TWI676955B - Artificial intelligence check system - Google Patents

Abstract

The intelligent reconciliation system of the present invention is communicatively connected to an online banking system. The online banking system includes a transaction detailed list, and the transaction detailed data includes at least one payment data and at least one payment data. The intelligent reconciliation system includes a voucher reading identification module, an accounting account processing center, and a comparison module. The voucher reading identification module is installed in an electronic device. The voucher reading identification module includes an image character reading unit. The image character reading unit reads a traditional invoice or a taxable certificate by using OCR text recognition technology. Or a type of receipt, or scanning a two-dimensional bar code of an electronic invoice to generate an input voucher data or an output voucher data. The comparison module is used to compare the input voucher data with the bank payment data or to compare the output voucher data with the bank receipt data. Wherein, when the input voucher data cannot correspond to the payment data, the input voucher data is marked as an account payable.

Description

Intelligent reconciliation system

The invention provides an intelligent reconciliation system, in particular to an intelligent reconciliation system with a voucher reading identification module and a comparison module.

The fast and accurate circulation of information flow and gold flow occupies an important position in business management, especially if the company's goods (or services) and capital transactions can be efficiently reconciled through online banking, it can improve business efficiency and Correctness. Under the traditional reconciliation method, the reconciling staff must manually compare the voucher data (such as traditional invoices, taxable vouchers or various receipts) and the income and expenditure of bank transaction details one by one to confirm the actual internal enterprise Credited and posted money. However, the traditional reconciliation method requires the experience of the reconciliation personnel to be relatively high, the time required for the reconciliation is longer, and there is also the negligence of human comparison, so the actual reconciliation is not effective.

Therefore, how to efficiently and effectively grasp the actual credential data of the enterprise's account entry and exit, and the audit trail left by the Internet bank can avoid human negligence. It is worth thinking about for those with ordinary knowledge in the field.

The purpose of the present invention is to provide an intelligent reconciliation system, which can more efficiently and effectively grasp the voucher data of the actual gold inflow and outflow of an enterprise, and avoid human error.

The intelligent reconciliation system of the present invention is communicatively connected to an internet banking system. The internet banking system includes a transaction detail list, and the transaction detail data includes at least one payment information and at least one payment receivable. material. The intelligent reconciliation system includes a voucher reading identification module, an accounting account processing center, and a comparison module. The voucher reading recognition module is installed in an electronic device. The voucher reading recognition module includes an image character reading unit, and the image character reading unit reads a traditional invoice or a variety of receipts by using OCR text recognition technology. To generate an input voucher data or an output voucher data. In addition, the accounting processing center is installed on a server, the input voucher data or the output voucher data is transmitted to the accounting processing center, and the transaction details list is downloaded to the accounting processing center. In addition, the comparison module is used to compare the input voucher data with the payment data or used to compare the output voucher data with the payment data, and the comparison module is installed on the server. Wherein, when the input voucher data cannot correspond to the payment data, the input voucher data is marked as an account payable, and when the output voucher data cannot correspond to the payment data, the output voucher data is Marked as a receivable.

In the intelligent reconciliation system described above, the transaction details list is a TXT file.

The smart reconciliation system described above further includes an encryption module that encrypts the transaction detail list.

The above-mentioned intelligent reconciliation system also includes a monitoring module, which is used to monitor the transaction details list in the accounting processing center, and when there is a change in the payment data and the receipt data , The monitoring module sends a warning message.

The intelligent reconciliation system described above, wherein the voucher reading identification module further includes a code reading unit that reads at least one electronic invoice to obtain the input voucher data or the output voucher data .

In the above-mentioned intelligent reconciliation system, the accounting processing center includes a data voucher management unit, and the data voucher management unit includes a duplicate voucher filtering unit and a character analysis management unit. The duplicate voucher filtering unit is used to check whether the input voucher data or the output voucher data is repeatedly created. In addition, the character analysis management unit includes a keyword database, and the keyword database includes For multiple keyword correspondence tables, the character analysis management unit classifies the input voucher data according to the contents of the keyword correspondence table to generate an account data.

In the above-mentioned intelligent reconciliation system, the voucher reading identification module further includes a manual input unit, and a user of a department uses the manual input unit to create the content of an unreadable invoice into the input voucher data. Or the debit voucher information.

In the above-mentioned intelligent reconciliation system, the electronic device is a smart phone, a tablet computer, a notebook computer, or a desktop computer.

In order to make the above-mentioned features and advantages more obvious and easy to understand, the following exemplifies preferred embodiments and the accompanying drawings for detailed description as follows.

6‧‧‧Server

81‧‧‧ traditional invoice

82‧‧‧ various receipts

83‧‧‧Electronic Invoice

830‧‧‧Two-dimensional barcode

84‧‧‧Unreadable invoice

9‧‧‧online banking system

90‧‧‧Transaction Details List

91‧‧‧Payment Information

92‧‧‧ Collection Information

10, 20‧‧‧ Intelligent Reconciliation System

11‧‧‧Electronic device

110‧‧‧ lens

112‧‧‧Certificate Read Identification Module

1121‧‧‧Image character reading unit

1122‧‧‧Barcode reading unit

1123‧‧‧Manual input unit

12‧‧‧Accounting Processing Center

121‧‧‧ Input Voucher Information

122‧‧‧ Output voucher information

123‧‧‧Data Certificate Management Unit

1231‧‧‧ Duplicate Certificate Filtering Unit

1232‧‧‧Character Analysis Management Unit

1232A‧‧‧Keyword Database

13‧‧‧Account information

14‧‧‧ Compare Module

25‧‧‧Encryption Module

26‧‧‧Monitoring Module

FIG. 1 illustrates an intelligent reconciliation system 10 according to this embodiment.

FIG. 2 is a schematic diagram of a conventional invoice 81 taken by the electronic device 11.

FIG. 3 is a schematic diagram of the electronic device 11 photographing and shooting the electronic invoice 83.

FIG. 4 illustrates an intelligent reconciliation system 20 according to another embodiment.

The comparison module 14 of the intelligent reconciliation system 10 in this embodiment can efficiently and correctly compare information flow and gold flow, which can reduce human error, errors and fraud. The detailed implementation and application of the intelligent reconciliation system 10 are as follows : Please refer to FIG. 1 and FIG. 2. FIG. 1 shows the intelligent reconciliation system 10 of this embodiment, and FIG. 2 shows a schematic diagram of the electronic device 11 taking a traditional invoice 81. The intelligent reconciliation system 10 is communicatively connected to an online banking system 9. The online banking system 9 includes a transaction detail list 90. The transaction detail list 90 is, for example, a TXT file, and the transaction detail information 90 includes at least one payment information 91 and at least One payment information 92. detailed In detail, the payment information 91 is generated through the expenses paid by the company, and the payment information 92 is generated through the expenses of the company's income. The intelligent reconciliation system 10 of this embodiment includes a voucher reading identification module 112, an accounting processing center 12 and a comparison module 14. The certificate reading identification module 112 is mounted on an electronic device 11. The electronic device 11 includes a lens 110. The electronic device 11 is, for example, a smart phone, a tablet computer, a notebook computer, or a desktop computer. In addition, the voucher reading identification module 112 includes an image character reading unit 1121. The image character reading unit 1121 reads a traditional invoice 81 or a receipt 82 of various types through the lens 110 and OCR text recognition technology to generate An input voucher data 121 or an output voucher data 122. In detail, when the traditional invoice 81 is an invoice or a voucher for input expenditure, the image character reading unit 1121 uses OCR character recognition technology (Optical Character Recognition) to identify the traditional invoice 81 to generate input voucher data 121. In more detail, the input voucher data 121 continues to save the graphics in the traditional invoice 81, and the text becomes a text that can be calculated (the text is not a picture file). Similarly, if the traditional invoice 81 is an invoice that belongs to the sales revenue, the image character reading unit 1121 will generate a sales voucher data 122 after identifying the traditional invoice 81. The sales voucher data 122 is also a graphic of the traditional invoice 81 Continue to save, and the text becomes the text that can be calculated (the text is not a kind of graphic file). In the above, in addition to the image character reading unit 1121 can recognize the traditional invoice 81, the image character reading unit 1121 can also read a receipt 82 by OCR text recognition technology, which will also generate the input voucher data 121 or the output voucher. Information 122.

In addition, the accounting processing center 12 is installed on a server 6, the input voucher data 121 or the output voucher data 122 are transmitted to the accounting processing center 12 by the electronic device 11, and the transaction details list 90 of the online banking system 9 It will also be downloaded to the Accounting Processing Center12. The accounting processing center 12 includes a data voucher management unit. The data voucher management unit includes a duplicate voucher filtering unit 1231 and a character analysis management unit 1232. The repeated voucher filtering unit 1231 is used to check the input voucher data 121 or sales. Whether the item voucher data 122 is repeatedly created. For example, the duplicate voucher filtering unit 1231 determines whether the input voucher data 121 or the output voucher data 122 has been stored according to the invoice number of the traditional invoice 81. In the accounting processing center 12. In this way, the same invoice will not be double-accounted. In addition, if the source of the input voucher data 121 or the output voucher data 122 is the receipt 82, the duplicate voucher filtering unit 1231 will determine whether the input voucher data 121 or the output voucher data 122 has been stored according to the date, item and amount of the receipt 82. In the accounting processing center 12, the same receipt can also be prevented from being posted again. In addition, the character analysis management unit 1232 includes a keyword database 1232A, the keyword database 1232A includes multiple keyword correspondence tables, and the character analysis management unit will input the input voucher data 121 according to the content of the keyword correspondence table Or the output voucher data 122 is classified to generate an account information13. For example, when the input voucher data 121 includes the keyword "pencil", the character analysis management unit 1232 finds the corresponding name in the keyword correspondence table as "stationery supplies" and the subject number as "5153". Or, when the input voucher data 121 includes keywords such as "water charges" or "electricity charges", the character analysis management unit 1232 finds the corresponding name in the keyword correspondence table as "water and gas charges" and the subject number is " 5161 ". In this way, the input voucher data 121 can quickly perform subject classification without manual processing.

Please refer to FIG. 1 again. The comparison module is also installed on the server 6. The comparison module 14 is used to compare the input voucher data 121 and payment data 91 or to compare the output voucher data 122 and the receipt data. 92. Thereafter, when the input voucher data 121 cannot correspond to the payment data 91, the input voucher data 121 is marked as an account payable. In detail, if the amount of the input voucher data 121 cannot be matched with any of the payment data 91, it means that an invoice or receipt from another company line number has been received, but the company has not actually made the payment. 121 must first be marked as an accounts payable. In addition, when the output voucher data 122 cannot correspond to the receivable data, the output voucher data 122 will also be marked as an account receivable. Similarly, if the amount of the output voucher data 122 cannot be matched with the amount of any payment data 92, it means that the invoice or receipt issued by the company has not been collected, that is, the other company's line number has not yet been collected. The actual payment is made, so the output voucher data 122 must also be marked as an account receivable to remind which payments will be received. Therefore, compared with the manual reconciliation method, the intelligent reconciliation system 10 can be more Quickly and effectively grasp the internal voucher data of the actual account entry and exit, effectively avoiding human reconciliation errors, and reducing the company's labor costs.

Please refer to FIG. 1 and FIG. 3 at the same time. FIG. 3 is a schematic diagram of the electronic device 11 shooting and shooting the electronic invoice 83. The voucher reading identification module 112 can read an electronic invoice 83 through the barcode reading unit 1122 and the lens 110 to generate input voucher data 121. In detail, the electronic invoice 83 itself has a two-dimensional barcode (QR code) 830, and the basic information of the entry voucher data 121 is stored in the two-dimensional barcode 830. Therefore, when the lens 110 is aligned with the two-dimensional barcode 830 of the electronic invoice 83 The barcode reading unit 1122 can also read the input voucher data 121 or the output voucher data 122 from the two-dimensional bar code 830. In this way, the data certificate management unit 123 can perform subsequent processing. In addition, when the lens 110 of the electronic device 11 cannot read the traditional invoice 81 or various receipts 82 (the traditional invoice 81 or various receipts 82 are too old or the surface is too vague), the users of the department of the electronic device 11 are different. The content of an unreadable invoice 84 can be created into the input voucher data 121 or the output voucher data 122 by the manual input unit 1123. In this way, the data voucher management unit 123 can still perform subsequent processing on the input voucher data 121 or the output voucher data 122 (generating accounting data 13).

Please refer to FIG. 4. FIG. 4 illustrates an intelligent reconciliation system 20 according to another embodiment. The difference between the intelligent reconciliation system 20 and the intelligent reconciliation system 10 is that the intelligent reconciliation system 20 further includes an encryption module 25 and A monitoring module 26. The encryption module 25 is used to encrypt the transaction details list 90 in the accounting processing center 12. Therefore, external unauthorized persons cannot modify the transaction details list 90 to ensure the correctness of the payment information 91 and the payment information 92. In this way, the comparison result of the data presented by the comparison module 14 is of reference and operational value. In addition, the monitoring module 26 is used to monitor the transaction details list 90 in the accounting processing center 12, and when the payment data 91 and the collection data 92 are changed, the monitoring module 26 issues a warning message. Specifically, when the encrypted transaction details list 90 is still cracked, the monitoring module 26 will continue to monitor whether the payment data 91 and the payment data 92 have changed. In addition, the monitoring module 26 issues a warning message when an external unauthorized person changes the transaction details list 90 Information to remind users of the intelligent reconciliation system 20. In this way, the risk of tampering with the transaction detail list 90 can be reduced.

In summary, the intelligent reconciliation system of the present invention uses the voucher reading identification module 112 to scan and identify different types of invoices or receipts. After that, the accounting data 13 is automatically generated through the accounting processing center 12. In addition, this system also uses the comparison module 14 to compare the input voucher data 121 or the output voucher data 122 to the transaction details list 90, so it can find out the company's actual unpaid accounts payable and receivables outstanding. .

Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. Any person with ordinary knowledge in the technical field can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope of the appended patent application.

Claims (8)

An intelligent reconciliation system is communicatively connected to an online banking system. The online banking system includes a transaction detail list, the transaction detail list includes at least one payment information and at least one payment information. The intelligent reconciliation system includes: a The voucher reading recognition module is installed in an electronic device. The voucher reading recognition module includes an image character reading unit, and the image character reading unit reads a traditional invoice of an input expense by using OCR text recognition technology. Or various receipts of input expenditure to generate an input voucher data; the image character reading unit reads a traditional invoice of an output revenue by OCR text recognition technology to generate an output voucher data; an accounting account Transaction processing center, which is installed on a server, the input voucher data or the output voucher data is transmitted to the accounting process center, and the transaction details list is downloaded to the accounting process center ; And a comparison module for comparing the input voucher data with the payment data or for comparing the output voucher data with the payment data, and The matching module is installed on the server; wherein, when the input voucher data cannot correspond to the payment data, the input voucher data is marked as an account payable, and when the output voucher data cannot correspond to the account receipt In the case of payment information, the data of the output voucher is marked as an account receivable. The intelligent reconciliation system described in item 1 of the scope of patent application, wherein the transaction detail list is a TXT file. The intelligent reconciliation system described in item 1 of the scope of patent application, further includes an encryption module, which encrypts the transaction details list in the accounting processing center. The intelligent reconciliation system described in item 1 of the scope of patent application, further includes a monitoring module, which is used to monitor the transaction details list in the accounting processing center, and when the payment information and the receipt When there is a change in the data, the monitoring module sends a warning message. The intelligent reconciliation system described in item 1 of the scope of patent application, wherein the voucher reading identification module further includes a code reading unit, which reads at least one electronic invoice to obtain the input voucher information or The debit voucher information. The intelligent reconciliation system described in item 1 of the scope of patent application, wherein the accounting processing center includes a data voucher management unit, the data voucher management unit includes a duplicate voucher filtering unit, and the duplicate voucher filtering unit is used to check Whether the input voucher data or the output voucher data has been repeatedly created. The intelligent reconciliation system described in item 1 of the scope of patent application, wherein the voucher reading identification module further includes a manual input unit, and a user of a department uses the manual input unit to input the content of an unreadable invoice Create the input voucher data or the output voucher data. The smart reconciliation system described in item 1 of the patent application scope, wherein the electronic device is a smart phone, a tablet computer, a notebook computer, or a desktop computer.