Search

CN-122023006-A - Transaction data processing method, apparatus, device, medium and program product

CN122023006ACN 122023006 ACN122023006 ACN 122023006ACN-122023006-A

Abstract

The application provides a transaction data processing method, a device, equipment, a storage medium and a program product, which can be applied to the technical field of finance and technology and the technical field of big data. The transaction data processing method comprises the steps of obtaining current transaction behavior data corresponding to transaction behaviors of a target user in a current time interval, carrying out first calculation processing on the current transaction behavior data based on at least one predetermined target index to obtain a first calculation result, carrying out second calculation processing on the historical transaction behavior data of the target user in a first predetermined historical time interval to obtain a second calculation result, wherein the second calculation result represents the probability of occurrence of the predetermined behaviors of the target user in a predetermined future time interval, and carrying out fusion processing on the first calculation result and the second calculation result to obtain a transaction data processing result corresponding to the target user.

Inventors

  • ZHOU YU

Assignees

  • 中国工商银行股份有限公司

Dates

Publication Date
20260512
Application Date
20260302

Claims (11)

  1. 1. A transaction data processing method, the method comprising: Acquiring current transaction behavior data corresponding to the transaction behavior of a target user in a current time interval; Performing first calculation processing on the current transaction behavior data based on at least one predetermined target index to obtain a first calculation result, wherein the first calculation result represents the probability of occurrence of the predetermined behavior of the target user in the current time interval, and the target index is determined from a plurality of initial indexes according to the respective importance of the initial indexes; Performing second calculation processing based on the historical transaction behavior data of the target user in a first preset historical time interval to obtain a second calculation result, wherein the second calculation result characterizes the probability of occurrence of preset behaviors of the target user in a preset future time interval; And carrying out fusion processing on the first calculation result and the second calculation result to obtain a transaction data processing result corresponding to the target user.
  2. 2. The method according to claim 1, wherein the method further comprises: The training sample set comprises a plurality of groups of training transaction behavior data generated by a plurality of users in a second preset historical time interval, wherein each group of training transaction behavior data comprises a plurality of historical index values of the initial indexes, each group of training transaction behavior data is provided with a preset label, and the preset label is used for representing the probability of preset behaviors of the corresponding users in the second preset time interval; Inputting the training sample set into a first calculation model, calling the first calculation model to determine the mapping relation between the plurality of historical index values and the labels, determining the importance of each initial index according to the mapping relation, and outputting a target index, wherein the importance of the target index meets the preset numerical condition.
  3. 3. The method of claim 1, wherein performing a second calculation based on historical transaction behavior data of the target user during a first predetermined historical time interval, the second calculation comprising: constructing a historical transaction behavior time sequence based on the historical transaction behavior data; Invoking a preset time sequence prediction model, and respectively extracting a plurality of groups of target historical transaction behavior data corresponding to a sliding time window from the historical transaction behavior time sequence by utilizing the sliding time window; Determining a plurality of change trend data corresponding to the sliding time window based on the plurality of groups of target historical transaction behavior data, wherein the change trend data is used for representing a behavior risk change trend corresponding to the transaction behavior of the target user in the sliding time window; and performing second calculation processing according to the plurality of change trend data to obtain a second calculation result.
  4. 4. The method of claim 3, wherein performing a second calculation process according to the plurality of trend data to obtain the second calculation result includes: Determining the association relation between each change trend data and a preset transaction risk level according to the time interval between the sliding time window corresponding to each change trend data and the current time interval and the behavior change trend represented by the change trend data; according to the association relation, determining the attention weight of each change trend data; weighting and summing the plurality of change trend data according to the attention weight of each change trend data; And determining the second calculation result according to the weighted summation result.
  5. 5. A method according to claim 3, characterized in that the method comprises: and determining the window size of the sliding time window according to the transaction scene corresponding to the transaction behavior and the acquisition frequency of the historical transaction behavior data.
  6. 6. The method according to claim 1, wherein the method further comprises: Determining a risk threshold corresponding to the current time interval according to the transaction environment information corresponding to the current time interval and the user type of the target user; and matching the transaction data processing result with a risk threshold value, and determining a limit determining strategy aiming at the target user according to the matching result.
  7. 7. The method of claim 1, wherein the performing a first calculation on the current transaction behavior data based on the predetermined at least one target indicator to obtain a first calculation result includes: Determining at least one indicator value of the current transaction behavior data for the at least one target indicator; and carrying out weighted summation on the at least one index value according to the respective weights of the at least one target index determined in advance to obtain the first calculation result.
  8. 8. A transaction data processing device, the device comprising: the first acquisition module is used for acquiring current transaction behavior data corresponding to the transaction behavior of the target user in the current time interval; the first processing module is used for carrying out first calculation processing on the current transaction behavior data based on at least one predetermined target index to obtain a first calculation result, wherein the first calculation result represents the probability of the occurrence of the predetermined behavior of the target user in the current time interval, and the target index is determined from a plurality of initial indexes according to the respective importance of the initial indexes; the second processing module is used for carrying out second calculation processing based on the historical transaction behavior data of the target user in a first preset historical time interval to obtain a second calculation result, wherein the second calculation result characterizes the probability of the target user in a preset future time interval that the preset behavior occurs; and the third processing module is used for carrying out fusion processing on the first calculation result and the second calculation result to obtain a transaction data processing result corresponding to the target user.
  9. 9. An electronic device, comprising: one or more processors; A memory for storing one or more computer programs, 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 1-7.
  10. 10. A computer-readable storage medium, on which a computer program or instructions is stored, which, when executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
  11. 11. A computer program product comprising a computer program or instructions which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.

Description

Transaction data processing method, apparatus, device, medium and program product Technical Field The application relates to the technical field of financial science and technology and the technical field of big data, in particular to a transaction data processing method, a device, equipment, a medium and a program product. Background In the field of financial risk management, in order to realize accurate credit allocation and dynamic credit decision, a user needs to be continuously subjected to risk level assessment. However, the static credit model mainly builds a fixed system according to historical data, is difficult to dynamically reflect the current risk state of a user and lacks sensitivity to real-time behavior data, and is difficult to adapt to complex and changeable risk management scenes due to the fact that the trigger mechanism lacks flexibility based on a fixed threshold value, and accuracy and timeliness of risk judgment and quota adjustment are limited. Disclosure of Invention In view of the foregoing, the present application provides a transaction data processing method, apparatus, device, medium, and program product. According to a first aspect of the application, a transaction data processing method is provided, which comprises the steps of obtaining current transaction behavior data corresponding to transaction behaviors of a target user in a current time interval, carrying out first calculation processing on the current transaction behavior data based on at least one predetermined target index to obtain a first calculation result, wherein the first calculation result represents probability of occurrence of preset behaviors of the target user in the current time interval, the target index is determined from a plurality of initial indexes according to respective importance of the initial indexes, carrying out second calculation processing on the basis of historical transaction behavior data of the target user in a first preset historical time interval to obtain a second calculation result, wherein the second calculation result represents probability of occurrence of preset behaviors of the target user in a preset future time interval, and carrying out fusion processing on the first calculation result and the second calculation result to obtain transaction data processing results corresponding to the target user. The transaction data processing method further comprises the steps of obtaining a training sample set, wherein the training sample set comprises a plurality of groups of training transaction behavior data generated by a plurality of users in a second preset historical time interval, each group of training transaction behavior data comprises a plurality of historical index values of a plurality of initial indexes, each group of training transaction behavior data is provided with a preset label, the preset labels are used for representing the probability of the corresponding users to conduct preset behaviors in the second preset time interval, inputting the training sample set into a first calculation model, calling the first calculation model to determine the mapping relation between the plurality of historical index values and the labels, determining the importance of each initial index according to the mapping relation, and outputting target indexes, wherein the importance of the target indexes meets the preset numerical conditions. According to the embodiment of the application, based on historical transaction behavior data of a target user in a first preset historical time interval, second calculation processing is carried out to obtain a second calculation result, wherein the second calculation result comprises the steps of building a historical transaction behavior time sequence based on the historical transaction behavior data, calling a preset time sequence prediction model, respectively extracting multiple groups of target historical transaction behavior data corresponding to a sliding time window from the historical transaction behavior time sequence by utilizing the sliding time window, and determining multiple groups of change trend data corresponding to the sliding time window based on the multiple groups of target historical transaction behavior data, wherein the change trend data is used for representing a behavior change trend corresponding to the transaction behavior of the target user in the sliding time window, and the second calculation processing is carried out according to the multiple change trend data to obtain the second calculation result. According to the embodiment of the application, the second calculation processing is performed according to the plurality of change trend data, and the second calculation result is obtained by determining the association relation between each change trend data and the preset transaction risk level according to the time interval between the sliding time window corresponding to each change trend data and the current time i