Intelligent bill classification and identification guarantee method and system and medium

Abstract

The invention provides a bill intelligent classification and identification guarantee method and system and a medium. The method comprises the following steps: verifying an online reimbursement bill to generate a corresponding reimbursement two-dimensional code, obtaining reimbursement equipment mode information, identifying the reimbursement two-dimensional code, scanning a reimbursement bill, obtaining a corresponding reimbursement bill image, processing according to the reimbursement bill image, obtaining a bill category, extracting key elements, obtaining bill elements, and displaying the bill elements. Performing bill authenticity verification and bill compliance verification at the same time to obtain a bill compliance state, if the bill compliance state is the bill compliance state, performing sum comparison, and if the sum is consistent, storing the reimbursement bill image according to the bill category and uploading the reimbursement bill image to an online reimbursement bill; according to the invention, through integration of the self-service reimbursement process, automatic verification and automatic classification, intelligent classification and identification of the bills are realized, and the reimbursement experience and the reimbursement accuracy are improved.

Description

Technical Field

[0001] This application relates to the field of financial document processing technology, and more specifically, to a method, system, and medium for intelligent classification and identification of documents. Background Technology

[0002] In corporate financial reimbursement processes, traditional invoice processing relies heavily on manual operations. Manually filling out forms requires repeated verification of reimbursement amounts and other information, leading to uncontrollable approval progress. Using high-speed scanners or mobile phones to take images, followed by manual uploading, categorization, image linking, and document transfer, is inefficient. Physical delivery requires face-to-face exchange during work hours, increasing the risk of lost invoices. The validity and compliance of physical invoices cannot be assessed promptly, and returned invoices result in long reimbursement cycles and a poor user experience. Verification of invoice authenticity and compliance relies on manual checks, lacking effective methods and being inefficient. Furthermore, the matching process between physical invoices and documents during review is cumbersome, inefficient, and labor-intensive. With the increasing demand for digital transformation in enterprises, there is a need for an intelligent invoice classification and recognition method to improve the accuracy, efficiency, and compliance of the reimbursement process.

[0003] Effective technical solutions are urgently needed to address the above problems. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, and medium for intelligent classification and recognition of invoices, which can achieve intelligent classification and recognition of invoices by integrating self-service reimbursement processes, automatic verification, and automatic classification, thereby improving the reimbursement experience and accuracy.

[0005] This application also provides a method for intelligent classification and recognition of invoices, including the following steps: The person seeking reimbursement fills out an online reimbursement form and undergoes verification. If the verification is successful, a corresponding reimbursement QR code is generated based on the online reimbursement form. Obtain the reimbursement device mode information, identify the reimbursement QR code based on the reimbursement device mode information and scan the reimbursement invoice to obtain the corresponding reimbursement invoice image; The reimbursement receipt image is processed to obtain the receipt category, and key elements are extracted to obtain the receipt elements. Based on the aforementioned bill elements, the authenticity and compliance of the bill are verified to obtain the bill's compliance status. If the invoices are compliant, the amounts of the online expense reports and the expense receipts will be compared. If the amounts are the same, the reimbursement receipt image will be stored and uploaded to the online reimbursement form according to the receipt category.

[0006] Optionally, in the intelligent invoice classification and recognition method described in this application, the person seeking reimbursement fills out an online reimbursement form and verifies it. If it passes, a corresponding reimbursement QR code is generated based on the online reimbursement form, including: The person seeking reimbursement fills out the online reimbursement form according to the preset template and extracts the reimbursement information from the online reimbursement form; The completeness of the reimbursement information is verified. If the verification is successful, the identity information of the person seeking reimbursement and the reimbursement amount are obtained. Based on the identity information of the person seeking reimbursement, the preset reimbursement limit database is queried to obtain the corresponding reimbursement limit. Compare the reimbursement amount with the maximum reimbursement limit; If the amount is less than or equal to the reimbursement limit, a corresponding reimbursement QR code will be generated based on the online reimbursement form. If the amount exceeds the reimbursement limit, the manual approval process will be activated.

[0007] Optionally, in the intelligent classification and recognition method for invoices described in this application, the step of obtaining the reimbursement device mode information, identifying the reimbursement QR code and scanning the reimbursement invoice based on the reimbursement device mode information, and obtaining the corresponding reimbursement invoice image includes: Obtain information on the reimbursement equipment mode, including self-service reimbursement mode or centralized reimbursement mode; The reimbursement QR code is identified and the reimbursement receipt is scanned according to the self-service reimbursement mode or centralized reimbursement mode to obtain the corresponding reimbursement receipt image.

[0008] Optionally, in the intelligent classification and recognition method for invoices described in this application, the step of processing the invoice image to obtain the invoice category and extracting key elements to obtain invoice elements includes: The reimbursement receipt image is input into a preset receipt matching and recognition model for processing to obtain the receipt category, including tax receipts, fiscal receipts, or transportation receipts. Based on the aforementioned bill category, key elements are extracted to obtain bill elements, including the bill entity name, bill entity tax number, bill number, invoice date, and invoice amount.

[0009] Optionally, in the intelligent classification and identification method for guaranteeing the authenticity of invoices described in this application, the step of verifying the authenticity and compliance of invoices based on the invoice elements to obtain the invoice compliance status includes: Obtain the verification date for verifying the authenticity of the invoice, and process it with the invoice issuance date to obtain the time interval; If the time interval is less than or equal to the preset ticket verification interval threshold, the verification is deemed successful and recorded. If the time interval is greater than the preset invoice verification interval threshold, the authenticity of the invoice will be verified through the preset invoice authenticity query platform based on the invoice number, invoice date and invoice amount. If the verification passes, the accuracy of the invoice unit, the duplicate reimbursement of the invoice, and the validity of the invoice issuance time will be verified separately to obtain the verification results of the accuracy of the unit, the duplicate reimbursement of the invoice, and the validity of the time. The accuracy verification result of the unit, the duplicate reimbursement verification result of the invoice, and the time validity verification result are ANDed. If the result passes, the invoice is determined to be compliant. If the result is not passed, the bill's compliance status is determined to be non-compliant.

[0010] Optionally, in the intelligent classification and identification method for invoices described in this application, if the invoice is compliant, the step of comparing the amount of the online reimbursement form with the reimbursement invoice includes: If the invoices are compliant, the invoice amount and the non-invoice amount will be extracted based on the reimbursement amount. The non-reimbursement amounts are removed, and the reimbursement amounts are determined as the actual reimbursement amounts. Sum the invoiced amounts and compare them with the actual reimbursement amount; If the amounts are inconsistent, the manual approval process will be activated.

[0011] Optionally, in the intelligent classification and recognition method for invoices described in this application, before the step of storing the image of the reimbursement invoice and uploading the online reimbursement form according to the invoice category if the amounts are consistent, the method further includes: If the reimbursement device mode information is self-service reimbursement mode, the tax invoices will be classified to obtain ordinary invoices or VAT special invoices. If it is a regular invoice, obtain the cover image of the online reimbursement form; if it exists, complete the reimbursement document exchange. If it does not exist, a cover image will be generated based on the preset template; If it is a VAT special invoice, obtain the deduction slip information and verify it in conjunction with the online reimbursement form; If the association is correct, the reimbursement receipts will be submitted. If the association is incorrect, an alert response will be activated and manual intervention will be required.

[0012] Secondly, this application provides a smart invoice classification and identification guarantee system, which includes: a memory and a processor. The memory includes a program for a smart invoice classification and identification guarantee method. When the program for the smart invoice classification and identification guarantee method is executed by the processor, it performs the following steps: The person seeking reimbursement fills out an online reimbursement form and undergoes verification. If the verification is successful, a corresponding reimbursement QR code is generated based on the online reimbursement form. Obtain the reimbursement device mode information, identify the reimbursement QR code based on the reimbursement device mode information and scan the reimbursement invoice to obtain the corresponding reimbursement invoice image; The reimbursement receipt image is processed to obtain the receipt category, and key elements are extracted to obtain the receipt elements. Based on the aforementioned bill elements, the authenticity and compliance of the bill are verified to obtain the bill's compliance status. If the invoices are compliant, the amounts of the online expense reports and the expense receipts will be compared. If the amounts are the same, the reimbursement receipt image will be stored and uploaded to the online reimbursement form according to the receipt category.

[0013] Optionally, in the intelligent invoice classification and recognition system described in this application, the person seeking reimbursement fills out an online reimbursement form and undergoes verification. If the verification is successful, a corresponding reimbursement QR code is generated based on the online reimbursement form, including: The person seeking reimbursement fills out the online reimbursement form according to the preset template and extracts the reimbursement information from the online reimbursement form; The completeness of the reimbursement information is verified. If the verification is successful, the identity information of the person seeking reimbursement and the reimbursement amount are obtained. Based on the identity information of the person seeking reimbursement, the preset reimbursement limit database is queried to obtain the corresponding reimbursement limit. Compare the reimbursement amount with the maximum reimbursement limit; If the amount is less than or equal to the reimbursement limit, a corresponding reimbursement QR code will be generated based on the online reimbursement form. If the amount exceeds the reimbursement limit, the manual approval process will be activated.

[0014] Thirdly, this application also provides a computer-readable storage medium storing a program for a smart classification and identification guarantee method for invoices, wherein when the program is executed by a processor, it implements the steps of the smart classification and identification guarantee method for invoices as described in any of the preceding claims.

[0015] As can be seen from the above, the intelligent classification and recognition method, system and medium for invoices provided in this application achieve intelligent classification and recognition of invoices by integrating self-service reimbursement process, automatic verification and automatic classification, thereby improving the reimbursement experience and accuracy.

[0016] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a method for intelligent classification and recognition of invoices provided in this application embodiment; Figure 2 A flowchart illustrating the generation of a corresponding reimbursement QR code in a smart invoice classification and recognition method provided in this application embodiment; Figure 3 A flowchart illustrating the process of obtaining corresponding reimbursement invoice images using a smart invoice classification and recognition method provided in this application embodiment; Figure 4 A flowchart illustrating the acquisition of invoice elements in a smart invoice classification and recognition method provided in this application embodiment; Figure 5 This is a high-level flowchart of various embodiments of the methods in this application, which can be used in a smart classification and recognition guarantee method for invoices. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0021] Please refer to Figure 1 , Figure 1 This is a flowchart of a method for intelligent classification and recognition of invoices to ensure security, as described in some embodiments of this application. This method is used in terminal devices, such as computers and mobile terminals. The method includes the following steps: S11. The person seeking reimbursement fills out the online reimbursement form and verifies it. If it passes, a corresponding reimbursement QR code is generated based on the online reimbursement form. S12. Obtain the reimbursement device mode information, identify the reimbursement QR code and scan the reimbursement invoice according to the reimbursement device mode information, and obtain the corresponding reimbursement invoice image. S13. Process the reimbursement receipt image to obtain the receipt category and extract key elements to obtain receipt elements; S14. Verify the authenticity and compliance of the bill based on the bill elements to obtain the bill compliance status. S15. If the invoice is compliant, the amount of the online expense report and the expense report shall be compared. S16. If the amounts are consistent, the reimbursement receipt image is stored according to the receipt type and uploaded to the online reimbursement form.

[0022] It should be noted that, in order to achieve intelligent management and invoice classification throughout the entire reimbursement process, online reimbursement forms are filled out based on preset templates and automatically checked and verified. If problems are found, the location of the problem is indicated and corrections are requested. If no problems are found, a corresponding reimbursement QR code is generated for subsequent identification by reimbursement terminal devices. Reimbursement devices include self-service reimbursement mode and centralized reimbursement mode. Centralized reimbursement mode only requires scanning, verification, classification, and uploading to the system. Self-service reimbursement mode requires further collection and sorting after scanning and verification before uploading to the system. The scanned invoice images are classified and identified, and invoice elements are extracted. Verification is performed based on the invoice elements to determine the compliance status of the invoices. Finally, the amounts are compared. If they match, they can be classified according to the invoice category and uploaded to the system for storage. If they do not match, manual confirmation is required to determine whether the comparison has passed.

[0023] Please refer to Figure 2 , Figure 2This is a flowchart illustrating the generation of a corresponding reimbursement QR code in a method for intelligent classification and recognition of invoices, as described in some embodiments of this application. According to an embodiment of the present invention, the person seeking reimbursement fills out an online reimbursement form and undergoes verification. If the verification is successful, a corresponding reimbursement QR code is generated based on the online reimbursement form, including: S21. The person seeking reimbursement fills out the online reimbursement form according to the preset template and extracts the reimbursement information from the online reimbursement form. S22. Perform an integrity check on the reimbursement element information. If the check passes, obtain the identity information of the person seeking reimbursement and the reimbursement amount. S23. Query the preset reimbursement limit database based on the identity information of the person seeking reimbursement to obtain the corresponding reimbursement limit. S24. Compare the reimbursement amount with the reimbursement limit; S25. If the amount is less than or equal to the reimbursement limit, a corresponding reimbursement QR code will be generated based on the online reimbursement form. S26. If the amount exceeds the reimbursement limit, the manual approval process will be activated.

[0024] It should be noted that, in order to reduce the workload of manually filling out expense reports and simplify self-review, the online expense report is filled out by the claimant according to a preset template. The online expense report extracts the expense information that needs to be verified, such as the reason for reimbursement, the date of reimbursement, and the amount of reimbursement. At the same time, a completeness check is performed. If any item is missing, an alert is issued and the missing item is sent to the claimant for supplementation. If the completeness check passes, the preset reimbursement limit database is queried based on the claimant's identity information to obtain the corresponding reimbursement limit. This limit is then compared with the reimbursement amount to determine if there is an over-limit. If there is an over-limit, manual confirmation is required for approval. If there is no over-limit, a reimbursement QR code corresponding to the online expense report is generated for identification by the reimbursement terminal device.

[0025] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the process of obtaining corresponding reimbursement receipt images using a smart invoice classification and recognition method according to some embodiments of this application. According to an embodiment of the present invention, obtaining reimbursement device mode information, identifying the reimbursement QR code based on the reimbursement device mode information, and scanning the reimbursement receipt to obtain the corresponding reimbursement receipt image includes: S31. Obtain information on the reimbursement equipment mode, including self-service reimbursement mode or centralized reimbursement mode; S32. Identify the reimbursement QR code and scan the reimbursement receipt according to the self-service reimbursement mode or centralized reimbursement mode to obtain the corresponding reimbursement receipt image.

[0026] It should be noted that, in order to accommodate different reimbursement needs, a self-service reimbursement mode or a centralized reimbursement mode is set up. The self-service reimbursement mode realizes the entire process of scanning, verification, delivery and sorting, and is suitable for single person reimbursement of small batches. The centralized reimbursement mode realizes scanning and verification processing, and is suitable for large batches of reimbursement at the same time.

[0027] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the process of obtaining invoice elements in a method for intelligent classification and recognition of invoices according to some embodiments of this application. According to an embodiment of the present invention, the step of processing the invoice image to obtain the invoice category and extracting key elements to obtain invoice elements includes: S41. Input the reimbursement receipt image into a preset receipt matching and recognition model for processing to obtain the receipt category, including tax receipts, fiscal receipts, or transportation receipts. S42. Extract key elements according to the bill category to obtain bill elements, including the name of the bill entity, the tax number of the bill entity, the bill number, the bill date, and the bill amount.

[0028] It should be noted that, in order to facilitate the classification, storage and verification of the authenticity of the receipts, the images of the reimbursement receipts are first input into a preset receipt matching and recognition model for processing to obtain the receipt category. The preset receipt matching and recognition model is trained by those skilled in the art by acquiring a large number of historical receipt samples and corresponding receipt category divisions into training sets, test sets and verification sets. Then, the receipt elements are extracted separately for verification of authenticity and comparison of amounts.

[0029] According to an embodiment of the present invention, the step of verifying the authenticity and compliance of the negotiable instrument based on the negotiable instrument elements to obtain the compliance status of the negotiable instrument includes: Obtain the verification date for verifying the authenticity of the invoice, and process it with the invoice issuance date to obtain the time interval; If the time interval is less than or equal to the preset ticket verification interval threshold, the verification is deemed successful and recorded. If the time interval is greater than the preset invoice verification interval threshold, the authenticity of the invoice will be verified through the preset invoice authenticity query platform based on the invoice number, invoice date and invoice amount. If the verification passes, the accuracy of the invoice unit, the duplicate reimbursement of the invoice, and the validity of the invoice issuance time will be verified separately to obtain the verification results of the accuracy of the unit, the duplicate reimbursement of the invoice, and the validity of the time. The accuracy verification result of the unit, the duplicate reimbursement verification result of the invoice, and the time validity verification result are ANDed. If the result passes, the invoice is determined to be compliant. If the result is not passed, the bill's compliance status is determined to be non-compliant.

[0030] It should be noted that before verifying the authenticity of the invoice, the verification date and the invoice issuance date are compared to determine whether the invoice is a newly issued invoice. For newly issued invoices, due to the delay in the invoice authenticity verification platform, the verification is confirmed to be successful first and recorded, and then verified separately later. If it is not a newly issued invoice, the authenticity of the invoice is verified through the preset invoice authenticity verification platform based on the invoice number, invoice issuance date, and invoice amount. After the authenticity verification is successful, compliance verification is performed, including the accuracy of the invoice unit, duplicate reimbursement of the invoice, and validity of the invoice issuance time. If all of these are successful, the invoice is deemed compliant; if any one of them fails, the invoice is deemed non-compliant. This improves the efficiency and accuracy of invoice review.

[0031] According to an embodiment of the present invention, if the invoice is compliant, comparing the amount of the online expense report with the expense invoice includes: If the invoices are compliant, the invoice amount and the non-invoice amount will be extracted based on the reimbursement amount. The non-reimbursement amounts are removed, and the reimbursement amounts are determined as the actual reimbursement amounts. Sum the invoiced amounts and compare them with the actual reimbursement amount; If the amounts are inconsistent, the manual approval process will be activated.

[0032] It should be noted that after the authenticity and compliance verification is passed, in order to determine whether the reimbursement amount is accurate, the reimbursement amount filled in by the person seeking reimbursement is first divided into the amount with receipts and the amount without receipts. The amount without receipts, such as living allowance, is a daily fixed amount and does not require receipts. The amount without receipts is excluded, and the amount with receipts is the actual reimbursement amount. It is used to compare with the sum of the invoice amounts of multiple receipts. If they are inconsistent, manual approval is allowed to confirm whether the amount comparison is successful.

[0033] According to an embodiment of the present invention, if the amounts are consistent, the method of storing the reimbursement receipt image according to the receipt type and uploading the online reimbursement form further includes: If the reimbursement device mode information is self-service reimbursement mode, the tax invoices will be classified to obtain ordinary invoices or VAT special invoices. If it is a regular invoice, obtain the cover image of the online reimbursement form; if it exists, complete the reimbursement document exchange. If it does not exist, a cover image will be generated based on the preset template; If it is a VAT special invoice, obtain the deduction slip information and verify it in conjunction with the online reimbursement form; If the association is correct, the reimbursement receipts will be submitted. If the association is incorrect, an alert response will be activated and manual intervention will be required.

[0034] It should be noted that in the centralized reimbursement mode, after scanning and verification, the invoice images are uploaded to the system according to the invoice category. However, the self-service reimbursement mode requires further processing of receipt and sorting. First, tax invoices are divided into general invoices or VAT special invoices. For general invoices, it is only necessary to confirm whether the person seeking reimbursement has submitted a reimbursement form cover. The reimbursement form cover is set by a person skilled in the art according to specific reimbursement needs and is used to fill in the main reimbursement items. If it exists and is on top of the invoice, the receipt is confirmed to be complete. If it does not exist, a cover image is generated according to a preset template and printed to avoid repetitive operations by the person seeking reimbursement. VAT special invoices include deduction copies. The deduction copies are sorted first and used for association verification with the online reimbursement form. If the association is correct, the receipt is completed. If the association is incorrect, an alarm response is activated and manual processing is required.

[0035] Please refer to Figure 5 , Figure 5 This is a high-level flowchart of various embodiments of the methods in this application, which can be used in a smart classification and recognition method for invoices. According to an embodiment of the invention, for example, in S57, the online expense report is compared with the expense invoice to determine if the expense amount is accurate. If the amounts do not match, S571 is executed, i.e., manual approval processing is activated to determine whether the expense is allowed. If the amounts match, different reimbursement modes are executed for delivery and sorting, or the invoice image is directly stored according to the invoice category and uploaded to the online expense report.

[0036] It is worth mentioning that, according to embodiments of the present invention, it further includes: Obtain the attachment type information uploaded by the person submitting the expense claim; Query the preset attachment type database according to the invoice category to obtain the corresponding required attachment type information; The attachment type information uploaded by the person seeking reimbursement is verified based on the required attachment type information; If the verification fails, the manual approval process will be activated.

[0037] It should be noted that when applying for reimbursement, in addition to receipts, corresponding attachments are generally required, such as meeting notices, to support the legitimacy of the reimbursement. Therefore, in addition to verifying the receipts, it is also necessary to further determine whether the attachments are complete. If the attachments are missing, the manual approval process will be activated to determine whether the approval is allowed.

[0038] It is worth mentioning that, according to embodiments of the present invention, it further includes: Obtain information on the business type and tax rate for the invoice; The tax rate to be invoiced is obtained by querying the preset invoicing tax rate database. The tax rate to be invoiced is compared with the tax rate invoiced. If they are the same, the tax rate is determined to be accurate.

[0039] It should be noted that different industries and businesses have different applicable tax rates. For example, the tax rate for small-scale taxpayers is 3%, but the current tax rate for additional revenue is 1%. It is necessary to check whether the tax rate on the invoice is accurate to prevent errors in the tax rate and tax amount even if the invoice amount is accurate.

[0040] This invention also discloses a smart invoice classification and identification guarantee system, including a memory and a processor. The memory includes a smart invoice classification and identification guarantee method program, which, when executed by the processor, performs the following steps: The person seeking reimbursement fills out an online reimbursement form and undergoes verification. If the verification is successful, a corresponding reimbursement QR code is generated based on the online reimbursement form. Obtain the reimbursement device mode information, identify the reimbursement QR code based on the reimbursement device mode information and scan the reimbursement invoice to obtain the corresponding reimbursement invoice image; The reimbursement receipt image is processed to obtain the receipt category, and key elements are extracted to obtain the receipt elements. Based on the aforementioned bill elements, the authenticity and compliance of the bill are verified to obtain the bill's compliance status. If the invoices are compliant, the amounts of the online expense reports and the expense receipts will be compared. If the amounts are the same, the reimbursement receipt image will be stored and uploaded to the online reimbursement form according to the receipt category.

[0041] It should be noted that, in order to achieve intelligent management and invoice classification throughout the entire reimbursement process, online reimbursement forms are filled out based on preset templates and automatically checked and verified. If problems are found, the location of the problem is indicated and corrections are requested. If no problems are found, a corresponding reimbursement QR code is generated for subsequent identification by reimbursement terminal devices. Reimbursement devices include self-service reimbursement mode and centralized reimbursement mode. Centralized reimbursement mode only requires scanning, verification, classification, and uploading to the system. Self-service reimbursement mode requires further collection and sorting after scanning and verification before uploading to the system. The scanned invoice images are classified and identified, and invoice elements are extracted. Verification is performed based on the invoice elements to determine the compliance status of the invoices. Finally, the amounts are compared. If they match, they can be classified according to the invoice category and uploaded to the system for storage. If they do not match, manual confirmation is required to determine whether the comparison has passed.

[0042] According to an embodiment of the present invention, the person seeking reimbursement fills out an online reimbursement form and performs verification. If the verification is successful, a corresponding reimbursement QR code is generated based on the online reimbursement form, including: The person seeking reimbursement fills out the online reimbursement form according to the preset template and extracts the reimbursement information from the online reimbursement form; The completeness of the reimbursement information is verified. If the verification is successful, the identity information of the person seeking reimbursement and the reimbursement amount are obtained. Based on the identity information of the person seeking reimbursement, the preset reimbursement limit database is queried to obtain the corresponding reimbursement limit. Compare the reimbursement amount with the maximum reimbursement limit; If the amount is less than or equal to the reimbursement limit, a corresponding reimbursement QR code will be generated based on the online reimbursement form. If the amount exceeds the reimbursement limit, the manual approval process will be activated.

[0043] It should be noted that, in order to reduce the workload of manually filling out expense reports and simplify self-review, the online expense report is filled out by the claimant according to a preset template. The online expense report extracts the expense information that needs to be verified, such as the reason for reimbursement, the date of reimbursement, and the amount of reimbursement. At the same time, a completeness check is performed. If any item is missing, an alert is issued and the missing item is sent to the claimant for supplementation. If the completeness check passes, the preset reimbursement limit database is queried based on the claimant's identity information to obtain the corresponding reimbursement limit. This limit is then compared with the reimbursement amount to determine if there is an over-limit. If there is an over-limit, manual confirmation is required for approval. If there is no over-limit, a reimbursement QR code corresponding to the online expense report is generated for identification by the reimbursement terminal device.

[0044] According to an embodiment of the present invention, the step of obtaining reimbursement device mode information, identifying the reimbursement QR code and scanning the reimbursement receipt based on the reimbursement device mode information, and obtaining the corresponding reimbursement receipt image includes: Obtain information on the reimbursement equipment mode, including self-service reimbursement mode or centralized reimbursement mode; The reimbursement QR code is identified and the reimbursement receipt is scanned according to the self-service reimbursement mode or centralized reimbursement mode to obtain the corresponding reimbursement receipt image.

[0045] It should be noted that, in order to accommodate different reimbursement needs, a self-service reimbursement mode or a centralized reimbursement mode is set up. The self-service reimbursement mode realizes the entire process of scanning, verification, delivery and sorting, and is suitable for single person reimbursement of small batches. The centralized reimbursement mode realizes scanning and verification processing, and is suitable for large batches of reimbursement at the same time.

[0046] According to an embodiment of the present invention, the step of processing the reimbursement receipt image to obtain the receipt category and extracting key elements to obtain receipt elements includes: The reimbursement receipt image is input into a preset receipt matching and recognition model for processing to obtain the receipt category, including tax receipts, fiscal receipts, or transportation receipts. Based on the aforementioned bill category, key elements are extracted to obtain bill elements, including the bill entity name, bill entity tax number, bill number, invoice date, and invoice amount.

[0047] It should be noted that, in order to facilitate the classification, storage and verification of the authenticity of the receipts, the images of the reimbursement receipts are first input into a preset receipt matching and recognition model for processing to obtain the receipt category. The preset receipt matching and recognition model is trained by those skilled in the art by acquiring a large number of historical receipt samples and corresponding receipt category divisions into training sets, test sets and verification sets. Then, the receipt elements are extracted separately for verification of authenticity and comparison of amounts.

[0048] According to an embodiment of the present invention, the step of verifying the authenticity and compliance of the negotiable instrument based on the negotiable instrument elements to obtain the compliance status of the negotiable instrument includes: Obtain the verification date for verifying the authenticity of the invoice, and process it with the invoice issuance date to obtain the time interval; If the time interval is less than or equal to the preset ticket verification interval threshold, the verification is deemed successful and recorded. If the time interval is greater than the preset invoice verification interval threshold, the authenticity of the invoice will be verified through the preset invoice authenticity query platform based on the invoice number, invoice date and invoice amount. If the verification passes, the accuracy of the invoice unit, the duplicate reimbursement of the invoice, and the validity of the invoice issuance time will be verified separately to obtain the verification results of the accuracy of the unit, the duplicate reimbursement of the invoice, and the validity of the time. The accuracy verification result of the unit, the duplicate reimbursement verification result of the invoice, and the time validity verification result are ANDed. If the result passes, the invoice is determined to be compliant. If the result is not passed, the bill's compliance status is determined to be non-compliant.

[0049] It should be noted that before verifying the authenticity of the invoice, the verification date and the invoice issuance date are compared to determine whether the invoice is a newly issued invoice. For newly issued invoices, due to the delay in the invoice authenticity verification platform, the verification is confirmed to be successful first and recorded, and then verified separately later. If it is not a newly issued invoice, the authenticity of the invoice is verified through the preset invoice authenticity verification platform based on the invoice number, invoice issuance date, and invoice amount. After the authenticity verification is successful, compliance verification is performed, including the accuracy of the invoice unit, duplicate reimbursement of the invoice, and validity of the invoice issuance time. If all of these are successful, the invoice is deemed compliant; if any one of them fails, the invoice is deemed non-compliant. This improves the efficiency and accuracy of invoice review.

[0050] According to an embodiment of the present invention, if the invoice is compliant, comparing the amount of the online expense report with the expense invoice includes: If the invoices are compliant, the invoice amount and the non-invoice amount will be extracted based on the reimbursement amount. The non-reimbursement amounts are removed, and the reimbursement amounts are determined as the actual reimbursement amounts. Sum the invoiced amounts and compare them with the actual reimbursement amount; If the amounts are inconsistent, the manual approval process will be activated.

[0051] It should be noted that after the authenticity and compliance verification is passed, in order to determine whether the reimbursement amount is accurate, the reimbursement amount filled in by the person seeking reimbursement is first divided into the amount with receipts and the amount without receipts. The amount without receipts, such as living allowance, is a daily fixed amount and does not require receipts. The amount without receipts is excluded, and the amount with receipts is the actual reimbursement amount. It is used to compare with the sum of the invoice amounts of multiple receipts. If they are inconsistent, manual approval is allowed to confirm whether the amount comparison is successful.

[0052] According to an embodiment of the present invention, if the amounts are consistent, the method of storing the reimbursement receipt image according to the receipt type and uploading the online reimbursement form further includes: If the reimbursement device mode information is self-service reimbursement mode, the tax invoices will be classified to obtain ordinary invoices or VAT special invoices. If it is a regular invoice, obtain the cover image of the online reimbursement form; if it exists, complete the reimbursement document exchange. If it does not exist, a cover image will be generated based on the preset template; If it is a VAT special invoice, obtain the deduction slip information and verify it in conjunction with the online reimbursement form; If the association is correct, the reimbursement receipts will be submitted. If the association is incorrect, an alert response will be activated and manual intervention will be required.

[0053] It should be noted that in the centralized reimbursement mode, after scanning and verification, the invoice images are uploaded to the system according to the invoice category. However, the self-service reimbursement mode requires further processing of receipt and sorting. First, tax invoices are divided into general invoices or VAT special invoices. For general invoices, it is only necessary to confirm whether the person seeking reimbursement has submitted a reimbursement form cover. The reimbursement form cover is set by a person skilled in the art according to specific reimbursement needs and is used to fill in the main reimbursement items. If it exists and is on top of the invoice, the receipt is confirmed to be complete. If it does not exist, a cover image is generated according to a preset template and printed to avoid repetitive operations by the person seeking reimbursement. VAT special invoices include deduction copies. The deduction copies are sorted first and used for association verification with the online reimbursement form. If the association is correct, the receipt is completed. If the association is incorrect, an alarm response is activated and manual processing is required.

[0054] According to an embodiment of the present invention, for example, in S57, the online expense report is compared with the expense receipt to determine whether the expense amount is accurate. If the amounts are inconsistent, S571 is executed, that is, manual approval processing is activated to determine whether the expense is allowed. If the amounts are consistent, the delivery and sorting of different expense reporting modes are executed or the receipt image is stored directly according to the receipt category and uploaded to the online expense report.

[0055] It is worth mentioning that, according to embodiments of the present invention, it further includes: Obtain the attachment type information uploaded by the person submitting the expense claim; Query the preset attachment type database according to the invoice category to obtain the corresponding required attachment type information; The attachment type information uploaded by the person seeking reimbursement is verified based on the required attachment type information; If the verification fails, the manual approval process will be activated.

[0056] It should be noted that when applying for reimbursement, in addition to receipts, corresponding attachments are generally required, such as meeting notices, to support the legitimacy of the reimbursement. Therefore, in addition to verifying the receipts, it is also necessary to further determine whether the attachments are complete. If the attachments are missing, the manual approval process will be activated to determine whether the approval is allowed.

[0057] It is worth mentioning that, according to embodiments of the present invention, it further includes: Obtain information on the business type and tax rate for the invoice; The tax rate to be invoiced is obtained by querying the preset invoicing tax rate database. The tax rate to be invoiced is compared with the tax rate invoiced. If they are the same, the tax rate is determined to be accurate.

[0058] It should be noted that different industries and businesses have different applicable tax rates. For example, the tax rate for small-scale taxpayers is 3%, but the current tax rate for additional revenue is 1%. It is necessary to check whether the tax rate on the invoice is accurate to prevent errors in the tax rate and tax amount even if the invoice amount is accurate.

[0059] A third aspect of the present invention provides a readable storage medium storing a program for a smart classification and identification guarantee method for invoices, wherein when the program is executed by a processor, it implements the steps of the smart classification and identification guarantee method for invoices as described in any of the preceding claims.

[0060] This invention discloses a method, system, and medium for intelligent classification and recognition of invoices. By integrating self-service reimbursement processes, automatic verification, and automatic classification, it achieves intelligent classification and recognition of invoices, thereby improving the reimbursement experience and accuracy.

[0061] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0062] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0063] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0064] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0065] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for intelligent classification and recognition of invoices, characterized in that, Includes the following steps: The person seeking reimbursement fills out an online reimbursement form and undergoes verification. If the form is verified, a corresponding reimbursement QR code is generated based on the online reimbursement form. Obtain the reimbursement device mode information, identify the reimbursement QR code based on the reimbursement device mode information and scan the reimbursement invoice to obtain the corresponding reimbursement invoice image; The reimbursement receipt image is processed to obtain the receipt category, and key elements are extracted to obtain the receipt elements. Based on the aforementioned bill elements, the authenticity and compliance of the bill are verified to obtain the bill's compliance status. If the invoices are compliant, the amounts of the online expense reports and the expense receipts will be compared. If the amounts are the same, the reimbursement receipt image will be stored according to the receipt category and uploaded to the online reimbursement form.

2. The intelligent classification and recognition method for invoices according to claim 1, characterized in that, The person submitting the expense report fills out an online expense report form and undergoes verification. If the verification is successful, a corresponding expense reimbursement QR code is generated based on the online expense report form, including: The person seeking reimbursement fills out the online reimbursement form according to the preset template and extracts the reimbursement information from the online reimbursement form; The completeness of the reimbursement information is verified. If the verification is successful, the identity information of the person seeking reimbursement and the reimbursement amount are obtained. Based on the identity information of the person seeking reimbursement, the preset reimbursement limit database is queried to obtain the corresponding reimbursement limit. Compare the reimbursement amount with the maximum reimbursement limit; If the amount is less than or equal to the reimbursement limit, a corresponding reimbursement QR code will be generated based on the online reimbursement form. If the amount exceeds the reimbursement limit, the manual approval process will be activated.

3. The intelligent classification and recognition method for invoices according to claim 2, characterized in that, The process of obtaining the reimbursement device mode information, identifying the reimbursement QR code based on the reimbursement device mode information, and scanning the reimbursement receipt to obtain the corresponding reimbursement receipt image includes: Obtain information on the reimbursement equipment mode, including self-service reimbursement mode or centralized reimbursement mode; The reimbursement QR code is identified and the reimbursement receipt is scanned according to the self-service reimbursement mode or centralized reimbursement mode to obtain the corresponding reimbursement receipt image.

4. The intelligent classification and recognition method for invoices according to claim 3, characterized in that, The process involves processing the reimbursement receipt image to obtain the receipt category and extracting key elements to obtain receipt elements, including: The reimbursement receipt image is input into a preset receipt matching and recognition model for processing to obtain the receipt category, including tax receipts, fiscal receipts, or transportation receipts. Based on the aforementioned bill category, key elements are extracted to obtain bill elements, including the bill entity name, bill entity tax number, bill number, invoice date, and invoice amount.

5. The intelligent classification and recognition method for invoices according to claim 4, characterized in that, The step of verifying the authenticity and compliance of the negotiable instrument based on its elements to obtain its compliance status includes: Obtain the verification date for verifying the authenticity of the invoice, and process it with the invoice issuance date to obtain the time interval; If the time interval is less than or equal to the preset ticket verification interval threshold, the verification is deemed successful and recorded. If the time interval is greater than the preset invoice verification interval threshold, the authenticity of the invoice will be verified through the preset invoice authenticity query platform based on the invoice number, invoice date and invoice amount. If the verification passes, the accuracy of the invoice unit, the duplicate reimbursement of the invoice, and the validity of the invoice issuance time will be verified separately to obtain the verification results of the accuracy of the unit, the duplicate reimbursement of the invoice, and the validity of the time. The accuracy verification result of the unit, the duplicate reimbursement verification result of the invoice, and the time validity verification result are ANDed. If the result passes, the invoice is determined to be compliant. If the result is not passed, the bill's compliance status is determined to be non-compliant.

6. The intelligent classification and recognition method for invoices according to claim 5, characterized in that, If the invoices are compliant, the online expense report will be compared with the expense invoices in terms of amount, including: If the invoices are compliant, the invoice amount and the non-invoice amount will be extracted based on the reimbursement amount. The non-reimbursement amounts are removed, and the reimbursement amounts are determined as the actual reimbursement amounts. Sum the invoiced amounts and compare them with the actual reimbursement amount; If the amounts are inconsistent, the manual approval process will be activated.

7. The intelligent classification and recognition method for invoices according to claim 6, characterized in that, If the amounts are consistent, the reimbursement receipt image is stored according to the receipt type and uploaded to the online reimbursement form. This also includes: If the reimbursement device mode information is self-service reimbursement mode, the tax invoices will be classified to obtain ordinary invoices or VAT special invoices. If it is a regular invoice, obtain the cover image of the online reimbursement form; if it exists, complete the reimbursement document exchange. If it does not exist, a cover image will be generated based on the preset template; If it is a VAT special invoice, obtain the deduction slip information and verify it in conjunction with the online reimbursement form; If the association is correct, the reimbursement receipts will be submitted. If the association is incorrect, an alert response will be activated and manual intervention will be required.

8. A smart classification and recognition system for invoices, characterized in that, The system includes a memory and a processor. The memory contains a program for a smart invoice classification and recognition guarantee method. When the program is executed by the processor, the smart invoice classification and recognition guarantee method performs the following steps: The person seeking reimbursement fills out an online reimbursement form and undergoes verification. If the form is verified, a corresponding reimbursement QR code is generated based on the online reimbursement form. Obtain the reimbursement device mode information, identify the reimbursement QR code based on the reimbursement device mode information and scan the reimbursement invoice to obtain the corresponding reimbursement invoice image; The reimbursement receipt image is processed to obtain the receipt category, and key elements are extracted to obtain the receipt elements. Based on the aforementioned bill elements, the authenticity and compliance of the bill are verified to obtain the bill's compliance status. If the invoice is compliant, the amount of the online expense report will be compared with that of the expense report. If the amounts are the same, the reimbursement receipt image will be stored according to the receipt category and uploaded to the online reimbursement form.

9. The intelligent classification and recognition system for invoices according to claim 8, characterized in that, The person submitting the expense report fills out an online expense report form and undergoes verification. If the verification is successful, a corresponding expense reimbursement QR code is generated based on the online expense report form, including: The person seeking reimbursement fills out the online reimbursement form according to the preset template and extracts the reimbursement information from the online reimbursement form; The completeness of the reimbursement information is verified. If the verification is successful, the identity information of the person seeking reimbursement and the reimbursement amount are obtained. Based on the identity information of the person seeking reimbursement, the preset reimbursement limit database is queried to obtain the corresponding reimbursement limit. Compare the reimbursement amount with the maximum reimbursement limit; If the amount is less than or equal to the reimbursement limit, a corresponding reimbursement QR code will be generated based on the online reimbursement form. If the amount exceeds the reimbursement limit, the manual approval process will be activated.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for a smart classification and identification guarantee method for invoices. When the program is executed by a processor, it implements the steps of a smart classification and identification guarantee method for invoices as described in any one of claims 1 to 7.

Images