Electronic storage method and device for paper invoices
By collecting and identifying paper invoices, generating electronic invoices and encoding and storing them, the loss, damage and complexity problems in paper invoice management are solved, and efficient electronic invoice management and query are achieved.
Patent Information
- Application Number
- CN202510021604.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-07
- Publication Date
- 2025-05-06
AI Technical Summary
In the prior art, the management of paper invoices has problems such as loss, damage and complex tax rate adjustment, resulting in financial leasing companies facing complexity and inefficiency in quotation calculation, collection write-off and tax management.
The image of paper invoices is obtained through the collection equipment, pre-processing and identification detection, output seal information and invoice content information, and encode the electronic invoices based on the invoice content information and store them in the invoice library.
It realizes efficient electronic storage of paper invoices, removes non-compliant and invalid invoices, and sets up a separate and unique encoding for each electronic invoice, which facilitates query and management, and improves the storage volume and management efficiency of invoices.
Smart Images
Figure CN119942578A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of invoice management, and in particular to a method and device for electronically storing paper invoices. Background Art
[0002] As a special financing method, financial leasing combines the characteristics of financing and leasing, providing enterprises with flexible asset management and fund-raising channels. With the development of the economy and the continuous improvement of tax laws, the financial leasing industry is facing the challenge of diversified tax rates. On the one hand, with the continuous enrichment of financial leasing equipment and the more diversified industry markets involved, various markets will advocate the issuance of invoices with different tax rates to improve competitiveness; on the other hand, the financial leasing business scenarios are complex, and there are many uncertainties in the management before, during and after the lease, and tax rates and tax amounts will be adjusted frequently. These have brought complexity to the quotation calculation, collection verification, tax management and other links of financial leasing companies, and also generated a large number of invoices.
[0003] Currently, a large number of invoices are mainly in paper form. It is rather troublesome for staff to organize, store or find invoices, and they are prone to loss or damage. Therefore, it is necessary for the development of the industry to store paper invoices in an electronic way. To this end, an electronic storage method and device for paper invoices are proposed. Summary of the invention
[0004] The purpose of the present invention is to solve the problems in the prior art and to propose an electronic storage method and device for paper invoices.
[0005] A method and device for electronic storage of paper invoices, comprising the following steps:
[0006] S1. Using a collection device to obtain an image of a paper invoice, and pre-processing the image to obtain an electronic invoice;
[0007] S2, input the electronic invoice into the recognition detection model for recognition detection, and output the seal information;
[0008] S3, input the electronic invoice into the content extraction model, and output the invoice content information;
[0009] S4. Encode the electronic invoice according to the invoice content information, and store the code and the corresponding electronic invoice in the invoice library.
[0010] Preferably, in step S1, preprocessing the image to obtain the electronic invoice includes the following steps:
[0011] a. Crop the image to keep only the invoice part;
[0012] b. Perform denoising on the image.
[0013] Preferably, in step S2, identifying and detecting the model to process the electronic invoice includes the following steps:
[0014] a. Identify the status of the machine-printed content on the electronic invoice and determine whether the machine-printed content is altered, blurred or blocked. If so, determine that the electronic invoice is an abnormal invoice, output abnormal information, and cancel the subsequent input of the electronic invoice; if not, proceed to the next step;
[0015] b. Identify the face status of the electronic invoice and determine the invoice damage coefficient according to the following formula:
[0016]
[0017] Among them, Q represents the invoice damage coefficient, S 0 represents the damaged area on the electronic invoice, S represents the original area of the electronic invoice, and A i represents the length of the i-th fold on the electronic invoice, n represents the number of folds on the electronic invoice, and α and β represent weight coefficients;
[0018] When the invoice damage coefficient Q is greater than or equal to the set damage threshold, the electronic invoice is judged to be an abnormal invoice, abnormal information is output, and the subsequent input of the electronic invoice is cancelled;
[0019] When the invoice damage coefficient Q is less than or equal to the set damage threshold, the electronic invoice is judged to be a normal invoice and the next step is carried out;
[0020] c. Extract the seal on the electronic invoice and identify whether the seal is complete. If so, proceed to the next step; if not, determine that the electronic invoice is an abnormal invoice, output abnormal information, and cancel the subsequent input of the electronic invoice;
[0021] d. Compare the extracted seal with the seals of all electronic invoices in the invoice database. If the extracted seal is the same as the seal of the electronic invoice in the invoice database, the seal information will be output through detection; otherwise, manual intervention will be performed to determine whether the extracted seal is correct. If it is correct, the seal information will be output through detection; if it is incorrect, the electronic invoice is judged to be an abnormal invoice, the abnormal information will be output, and the subsequent input of the electronic invoice will be cancelled.
[0022] Preferably, in step S3, the content extraction model processes the electronic invoice including the following steps:
[0023] a. Extract the invoice code on the electronic invoice and output it;
[0024] b. Extract the invoice number on the electronic invoice and output it;
[0025] c. Extract the taxpayer identification number on the electronic invoice and output it.
[0026] Preferably, in step S4, the corresponding code of the electronic invoice is composed of the invoice code, invoice number and taxpayer identification number on the electronic invoice, and the code is composed of 40 digits and letters, the first 12 digits of the code are filled with the invoice code, the middle 8 digits of the code are filled with the invoice number, and the last 20 digits of the code are filled with the taxpayer identification number.
[0027] Preferably, the invoice database stores not only the electronic invoices that have passed the identification test and the corresponding codes, but also the seal information of the electronic invoices.
[0028] An electronic storage device for paper invoices, comprising:
[0029] A collection device for collecting images of paper invoices;
[0030] An image processing module, used for pre-processing the image to obtain an electronic invoice;
[0031] The recognition and detection module is used to input the electronic invoice into the recognition and detection model for recognition and detection;
[0032] A content extraction module, used to input the electronic invoice into the content extraction model and output the invoice content information;
[0033] The coding generation module is used to encode the electronic invoice.
[0034] Preferably, it also includes:
[0035] The invoice database is used to store the electronic invoices that have passed the identification test and the corresponding codes and seal information.
[0036] Compared with the prior art, the present invention has the following advantages:
[0037] The storage method of the present invention can efficiently convert paper invoices into electronic invoices for storage. At the same time, the electronic invoices are identified and detected before storage, and abnormal invoices such as non-compliant and invalid invoices are removed. A separate and unique code is established for each electronic invoice, which not only facilitates subsequent inquiries, but also increases the storage capacity of invoices. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION
[0039] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.
[0040] Reference Figure 1 As shown, a method for electronic storage of paper invoices includes the following steps:
[0041] S1. Using a collection device to obtain an image of a paper invoice, and pre-processing the image to obtain an electronic invoice;
[0042] S2, input the electronic invoice into the recognition detection model for recognition detection, and output the seal information;
[0043] S3, input the electronic invoice into the content extraction model, and output the invoice content information;
[0044] S4. Encode the electronic invoice according to the invoice content information, and store the code and the corresponding electronic invoice in the invoice library.
[0045] In step S1, preprocessing the image to obtain the electronic invoice includes the following steps:
[0046] a. Crop the image to keep only the invoice part. The captured image will have a background. Crop and remove this background to avoid errors in subsequent electronic invoice recognition.
[0047] b. Perform denoising on the image. Since images are usually acquired through scanning or photographing, in addition to being generated electronically, they inevitably contain certain noise, such as blur, shadow, etc. Therefore, the image filtering method in image processing technology can be used to denoise the invoice image.
[0048] In step S2, the identification and detection model processing of electronic invoices includes the following steps:
[0049] a. Identify the status of the machine-printed content on the electronic invoice and determine whether the machine-printed content is altered, blurred or blocked. If so, determine that the electronic invoice is an abnormal invoice, output abnormal information, and cancel the subsequent input of the electronic invoice; if not, proceed to the next step;
[0050] If there is any erasure, blurring or obstruction of key information in the machine-printed content of the invoice, the invoice will be invalid. These invoices that do not comply with regulations shall not be used as financial reimbursement vouchers, and any unit or individual has the right to refuse to accept them. Therefore, invoices need to be identified and abnormal invoices removed before electronic invoices are stored.
[0051] b. Identify the face status of the electronic invoice and determine the invoice damage coefficient according to the following formula:
[0052]
[0053] Among them, Q represents the invoice damage coefficient, S 0 represents the damaged area on the electronic invoice, S represents the original area of the electronic invoice, and A irepresents the length of the i-th fold on the electronic invoice, n represents the number of folds on the electronic invoice, α and β represent weight coefficients; among them, the weight coefficient of α is larger, indicating that the damage on the face of the invoice has a greater impact on the invoice damage coefficient of the electronic invoice, and the damaged area S on the electronic invoice 0 Includes the area occupied by missing corners and holes.
[0054] When the invoice damage coefficient Q is greater than or equal to the set damage threshold, the electronic invoice is judged to be an abnormal invoice, abnormal information is output, and the subsequent input of the electronic invoice is cancelled;
[0055] When the invoice damage coefficient Q is less than or equal to the set damage threshold, the electronic invoice is judged to be a normal invoice and the next step is carried out;
[0056] The formula is used to determine the invoice damage coefficient Q of the electronic invoice. When the Q value is too large, it indicates that the original paper invoice of the electronic invoice is seriously damaged. For invoices with too large a damaged area or too many creases, although they are not unsightly, they need to be reissued, so they are not encoded and stored in the invoice database.
[0057] c. Extract the seal on the electronic invoice and identify whether the seal is complete. If so, proceed to the next step; if not, determine that the electronic invoice is an abnormal invoice, output abnormal information, and cancel the subsequent input of the electronic invoice;
[0058] d. Compare the extracted seal with the seals of all electronic invoices in the invoice database. If the extracted seal is the same as the seal of the electronic invoice in the invoice database, the seal information will be output through detection; otherwise, manual intervention will be performed to determine whether the extracted seal is correct. If it is correct, the seal information will be output through detection; if it is incorrect, the electronic invoice is judged to be an abnormal invoice, the abnormal information will be output, and the subsequent input of the electronic invoice will be cancelled.
[0059] The seals on invoices used by enterprises are mostly commonly used seals, that is, they have been used before. If an unused seal is detected after comparison, it is necessary to determine whether it is a fake seal. Financial personnel are required to confirm the seal to avoid the storage of fake invoices.
[0060] In step S3, the content extraction model processes the electronic invoice including the following steps:
[0061] a. Extract the invoice code on the electronic invoice and output it;
[0062] b. Extract the invoice number on the electronic invoice and output it;
[0063] c. Extract the taxpayer identification number on the electronic invoice and output it.
[0064] In step S4, the corresponding code of the electronic invoice is composed of the invoice code, invoice number and taxpayer identification number on the electronic invoice. The code is composed of 40 digits and letters. The first 12 digits of the code are filled with the invoice code, the middle 8 digits of the code are filled with the invoice number, and the last 20 digits of the code are filled with the taxpayer identification number. my country's taxpayer identification number is 15, 18 or 20 digits. When the taxpayer identification number is 15 digits, the last 15 digits of the code are filled, and the remaining 5 digits are filled with 0; when the taxpayer identification number is 18 digits, the last 18 digits of the code are filled, and the remaining 2 digits are filled with 0. In this way, each invoice has a separate and unique code, which is convenient for subsequent inquiries.
[0065] In addition to storing the electronic invoices and corresponding codes that have passed the identification test, the invoice database also stores the seal information of the electronic invoice. The seal information stored in the invoice database can be used for subsequent comparison of electronic invoices.
[0066] An electronic storage device for paper invoices, comprising:
[0067] A collection device for collecting images of paper invoices;
[0068] An image processing module, used for pre-processing the image to obtain an electronic invoice;
[0069] The recognition and detection module is used to input the electronic invoice into the recognition and detection model for recognition and detection;
[0070] A content extraction module, used to input the electronic invoice into the content extraction model and output the invoice content information;
[0071] The coding generation module is used to encode the electronic invoice.
[0072] The invoice database is used to store the electronic invoices that have passed the identification test and their corresponding codes.
[0073] In summary, the storage method of the present invention can efficiently convert paper invoices into electronic invoices for storage. At the same time, the electronic invoices are identified and detected before storage, and abnormal invoices such as non-compliant and invalid invoices are removed. A separate and unique code is set for each electronic invoice, which not only facilitates subsequent inquiries, but also increases the storage capacity of invoices.
[0074] It is known from common technical knowledge that the present invention can be implemented by other embodiments that do not deviate from its spirit or essential features. Therefore, the above disclosed embodiments are only illustrative in all respects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are included in the present invention.
Claims
1. A method for electronic storage of paper invoices, characterized by: The following steps are involved: S1. Using a collection device to obtain an image of a paper invoice, and pre-processing the image to obtain an electronic invoice; S2, input the electronic invoice into the recognition detection model for recognition detection, and output the seal information; S3, input the electronic invoice into the content extraction model, and output the invoice content information; S4. Encode the electronic invoice according to the invoice content information, and store the code and the corresponding electronic invoice in the invoice library.
2. The electronic storage method of paper invoices according to claim 1, characterized in that: In step S1, preprocessing the image to obtain the electronic invoice includes the following steps: a. Crop the image to keep only the invoice part; b. Perform denoising on the image.
3. The electronic storage method of paper invoices according to claim 1, characterized in that: In step S2, the identification and detection model processing of electronic invoices includes the following steps: a. Identify the status of the machine-printed content on the electronic invoice and determine whether the machine-printed content is altered, blurred or blocked. If so, determine that the electronic invoice is an abnormal invoice, output abnormal information, and cancel the subsequent input of the electronic invoice; if not, proceed to the next step; b. Identify the face status of the electronic invoice and determine the invoice damage coefficient according to the following formula: Where Q represents the invoice damage coefficient, S0 represents the damaged area on the electronic invoice, S represents the original area of the electronic invoice, and A i represents the length of the i-th fold on the electronic invoice, n represents the number of folds on the electronic invoice, and α and β represent weight coefficients; When the invoice damage coefficient Q is greater than or equal to the set damage threshold, the electronic invoice is judged to be an abnormal invoice, abnormal information is output, and the subsequent input of the electronic invoice is cancelled; When the invoice damage coefficient Q is less than or equal to the set damage threshold, the electronic invoice is judged to be a normal invoice and the next step is carried out; c. Extract the seal on the electronic invoice and identify whether the seal is complete. If so, proceed to the next step; if not, determine that the electronic invoice is an abnormal invoice, output abnormal information, and cancel the subsequent input of the electronic invoice; d. Compare the extracted seal with the seals of all electronic invoices in the invoice database. If the extracted seal is the same as the seal of the electronic invoice in the invoice database, the seal information will be output through detection; otherwise, manual intervention will be performed to determine whether the extracted seal is correct. If it is correct, the seal information will be output through detection; if it is incorrect, the electronic invoice is judged to be an abnormal invoice, the abnormal information will be output, and the subsequent input of the electronic invoice will be cancelled.
4. The electronic storage method of paper invoices according to claim 1, characterized in that: In step S3, the content extraction model processes the electronic invoice including the following steps: a. Extract the invoice code on the electronic invoice and output it; b. Extract the invoice number on the electronic invoice and output it; c. Extract the taxpayer identification number on the electronic invoice and output it.
5. The electronic storage method of paper invoices according to claim 1, characterized in that: In step S4, the corresponding code of the electronic invoice is composed of the invoice code, invoice number and taxpayer identification number on the electronic invoice. The code is composed of 40 digits and letters, the first 12 digits of the code are filled with the invoice code, the middle 8 digits of the code are filled with the invoice number, and the last 20 digits of the code are filled with the taxpayer identification number.
6. The electronic storage method of paper invoices according to claim 1, characterized in that: In addition to storing the electronic invoices and corresponding codes that have passed the identification test, the invoice database also stores the seal information of the electronic invoices.
7. An electronic storage device for paper invoices, based on the electronic storage method for paper invoices according to claims 1-6, characterized in that: include: A collection device for collecting images of paper invoices; An image processing module, used for pre-processing the image to obtain an electronic invoice; The recognition and detection module is used to input the electronic invoice into the recognition and detection model for recognition and detection; A content extraction module, used to input the electronic invoice into the content extraction model and output the invoice content information; The coding generation module is used to encode the electronic invoice.
8. The electronic storage device for paper invoices according to claim 7, characterized in that: Also includes: The invoice database is used to store the electronic invoices that have passed the identification test and the corresponding codes and seal information.