CN118967322A - A reconciliation method, system and storage medium for a payment and clearing system - Google Patents
A reconciliation method, system and storage medium for a payment and clearing system Download PDFInfo
- Publication number
- CN118967322A CN118967322A CN202411432978.5A CN202411432978A CN118967322A CN 118967322 A CN118967322 A CN 118967322A CN 202411432978 A CN202411432978 A CN 202411432978A CN 118967322 A CN118967322 A CN 118967322A
- Authority
- CN
- China
- Prior art keywords
- transaction
- payment
- feature vector
- reconciliation
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Finance (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a checking method, a system and a storage medium of a payment clearing system, which relate to the technical field of big data processing, when the system operates, collected transaction data are packed into a feature vector V, an amount anomaly detection score D1 and a time anomaly detection score D2 are calculated, risk assessment is carried out, a level label index L is generated, and performing fitting calculation with the stored waiting time information and channel identification information to obtain a processing priority index P, so as to determine the processing sequence of the transaction records, preferentially process transactions with high risk or longer waiting time, and further executing an optimization and repair strategy by the evaluation and optimization module according to the abnormal condition, and performing rule correction by optimizing the evaluation index Y. The whole system solves the defect that the traditional reconciliation system cannot efficiently mark and process abnormal payment through intelligent and automatic abnormal payment recognition and processing, and reduces risk and reconciliation workload in payment clearing.
Description
Technical Field
The invention relates to the technical field of big data processing, in particular to a reconciliation method, a reconciliation system and a storage medium of a payment clearing system.
Background
With the rapid growth of global digital transactions, the financial technology not only covers emerging technologies such as digital payment, electronic wallets, blockchains, and the like, but also includes background clearing and checking systems. Payment clearing is an important link in financial transactions, ensuring the accuracy of funds transfer and accounting between different institutions. The payment clearing system is responsible for transferring, settling, and reconciling funds across different payment channels, such as banks and third party payment platforms.
In the process of checking accounts of a specific payment clearing system, frequently occurring abnormal payment records are a great difficulty in checking accounts. These abnormal payment records include: inconsistent amount, abnormal payment time, repeated payment, mismatch of cross-channel transaction data, and the like. Current systems rely primarily on rules and manual intervention to identify these anomalies, and the ledgers need to manually troubleshoot the problem through complex form comparisons or by relying on histories. This is not only time consuming, but also prone to missed or erroneous decisions.
Meanwhile, a key disadvantage of the traditional checking method is that the abnormal payment records cannot be efficiently identified and processed, and especially when the payment transaction amount is large and the transaction flow is complex, the automatic identification capability of the system is weak, so that abnormal payment cannot be marked effectively and timely. In this case, the abnormal payment records are easy to accumulate, the workload of subsequent reconciliation is increased, and the whole payment clearing flow is further dragged.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a reconciliation method, a system and a storage medium of a payment clearing system, which solve the problems mentioned in the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme: the account checking system of the payment clearing system comprises a data acquisition module, an abnormality detection module, an intelligent tag management module, a tag priority processing module, a summary account checking module and an evaluation and optimization module;
The data acquisition module is connected with a plurality of sources of the payment system, the invoice system and the banking system to acquire related transaction data, packages the acquired transaction data into a feature vector V and stores the feature vector V;
the abnormality detection module extracts relevant abnormality detection parameters from the stored feature vector V, performs an abnormality detection process, and obtains an amount abnormality detection score D1 and a time abnormality detection score D2;
The intelligent tag management module is used for carrying out fitting on the historical transaction frequency TF of V4 and the channel identifier TC of V5 stored in the feature vector V according to the monetary anomaly detection score D1 and the time anomaly detection score D2, so as to reflect the risk level of the transaction and obtain a level tag index L;
The tag priority processing module carries out fitting calculation according to the level tag index L and the waiting time information and channel identification information stored in the feature vector V as the basis to obtain a processing priority index P, and the processing priority index P is used for determining the processing sequence of the transaction records;
The summary accounting module calculates according to transaction amount information stored in the processing priority index P and the feature vector V as a basis, acquires accounting difference information, gathers and acquires a summary accounting difference value S, and matches with a preset summary accounting difference threshold CZ to generate an abnormal marking flow evaluation result;
And the evaluation and optimization module judges and executes an optimization strategy and a repair strategy according to the evaluation result of the abnormal marking process, processes and acquires an optimization evaluation index Y according to the execution feedback information of the optimization strategy and the repair strategy, and corrects rules and adjusts transactions.
Preferably, the data acquisition module comprises a data acquisition unit and a feature vector construction unit;
The data acquisition unit is connected with a plurality of source channels of the payment system, the invoice system and the banking system by using an API call and a database connection mode to acquire related transaction data, wherein the related transaction data comprises actual transaction amount TA, expected amount EA, payment time TT, historical transaction frequency TF, channel identification TC, exchange rate fluctuation FR and transaction time period identification TID;
The feature vector construction unit sequentially packages the obtained actual transaction amount TA, expected amount EA, payment time TT, historical transaction frequency TF, channel identification TC, exchange rate fluctuation FR and transaction time period identification TID into the actual transaction amount TA of feature vector parameters V1, the expected amount EA of V2, the payment time TT of V3, the historical transaction frequency TF of V4, the channel identification TC of V5, the exchange rate fluctuation FR of V6, the transaction time period identification TID of V7 and the waiting time WT of V8, and marks the package time SJ of V9, forms feature vectors v= { V1, V2, V3, V4, V5, V6, V7, V8, V9}, and stores the feature vectors in a system database.
Preferably, the abnormality detection module comprises a parameter extraction unit and an abnormality detection unit;
the parameter extraction unit extracts related abnormality detection parameters from the stored feature vector V, wherein the parameters comprise the actual transaction amount TA of V1, the expected amount EA of V2, the payment time TT of V3 and the historical transaction frequency TF of V4;
the abnormality detection unit performs an abnormality detection flow on the extracted abnormality detection parameters to obtain an amount abnormality detection score D1 and a time abnormality detection score D2;
the monetary anomaly detection score D1 is obtained by the following calculation formula:
；
where V1 represents the actual transaction amount TA, V2 represents the desired amount EA, The standard deviation of the actual transaction amount TA, representing V1, reflects in particular the volatility of the transaction amount,An average value representing the actual transaction amount TA of V1;
The time anomaly detection score D2 is obtained by the following calculation formula:
；
Where V3 represents the payment time TT, V4 represents the historical transaction frequency TF, Represents the average value of the payment time TT of V3,The standard deviation of the payment time TT of V3 is represented, and log represents a logarithmic function.
Preferably, the intelligent tag management module performs fitting with the historical transaction frequency TF of V4 and the channel identifier TC of V5 in the stored feature vector V according to the monetary anomaly detection score D1 and the time anomaly detection score D2 to obtain a level tag index L;
The level tag index L is obtained by the following calculation formula:
；
wherein r1 and r2 respectively represent preset risk weight values of the monetary anomaly detection score D1 and the time anomaly detection score D2, an V4 represents the historical transaction frequency TF, V5 represents the channel identification TC,Representing the mapping of the historical trading frequency TF of V4 into the range 0,1,Channel identification TC representing the nonlinear adjustment V5,Representing mathematical constants, in particular the circumference ratio.
Preferably, the tag priority processing module comprises a priority calculating unit and a sequencing unit;
The priority calculating unit is based on the level tag index L, the stored waiting time information and channel identification information, wherein the waiting time information comprises the waiting time length WT of V8 in the feature vector V, the channel identification information comprises the channel identification TC of V5 in the feature vector V, and fitting calculation is carried out on the waiting time length WT of the level tag index L, V and the channel identification TC of V5 to obtain a processing priority index P;
The processing priority index P is obtained by the following calculation formula:
；
Where V8 represents the duration to be processed WT, V5 represents the channel identifier TC, and tan represents the arctangent function.
Preferably, the sorting unit obtains 1 to n processing priority indexes P according to fitting calculation, forms a priority processing list Pn, and readjusts positions of the 1 to n processing priority indexes P in the priority processing list Pn by performing bubbling sorting on the priority processing list Pn, wherein the sorted priority processing list Pn is used for determining a processing sequence of the transaction record.
Preferably, the summary reconciliation module comprises a difference calculation unit and a summary evaluation unit;
The difference calculation unit calculates according to the processing priority index P and transaction amount information stored in the feature vector V, wherein the transaction amount information comprises actual transaction amounts TA of V1 in the feature vector V, expected amounts EA of V2 and historical transaction frequencies TF of V4, and the transaction amount information is acquired and summarized to acquire a summarized reconciliation difference value S;
the summarized reconciliation difference value S is obtained through the following calculation formula:
；
where V1 represents the actual transaction amount TA, V2 represents the expected amount EA, V4 represents the historical transaction frequency TF, V1i represents the actual transaction amount TA in the ith record, V2i represents the expected amount EA in the ith record, V4i represents the historical transaction frequency TF in the ith record, n represents the total number of records in the priority list Pn, i represents the ith record, pi represents the processing priority index P of the ith record in the priority list Pn, and log represents a logarithmic function.
The summary evaluation unit matches the summary reconciliation difference value S with a preset summary reconciliation difference threshold CZ to generate an abnormal marking process evaluation result;
the abnormal marking process evaluation result is generated by the following matching mode:
When the summary accounting difference value S is larger than the summary accounting difference threshold CZ, generating an abnormal marking flow evaluation result as an abnormal result;
when the summary account checking difference value S is smaller than or equal to the summary account checking difference threshold CZ, an abnormal marking flow evaluation result is generated to be an abnormal-free result.
Preferably, the evaluation and optimization module comprises an abnormality judgment unit and an optimization recognition unit;
The anomaly judgment unit judges and executes an optimization strategy and a repair strategy according to the anomaly marking flow evaluation result, when the anomaly marking flow evaluation result is an anomaly result, the optimization strategy comprises regenerating an invoice, correcting payment data and notifying related personnel to perform manual intervention, and the repair strategy comprises adjusting transaction amount difference tolerance and optimizing rules in a reconciliation flow;
The optimization recognition unit processes the execution feedback information of the optimization strategy and the repair strategy to obtain an optimization evaluation index Y, carries out correction rules and adjustment transactions, and comprises a calculation method for judging the reconciliation rules according to the optimization evaluation index Y, carrying out correction rules and adjustment transactions, wherein the correction rules comprise updating abnormal detection parameters and redefining reconciliation differences;
The optimized evaluation index Y passes And obtaining a calculation formula, wherein exp represents an exponential function.
A reconciliation method of a payment clearing system, comprising the steps of:
step one: the data acquisition module is connected with a plurality of source channels of the payment system, the invoice system and the banking system to acquire related transaction data, packages the acquired transaction data into a feature vector V and stores the feature vector V;
step two: the abnormality detection module extracts relevant abnormality detection parameters from the stored feature vector V, and performs an abnormality detection flow to obtain an amount abnormality detection score D1 and a time abnormality detection score D2;
step three: the intelligent tag management module carries out fitting with historical transaction frequency TF of V4 and channel identification TC of V5 stored in the feature vector V according to the monetary anomaly detection score D1 and the time anomaly detection score D2, and carries out risk level reflecting transaction to obtain a level tag index L;
step four: the tag priority processing module carries out fitting calculation according to the level tag index L and the waiting time information and channel identification information stored in the feature vector V as the basis to obtain a processing priority index P, and the processing priority index P is used for determining the processing sequence of the transaction records;
Step five: the summary accounting module calculates according to transaction amount information stored in the processing priority index P and the feature vector V as a basis, acquires accounting difference information, gathers and acquires a summary accounting difference value S, matches with a preset summary accounting difference threshold CZ, and generates an abnormal marking flow evaluation result;
Step six: the evaluation and optimization module judges and executes an optimization strategy and a repair strategy according to the evaluation result of the abnormal marking process, processes and acquires an optimization evaluation index Y according to the execution feedback information of the optimization strategy and the repair strategy, and corrects rules and adjusts transactions.
A reconciliation storage medium of a payment clearing system, the storage medium storing a computer program which when executed implements a reconciliation system of a payment clearing system.
The invention provides a checking method, a checking system and a storage medium of a payment clearing system, which have the following beneficial effects:
(1) When the system operates, a unified and efficient data base is provided for the subsequent modules by packing the collected transaction data into the feature vector V. The abnormality detection module calculates an amount abnormality detection score D1 and a time abnormality detection score D2 by extracting transaction data in the feature vector V, performs risk assessment on the transaction by combining the historical transaction frequency TF and the channel identification TC, generates a level tag index L, performs fitting calculation with stored waiting time information and channel identification information to obtain a processing priority index P, so that the processing sequence of the transaction records is determined, transactions with high risk or longer waiting time are processed preferentially, and the response speed of the system is improved. Finally, the summary reconciliation module generates a summary reconciliation difference value S, and identifies abnormality by matching with a preset summary reconciliation difference threshold CZ, and the evaluation and optimization module further executes optimization and restoration strategies according to the abnormal conditions and carries out rule correction through an optimization evaluation index Y. The whole system solves the defect that the traditional checking system cannot efficiently mark and process abnormal payment through intelligent and automatic abnormal payment recognition and processing, ensures smoother and efficient checking process, reduces manual intervention, and reduces risk and checking workload in payment clearing.
(2) By combining the monetary anomaly detection score D1 and the time anomaly detection score D2 and combining the feature vector V, carrying out risk level assessment on each transaction to generate a level tag index L, and calculating a processing priority index P of each transaction by combining the level tag index L and the feature vector V, the system can not only identify high-risk transactions, but also reasonably arrange processing sequences according to waiting time and channel characteristics. Smooth processing is carried out on the duration WT to be processed through the arctangent function, so that excessive expansion of priority caused by overlong waiting time is avoided, and the processing sequence is ensured to be more scientific and reasonable. By combining the use of the bubbling sequencing algorithm, the system can dynamically adjust the priority processing list of the transaction records and quickly respond to the processing requirements of different transactions.
(3) The account checking difference information of each transaction is effectively calculated by combining the processing priority index P and the feature vector V, and a summary account checking difference value S is generated by accumulating the difference information, so that accurate account checking calculation of all transactions is ensured. Then, the summary evaluation unit generates an anomaly flag and triggers a corresponding evaluation and processing procedure by matching the summary reconciliation difference value S with the summary reconciliation difference threshold CZ. The method ensures that the efficient and accurate reconciliation processing is still maintained in the face of complex and high-frequency transactions, effectively reduces transaction risks and improves the reliability and efficiency of overall operation.
Drawings
FIG. 1 is a schematic diagram of a reconciliation system flow of a payment clearing system of the present invention;
fig. 2 is a schematic diagram of the steps of a reconciliation method of a payment clearing system of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
Example 1
The invention provides a checking system of a payment clearing system, please refer to fig. 1, which comprises a data acquisition module, an anomaly detection module, an intelligent label management module, a label priority processing module, a summary checking module and an evaluation and optimization module;
The data acquisition module is connected with a plurality of sources of the payment system, the invoice system and the banking system to acquire related transaction data, packages the acquired transaction data into a feature vector V and stores the feature vector V;
the abnormality detection module extracts relevant abnormality detection parameters from the stored feature vector V, performs an abnormality detection process, and obtains an amount abnormality detection score D1 and a time abnormality detection score D2;
The intelligent tag management module is used for carrying out fitting on the historical transaction frequency TF of V4 and the channel identifier TC of V5 stored in the feature vector V according to the monetary anomaly detection score D1 and the time anomaly detection score D2, so as to reflect the risk level of the transaction and obtain a level tag index L;
The tag priority processing module carries out fitting calculation according to the level tag index L and the waiting time information and channel identification information stored in the feature vector V as the basis to obtain a processing priority index P, and the processing priority index P is used for determining the processing sequence of the transaction records;
The summary accounting module calculates according to transaction amount information stored in the processing priority index P and the feature vector V as a basis, acquires accounting difference information, gathers and acquires a summary accounting difference value S, and matches with a preset summary accounting difference threshold CZ to generate an abnormal marking flow evaluation result;
And the evaluation and optimization module judges and executes an optimization strategy and a repair strategy according to the evaluation result of the abnormal marking process, processes and acquires an optimization evaluation index Y according to the execution feedback information of the optimization strategy and the repair strategy, and corrects rules and adjusts transactions.
In this embodiment, the data acquisition module is in butt joint with the multi-source channels of the payment system, the invoice system and the banking system, so that the acquired transaction data are packed into the feature vector V, and a unified and efficient data base is provided for the subsequent modules. The abnormality detection module calculates an amount abnormality detection score D1 and a time abnormality detection score D2 by extracting transaction data in the feature vector V, so that the capability of automatically identifying abnormal transactions is realized, and the problem of inefficiency of manual reconciliation in the traditional method is avoided. And then, the intelligent label management module carries out risk assessment on the transaction according to the monetary anomaly detection score D1 and the time anomaly detection score D2 by combining the historical transaction frequency TF and the channel identifier TC to generate a grade label index L, so that the system can rapidly and accurately judge and mark the high-risk transaction. Then, the tag priority processing module carries out fitting calculation according to the level tag index L, the stored waiting time information and the channel identification information to obtain a processing priority index P, so that the processing sequence of the transaction records is determined, and the transactions with high risk or longer waiting time are processed preferentially, thereby improving the response speed of the system. Finally, the summary reconciliation module performs reconciliation difference calculation based on the transaction amount information stored in the processing priority index P and the feature vector V, generates a summary reconciliation difference value S, identifies abnormality by matching with a preset summary reconciliation difference threshold CZ, and the evaluation and optimization module further executes optimization and repair strategies according to the abnormality conditions and performs rule correction by optimizing the evaluation index Y. The whole system solves the defect that the traditional checking system cannot efficiently mark and process abnormal payment through intelligent and automatic abnormal payment recognition and processing, ensures smoother and efficient checking process, reduces manual intervention, and reduces risk and checking workload in payment clearing.
Example 2
This embodiment is explained in embodiment 1, please refer to fig. 1, specifically: the data acquisition module comprises a data acquisition unit and a feature vector construction unit;
The data acquisition unit is connected with a plurality of source channels of the payment system, the invoice system and the banking system by using an API call and a database connection mode to acquire related transaction data, wherein the related transaction data comprises actual transaction amount TA, expected amount EA, payment time TT, historical transaction frequency TF, channel identification TC, exchange rate fluctuation FR and transaction time period identification TID;
The feature vector construction unit sequentially packages the obtained actual transaction amount TA, expected amount EA, payment time TT, historical transaction frequency TF, channel identification TC, exchange rate fluctuation FR and transaction time period identification TID into the actual transaction amount TA of feature vector parameters V1, the expected amount EA of V2, the payment time TT of V3, the historical transaction frequency TF of V4, the channel identification TC of V5, the exchange rate fluctuation FR of V6, the transaction time period identification TID of V7 and the waiting time WT of V8, and marks the packaging time SJ as the packaging time SJ of V9, forms feature vectors v= { V1, V2, V3, V4, V5, V6, V7, V8, V9}, represents specific transaction data by marking V1 to V9, thereby protecting privacy and reducing occurrence of related conditions of data leakage, and stores the privacy in a system database.
The abnormality detection module comprises a parameter extraction unit and an abnormality detection unit;
the parameter extraction unit extracts related abnormality detection parameters from the stored feature vector V, wherein the parameters comprise the actual transaction amount TA of V1, the expected amount EA of V2, the payment time TT of V3 and the historical transaction frequency TF of V4;
the abnormality detection unit performs an abnormality detection flow on the extracted abnormality detection parameters to obtain an amount abnormality detection score D1 and a time abnormality detection score D2;
the monetary anomaly detection score D1 is obtained by the following calculation formula:
；
where V1 represents the actual transaction amount TA, V2 represents the desired amount EA, The standard deviation of the actual transaction amount TA, representing V1, reflects in particular the volatility of the transaction amount,An average value representing the actual transaction amount TA of V1;
The time anomaly detection score D2 is obtained by the following calculation formula:
；
Where V3 represents the payment time TT, V4 represents the historical transaction frequency TF, Represents the average value of the payment time TT of V3,Represents the standard deviation of the payment time TT of V3, log represents a logarithmic function,The historical transaction frequency TF is smoothed to ensure that high transaction frequency users do not excessively amplify their impact in anomaly detection scoring.
Example 3
This embodiment is explained in embodiment 1, please refer to fig. 1, specifically: the intelligent tag management module obtains a level tag index L by fitting with historical transaction frequency TF of V4 in a stored feature vector V and channel identification TC of V5 according to an amount anomaly detection score D1 and a time anomaly detection score D2;
The level tag index L is obtained by the following calculation formula:
；
wherein r1 and r2 respectively represent preset risk weight values of the monetary anomaly detection score D1 and the time anomaly detection score D2, an V4 represents the historical transaction frequency TF, V5 represents the channel identification TC,Representing the mapping of the historical trading frequency TF of V4 into the range 0,1,Channel identification TC representing the nonlinear adjustment V5,Representing a mathematical constant, in particular a circumference ratio,Mapping the historical transaction frequency TF using a Sigmoid function, the higher the transaction frequency, the more stable the transaction behavior, the lower the risk may be,And carrying out nonlinear processing on the channel identification TC to reflect the risk differences of different transaction channels.
The label priority processing module comprises a priority calculating unit and a sequencing unit;
The priority calculating unit is based on the level tag index L, the stored waiting time information and channel identification information, wherein the waiting time information comprises the waiting time length WT of V8 in the feature vector V, the channel identification information comprises the channel identification TC of V5 in the feature vector V, and fitting calculation is carried out on the waiting time length WT of the level tag index L, V and the channel identification TC of V5 to obtain a processing priority index P;
The processing priority index P is obtained by the following calculation formula:
；
Where V8 denotes the duration to be processed WT, V5 denotes the channel identifier TC, tan denotes the arctangent function, The processing priority is dynamically calculated by combining the level label index L, the duration to be processed WT and the channel identifier TC, the duration to be processed WT is increased in priority, the influence of different channels is balanced by the evolution of the channel identifier TC,Reflecting the length of time to be processed WT, further influencing the priority, using an arctangent functionTo smooth out the latency impact and avoid excessive expansion of long waiting transaction priorities.
The sorting unit obtains 1 to n processing priority indexes P according to fitting calculation, forms a priority processing list Pn, and readjusts the positions of the 1 to n processing priority indexes P in the priority processing list Pn by bubbling sorting the priority processing list Pn, wherein the sorted priority processing list Pn is used for determining the processing sequence of the transaction records.
In this embodiment, by combining the monetary anomaly detection score D1 and the time anomaly detection score D2 and combining the historical transaction frequency TF and the channel identifier TC in the feature vector V, risk level evaluation is performed on each transaction, and a level tag index L is generated. Meanwhile, the tag priority processing module comprehensively calculates the processing priority index P of each transaction by using the level tag index L, the duration to be processed WT in the feature vector V and the channel identifier TC, so that the system can not only identify high-risk transactions, but also reasonably arrange the processing sequence according to the waiting time and the channel characteristics. Smooth processing is carried out on the duration WT to be processed through the arctangent function, so that excessive expansion of priority caused by overlong waiting time is avoided, and the processing sequence is ensured to be more scientific and reasonable. By combining the use of the bubbling sequencing algorithm, the system can dynamically adjust the priority processing list of the transaction records, quickly respond to the processing requirements of different transactions, ensure that the transactions with high priority can be processed in time, and remarkably improve the processing efficiency of the system and the security of the transactions.
Example 4
This embodiment is explained in embodiment 1, please refer to fig. 1, specifically: the summary reconciliation module comprises a difference calculation unit and a summary evaluation unit;
The difference calculation unit calculates according to the processing priority index P and transaction amount information stored in the feature vector V, wherein the transaction amount information comprises actual transaction amounts TA of V1 in the feature vector V, expected amounts EA of V2 and historical transaction frequencies TF of V4, and the transaction amount information is acquired and summarized to acquire a summarized reconciliation difference value S;
the summarized reconciliation difference value S is obtained through the following calculation formula:
；
where V1 represents the actual transaction amount TA, V2 represents the expected amount EA, V4 represents the historical transaction frequency TF, V1i represents the actual transaction amount TA in the ith record, V2i represents the expected amount EA in the ith record, V4i represents the historical transaction frequency TF in the ith record, n represents the total number of records in the priority list Pn, i represents the ith record, pi represents the processing priority index P of the ith record in the priority list Pn, log represents a logarithmic function, The historical transaction frequency TF is smoothed to ensure that high transaction frequency users do not excessively amplify their impact in anomaly detection scoring.
The summary evaluation unit matches the summary reconciliation difference value S with a preset summary reconciliation difference threshold CZ to generate an abnormal marking process evaluation result;
the abnormal marking process evaluation result is generated by the following matching mode:
When the summary accounting difference value S is larger than the summary accounting difference threshold CZ, generating an abnormal marking flow evaluation result as an abnormal result;
when the summary account checking difference value S is smaller than or equal to the summary account checking difference threshold CZ, an abnormal marking flow evaluation result is generated to be an abnormal-free result.
The evaluation and optimization module comprises an abnormality judgment unit and an optimization recognition unit;
The anomaly judgment unit judges and executes an optimization strategy and a repair strategy according to the anomaly marking flow evaluation result, when the anomaly marking flow evaluation result is an anomaly result, the optimization strategy comprises regenerating an invoice, correcting payment data and notifying related personnel to perform manual intervention, and the repair strategy comprises adjusting transaction amount difference tolerance and optimizing rules in a reconciliation flow;
The optimization recognition unit processes the execution feedback information of the optimization strategy and the repair strategy to obtain an optimization evaluation index Y, carries out correction rules and adjustment transactions, and comprises a calculation method for judging the reconciliation rules according to the optimization evaluation index Y, carrying out correction rules and adjustment transactions, wherein the correction rules comprise updating abnormal detection parameters and redefining reconciliation differences;
The optimized evaluation index Y passes The calculation formula is obtained, wherein exp represents an exponential function,The result is converted to a value between 0 and 1.
In this embodiment, the reconciliation difference information of each transaction is effectively calculated by combining the processing priority index P with the actual transaction amount TA in the feature vector V, the expected amount EA in the feature vector V, and the historical transaction frequency TF in the feature vector V, and the summary reconciliation difference value S is generated by accumulating the difference information, so as to ensure accurate reconciliation calculation for all transactions. Then, the summary evaluation unit generates an anomaly flag and triggers a corresponding evaluation and processing procedure by matching the summary reconciliation difference value S with the summary reconciliation difference threshold CZ. If an abnormality is found, the abnormality judgment unit automatically executes corresponding optimization and repair strategies, including regenerating invoices or correcting payment data, so that the automatic repair capability in the system reconciliation process is greatly improved. Meanwhile, the system feeds back the optimization result in real time through the optimization recognition unit, generates an optimization evaluation index Y, and corrects and adjusts the rule so that the system can optimize itself after each account checking operation. Through the continuous automatic optimization and rule correction mechanism, the system can dynamically update the abnormal detection parameters and the calculation method of the reconciliation difference, ensure that the efficient and accurate reconciliation processing is still maintained when complex and high-frequency transactions are faced, effectively reduce transaction risks and improve the reliability and efficiency of overall operation.
Example 5
Referring to fig. 2, a method for checking a payment clearing system is specifically shown as follows: the method comprises the following steps:
step one: the data acquisition module is connected with a plurality of source channels of the payment system, the invoice system and the banking system to acquire related transaction data, packages the acquired transaction data into a feature vector V and stores the feature vector V;
step two: the abnormality detection module extracts relevant abnormality detection parameters from the stored feature vector V, and performs an abnormality detection flow to obtain an amount abnormality detection score D1 and a time abnormality detection score D2;
step three: the intelligent tag management module carries out fitting with historical transaction frequency TF of V4 and channel identification TC of V5 stored in the feature vector V according to the monetary anomaly detection score D1 and the time anomaly detection score D2, and carries out risk level reflecting transaction to obtain a level tag index L;
step four: the tag priority processing module carries out fitting calculation according to the level tag index L and the waiting time information and channel identification information stored in the feature vector V as the basis to obtain a processing priority index P, and the processing priority index P is used for determining the processing sequence of the transaction records;
Step five: the summary accounting module calculates according to transaction amount information stored in the processing priority index P and the feature vector V as a basis, acquires accounting difference information, gathers and acquires a summary accounting difference value S, matches with a preset summary accounting difference threshold CZ, and generates an abnormal marking flow evaluation result;
Step six: the evaluation and optimization module judges and executes an optimization strategy and a repair strategy according to the evaluation result of the abnormal marking process, processes and acquires an optimization evaluation index Y according to the execution feedback information of the optimization strategy and the repair strategy, and corrects rules and adjusts transactions.
Example 6
A reconciliation storage medium of a payment clearing system, in particular: the storage medium stores a computer program which, when executed, implements a reconciliation system of a payment clearing system.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A reconciliation system for a payment clearing system, characterized by: the system comprises a data acquisition module, an abnormality detection module, an intelligent tag management module, a tag priority processing module, a summary checking module and an evaluation and optimization module;
The data acquisition module is connected with a plurality of sources of the payment system, the invoice system and the banking system to acquire related transaction data, packages the acquired transaction data into a feature vector V and stores the feature vector V;
the abnormality detection module extracts relevant abnormality detection parameters from the stored feature vector V, performs an abnormality detection process, and obtains an amount abnormality detection score D1 and a time abnormality detection score D2;
The intelligent tag management module is used for carrying out fitting on the historical transaction frequency TF of V4 and the channel identifier TC of V5 stored in the feature vector V according to the monetary anomaly detection score D1 and the time anomaly detection score D2, so as to reflect the risk level of the transaction and obtain a level tag index L;
The tag priority processing module carries out fitting calculation according to the level tag index L and the waiting time information and channel identification information stored in the feature vector V as the basis to obtain a processing priority index P, and the processing priority index P is used for determining the processing sequence of the transaction records;
The summary accounting module calculates according to transaction amount information stored in the processing priority index P and the feature vector V as a basis, acquires accounting difference information, gathers and acquires a summary accounting difference value S, and matches with a preset summary accounting difference threshold CZ to generate an abnormal marking flow evaluation result;
And the evaluation and optimization module judges and executes an optimization strategy and a repair strategy according to the evaluation result of the abnormal marking process, processes and acquires an optimization evaluation index Y according to the execution feedback information of the optimization strategy and the repair strategy, and corrects rules and adjusts transactions.
2. The reconciliation system of the payment clearing system of claim 1, wherein: the data acquisition module comprises a data acquisition unit and a feature vector construction unit;
The data acquisition unit is connected with a plurality of source channels of the payment system, the invoice system and the banking system by using an API call and a database connection mode to acquire related transaction data, wherein the related transaction data comprises actual transaction amount TA, expected amount EA, payment time TT, historical transaction frequency TF, channel identification TC, exchange rate fluctuation FR and transaction time period identification TID;
The feature vector construction unit sequentially packages the obtained actual transaction amount TA, expected amount EA, payment time TT, historical transaction frequency TF, channel identification TC, exchange rate fluctuation FR and transaction time period identification TID into the actual transaction amount TA of feature vector parameters V1, the expected amount EA of V2, the payment time TT of V3, the historical transaction frequency TF of V4, the channel identification TC of V5, the exchange rate fluctuation FR of V6, the transaction time period identification TID of V7 and the waiting time WT of V8, and marks the package time SJ of V9, forms feature vectors v= { V1, V2, V3, V4, V5, V6, V7, V8, V9}, and stores the feature vectors in a system database.
3. The reconciliation system of the payment clearing system of claim 2, wherein: the abnormality detection module comprises a parameter extraction unit and an abnormality detection unit;
the parameter extraction unit extracts related abnormality detection parameters from the stored feature vector V, wherein the parameters comprise the actual transaction amount TA of V1, the expected amount EA of V2, the payment time TT of V3 and the historical transaction frequency TF of V4;
the abnormality detection unit performs an abnormality detection flow on the extracted abnormality detection parameters to obtain an amount abnormality detection score D1 and a time abnormality detection score D2;
the monetary anomaly detection score D1 is obtained by the following calculation formula:
；
where V1 represents the actual transaction amount TA, V2 represents the desired amount EA, The standard deviation of the actual transaction amount TA, representing V1, reflects in particular the volatility of the transaction amount,An average value representing the actual transaction amount TA of V1;
The time anomaly detection score D2 is obtained by the following calculation formula:
；
Where V3 represents the payment time TT, V4 represents the historical transaction frequency TF, Represents the average value of the payment time TT of V3,The standard deviation of the payment time TT of V3 is represented, and log represents a logarithmic function.
4. A reconciliation system of a payment clearing system as defined in claim 3, wherein: the intelligent tag management module obtains a level tag index L by fitting with historical transaction frequency TF of V4 in a stored feature vector V and channel identification TC of V5 according to an amount anomaly detection score D1 and a time anomaly detection score D2;
The level tag index L is obtained by the following calculation formula:
；
wherein r1 and r2 respectively represent preset risk weight values of the monetary anomaly detection score D1 and the time anomaly detection score D2, an V4 represents the historical transaction frequency TF, V5 represents the channel identification TC,Representing the mapping of the historical trading frequency TF of V4 into the range 0,1,Channel identification TC representing the nonlinear adjustment V5,Representing mathematical constants, in particular the circumference ratio.
5. The reconciliation system of the payment clearing system of claim 4, wherein: the label priority processing module comprises a priority calculating unit and a sequencing unit;
The priority calculating unit is based on the level tag index L, the stored waiting time information and channel identification information, wherein the waiting time information comprises the waiting time length WT of V8 in the feature vector V, the channel identification information comprises the channel identification TC of V5 in the feature vector V, and fitting calculation is carried out on the waiting time length WT of the level tag index L, V and the channel identification TC of V5 to obtain a processing priority index P;
The processing priority index P is obtained by the following calculation formula:
；
Where V8 represents the duration to be processed WT, V5 represents the channel identifier TC, and tan represents the arctangent function.
6. The reconciliation system of the payment clearing system of claim 5, wherein: the sorting unit obtains 1 to n processing priority indexes P according to fitting calculation, forms a priority processing list Pn, and readjusts the positions of the 1 to n processing priority indexes P in the priority processing list Pn by bubbling sorting the priority processing list Pn, wherein the sorted priority processing list Pn is used for determining the processing sequence of the transaction records.
7. The reconciliation system of the payment clearing system of claim 6, wherein: the summary reconciliation module comprises a difference calculation unit and a summary evaluation unit;
The difference calculation unit calculates according to the processing priority index P and transaction amount information stored in the feature vector V, wherein the transaction amount information comprises actual transaction amounts TA of V1 in the feature vector V, expected amounts EA of V2 and historical transaction frequencies TF of V4, and the transaction amount information is acquired and summarized to acquire a summarized reconciliation difference value S;
the summarized reconciliation difference value S is obtained through the following calculation formula:
；
Wherein V1 represents the actual transaction amount TA, V2 represents the expected amount EA, V4 represents the history transaction frequency TF, V1i represents the actual transaction amount TA in the ith record, V2i represents the expected amount EA in the ith record, V4i represents the history transaction frequency TF in the ith record, n represents the total number of records in the priority list Pn, i represents the ith record, pi represents the processing priority index P of the ith record in the priority list Pn, and log represents a logarithmic function;
the summary evaluation unit matches the summary reconciliation difference value S with a preset summary reconciliation difference threshold CZ to generate an abnormal marking process evaluation result;
the abnormal marking process evaluation result is generated by the following matching mode:
When the summary accounting difference value S is larger than the summary accounting difference threshold CZ, generating an abnormal marking flow evaluation result as an abnormal result;
when the summary account checking difference value S is smaller than or equal to the summary account checking difference threshold CZ, an abnormal marking flow evaluation result is generated to be an abnormal-free result.
8. The reconciliation system of the payment clearing system of claim 7, wherein: the evaluation and optimization module comprises an abnormality judgment unit and an optimization recognition unit;
The anomaly judgment unit judges and executes an optimization strategy and a repair strategy according to the anomaly marking flow evaluation result, when the anomaly marking flow evaluation result is an anomaly result, the optimization strategy comprises regenerating an invoice, correcting payment data and notifying related personnel to perform manual intervention, and the repair strategy comprises adjusting transaction amount difference tolerance and optimizing rules in a reconciliation flow;
The optimization recognition unit processes the execution feedback information of the optimization strategy and the repair strategy to obtain an optimization evaluation index Y, carries out correction rules and adjustment transactions, and comprises a calculation method for judging the reconciliation rules according to the optimization evaluation index Y, carrying out correction rules and adjustment transactions, wherein the correction rules comprise updating abnormal detection parameters and redefining reconciliation differences;
The optimized evaluation index Y passes And obtaining a calculation formula, wherein exp represents an exponential function.
9. A method of reconciliation of a payment clearing system applied to a reconciliation system of a payment clearing system as defined in any one of claims 1-8, wherein: the method comprises the following steps:
step one: the data acquisition module is connected with a plurality of source channels of the payment system, the invoice system and the banking system to acquire related transaction data, packages the acquired transaction data into a feature vector V and stores the feature vector V;
step two: the abnormality detection module extracts relevant abnormality detection parameters from the stored feature vector V, and performs an abnormality detection flow to obtain an amount abnormality detection score D1 and a time abnormality detection score D2;
step three: the intelligent tag management module carries out fitting with historical transaction frequency TF of V4 and channel identification TC of V5 stored in the feature vector V according to the monetary anomaly detection score D1 and the time anomaly detection score D2, and carries out risk level reflecting transaction to obtain a level tag index L;
step four: the tag priority processing module carries out fitting calculation according to the level tag index L and the waiting time information and channel identification information stored in the feature vector V as the basis to obtain a processing priority index P, and the processing priority index P is used for determining the processing sequence of the transaction records;
Step five: the summary accounting module calculates according to transaction amount information stored in the processing priority index P and the feature vector V as a basis, acquires accounting difference information, gathers and acquires a summary accounting difference value S, matches with a preset summary accounting difference threshold CZ, and generates an abnormal marking flow evaluation result;
Step six: the evaluation and optimization module judges and executes an optimization strategy and a repair strategy according to the evaluation result of the abnormal marking process, processes and acquires an optimization evaluation index Y according to the execution feedback information of the optimization strategy and the repair strategy, and corrects rules and adjusts transactions.
10. A reconciliation storage medium of a payment clearing system, characterized by: the storage medium stores a computer program which, when executed, implements a reconciliation system of a payment clearing system of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411432978.5A CN118967322A (en) | 2024-10-15 | 2024-10-15 | A reconciliation method, system and storage medium for a payment and clearing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411432978.5A CN118967322A (en) | 2024-10-15 | 2024-10-15 | A reconciliation method, system and storage medium for a payment and clearing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118967322A true CN118967322A (en) | 2024-11-15 |
Family
ID=93391607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411432978.5A Pending CN118967322A (en) | 2024-10-15 | 2024-10-15 | A reconciliation method, system and storage medium for a payment and clearing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118967322A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119624613A (en) * | 2025-02-17 | 2025-03-14 | 贵阳高登世德金融科技有限公司 | A bank statement verification method and system based on OCR recognition technology |
| CN119741140A (en) * | 2025-03-04 | 2025-04-01 | 德卡云创科技(西安)有限公司 | An AI-based automatic reconciliation optimization and processing method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030055783A1 (en) * | 2000-11-06 | 2003-03-20 | Cataline Glen R. | System and method for optimized funding of electronic transactions |
| US20100305993A1 (en) * | 2009-05-28 | 2010-12-02 | Richard Fisher | Managed real-time transaction fraud analysis and decisioning |
| CN114418559A (en) * | 2022-01-18 | 2022-04-29 | 北京融威众邦电子技术有限公司 | Automatic payment clearing method and system |
| CN118761773A (en) * | 2024-09-05 | 2024-10-11 | 广东通莞科技股份有限公司 | A bill payment system based on business configuration |
-
2024
- 2024-10-15 CN CN202411432978.5A patent/CN118967322A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030055783A1 (en) * | 2000-11-06 | 2003-03-20 | Cataline Glen R. | System and method for optimized funding of electronic transactions |
| US20100305993A1 (en) * | 2009-05-28 | 2010-12-02 | Richard Fisher | Managed real-time transaction fraud analysis and decisioning |
| CN114418559A (en) * | 2022-01-18 | 2022-04-29 | 北京融威众邦电子技术有限公司 | Automatic payment clearing method and system |
| CN118761773A (en) * | 2024-09-05 | 2024-10-11 | 广东通莞科技股份有限公司 | A bill payment system based on business configuration |
Non-Patent Citations (1)
| Title |
|---|
| 陈雪仪;: "区块链技术在商业银行内部控制优化中的应用研究", 中国注册会计师, no. 07, 8 July 2020 (2020-07-08), pages 108 - 112 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119624613A (en) * | 2025-02-17 | 2025-03-14 | 贵阳高登世德金融科技有限公司 | A bank statement verification method and system based on OCR recognition technology |
| CN119741140A (en) * | 2025-03-04 | 2025-04-01 | 德卡云创科技(西安)有限公司 | An AI-based automatic reconciliation optimization and processing method and system |
| CN119741140B (en) * | 2025-03-04 | 2025-06-03 | 德卡云创科技(西安)有限公司 | Automatic account checking optimization and processing method and system based on AI |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118967322A (en) | A reconciliation method, system and storage medium for a payment and clearing system | |
| CN103984726B (en) | A kind of local correction method of data base's implement plan | |
| CN111177250A (en) | Abnormal transaction monitoring method, system and storage medium | |
| CN109583773A (en) | A kind of method, system and relevant apparatus that taxpaying credit integral is determining | |
| CN116777633A (en) | Financial asset management system based on data management | |
| CN118037469B (en) | Financial management system based on big data | |
| CN119831767A (en) | System and method for automatically extracting and checking financial data | |
| CN116303404B (en) | Big data storage system for preventing data redundancy based on data classification and peer comparison | |
| CN115439265A (en) | Intelligent insurance industry compensation abnormal transaction risk control system | |
| CN114676931B (en) | A power prediction system based on data center technology | |
| CN115641202A (en) | Small loan industry group lending risk measurement method based on knowledge graph and graph calculation | |
| CN117952620B (en) | Commission settlement method and system for restoring online rate of statement based on data processing | |
| CN117971818B (en) | A data governance task operation method based on big data | |
| CN117495572A (en) | Construction method of credit risk assessment and prediction model for small and medium-sized enterprises in supply chain finance | |
| CN116739823A (en) | Information acquisition method and device, terminal and storage medium during ammeter replacement | |
| CN109118378A (en) | Insurance risk assessment method based on enterprise process data | |
| CN115205031A (en) | Financial wind control rule engine system based on big data technology | |
| CN113674081A (en) | Graph database-based wind control management system and method for small and medium-sized enterprises | |
| CN119741140B (en) | Automatic account checking optimization and processing method and system based on AI | |
| CN114153915A (en) | Method and system for tracing and tracing information in block chain | |
| CN112561368B (en) | Visual performance calculation method and device for OA approval system | |
| CN117973879A (en) | Power payment risk identification method and system based on multi-source data joint analysis | |
| CN120374057A (en) | Scientific and technological information management method and system based on big data | |
| CN119048309A (en) | Customer service processing method and device | |
| CN120765384A (en) | A system for constructing quantitative indicators of investor sentiment divergence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |