extended transaction behavior data and the multiple target extended transaction risk data, and outputting the initial data processing result.

[0006] According to an embodiment of the present disclosure, data expansion processing is performed on multiple target transaction data, and multiple extended transaction data are output, including: obtaining predetermined transaction data distribution characteristics; determining distribution characteristic parameters corresponding to the predetermined transaction data distribution characteristics; based on the distribution characteristic parameters, data expansion processing is performed on multiple target transaction data, and multiple extended transaction data are output.

[0007] According to an embodiment of the present disclosure, the data processing method also includes the following operations performed by the data analysis system: receiving N initial data processing results sent by the data simulation system; calculating the risk indicator value corresponding to each predetermined risk indicator based on the N initial data processing results; generating the target data processing result based on the risk indicator value; and sending the target data processing result to the data simulation system.

[0008] According to an embodiment of the present disclosure, a plurality of pre-built risk prediction models are stored in a data prediction system; obtaining a plurality of target transaction data corresponding to a target transaction object from the data prediction system includes: reading a target risk prediction model corresponding to a data processing instruction from the data prediction system; determining a plurality of model parameters corresponding to the target risk prediction model; and obtaining a plurality of target transaction data based on the plurality of model parameters.

[0009] According to an embodiment of the present disclosure, the risk prediction model includes a linear regression model; the linear regression model is constructed based on a target variable, multiple model parameters, multiple feature variables corresponding one-to-one to the multiple model parameters, and an error term.

[0010] According to an embodiment of the present disclosure, the data processing method further includes: optimizing multiple model parameters based on the target data processing result to obtain optimized model parameters; and sending the optimized model parameters to the data prediction system.

[0011] The second aspect of the present disclosure provides a data processing device, including: an acquisition module, which is used to respond to a data processing instruction sent by a terminal to acquire multiple target transaction data corresponding to the target transaction object from a data prediction system; a data expansion module, which is used to perform data expansion processing on the multiple target transaction data and output multiple extended transaction data; a data combination module, which is used to perform N data combination processing on the multiple extended transaction data and output N initial data processing results corresponding to the N data combination processing; a first receiving module, which is used to receive a target data processing result corresponding to the target transaction object and sent by a data analysis system, wherein the target data processing result is generated by the data analysis system based on the N initial data processing results; and a first sending module, which is used to send the target data processing result to a result display system.

[0012] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0013] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the above computer program or instructions are executed by a processor.

[0014] The fifth aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the above computer program or instructions are executed by a processor.

[0015] According to the embodiments of the present disclosure, transaction behavior analysis is performed based on a data prediction system, a data analysis system, a data simulation system, and a result display system, rather than only performing the analysis process based on a single system. It can be configured and optimized according to different transaction behavior analysis requirements and tasks, making the computer system more flexible; and in the event of a system failure, other systems can continue to operate, thereby improving the fault tolerance of the entire system. In addition, through the interaction between multiple systems, the analysis decision-making efficiency and response speed can be improved, and the scalability of the system can be improved. Data expansion processing is performed on multiple target transaction data to obtain multiple extended transaction data, and transaction behavior analysis is performed based on the extended transaction data, which can increase the amount of data used for transaction behavior analysis, and can ensure that the extended transaction data has similar data distribution characteristics as the target transaction data, thereby improving the accuracy of the target data processing results. Therefore, the technical problems of low accuracy, low analysis efficiency and response speed, and poor scalability of the relevant transaction data processing methods are at least partially solved, thereby achieving the technical effects of improving the analysis decision-making efficiency and response speed, improving the scalability of the system, and improving the accuracy of the data processing results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0017] Figure 1 The application scenario diagram of the data processing method, apparatus, device, storage medium and program product according to the embodiments of the present disclosure is schematically shown;

[0018] Figure 2 A flowchart schematically shows a data processing method according to an embodiment of the present disclosure;

[0019] Figure 3 A system structure diagram schematically shows a data processing method according to an embodiment of the present disclosure;

[0020] Figure 4 A flowchart schematically shows a data processing method according to another embodiment of the present disclosure;

[0021] Figure 5 A structural block diagram schematically shows a data processing device according to an embodiment of the present disclosure; and

[0022] Figure 6A block diagram of an electronic device suitable for implementing a data processing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0024] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0025] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0026] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0027] It should be noted that the data processing method and device disclosed herein can be used in the fields of big data and financial technology, and can also be used in any field other than the fields of big data and financial technology. The application field of the data processing method and device disclosed herein is not limited.

[0028] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0029] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0030] The results of trading behavior analysis are usually affected by many factors, such as market fluctuations, trading environment, and internal factors of financial institutions. Due to the large volatility and uncertainty of the above factors, the accuracy of trading behavior analysis results is low, the information lag is strong, and it is difficult to capture new changes in influencing factors in a timely manner, resulting in the lag of trading behavior analysis; and the existing trading behavior analysis methods are mostly based on historical data, technical analysis and professional knowledge, which makes the trading behavior analysis results susceptible to personal experience. Therefore, the results of trading behavior analysis are highly subjective and have large human errors; in addition, the analysis process is usually performed by only a single system, resulting in low analysis decision efficiency and response speed, and poor scalability.

[0031] In view of this, an embodiment of the present disclosure provides a data processing method, including: in response to a data processing instruction sent by a terminal, obtaining multiple target transaction data corresponding to a target transaction object from a data prediction system; performing data expansion processing on the multiple target transaction data, and outputting multiple extended transaction data; performing N data combination processing on the multiple extended transaction data, and outputting N initial data processing results corresponding to the N data combination processing; receiving a target data processing result corresponding to the target transaction object sent by a data analysis system, wherein the target data processing result is generated by the data analysis system based on the N initial data processing results; and sending the target data processing result to a result presentation system.

[0032] Figure 1 The application scenario diagram of the data processing method, apparatus, device, storage medium and program product according to the embodiments of the present disclosure is schematically shown.

[0033] like Figure 1As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0034] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0035] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0036] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0037] It should be noted that the data processing method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the data processing device provided in the embodiment of the present disclosure can generally be set in the server 105. The data processing method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the data processing device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0038] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0039] The following will be based on Figure 1 The scene described by Figure 2~Figure 4 The data processing method of the embodiment of the present disclosure is described in detail.

[0040] Figure 2 The flowchart of the data processing method according to the embodiment of the present disclosure is schematically shown. The data processing method can be executed by a transaction simulation system.

[0041] like Figure 2 As shown, the data processing method of this embodiment includes operations S210 to S250.

[0042] In operation S210, in response to a data processing instruction sent by a terminal, a plurality of target transaction data corresponding to a target transaction object is acquired from a data prediction system.

[0043] In operation S220, data expansion processing is performed on the plurality of target transaction data, and a plurality of extended transaction data is output.

[0044] In operation S230, N data combination processes are performed on the plurality of extended transaction data, and N initial data processing results corresponding to the N data combination processes are output.

[0045] In operation S240, a target data processing result corresponding to a target transaction object and sent by the data analysis system is received, wherein the target data processing result is generated by the data analysis system based on N initial data processing results.

[0046] In operation S250, the target data processing result is sent to the result presentation system.

[0047] Figure 3 The system structure diagram of the data processing method according to the embodiment of the present disclosure is schematically shown. Figure 3 As shown, the system structure of the data processing method of the embodiment of the present disclosure includes a data prediction system, a data analysis system, a data simulation system and a result display system.

[0048] Specifically, in operation S210, the data simulation system may analyze the transaction behavior of the target transaction object based on the transaction data. Specifically, in response to the data processing instruction sent by the terminal, the data simulation system may obtain multiple target transaction data corresponding to the target transaction object from the data prediction system. Among them, the data processing instruction may be used to instruct the target transaction object to perform a transaction behavior analysis, and the transaction behavior analysis may include, for example, analyzing the transaction risk of the target transaction object. The target transaction object may be a product whose transaction information needs to be analyzed. The data prediction system stores multiple risk prediction models corresponding to multiple transaction objects, and the multiple transaction objects include the target transaction object. Based on the risk prediction model corresponding to the target transaction object, multiple target transaction data corresponding to the target transaction object may be obtained.

[0049] Most of the related technologies only analyze trading behavior based on actual historical data. However, the amount of actual historical data may be limited, and analyzing trading behavior based only on a limited amount of data may result in low accuracy of trading behavior analysis results.

[0050] According to an embodiment of the present disclosure, in operation S220, after acquiring the target transaction data, the data simulation system may perform data expansion processing on the multiple target transaction data. The data expansion processing may be used to generate a large amount of expanded transaction data based on the multiple target transaction data.

[0051] The target transaction data is data that can reflect the real transaction behavior of the target transaction object, so it has high reliability. By performing data expansion processing on multiple target transaction data through the data expansion model, the extended transaction data can be obtained. On the one hand, the amount of transaction data used for data analysis of transaction behavior can be expanded, and on the other hand, the extended transaction data can have similar data distribution characteristics to the target transaction data, so that the extended transaction data can also reflect the real transaction behavior of the target transaction object, thereby making the data processing results based on the extended transaction data more accurate.

[0052] According to an embodiment of the present disclosure, in operation S230, the extended transaction data may include multiple types of data, for example, data for characterizing a transaction risk scenario class corresponding to the target transaction object, and the transaction risk scenario class data may, for example, be market risk data, credit risk data, etc.; the extended transaction data may also include data for characterizing a transaction behavior class corresponding to the target transaction object, and the transaction behavior class data may, for example, include historical yields, etc.

[0053] Different types of extended transaction data may be combined to obtain a combined extended transaction data set, and the initial data processing result may be calculated based on the extended transaction data set. The different types of extended transaction data may be combined by combining data of a transaction risk scenario class with data of a transaction behavior class. The initial data processing result may be calculated based on the extended transaction data set by respectively determining data values ​​of data of a transaction risk scenario class and data of a transaction behavior class, and respectively determining weights of data of a transaction risk scenario class and data of a transaction behavior class, and calculating the initial data processing result based on the weights and data values.

[0054] According to an embodiment of the present disclosure, in operation S240, after generating the initial data processing result, the data simulation system may send the initial data processing result to the data analysis system. The data analysis system may generate the data processing result based on the received N initial data processing results, for example, it may calculate the average return, standard deviation, quantile and other indicator values ​​of the N initial data processing results, or it may analyze the central tendency and distribution range of the N initial data processing results to obtain the target data processing result. The target data processing result may be used to characterize the transaction risk level of the target transaction object.

[0055] According to an embodiment of the present disclosure, in operation S250, after the data analysis system sends the generated target data processing result to the data simulation system, the data simulation system can send the target data processing result to the result display system, so that the result display system can generate a transaction data analysis report based on the target data processing result, and display the above transaction data analysis report. It is also possible to design the configuration and weight of the transaction product portfolio in a personalized manner based on the target data processing result, thereby reducing the transaction risk of the transaction product, and at the same time, it can also meet the needs and risk preferences of different users, thereby improving the practicality and applicability of the data processing method.

[0056] According to the embodiments of the present disclosure, transaction behavior analysis is performed based on a data prediction system, a data analysis system, a data simulation system, and a result presentation system, rather than executing the analysis process based on only a single system. It can be configured and optimized according to different transaction behavior analysis requirements and tasks, making the computer system more flexible; and in the event of a system failure, other systems can continue to operate, thereby improving the fault tolerance of the entire system. In addition, through the interaction between multiple systems, the analysis decision-making efficiency and response speed can be improved, thereby improving the scalability of the system.

[0057] According to an embodiment of the present disclosure, data expansion processing is performed on multiple target transaction data to obtain multiple extended transaction data, and transaction behavior analysis is performed based on the extended transaction data. This can increase the amount of data used for transaction behavior analysis and ensure that the extended transaction data and the target transaction data have similar data distribution characteristics, thereby improving the accuracy of the target data processing results.

[0058] According to an embodiment of the present disclosure, N initial data processing results may be generated based on Monte Carlo simulation. Specifically, generating N initial data processing results based on Monte Carlo simulation may include performing data expansion processing on multiple target transaction data, outputting multiple expanded transaction data, and performing N data combination processing on the multiple expanded transaction data, and outputting N initial data processing results corresponding to the N data combination processing.

[0059] According to an embodiment of the present disclosure, specifically, the multiple extended transaction data include K extended transaction behavior data and L extended transaction risk data. The data combination processing includes: performing a first random extraction process on the K extended transaction behavior data to obtain multiple target extended transaction behavior data; performing a second random extraction process on the L extended transaction risk data to obtain multiple target extended transaction risk data; performing data combination processing on the multiple target extended transaction behavior data and the multiple target extended transaction risk data, and outputting an initial data processing result.

[0060] According to an embodiment of the present disclosure, extended transaction behavior data may include: historical rate of return data, expected rate of return data; extended transaction risk data may characterize the transaction risk scenarios corresponding to the target transaction objects, and the extended transaction risk data may include, for example: market risk data, credit risk data, operational risk data, etc.

[0061] According to an embodiment of the present disclosure, the first random extraction process may be: randomly extracting a predetermined number of extended transaction behavior data from K extended transaction behavior data to obtain target extended transaction risk data; the second random extraction process may be randomly extracting a predetermined number of extended transaction risk data from L extended transaction risk data to obtain target extended transaction risk data.

[0062] According to an embodiment of the present disclosure, different extended transaction behavior data and different extended transaction risk data can be combined to form different transaction combination scenarios. The expected return values ​​corresponding to different transaction combination scenarios can be calculated to obtain initial data processing results. Specifically, the values ​​and weights of the target extended transaction behavior data and the target extended transaction risk data can be determined respectively. The data combination processing can include: based on the values ​​and weights of the target extended transaction behavior data and the target extended transaction risk data, calculating the expected return value to obtain the initial data processing result.

[0063] For example: the randomly drawn target extended transaction behavior data is historical yield data, and the randomly drawn target extended transaction risk data is market risk data. The values ​​of the above historical yield data and market risk data can be determined, as well as the weights of the above historical yield data and market risk data. Based on the values ​​and weights of the above historical yield data and market risk data, the expected return value of the target transaction object can be calculated. For example, the historical yield data value and the market risk data value can be weightedly summed.

[0064] Furthermore, before performing data combination processing, the correlation between the target extended transaction risk data and the target extended transaction behavior data can also be determined, and the target extended transaction behavior data that has no correlation with the target extended transaction risk data can be eliminated, that is, data combination processing is not performed on the target extended transaction risk data and the target extended transaction behavior data that has no correlation with it.

[0065] According to the embodiments of the present disclosure, data combination processing is performed based on randomly extracted extended transaction behavior data and extended transaction risk data, and a large number of transaction combination scenarios can be generated, and then a large number of initial data processing results corresponding to the transaction combination scenarios can be generated. Compared with generating target data processing results based only on a limited number of data, by increasing the number of transaction combination scenarios and correspondingly increasing the number of initial data processing results, the accuracy of the target data processing results can be improved.

[0066] According to an embodiment of the present disclosure, data expansion processing is performed on multiple target transaction data, and multiple extended transaction data are output, including: obtaining predetermined transaction data distribution characteristics; determining distribution characteristic parameters corresponding to the predetermined transaction data distribution characteristics; based on the distribution characteristic parameters, data expansion processing is performed on multiple target transaction data, and multiple extended transaction data are output.

[0067] According to an embodiment of the present disclosure, the distribution characteristics of the predetermined transaction data may include normal distribution, Beta distribution, etc. In the case where the distribution characteristics are normal distribution, the distribution characteristic parameters corresponding to the distribution characteristics of the predetermined transaction data may include a mean and a mean difference. Performing data expansion processing on multiple target transaction data and outputting multiple extended transaction data may: based on the distribution characteristic parameters, perform data expansion processing on multiple target transaction data to generate multiple extended transaction data that obey the normal distribution.

[0068] According to an embodiment of the present disclosure, by performing data expansion processing on multiple target transaction data to generate multiple extended transaction data that obey a normal distribution, the extended transaction data can have similar data distribution characteristics to the target transaction data, and the amount of transaction data used for data analysis of transaction behavior can be expanded, thereby improving the accuracy of the data processing results.

[0069] According to an embodiment of the present disclosure, based on Monte Carlo simulation, multiple extended transaction data are generated, and initial data processing results are generated based on the multiple extended transaction data. A large number of possible transaction combination scenarios can be generated, and the generated transaction combination scenarios can reflect the actual transaction behavior of the target transaction object, thereby improving the accuracy of the target data processing results and reducing the uncertainty of the data processing results caused by the large volatility of factors affecting the transaction behavior.

[0070] According to an embodiment of the present disclosure, the data processing method further includes the data analysis system performing the following operations 11 to 14.

[0071] Operation 11: Receive N initial data processing results sent by the data simulation system.

[0072] Operation 12: Calculate the risk indicator value corresponding to each predetermined risk indicator based on the N initial data processing results.

[0073] Operation 13: Generate target data processing results based on the risk indicator value.

[0074] Operation 14: Send the target data processing result to the data simulation system.

[0075] According to an embodiment of the present disclosure, the initial data processing result may be an expected return value of the target transaction object. Each predetermined risk indicator may include the average value, standard deviation, quantile, etc. of the initial data processing result. After determining the predetermined risk indicator, the risk indicator values ​​of N initial data processing results may be calculated, for example, the average value, standard deviation, and quantile of the expected return value may be calculated to obtain the risk indicator value. Based on the risk indicator value, generating the target data processing result may include: calculating the transaction risk indicator value based on the risk indicator value to obtain the target data processing result, wherein the transaction risk indicator value may include the return volatility value and the maximum drawdown value.

[0076] According to an embodiment of the present disclosure, different initial data processing results correspond to different transaction combination scenarios. By generating a target data processing result through multiple initial data processing results, the influence of multiple transaction combination scenarios can be comprehensively considered, thereby improving the accuracy of the target data processing result.

[0077] According to an embodiment of the present disclosure, a plurality of pre-built risk prediction models are stored in the data prediction system.

[0078] According to an embodiment of the present disclosure, obtaining multiple target transaction data corresponding to the target transaction object from the data prediction system includes: reading a target risk prediction model corresponding to the data processing instruction from the data prediction system; determining multiple model parameters corresponding to the target risk prediction model; and obtaining multiple target transaction data based on the multiple model parameters.

[0079] According to an embodiment of the present disclosure, a plurality of risk prediction models corresponding to a plurality of transaction objects may be stored in a data prediction system, and a target risk prediction model corresponding to a target transaction object may be read from the data prediction system based on a data processing instruction. The target risk prediction model may include a plurality of model parameters, and the model parameters may be directly used as target transaction data. The target transaction data may also be obtained after parameter conversion processing is performed on the model parameters. The parameter conversion processing may include: standardizing the model parameters, or transforming the model parameters. Among them, the transformation processing may include logarithmic transformation processing, square root transformation processing, and the like.

[0080] According to an embodiment of the present disclosure, the risk prediction model includes a linear regression model; the linear regression model is constructed based on a target variable, multiple model parameters, multiple feature variables corresponding one-to-one to the multiple model parameters, and an error term.

[0081] According to an embodiment of the present disclosure, a data set containing n samples can be obtained, wherein each sample has m features, and the feature matrix can be represented by x, with a dimension of (n, m), and the target variable can be represented by y, with a dimension of (n, 1). A risk prediction model can be constructed based on a linear regression model, wherein the linear regression model is shown in the following formula (1).

[0082] (1)

[0083] Among them, y is the target variable, x1, x2, ...x m are characteristic variables, β0, β1, β2, ...β m are model parameters, is the error term.

[0084] According to the embodiments of the present disclosure, a trading data sample set may be obtained from multiple sources such as data providers and company reports, and the trading data training sample set may include, for example, historical investment data, trading market data, trading indicators, etc. The data in the trading data sample set may be cleaned, processed, and integrated to ensure the quality and consistency of the data.

[0085] The transaction data sample set can be divided into a training set, a validation set, and a test set. The risk prediction model can be trained using the training set by minimizing the loss function. The minimization loss function can be shown as formula (2).

[0086] (2)

[0087] in, is the predicted value of the risk prediction model for the i-th sample, n is the number of samples, y i is the actual value of the i-th sample.

[0088] Parameter tuning can be performed by gradient descent and other methods. For example, the model parameters β0, β1, β2, ...β m To reduce the loss function. The mean square error indicator can also be used on the validation set to evaluate the performance of the model to observe the prediction effect of the model. Based on the prediction results of the model, it can be observed whether there are problems such as overfitting or underfitting, and adjustments and optimizations can be made as needed. The final model can be verified on the test set to evaluate the generalization ability and prediction accuracy of the risk prediction model.

[0089] According to the embodiments of the present disclosure, the risk prediction model is trained based on the transaction data sample set, which realizes the intelligence of the transaction processing process, can conduct in-depth and comprehensive analysis of historical transaction data, more accurately identify market trends and risk factors, improve the accuracy and scientificity of risk prediction, and reduce the uncertainty of the transaction combination determination process. Based on the model parameters of the risk prediction model, the target transaction data is determined, and the target transaction data is used as the input data of the Monte Carlo simulation. It can combine big data processing and machine learning technology at the same time, so that the system can process large-scale data and realize intelligent investment decision support, and make the data processing method widely applicable to various fields, such as the financial investment field, and can also be applied to risk management and asset allocation.

[0090] According to an embodiment of the present disclosure, the data processing method further includes: optimizing multiple model parameters based on the target data processing result to obtain optimized model parameters; and sending the optimized model parameters to the data prediction system.

[0091] Figure 4 The flowchart schematically shows a data processing method according to another embodiment of the present disclosure.

[0092] like Figure 4 As shown, the data processing method of this embodiment includes operations S410 to S450.

[0093] In operation S410 , a target data processing result is generated by the data analysis system.

[0094] In operation S420, the target data processing result is sent to the data simulation system.

[0095] In operation S430, model parameters are optimized according to the target data processing result.

[0096] In operation S440, the optimized model parameters are sent to the data prediction system.

[0097] In operation S450, the optimized model parameters are stored by the data prediction system.

[0098] According to an embodiment of the present disclosure, after generating the target data processing result, the model parameters can be optimized and the optimized model parameters can be sent to the data prediction system, so that when the data processing instruction sent by the terminal is received next time, the optimized model parameters can be obtained from the data prediction system, thereby improving the accuracy of the target data processing result.

[0099] Based on the above data processing method, the present disclosure also provides a data processing device. Figure 5 The device is described in detail.

[0100] Figure 5 The structure block diagram of a data processing device according to an embodiment of the present disclosure is schematically shown.

[0101] like Figure 5 As shown, the data processing device 500 of this embodiment includes an acquisition module 510 , a data expansion module 520 , a data combination module 530 , a first receiving module 540 and a first sending module 550 .

[0102] The acquisition module 510 is used to respond to the data processing instruction sent by the terminal and acquire multiple target transaction data corresponding to the target transaction object from the data prediction system. In one embodiment, the acquisition module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0103] The data expansion module 520 is used to perform data expansion processing on multiple target transaction data and output multiple expanded transaction data. In one embodiment, the data expansion module 520 can be used to perform the operation S220 described above, which will not be described in detail here.

[0104] The data combination module 530 is used to perform N data combination processes on the multiple extended transaction data, and output N initial data processing results corresponding to the N data combination processes. In one embodiment, the data combination module 530 can be used to perform the operation S230 described above, which will not be repeated here.

[0105] The first receiving module 540 is used to receive the target data processing result corresponding to the target transaction object sent by the data analysis system, wherein the target data processing result is generated by the data analysis system based on the N initial data processing results. In one embodiment, the first receiving module 540 can be used to perform the operation S240 described above, which will not be repeated here.

[0106] The first sending module 550 is used to send the target data processing result to the result display system. In one embodiment, the first sending module 550 can be used to perform the operation S250 described above, which will not be described in detail here.

[0107] According to an embodiment of the present disclosure, the data combination module includes a first random extraction submodule, a second random extraction submodule and a first output submodule.

[0108] The first random extraction submodule is used to perform a first random extraction process on K extended transaction behavior data to obtain multiple target extended transaction behavior data; the second random extraction submodule is used to perform a second random extraction process on L extended transaction risk data to obtain multiple target extended transaction risk data; the first output submodule is used to perform data combination processing on multiple target extended transaction behavior data and multiple target extended transaction risk data, and output the initial data processing result.

[0109] According to an embodiment of the present disclosure, the data expansion module includes an acquisition submodule, a first determination submodule and a second output submodule.

[0110] The acquisition submodule is used to obtain the predetermined transaction data distribution characteristics; the first determination submodule is used to determine the distribution characteristic parameters corresponding to the predetermined transaction data distribution characteristics; the second output submodule is used to perform data expansion processing on multiple target transaction data based on the distribution characteristic parameters and output multiple extended transaction data.

[0111] According to an embodiment of the present disclosure, the data processing device further includes a second receiving module, a calculating module, a generating module and a second sending module.

[0112] The second receiving module is used to receive N initial data processing results sent by the data simulation system; the calculation module is used to calculate the risk indicator value corresponding to each predetermined risk indicator based on the N initial data processing results; the generation module is used to generate the target data processing result based on the risk indicator value; the second sending module is used to send the target data processing result to the data simulation system.

[0113] According to an embodiment of the present disclosure, the acquisition module includes a reading submodule and a second determination submodule.

[0114] The reading submodule is used to read the target risk prediction model corresponding to the data processing instruction from the data prediction system; the second determination submodule is used to determine multiple model parameters corresponding to the target risk prediction model, and obtain multiple transaction data based on the multiple target model parameters.

[0115] According to an embodiment of the present disclosure, the data processing device further includes an optimization module and a third sending module.

[0116] The optimization module is used to optimize multiple model parameters based on the target data processing results to obtain optimized model parameters; the third sending module is used to send the optimized model parameters to the data prediction system.

[0117] According to an embodiment of the present disclosure, any multiple modules among the acquisition module 510, the data expansion module 520, the data combination module 530, the first receiving module 540 and the first sending module 550 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 510, the data expansion module 520, the data combination module 530, the first receiving module 540 and the first sending module 550 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of the acquisition module 510, the data expansion module 520, the data combination module 530, the first receiving module 540 and the first sending module 550 can be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function can be performed.

[0118] Figure 6 A block diagram of an electronic device suitable for implementing a data processing method according to an embodiment of the present disclosure is schematically shown.

[0119] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0120] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0121] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0122] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0123] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0124] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the data processing method provided by the embodiment of the present disclosure.

[0125] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 601. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0126] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0127] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, apparatus, module, unit, etc. described above can be implemented by a computer program module.

[0128] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0129] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0130] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0131] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A data processing method, characterized in that: The method comprises: In response to the data processing instruction sent by the terminal, a plurality of target transaction data corresponding to the target transaction object is acquired from the data prediction system; Performing data expansion processing on the multiple target transaction data, and outputting multiple extended transaction data; Performing N data combination processing on the multiple extended transaction data, and outputting N initial data processing results corresponding to the N data combination processing; Receiving a target data processing result corresponding to the target transaction object and sent by a data analysis system, wherein the target data processing result is generated by the data analysis system based on the N initial data processing results; The target data processing result is sent to a result presentation system.

2. The method according to claim 1, characterized in that The multiple extended transaction data include K extended transaction behavior data and L extended transaction risk data; The data combination process includes: Performing a first random extraction process on the K extended transaction behavior data to obtain a plurality of target extended transaction behavior data; Performing a second random extraction process on the L extended transaction risk data to obtain a plurality of target extended transaction risk data; Perform data combination processing on the plurality of target extended transaction behavior data and the plurality of target extended transaction risk data, and output the initial data processing result.

3. The method according to claim 1, characterized in that The performing data expansion processing on the plurality of target transaction data and outputting a plurality of extended transaction data comprises: Obtaining distribution characteristics of predetermined transaction data; Determining a distribution characteristic parameter corresponding to the predetermined transaction data distribution characteristic; Based on the distribution characteristic parameters, data expansion processing is performed on the multiple target transaction data, and the multiple expanded transaction data are output.

4. The method according to claim 1, characterized in that: The method further includes executing the following operations by the data analysis system: Receiving the N initial data processing results sent by the data simulation system; Calculating risk indicator values ​​corresponding to each predetermined risk indicator based on the N initial data processing results; Based on the risk indicator value, generating the target data processing result; The target data processing result is sent to the data simulation system.

5. The method according to claim 1, characterized in that The data prediction system stores a plurality of pre-built risk prediction models; The acquiring of a plurality of target transaction data corresponding to the target transaction object from the data prediction system comprises: Reading a target risk prediction model corresponding to the data processing instruction from the data prediction system; Determining a plurality of model parameters corresponding to the target risk prediction model; Based on the multiple model parameters, the multiple target transaction data are obtained.

6. The method according to claim 5, characterized in that: The risk prediction model includes a linear regression model; The linear regression model is constructed based on the target variable, the multiple model parameters, a plurality of feature variables corresponding one-to-one to the multiple model parameters, and an error term.

7. The method according to claim 6, characterized in that The method further comprises: Based on the target data processing result, optimizing the multiple model parameters to obtain optimized model parameters; The optimized model parameters are sent to the data prediction system.

8. A data processing device, characterized in that: The device comprises: An acquisition module, configured to acquire a plurality of target transaction data corresponding to a target transaction object from a data prediction system in response to a data processing instruction sent by a terminal; A data expansion module, used for performing data expansion processing on the plurality of target transaction data and outputting a plurality of extended transaction data; A data combination module, used for performing N data combination processing on the plurality of extended transaction data, and outputting N initial data processing results corresponding to the N data combination processing; A first receiving module is configured to receive a target data processing result corresponding to the target transaction object and sent by a data analysis system, wherein the target data processing result is generated by the data analysis system based on the N initial data processing results; The first sending module is used to send the target data processing result to the result display system.

9. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images