CN-121981834-A - Method, device, equipment and storage medium for checking and verifying money based on artificial intelligence

CN121981834ACN 121981834 ACN121981834 ACN 121981834ACN-121981834-A

Abstract

The application provides a collection verification method, a device, equipment and a storage medium based on artificial intelligence, which belong to the technical field of artificial intelligence; the method comprises the steps of carrying out running money information identification on bank running information through a preset running data identification model to obtain money characteristic information of customer repayment, obtaining a historical money characteristic information base, adjusting the money characteristic information according to the historical money characteristic information base to obtain target money characteristic information, and carrying out money verification processing on the target money characteristic information and financial service data through a preset decision tree model to obtain a money verification result. The application can accurately and conveniently complete money verification, greatly improves the efficiency and accuracy of money verification and greatly improves the satisfaction degree of customers on financial services. The application can be applied to the technical field of finance, and the accuracy of financial product money verification and approval is improved.

Inventors

WANG FUQI

Assignees

平安国际融资租赁有限公司

Dates

Publication Date: 20260505
Application Date: 20260123

Claims (10)

1. An artificial intelligence based method for verifying and verifying a receipt of money, comprising: responding to repayment operation of a customer, and acquiring bank flow information and financial service data of the customer; carrying out running amount information identification on the bank running information through a preset running amount data identification model to obtain amount characteristic information of customer repayment, wherein the preset running amount data identification model is obtained by training a neural network model based on a plurality of sample data in advance, and the sample data comprises the bank running amount information and marked amount characteristic information; acquiring a historical amount characteristic information base, wherein the historical amount characteristic information base is amount characteristic information of money paid by each customer before the current moment; According to the historical money characteristic information base, adjusting money characteristic information paid by the customer to obtain target money characteristic information of the customer; and performing money verification processing on the target money characteristic information and the financial service data through a preset decision tree model to obtain a money verification result.
2. The method for verifying and verifying the payment of the bank according to claim 1, wherein the predetermined serial data identification model comprises an encoder layer, a full connection layer and a decoder layer, wherein the serial data identification model is used for identifying the serial amount information of the bank to obtain the amount characteristic information of the customer payment, and the method comprises the following steps: carrying out feature coding on the bank pipelining information through the encoder layer to obtain a bank pipelining information feature vector; Extracting data characteristic parameters of the bank flow information characteristic vector through the full connection layer to obtain an amount characteristic vector; And decoding the money amount characteristic vector through the decoder layer to obtain money amount characteristic information, wherein the money amount characteristic information comprises a money amount, a running date, a transaction account name and remark information.
3. The artificial intelligence based money collection and verification method according to claim 1, wherein the adjusting the money amount characteristic information of the customer repayment according to the history money amount characteristic information base to obtain the target money amount characteristic information of the customer comprises: Acquiring a characteristic information adjustment model, wherein the characteristic information adjustment model is obtained by training a neural network model on the basis of a plurality of sample data in advance, and the sample data comprises sample amount characteristic information, a historical amount characteristic information sample and marked target amount characteristic information; And adjusting the amount characteristic information based on the historical amount characteristic information in the historical amount characteristic information base through the characteristic information adjustment model to obtain the target amount characteristic information.
4. The method for verifying and verifying money according to claim 1, wherein the target money feature information includes money amount, running date, transaction account name and remark information, and the performing money verifying and verifying processing on the target money feature information and the financial service data through a preset decision tree model to obtain a money verifying and verifying result comprises the steps of: If remark information in the target money amount characteristic information is not empty, comparing the money amount with money amount in the financial service data; If the amount is the same as the amount of money in the financial service data, verifying and verifying the money in the financial service data; If the amount is different from the amount of money in the financial service data, account hanging processing is carried out on the money in the financial service data.
5. The artificial intelligence based money collection verification method according to claim 4, wherein if the remark information in the target amount feature information is empty, further comprising: If the transaction account name is the same as the account name in the financial service data, performing money verification processing according to the running date and the transaction date in the financial service data; And if the transaction account name is different from the account name in the financial service data, performing account hanging processing on money in the financial service data.
6. The artificial intelligence based money collection and verification method according to claim 5, wherein the money collection and verification process according to the running date and the transaction date in the financial service data comprises: if the difference between the running date and the transaction date is smaller than or equal to a preset time difference, verifying and verifying money in the financial service data; And if the difference between the running date and the transaction date is larger than the preset time difference, performing account hanging processing on the money in the financial service data.
7. The artificial intelligence based checkout verification method as defined in any one of claims 1 to 6, wherein the method further comprises: acquiring a sample data set, wherein the sample data set comprises a plurality of sample data, and the sample data comprises sample bank flow information and marked amount characteristic information; Acquiring a preset neural network model, and selecting one sample data from the sample data set as target sample data; carrying out running amount information identification on sample bank running information in the target sample data through the preset neural network model to obtain predicted amount characteristic information; Determining whether the preset neural network model converges or not according to the predicted monetary characteristic information and the marked monetary characteristic information; and if the preset neural network model is not converged, adjusting model parameters of the preset neural network model, and continuously executing the step of selecting one sample data from the sample data set as target sample data until a converged pipeline data identification model is obtained.
8. The utility model provides a collection verification device which characterized in that, collection verification device includes acquisition module, generation module and adjustment module, wherein: The acquiring module is used for responding to the repayment operation of the customer and acquiring bank flow information and financial service data of the customer; The generation module is used for carrying out running money information identification on the bank running information through a preset running data identification model to obtain money characteristic information of the customer repayment, the preset running data identification model is obtained by training a neural network model on the basis of a plurality of sample data in advance, and the sample data comprise the bank running information and marked money characteristic information; the acquisition module is also used for acquiring a historical money characteristic information base, wherein the historical money characteristic information base is money characteristic information of money paid by each customer before the current moment; The adjustment module is used for adjusting the amount characteristic information paid by the client according to the historical amount characteristic information base to obtain target amount characteristic information of the client; The generation module is further used for performing money verification processing on the target amount characteristic information and the financial service data through a preset decision tree model to obtain a money verification result.
9. A computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor performs the steps of the artificial intelligence based checkout verification method as claimed in any one of claims 1 to 7.
10. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, wherein the computer program, when executed by a processor, implements the steps of the artificial intelligence based checkout verification method as defined in any one of claims 1 to 7.

Description

Method, device, equipment and storage medium for checking and verifying money based on artificial intelligence Technical Field The application relates to the technical field of artificial intelligence, in particular to a collection verification method, device and equipment based on artificial intelligence and a storage medium. Background With the rapid development of the financial industry, the business financial business and insurance business are increasingly involved in accounting and verifying of large amount, at present accounting and verifying business is mostly completed in a manual operation mode, service personnel check and verify through a return bill provided by a client, and meanwhile, a manual account is required to be maintained for managing and recording the return and verifying conditions of accounts payable of all buyers. Some customers should pay, pay back and pay for the insurance will have a scene of multiple periods and different amounts, so that business personnel need to check each time and communicate with customers, and there are problems of low payment verification efficiency and high verification error rate. Therefore, how to accurately and efficiently complete the verification and verification of the receipt is a problem to be solved at present. Disclosure of Invention The application mainly aims to provide a method, a device, equipment and a storage medium for checking and verifying money based on artificial intelligence, which aim to improve the efficiency and accuracy of checking and verifying money. In a first aspect, the present application provides an artificial intelligence based method of verifying and verifying a receipt, the artificial intelligence based method of verifying and verifying a receipt comprising the steps of: responding to repayment operation of a customer, and acquiring bank flow information and financial service data of the customer; carrying out running amount information identification on the bank running information through a preset running amount data identification model to obtain amount characteristic information of customer repayment, wherein the preset running amount data identification model is obtained by training a neural network model based on a plurality of sample data in advance, and the sample data comprises the bank running amount information and marked amount characteristic information; acquiring a historical amount characteristic information base, wherein the historical amount characteristic information base is amount characteristic information of money paid by each customer before the current moment; According to the historical money characteristic information base, adjusting money characteristic information paid by the customer to obtain target money characteristic information of the customer; and performing money verification processing on the target money characteristic information and the financial service data through a preset decision tree model to obtain a money verification result. In a second aspect, the present application further provides a payment verification device, where the payment verification device includes an acquisition module, a generation module, and an adjustment module, where: The acquiring module is used for responding to the repayment operation of the customer and acquiring bank flow information and financial service data of the customer; The generation module is used for carrying out running money information identification on the bank running information through a preset running data identification model to obtain money characteristic information of the customer repayment, the preset running data identification model is obtained by training a neural network model on the basis of a plurality of sample data in advance, and the sample data comprise the bank running information and marked money characteristic information; the acquisition module is also used for acquiring a historical money characteristic information base, wherein the historical money characteristic information base is money characteristic information of money paid by each customer before the current moment; The adjustment module is used for adjusting the amount characteristic information paid by the client according to the historical amount characteristic information base to obtain target amount characteristic information of the client; The generation module is further used for performing money verification processing on the target amount characteristic information and the financial service data through a preset decision tree model to obtain a money verification result. In a third aspect, the present application also provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the steps of an artificial intelligence based cash register verification method as described above. In a fourth aspect, the p