Transaction log data correlation analysis processing method and device, equipment and medium

Abstract

The invention discloses a transaction log data correlation analysis processing method and device, equipment and a medium. Performing sorting processing on the obtained current to-be-processed transaction log data set through the transaction log variety classification options to obtain at least one data correlation analysis processing subset; sequentially selecting a current data correlation analysis processing subset, and obtaining a current transaction code behavior extraction result through a transaction code behavior extraction rule; obtaining a target transaction code behavior correlation analysis order, and carrying out word group counting processing on each current transaction code behavior through a correlation counting rule to obtain a current counting result; and respectively calculating through a support degree calculation formula and a confidence coefficient calculation formula to obtain a correlation analysis processing result of the current subset data, and further obtaining and feeding back a correlation analysis processing result of the current data. The problem of correlation analysis of a large amount of transaction log data is solved, and the accuracy of transaction log data correlation analysis is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a transaction log data correlation analysis and processing method, device, equipment and medium. Background Art

[0002] As the amount of bank transaction log data increases, it is necessary to analyze the value contained in the transaction log data. Therefore, it is crucial to analyze the correlation between transaction log data.

[0003] In the process of realizing the present invention, the inventors found that the existing technology has the following defects: Currently, the amount of transaction log data is relatively large, but the correlation between the transaction log data of previous and subsequent customers cannot be analyzed, and it is impossible to predict related transactions of customers. Summary of the Invention

[0004] The present invention provides a transaction log data correlation analysis processing method, device, equipment and medium to improve the accuracy of transaction log data correlation analysis.

[0005] According to one aspect of the present invention, a transaction log data correlation analysis and processing method is provided, which includes:

[0006] Acquire a current transaction log data set to be processed, and sort the current transaction log data set to be processed using pre-set transaction log category classification options to obtain at least one data correlation analysis processing subset;

[0007] Selecting a current data correlation analysis processing subset in turn, and obtaining a current transaction code behavior extraction result by using a pre-set transaction code behavior extraction rule; wherein the current transaction code behavior extraction result includes multiple current transaction code behaviors;

[0008] Obtaining the target transaction code behavior correlation analysis order, and performing phrase counting processing on each current transaction code behavior using a preset correlation counting rule to obtain a current counting result;

[0009] According to the current counting result, the support calculation formula and the confidence calculation formula are used to calculate respectively to obtain the current subset data association analysis processing result, and return to execute the operation of selecting one current data association analysis processing subset in turn until all data association analysis processing subsets are traversed;

[0010] According to the results of the current subset data association analysis, the current data association analysis result is obtained and fed back.

[0011] According to another aspect of the present invention, a transaction log data correlation analysis and processing device is provided, comprising:

[0012] a data relevance analysis processing subset determination module, configured to obtain a current transaction log data set to be processed, and sort the current transaction log data set to be processed using pre-set transaction log type classification options to obtain at least one data relevance analysis processing subset;

[0013] The current transaction code behavior extraction result determination module is used to sequentially select a current data correlation analysis processing subset and obtain the current transaction code behavior extraction result based on the pre-set transaction code behavior extraction rules; wherein the current transaction code behavior extraction result includes multiple current transaction code behaviors;

[0014] A current counting result determination module is used to obtain the correlation analysis order of the target transaction code behavior and perform phrase counting processing on each current transaction code behavior according to a preset correlation counting rule to obtain the current counting result;

[0015] A module for obtaining the result of the data association analysis of the current subset is used to calculate the result of the data association analysis of the current subset based on the current counting result using the support calculation formula and the confidence calculation formula, and return to execute the operation of selecting one current data association analysis processing subset in turn until all data association analysis processing subsets are traversed;

[0016] The current data relevance analysis processing result determination and feedback module is used to obtain and feedback the current data relevance analysis processing result based on each of the current subset data relevance analysis processing results.

[0017] According to another aspect of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the transaction log data correlation analysis and processing method described in any embodiment of the present invention is implemented.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the transaction log data correlation analysis and processing method according to any embodiment of the present invention when executed.

[0019] The technical solution of an embodiment of the present invention obtains a current transaction log dataset to be processed and sorts it using pre-set transaction log category classification options to obtain at least one data correlation analysis processing subset. It then sequentially selects one of the current data correlation analysis processing subsets and obtains a current transaction code behavior extraction result using pre-set transaction code behavior extraction rules. It then obtains the target transaction code behavior correlation analysis order and performs phrase counting on each of the current transaction code behaviors using pre-set correlation counting rules to obtain a current counting result. Based on the current counting result, it calculates using support and confidence calculation formulas to obtain a current subset data correlation analysis processing result. The process then returns to executing the sequential selection of one of the current data correlation analysis processing subsets until all data correlation analysis processing subsets are traversed. Based on the data correlation analysis processing results of each current subset, it obtains and feeds back the current data correlation analysis processing result. This solves the problem of performing correlation analysis on large amounts of transaction log data and improves the accuracy of correlation analysis of transaction log data.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a flowchart of a transaction log data correlation analysis and processing method provided in accordance with the first embodiment of the present invention;

[0023] Figure 2 This is a detailed flow chart of a transaction log data correlation analysis and processing method provided in accordance with the second embodiment of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of a transaction log data correlation analysis and processing device provided in accordance with a third embodiment of the present invention;

[0025] Figure 4 It is a structural diagram of an electronic device provided according to the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "target", "current", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Example 1

[0029] Figure 1 A flowchart of a transaction log data correlation analysis and processing method is provided for embodiment 1 of the present invention. This embodiment is applicable to situations where correlation analysis is performed on a large amount of transaction log data. The method can be executed by a transaction log data correlation analysis and processing device, which can be implemented in the form of hardware and / or software.

[0030] Correspondingly, such as Figure 1 As shown, the method includes:

[0031] S110 , obtaining a current transaction log data set to be processed, and sorting the current transaction log data set to be processed according to pre-set transaction log category classification options to obtain at least one data correlation analysis processing subset.

[0032] Among them, the current transaction log data set to be processed can be screened from massive transaction logs, and log data during peak hours with richer business types, diverse types of bank tellers, and numerous transaction codes can be selected as the preliminary analysis data set.

[0033] Among them, the transaction log category classification options may include branch department, institution code, transaction time and business type;

[0034] Optionally, the method of obtaining a current transaction log data set to be processed and sorting the current transaction log data set to be processed according to preset transaction log type classification options to obtain at least one data correlation analysis processing subset includes: performing data preprocessing operations on the obtained current transaction log data set to be processed according to a preset transaction log data preprocessing method to obtain a current transaction log data preprocessing set to be processed; and sorting the current transaction log data set to be processed according to branch department, institution code, transaction time and business type to obtain corresponding data correlation analysis processing subsets.

[0035] The transaction log data preprocessing method may be a method for performing operations such as data screening, extraction, and anomaly removal on the transaction log data.

[0036] Specifically, the current pending transaction log data set can be first screened, including horizontal or vertical screening. Specifically, the transaction log data can be screened by branch type (first-tier branch, second-tier branch, or sub-branch), branch, teller, deposit and withdrawal category, wealth management category, or loan category. Transaction logs from different time periods, morning and afternoon, can be combined to form a pre-processed set of pending transaction log data. Abnormal and erroneous transactions can also be removed. Additionally, transaction data in the error transaction log table can be screened using this logic to conduct error transaction correlation analysis.

[0037] Furthermore, the current transaction log data set to be processed can be sorted by branch department, institution code, transaction time and business type to obtain corresponding data correlation analysis processing subsets.

[0038] For example, suppose the pre-processed set of transaction log data to be processed is sorted by branch department, institution code, transaction time, and business type to obtain subsets corresponding to branch department, institution code, transaction time, and business type. Assume that the branch department obtains corresponding data correlation analysis processing subset 1, the institution code obtains corresponding data correlation analysis processing subset 2, the transaction time obtains corresponding data correlation analysis processing subset 3, and the business type obtains corresponding data correlation analysis processing subset 4.

[0039] S120 , selecting one current data correlation analysis processing subset in turn, and obtaining a current transaction code behavior extraction result through a preset transaction code behavior extraction rule.

[0040] The current transaction code behavior extraction result includes multiple current transaction code behaviors.

[0041] The transaction code behavior extraction rule may be a rule for extracting transaction code behaviors preset in the current data association analysis processing subset.

[0042] Exemplarily, assuming that the transaction code behavior extraction rule may be to extract the transaction business content type in the current data relevance analysis processing subset, multiple current transaction code behaviors may be extracted.

[0043] For example, by extracting the transaction business content type from the data association analysis processing subset 1 through the transaction code behavior extraction rule, the current transaction code behavior extraction result 1 can be obtained.

[0044] Specifically, after obtaining the current transaction code behavior extraction result through the pre-set transaction code behavior extraction rule, the method further includes: sorting the current transaction code behavior extraction result through the pre-set transaction code sorting rule to obtain the current transaction code behavior sorting result; traversing each pair of transaction code behavior phrases in the current transaction code behavior sorting result in sequence, and determining whether they fall into a pre-constructed transaction code abnormal logical sequence vocabulary; if so, removing the current pair of transaction code behavior phrases to obtain the processed current transaction code behavior extraction result.

[0045] In this embodiment, the transaction codes can be sorted according to a preset transaction code sorting rule, assuming that the transaction codes can be sorted according to their business identifiers. Assume that the sorting result corresponding to the current transaction code behavior extraction result 1 is: [W1, W2, W3, W4, W5, W6, W7, W1, W2, W1, W3, W4], where Wi represents the current transaction code behavior and i is an arbitrary natural number. It can be assumed that W1 represents card activation and W2 represents deposit.

[0046] The transaction code abnormal logical sequence vocabulary can be composed of multiple pairs of transaction code abnormal logical sequences. For example, for a second-order transaction code phrase, [W1, W2] indicates that a user will deposit money after opening a card. [W2, W1] indicates that a user will open a card after making a deposit. This situation clearly exhibits abnormal logic, so [W1, W2] needs to be removed.

[0047] Furthermore, the current transaction code behavior extraction result after elimination is: [W1, W2, W3, W4, W5, W6, W7, W1, W3, W4].

[0048] S130: Obtain the target transaction code behavior correlation analysis order, and perform phrase counting processing on each current transaction code behavior according to a preset correlation counting rule to obtain a current counting result.

[0049] Specifically, the relevance counting rule includes a shopping basket relevance counting rule or a reverse sorting relevance counting rule.

[0050] Among them, the shopping basket association counting rule is to count the number of occurrences of adjacent transaction code behavior phrases of a preset order in each current transaction code behavior in positive order; wherein, the reverse sorting association counting rule is to count the number of occurrences of adjacent transaction code behavior phrases of a preset order in positive order and reverse order in each current transaction code behavior.

[0051] Optionally, the obtaining of the target transaction code behavior correlation analysis order, and performing phrase counting processing on each of the current transaction code behaviors through a preset correlation counting rule to obtain a current counting result, includes: obtaining the target transaction code behavior correlation analysis order; if the correlation counting rule is a shopping basket correlation counting rule, performing phrase counting processing on each of the current transaction code behaviors through the shopping basket correlation counting rule and the target transaction code behavior correlation analysis order to obtain a current counting result; if the correlation counting rule is a reverse sorting correlation counting rule, performing phrase counting processing on each of the current transaction code behaviors through the shopping basket correlation counting rule and the target transaction code behavior correlation analysis order to obtain a current counting result.

[0052] In this embodiment, phrase counting processing may be performed using a shopping basket relevance counting rule or a reverse sorting relevance counting rule.

[0053] Specifically, using the shopping basket association counting rule, [W1, W2, W3, W4, W5, W6, W7, W1, W3, W4] is counted. Assuming the target transaction code behavior association analysis order is second-order, it can be divided into multiple phrases: [W1, W2], [W2, W3], [W3, W4], [W4, W5], [W5, W6], [W6, W7], [W7, W1], [W1, W3], and [W3, W4]. These phrases are sent to the reducer for statistics, and the current counting results are obtained. The count result for [W3, W4] is 2, and the count results for the remaining phrases [W1, W2], [W2, W3], [W4, W5], [W5, W6], [W6, W7], [W7, W1], and [W1, W3] are 1.

[0054] Specifically, for the reverse sorting association counting rule, [W1, W2, W3, W4, W5, W6, W7, W1, W3, W4] are counted. Assuming that the target transaction code behavior association analysis order is second order, it can be divided into multiple phrases, namely: [W1, W2], [W2, W1], [W2, W3], [W3, W2], [W3, W4], [W4, W3], [W4, W5], [W5, W4], [W5, W6], [W6, W5], [W6, W7], [W7, W6], [W7, W1], [W1, W7], [W1, W3], [W3, W1], [W3, W4] and [W4, W3]. The phrases are sent to the reducer for statistics to obtain the current counting results. Among them, the counting results corresponding to [W3, W4] and [W4, W3] are both 2, and the counting results corresponding to the remaining phrases are all 1.

[0055] Furthermore, using the shopping basket association counting rule, [W1, W2, W3, W4, W5, W6, W7, W1, W3, W4] is counted. Assuming the target transaction code behavior association analysis level is four, it can be divided into multiple phrases: [W1, W2, W3, W4], [W2, W3, W4, W5], [W3, W4, W5, W6], [W4, W5, W6, W7], [W5, W6, W7, W1], [W6, W7, W1, W3], [W7, W1, W3, W4]. These phrases are then sent to the reducer for statistics, yielding the current count result. The count results for the four-order phrases are all 1.

[0056] The advantage of this setting is that by performing phrase counting processing through the shopping basket relevance counting rule or the reverse sorting relevance counting rule, the relevance between phrases of different orders can be analyzed more accurately, thereby achieving more precise counting and statistical processing.

[0057] Optionally, after obtaining the target transaction code behavior correlation analysis order and performing counting processing on each of the current transaction code behaviors according to a preset correlation counting rule to obtain a current counting result, the method further includes: obtaining a preset counting result threshold; judging whether the number of occurrences of each transaction code behavior phrase in the current counting result processing meets the requirement of the counting result threshold; if not, eliminating the corresponding transaction code behavior phrase to obtain the current counting result corresponding to the processed transaction code behavior phrase.

[0058] The counting result threshold may be a preset threshold value.

[0059] Continuing with the previous example, assuming the counting result threshold is 2, then for the shopping basket association counting rule, the counting result for [W3, W4] is 2, meeting the requirement, and the remaining transaction code behavior phrases are deleted. For the reverse sort association counting rule, the counting results for [W3, W4] and [W4, W3] are both 2, meeting the requirement, and the remaining transaction code behavior phrases are deleted. Thus, the current counting result for the corresponding transaction code behavior phrase is obtained.

[0060] S140. According to the current counting result, the support calculation formula and the confidence calculation formula are used to calculate respectively to obtain the current subset data association analysis processing result, and return to execute the operation of selecting one current data association analysis processing subset in turn until all data association analysis processing subsets are traversed.

[0061] The support calculation formula may be a formula for calculating the ratio of the number of occurrences of the target transaction code behavior phrase to the total number of phrases. The confidence calculation formula may be a formula for calculating the probability of the subsequent transaction code behavior occurring in the target transaction code behavior phrase when the preceding transaction code behavior occurs.

[0062] In this embodiment, after obtaining the current counting result, it is necessary to calculate the transaction code behavior phrases corresponding to the current counting result through the support calculation formula and the confidence calculation formula to further obtain the current subset data correlation analysis processing result.

[0063] After obtaining the current subset data correlation analysis and processing results of the data correlation analysis and processing subset 1 corresponding to the branch department, it is also necessary to perform corresponding processing on the institution code to obtain the corresponding data correlation analysis and processing subset 2, the transaction time to obtain the corresponding data correlation analysis and processing subset 3, and the business type to obtain the corresponding data correlation analysis and processing subset 4 to obtain the corresponding current subset data correlation analysis and processing results.

[0064] S150 , obtaining and feeding back a current data correlation analysis result based on the correlation analysis results of each current subset data.

[0065] Illustratively, the above four current subset data association analysis processing results are combined to obtain the current data association analysis processing result, and the obtained current data association analysis processing result is fed back to the user.

[0066] In addition, before providing feedback to the user, it is necessary to determine whether the current data correlation analysis results meet expectations. If they do, feedback is provided directly to the user. If not, adjustments and optimizations are required before providing feedback.

[0067] The technical solution of an embodiment of the present invention obtains a current transaction log dataset to be processed and sorts it using pre-set transaction log category classification options to obtain at least one data correlation analysis processing subset. It then sequentially selects one of the current data correlation analysis processing subsets and obtains a current transaction code behavior extraction result using pre-set transaction code behavior extraction rules. It then obtains the target transaction code behavior correlation analysis order and performs phrase counting on each of the current transaction code behaviors using pre-set correlation counting rules to obtain a current counting result. Based on the current counting result, it calculates using support and confidence calculation formulas to obtain a current subset data correlation analysis processing result. The process then returns to executing the sequential selection of one of the current data correlation analysis processing subsets until all data correlation analysis processing subsets are traversed. Based on the data correlation analysis processing results of each current subset, it obtains and feeds back the current data correlation analysis processing result. This solves the problem of performing correlation analysis on large amounts of transaction log data and improves the accuracy of correlation analysis of transaction log data.

[0068] Example 2

[0069] Figure 2 A detailed flow chart of a transaction log data correlation analysis and processing method is provided for the second embodiment of the present invention. This embodiment is based on the above embodiments and is refined. In this embodiment, the current counting result is calculated using the support calculation formula and the confidence calculation formula respectively, and the current subset data correlation analysis processing result is further refined.

[0070] Correspondingly, such as Figure 2 As shown, the method includes:

[0071] S210: Acquire a current transaction log data set to be processed, and sort the current transaction log data set to be processed using pre-set transaction log category classification options to obtain at least one data correlation analysis processing subset.

[0072] S220. Select one current data correlation analysis processing subset in turn, and obtain a current transaction code behavior extraction result through a preset transaction code behavior extraction rule; wherein the current transaction code behavior extraction result includes multiple current transaction code behaviors.

[0073] S230: Obtain the target transaction code behavior correlation analysis order, and perform phrase counting processing on each current transaction code behavior according to a preset correlation counting rule to obtain a current counting result.

[0074] S240: Obtain each transaction code behavior phrase corresponding to the current counting result, and the phrase support corresponding to each transaction code behavior phrase.

[0075] The phrase support may be the number of times the target transaction code behavior phrase appears.

[0076] For example, for the reverse sorting relevance counting rule, the current counting result includes two transaction code behavior phrases [W3, W4] and [W4, W3]. Assume that the phrase support of [W3, W4] is 4000 and the phrase support of [W4, W3] is 500.

[0077] S250: Obtain the total support, and calculate the support of each phrase separately using the support calculation formula to obtain the calculation probability of each support.

[0078] The total support can be the number of times a phrase describing all transaction code behaviors appears.

[0079] Continuing with the previous example, assuming the total support is 50,000, the support calculation formula can be used to calculate that the support calculation probability of [W3, W4] is 8%; the support calculation probability of [W4, W3] is 1%.

[0080] S260: Obtain a preset minimum support probability threshold, and compare it with each support calculation probability to obtain a support-removed transaction code behavior phrase.

[0081] The minimum support probability threshold may be the size of the minimum required support probability threshold.

[0082] Continuing with the previous example, assuming that the minimum support probability threshold is 7%, since the support calculation probability of [W4, W3] is 1%, which does not meet the minimum support probability threshold, [W4, W3] is eliminated; since the support calculation probability of [W3, W4] is 8%, which meets the minimum support probability threshold, the transaction code behavior phrase is retained, thus obtaining the support-eliminated transaction code behavior phrase.

[0083] S270: Calculate the confidence of each support-removed transaction code behavior phrase using the confidence calculation formula to obtain the current subset data correlation analysis processing result.

[0084] Among them, for the transaction code behavior phrase [W3, W4], the confidence calculation formula can be used to calculate the probability of the subsequent transaction code behavior W4 occurring when the preceding transaction code behavior W3 occurs.

[0085] Optionally, the confidence calculation formula is used to calculate the confidence of each transaction code behavior phrase with support excluded, and obtain the current subset data association analysis processing result, including: using the confidence calculation formula to calculate the confidence of each transaction code behavior phrase with support excluded, and obtain the confidence probability value of each transaction code behavior phrase; obtaining a preset minimum confidence probability threshold, and comparing it with the confidence probability value of each transaction code behavior phrase respectively, to obtain the current subset data association analysis processing result.

[0086] The transaction code behavior phrase confidence probability value may be a probability value describing the confidence level of the transaction code behavior phrase, and the minimum confidence probability threshold may be a threshold value of a minimum required confidence probability.

[0087] For example, the minimum confidence probability threshold can be set to 70%, and the confidence probability value of the transaction code behavior phrase [W3, W4] can be calculated to be 80% through the confidence calculation formula, which means that [W3, W4] meets the requirements of the minimum confidence probability threshold. In this case, the transaction code behavior phrase is retained, and the current subset data correlation analysis processing results can be further obtained.

[0088] S280 , determining whether all data relevance analysis processing subsets have been traversed; if not, returning to S220 ; if so, executing S290 .

[0089] S290 , obtaining and feeding back a current data correlation analysis result based on the correlation analysis results of each current subset data.

[0090] The technical solution of the embodiments of the present invention uses support and confidence calculation formulas based on the current counting results to obtain the current subset data association analysis results, and further obtains the current data association analysis results. By reprocessing the current counting results, namely, calculating support and confidence, transaction code behavior phrases can be removed and retained, thereby better analyzing the association of transaction log data and improving the accuracy of transaction log data association analysis.

[0091] Example 3

[0092] Figure 3This is a structural diagram of a transaction log data correlation analysis and processing device provided in the third embodiment of the present invention. The transaction log data correlation analysis and processing device provided in this embodiment can be implemented by software and / or hardware, and can be configured in a terminal device or server to implement a transaction log data correlation analysis and processing method in the embodiment of the present invention. Figure 3 As shown, the device includes: a data correlation analysis processing subset determination module 310, a current transaction code behavior extraction result determination module 320, a current counting result determination module 330, a current subset data correlation analysis processing result acquisition module 340 and a current data correlation analysis processing result determination and feedback module 350.

[0093] The data relevance analysis processing subset determination module 310 is configured to obtain a current transaction log data set to be processed, and sort the current transaction log data set to be processed using pre-set transaction log type classification options to obtain at least one data relevance analysis processing subset;

[0094] The current transaction code behavior extraction result determination module 320 is used to sequentially select a current data association analysis processing subset and obtain a current transaction code behavior extraction result based on a preset transaction code behavior extraction rule. The current transaction code behavior extraction result includes multiple current transaction code behaviors.

[0095] The current counting result determination module 330 is used to obtain the correlation analysis order of the target transaction code behavior and perform phrase counting processing on each current transaction code behavior according to the preset correlation counting rules to obtain the current counting result;

[0096] The module 340 for obtaining the result of the data association analysis processing of the current subset is used to calculate the result of the data association analysis processing of the current subset using the support calculation formula and the confidence calculation formula according to the current counting result, and returns to execute the operation of selecting one current data association analysis processing subset in turn until all data association analysis processing subsets are traversed;

[0097] The current data relevance analysis processing result determination and feedback module 350 is used to obtain and feedback the current data relevance analysis processing result based on the current subset data relevance analysis processing results.

[0098] The technical solution of an embodiment of the present invention obtains a current transaction log dataset to be processed and sorts it using pre-set transaction log category classification options to obtain at least one data correlation analysis processing subset. It then sequentially selects one of the current data correlation analysis processing subsets and obtains a current transaction code behavior extraction result using pre-set transaction code behavior extraction rules. It then obtains the target transaction code behavior correlation analysis order and performs phrase counting on each of the current transaction code behaviors using pre-set correlation counting rules to obtain a current counting result. Based on the current counting result, it calculates using support and confidence calculation formulas to obtain a current subset data correlation analysis processing result. The process then returns to executing the sequential selection of one of the current data correlation analysis processing subsets until all data correlation analysis processing subsets are traversed. Based on the data correlation analysis processing results of each current subset, it obtains and feeds back the current data correlation analysis processing result. This solves the problem of performing correlation analysis on large amounts of transaction log data and improves the accuracy of correlation analysis of transaction log data.

[0099] Based on the above embodiments, the transaction log category classification options include branch department, institution code, transaction time and business category.

[0100] Based on the above embodiments, the data correlation analysis processing subset determination module 310 can be specifically used to: perform data preprocessing operations on the acquired current transaction log data set to be processed through a preset transaction log data preprocessing method to obtain a current transaction log data preprocessing set to be processed; sort the current transaction log data set to be processed by branch department, institution code, transaction time and business type to obtain corresponding data correlation analysis processing subsets.

[0101] On the basis of the above embodiments, it further includes a current transaction code behavior extraction result processing module, which can be specifically used to: after obtaining the current transaction code behavior extraction result through the pre-set transaction code behavior extraction rule, sort the current transaction code behavior extraction result through the pre-set transaction code sorting rule to obtain the current transaction code behavior sorting result; traverse each pair of transaction code behavior phrases in the current transaction code behavior sorting result in turn, and determine whether they fall into the pre-built transaction code abnormal logical sequence vocabulary. If so, eliminate the current pair of transaction code behavior phrases to obtain the processed current transaction code behavior extraction result.

[0102] Based on the above embodiments, the relevance counting rule includes a shopping basket relevance counting rule or a reverse sorting relevance counting rule.

[0103] On the basis of the above embodiments, the current counting result determination module 330 can be specifically used to: obtain the target transaction code behavior correlation analysis order; if the correlation counting rule is the shopping basket correlation counting rule, perform phrase counting processing on each of the current transaction code behaviors through the shopping basket correlation counting rule and the target transaction code behavior correlation analysis order to obtain the current counting result; if the correlation counting rule is the reverse sorting correlation counting rule, perform phrase counting processing on each of the current transaction code behaviors through the shopping basket correlation counting rule and the target transaction code behavior correlation analysis order to obtain the current counting result; wherein, the shopping basket correlation counting rule is to count the number of occurrences of adjacent transaction code behavior phrases of a preset order in each current transaction code behavior in positive order; wherein, the reverse sorting correlation counting rule is to count the number of occurrences of adjacent transaction code behavior phrases of a preset order in positive order and reverse order in each current transaction code behavior.

[0104] On the basis of the above embodiments, it also includes a transaction code behavior phrase elimination module, which can be specifically used to: obtain the target transaction code behavior correlation analysis order, and count each current transaction code behavior according to a preset correlation counting rule to obtain the current counting result, and then obtain a preset counting result threshold; determine whether the number of occurrences of each transaction code behavior phrase in the current counting result processing meets the requirement of the counting result threshold; if not, eliminate the corresponding transaction code behavior phrase to obtain the current counting result corresponding to the processed transaction code behavior phrase.

[0105] On the basis of the above embodiments, the module 340 for obtaining the result of the association analysis of the current subset data can be specifically used to: obtain the transaction code behavior phrases corresponding to the current counting result, and the phrase support corresponding to each transaction code behavior phrase; obtain the total support, and calculate the support of each phrase separately through the support calculation formula to obtain the support calculation probability; obtain the preset minimum support probability threshold, and compare it with each support calculation probability to obtain the support of the transaction code behavior phrase; calculate the confidence of each support-excluding transaction code behavior phrase through the confidence calculation formula to obtain the result of the association analysis of the current subset data.

[0106] On the basis of the above embodiments, the module 340 for obtaining the result of the current subset data association analysis can also be specifically used to: calculate the confidence of each transaction code behavior phrase after support elimination through the confidence calculation formula to obtain the confidence probability value of each transaction code behavior phrase; obtain a preset minimum confidence probability threshold, and compare it with the confidence probability value of each transaction code behavior phrase respectively to obtain the result of the current subset data association analysis.

[0107] The transaction log data correlation analysis and processing device provided in the embodiment of the present invention can execute the transaction log data correlation analysis and processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0108] Example 4

[0109] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement the fourth embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0110] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0111] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0112] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processors (DSPs), and any other suitable processor, controller, or microcontroller. Processor 11 executes the various methods and processes described above, such as the transaction log data correlation analysis and processing method.

[0113] In some embodiments, the transaction log data correlation analysis and processing method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the transaction log data correlation analysis and processing method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the transaction log data correlation analysis and processing method by any other appropriate means (for example, by means of firmware).

[0114] The method includes: obtaining a current transaction log data set to be processed, and sorting the current transaction log data set to be processed according to preset transaction log variety classification options to obtain at least one data correlation analysis processing subset; selecting one current data correlation analysis processing subset in turn, and obtaining a current transaction code behavior extraction result according to a preset transaction code behavior extraction rule; wherein the current transaction code behavior extraction result includes multiple current transaction code behaviors; obtaining a target transaction code behavior correlation analysis order, and performing phrase counting processing on each of the current transaction code behaviors according to a preset correlation counting rule to obtain a current counting result; performing calculations according to the current counting result according to a support calculation formula and a confidence calculation formula to obtain a current subset data correlation analysis processing result, and returning to execute the operation of selecting one current data correlation analysis processing subset in turn until all data correlation analysis processing subsets are traversed; obtaining and feeding back a current data correlation analysis processing result according to each current subset data correlation analysis processing result.

[0115] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0117] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0119] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0120] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0121] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0122] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

[0123] Example 5

[0124] A fifth embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable instructions, when executed by a computer processor, are configured to perform a transaction log data relevance analysis and processing method, the method comprising: obtaining a current transaction log data set to be processed, and sorting the current transaction log data set according to preset transaction log type classification options to obtain at least one data relevance analysis and processing subset; sequentially selecting one current data relevance analysis and processing subset, and obtaining a current transaction code behavior extraction result according to preset transaction code behavior extraction rules; wherein the current transaction code behavior extraction result includes multiple current transaction code behaviors; obtaining a target transaction code behavior relevance analysis order, and performing phrase counting processing on each current transaction code behavior according to a preset relevance counting rule to obtain a current counting result; performing calculations based on the current counting result using a support calculation formula and a confidence calculation formula to obtain a current subset data relevance analysis and processing result, and returning to executing the operation of sequentially selecting one current data relevance analysis and processing subset until all data relevance analysis and processing subsets are traversed; and obtaining and feeding back a current data relevance analysis and processing result based on each current subset data relevance analysis and processing result.

[0125] Of course, the computer-readable storage medium provided in the embodiment of the present invention has computer-executable instructions that are not limited to the method operations described above, and can also execute related operations in the transaction log data correlation analysis processing provided in any embodiment of the present invention.

[0126] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0127] It is worth noting that in the above-mentioned embodiment of transaction log data correlation analysis and processing, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0128] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A transaction log data correlation analysis and processing method, characterized in that: include: Acquire a current transaction log data set to be processed, and sort the current transaction log data set to be processed using pre-set transaction log category classification options to obtain at least one data correlation analysis processing subset; Selecting a current data correlation analysis processing subset in turn, and obtaining a current transaction code behavior extraction result by using a pre-set transaction code behavior extraction rule; wherein the current transaction code behavior extraction result includes multiple current transaction code behaviors; Obtaining the target transaction code behavior correlation analysis order, and performing phrase counting processing on each current transaction code behavior using a preset correlation counting rule to obtain a current counting result; According to the current counting result, the support calculation formula and the confidence calculation formula are used to calculate respectively to obtain the current subset data association analysis processing result, and return to execute the operation of selecting one current data association analysis processing subset in turn until all data association analysis processing subsets are traversed; According to the results of the current subset data association analysis, the current data association analysis result is obtained and fed back.

2. The method according to claim 1, characterized in that The transaction log classification options include branch department, institution code, transaction time and business type; The step of obtaining a current transaction log data set to be processed and sorting the current transaction log data set to be processed using pre-set transaction log category classification options to obtain at least one data correlation analysis processing subset includes: Performing data preprocessing operations on the acquired current transaction log data set to be processed using a preset transaction log data preprocessing method to obtain a current transaction log data preprocessing set to be processed; The current transaction log data set to be processed is sorted by branch department, institution code, transaction time and business type to obtain corresponding data correlation analysis processing subsets.

3. The method according to claim 2, characterized in that After obtaining the current transaction code behavior extraction result by using the preset transaction code behavior extraction rule, the method further includes: Sorting the current transaction code behavior extraction results according to a preset transaction code sorting rule to obtain a current transaction code behavior sorting result; Each pair of transaction code behavior phrases in the current transaction code behavior sorting result is traversed in turn, and it is determined whether they fall into the pre-built transaction code abnormal logical sequence vocabulary. If they do, the current pair of transaction code behavior phrases is removed to obtain the current transaction code behavior extraction result after processing.

4. The method according to claim 3, characterized in that The relevance counting rule includes a shopping basket relevance counting rule or a reverse sorting relevance counting rule; The target transaction code behavior correlation analysis order is obtained, and phrase counting processing is performed on each current transaction code behavior according to a preset correlation counting rule to obtain a current counting result, including: Obtain the target transaction code behavior correlation analysis order; If the relevance counting rule is a shopping basket relevance counting rule, performing phrase counting processing on each current transaction code behavior by using the shopping basket relevance counting rule and the target transaction code behavior relevance analysis order to obtain a current counting result; If the relevance counting rule is a reverse sorting relevance counting rule, phrase counting processing is performed on each current transaction code behavior using the shopping basket relevance counting rule and the target transaction code behavior relevance analysis order to obtain a current counting result; The shopping basket association counting rule is to count the number of occurrences of adjacent transaction code behavior phrases of a preset order in each current transaction code behavior in positive order; The reverse sorting relevance counting rule is to count the number of occurrences of adjacent transaction code behavior phrases of a preset order in each current transaction code behavior in positive order and reverse order respectively.

5. The method according to claim 4, characterized in that After obtaining the target transaction code behavior correlation analysis order and performing counting processing on each current transaction code behavior according to a preset correlation counting rule to obtain a current counting result, the method further includes: Get the preset counting result threshold; Determine whether the number of occurrences of each transaction code behavior phrase in the current counting result processing meets the requirement of the counting result threshold. If not, eliminate the corresponding transaction code behavior phrase to obtain the current counting result corresponding to the processed transaction code behavior phrase.

6. The method according to claim 5, characterized in that The current counting result is calculated by using the support calculation formula and the confidence calculation formula to obtain the current subset data association analysis processing result, including: Obtain each transaction code behavior phrase corresponding to the current counting result, and the phrase support corresponding to each transaction code behavior phrase; Obtain the total support, and calculate the support of each phrase separately using the support calculation formula to obtain the calculation probability of each support; Obtain the preset minimum support probability threshold and compare it with each support calculation probability to obtain the support-removed transaction code behavior phrase; By using the confidence calculation formula, the confidence of each support-removed transaction code behavior phrase is calculated to obtain the current subset data association analysis processing result.

7. The method according to claim 6, characterized in that The confidence calculation formula is used to calculate the confidence of each support-removed transaction code behavior phrase to obtain the current subset data correlation analysis processing result, including: By using the confidence calculation formula, the confidence of each transaction code behavior phrase with support removed is calculated to obtain the confidence probability value of each transaction code behavior phrase; Obtain the preset minimum confidence probability threshold and compare it with the confidence probability value of each transaction code behavior phrase to obtain the current subset data correlation analysis processing result.

8. A transaction log data correlation analysis and processing device, characterized in that: include: a data relevance analysis processing subset determination module, configured to obtain a current transaction log data set to be processed, and sort the current transaction log data set to be processed using pre-set transaction log type classification options to obtain at least one data relevance analysis processing subset; The current transaction code behavior extraction result determination module is used to sequentially select a current data correlation analysis processing subset and obtain the current transaction code behavior extraction result based on the pre-set transaction code behavior extraction rules; wherein the current transaction code behavior extraction result includes multiple current transaction code behaviors; A current counting result determination module is used to obtain the correlation analysis order of the target transaction code behavior and perform phrase counting processing on each current transaction code behavior according to a preset correlation counting rule to obtain the current counting result; A module for obtaining the result of the data association analysis of the current subset is used to calculate the result of the data association analysis of the current subset based on the current counting result using the support calculation formula and the confidence calculation formula, and return to execute the operation of selecting one current data association analysis processing subset in turn until all data association analysis processing subsets are traversed; The current data relevance analysis processing result determination and feedback module is used to obtain and feedback the current data relevance analysis processing result based on each of the current subset data relevance analysis processing results.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for analyzing and processing transaction log data correlation according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a transaction log data correlation analysis and processing method according to any one of claims 1 to 7 when executed.

Images