CN-114610965-B - Data processing method, device, equipment and storage medium

CN114610965BCN 114610965 BCN114610965 BCN 114610965BCN-114610965-B

Abstract

The application discloses a data processing method, a device, equipment and a storage medium; the input reference value is used for representing a magnitude value of a first output value corresponding to the first input value, which affects the first input value, determining a deviation degree based on a second output value and a second actual value, determining a first state value based on the input reference value, the deviation degree and a second state value, wherein the second state value is a state value corresponding to the second input value, and determining the first output value based on at least the first state value. On the one hand, the method increases the verification process of calculating the deviation degree in the process of data analysis, realizes the automatic verification function and is simple to realize, and on the other hand, in the process of determining the output value, the influence of the input value and the influence of the historical state value are considered, so that the accuracy of the prediction result is improved.

Inventors

SHEN NINGBEINI
DENG XIANG
XU FENG
LU DAOHE
ZHANG ZHENG
MA ZHENG
ZHUO YANKUN
LI HANJU
CHEN JIE

Assignees

深圳前海微众银行股份有限公司

Dates

Publication Date: 20260505
Application Date: 20220208

Claims (9)

1. A method of data processing, the method comprising: determining an input reference value based on a first input value, wherein the input reference value is used for representing a magnitude value which influences a first output value corresponding to the first input value in the first input value; Determining a deviation degree based on a second output value and a second actual value, wherein the deviation degree is used for representing the deviation degree between the second output value and the second actual value, the second output value is an output value corresponding to a second input value, the second actual value is an actual value corresponding to the second input value, and the second input value is a historical input value; Determining a first state value based on the input reference value, the deviation degree and a second state value, wherein the second state value is a state value corresponding to the second input value; obtaining a history output set and a plurality of types of history input values; calculating a correlation coefficient between input and output based on the set of historical outputs and the plurality of types of historical input values; determining the first output value according to a fourth formula; The fourth formula includes: The following steps Representing the first output value, the Representing the correlation coefficient, the Representing the first state value.
2. The method of claim 1, wherein determining the input reference value based on the first input value comprises: determining the input reference value according to a first formula; wherein the first formula comprises: The following steps Representing the input reference value, the Representing the first input value, the Representing the input average.
3. The method of claim 1, wherein determining the degree of deviation based on the second output value and the second actual value comprises: Determining the degree of deviation according to a second formula; The second formula includes: The following steps Representing the degree of deviation, the Representing the second actual value, the Representing the second output value.
4. The method of claim 1, wherein the determining a first state value based on the input reference value, the degree of deviation, and a second state value comprises: Determining the first state value according to a third formula; the third formula includes: The following steps Representing the first state value, the Representing the degree of deviation of Representing the input reference value, the Representing the second state value.
5. The method of claim 1, wherein the obtaining a set of historical outputs comprises: clustering a first set to obtain at least one cluster, wherein the first set comprises at least two historical output values; Performing a second process for each of the at least one cluster to obtain a distance between each of the at least two historical output values and a center point, the second process comprising calculating a distance between each of the at least one historical output values comprised by the cluster and a center point; Adjusting the at least one cluster based on a distance between each of the at least two historical output values and a center point; Judging whether the adjusted historical output value included in each cluster is converged or not; and deleting the discrete data included in each cluster to obtain the history output set, wherein the discrete data are data which cannot be converged.
6. The method of claim 1, wherein the calculating a correlation coefficient between an input and an output based on the set of historical outputs and the plurality of types of historical input values comprises: performing a first process for each of the plurality of types to obtain a correlation corresponding to the plurality of types, wherein the first process comprises calculating a correlation between a historical input value of the type and the historical output set based on the historical input value of the type and the historical output set; Determining the type meeting the first condition as a reference type in the correlation degrees corresponding to the types; the correlation coefficient is determined based on the historical input values of the reference type and the set of historical outputs.
7. A data processing apparatus, the apparatus comprising: the device comprises a first determining unit, a first input value determining unit and a second determining unit, wherein the first determining unit is used for determining an input reference value based on a first input value, and the input reference value is used for representing a magnitude value of a first output value corresponding to the first input value in the first input value; The device comprises a first determining unit, a second determining unit and a first judging unit, wherein the first determining unit is used for determining a deviation degree based on a first output value and a first actual value, the deviation degree is used for representing the deviation degree between the first output value and the first actual value, the first output value is an output value corresponding to a first input value, the second actual value is an actual value corresponding to the first input value, and the first input value is a historical input value; the third determining unit is used for determining a first state value based on the input reference value, the deviation degree and a second state value, wherein the second state value is a state value corresponding to the second input value; a fourth determining unit configured to determine a first output value based at least on the first state value; the fourth determining unit is further configured to: obtaining a history output set and a plurality of types of history input values; calculating a correlation coefficient between input and output based on the set of historical outputs and the plurality of types of historical input values; determining the first output value according to a fourth formula; The fourth formula includes: The following steps Representing the first output value, the Representing the correlation coefficient, the Representing the first state value.
8. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, the processor implementing the data processing method of any one of claims 1 to 6 when the program is executed.
9. A storage medium having stored thereon a computer program which, when executed by a processor, implements the data processing method of any of claims 1 to 6.

Description

Data processing method, device, equipment and storage medium Technical Field The present application relates to the field of data processing technology, and relates to, but is not limited to, data processing methods, apparatuses, devices, and storage media. Background With the rapid development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually changed to the financial technology (Fintech), but due to the requirements of safety and real-time performance of the financial industry, higher requirements are also put on the technologies. Among other things, data analysis plays an increasingly important role in business practice. In the current data analysis process, the sampled data volume is large, the calculation process is relatively complex, the data sampling dimension is mostly determined by business personnel with abundant experience, the manual intervention influence of the data analysis result is too large, and the input item and the output item cannot have a stable association relation. For example, in the related art, when data analysis is performed, an input value is analyzed by using a data model to obtain a predicted result, a final result is determined based on the predicted result by a manual method, and then the predicted result is verified by a manual method. In this way, on the one hand, the accuracy of the prediction result obtained by the data model is poor because the prediction result is separated from the verification process, and on the other hand, the verification is performed independently by a manual mode, so that the implementation process is complex, and time and labor are consumed. Disclosure of Invention The application provides a data processing method, a device, equipment and a storage medium, and for the scheme of the application, on one hand, a verification process for calculating the deviation degree is added in the process of data analysis, so that an automatic verification function is realized, and the realization is simple; on the other hand, in the process of determining the output value, the influence of the input value is considered, and the influence of the historical state value is also considered, so that the accuracy of the prediction result is improved. The technical scheme of the application is realized as follows: the application provides a data processing method, which comprises the following steps: determining an input reference value based on a first input value, wherein the input reference value is used for representing a magnitude value which influences a first output value corresponding to the first input value in the first input value; Determining a deviation degree based on a second output value and a second actual value, wherein the deviation degree is used for representing the deviation degree between the second output value and the second actual value, the second output value is an output value corresponding to a second input value, the second actual value is an actual value corresponding to the second input value, and the second input value is a historical input value; Determining a first state value based on the input reference value, the deviation degree and a second state value, wherein the second state value is a state value corresponding to the second input value; a first output value is determined based at least on the first state value. The present application provides a data processing apparatus, the apparatus comprising: the device comprises a first determining unit, a first input value determining unit and a second determining unit, wherein the first determining unit is used for determining an input reference value based on a first input value, and the input reference value is used for representing a magnitude value of a first output value corresponding to the first input value in the first input value; The device comprises a first determining unit, a second determining unit and a first judging unit, wherein the first determining unit is used for determining a deviation degree based on a first output value and a first actual value, the deviation degree is used for representing the deviation degree between the first output value and the first actual value, the first output value is an output value corresponding to a first input value, the second actual value is an actual value corresponding to the first input value, and the first input value is a historical input value; the third determining unit is used for determining a first state value based on the input reference value, the deviation degree and a second state value, wherein the second state value is a state value corresponding to the second input value; And a fourth determining unit configured to determine a first output value based at least on the first state value. The application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program whic