An intelligent ticket management method, system and medium
By preprocessing the ticket images and extracting text features, annotation information is generated and classified for storage, solving the problem of automatic identification and retrieval in ticket management, improving management efficiency and quality, and reducing manual input errors and costs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGDONG ELECTRIC POWER COMM CO LTD
- Filing Date
- 2023-04-10
- Publication Date
- 2026-05-19
AI Technical Summary
Existing technologies lack effective intelligent invoice management methods, resulting in difficulties in automatically identifying and retrieving invoice content, frequent errors in manual data entry, low management efficiency, and high costs.
By collecting invoice images, preprocessing and extracting text features, generating invoice annotation information, and using comparison parameters to classify and store the invoice images, a standardized database management system is established.
It has enabled efficient management and automated processing of invoice information, improved management quality and efficiency, reduced manual input errors, and lowered labor costs.
Smart Images
Figure CN116486416B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of bill management, and more specifically, to an intelligent bill management method, system, and medium. Background Technology
[0002] Currently, the automated computer processing of paper tickets generally involves the following methods: Automatic image acquisition and storage of tickets, typically using specialized equipment for automatic acquisition and compressed storage. However, due to the lack of automatic recognition and processing of text and other information on the tickets, it is difficult to perform automatic retrieval based on ticket content and subsequent effective management, such as automatic computer verification and checking of ticket content. Manual entry of ticket content, usually done manually for subsequent automated computer management, is unsuitable for large-scale automated ticket processing, and manual entry is prone to errors and incurs high labor costs. Existing technology lacks a reliable and effective intelligent management method for tickets.
[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 an intelligent invoice management method, system, and medium. This method involves inputting and analyzing invoice images to obtain key text information, associating and storing the obtained key text information with the invoice images, generating unique invoice tags to label each input invoice, and storing the data in a dedicated database. This standardized and efficient database establishment and management of invoice information facilitates future retrieval and querying of invoices, effectively improving the quality and efficiency of invoice management.
[0005] This application also provides an intelligent invoice management method, including:
[0006] Acquire ticket images, preprocess the ticket images to obtain clear ticket image information;
[0007] Extract the text features of the invoice based on the clear image information of the processed invoice;
[0008] Input the textual features of the invoice into the invoice management model to generate invoice annotation information;
[0009] The invoice image is annotated using the invoice annotation information to obtain the annotated image;
[0010] Establish comparison parameters, and compare several labeled ticket images using the comparison parameters to obtain similarity information;
[0011] The similarity information is compared with the preset similarity information to obtain the similarity deviation rate;
[0012] Determine whether the similarity deviation rate is greater than a preset deviation rate threshold;
[0013] If so, the two corresponding tickets will be categorized and stored in different categories of databases;
[0014] If not, store the tickets in the same category database.
[0015] Optionally, in the intelligent invoice management method described in this application embodiment, the step of acquiring invoice images and preprocessing the invoice images to obtain clear invoice image information includes:
[0016] The ticket image is segmented according to its functions to obtain multiple sub-region images displaying different functions;
[0017] Extract feature values from sub-region images, differentiate functions between different sub-regions, and filter tickets.
[0018] Store the same functional information for all tickets in the same partition.
[0019] Optionally, in the intelligent ticket management method described in the embodiments of this application, the step of extracting feature values of sub-region images, distinguishing functions of different sub-regions, and filtering ticket functions includes:
[0020] The document filtering function categorizes documents according to predefined categories;
[0021] The total amount of the bills is obtained by summing the amounts of the same type of bills.
[0022] Determine whether the total amount of the bills is greater than the preset total amount of bills;
[0023] If the amount exceeds the limit, an over-limit notification will be issued.
[0024] Optionally, in the intelligent invoice management method described in the embodiments of this application, the invoice filtering function classifies invoices according to predetermined categories, including:
[0025] The tickets are categorized according to their functions, stored in the same functional area, and their quantities are updated.
[0026] Determine whether the number of tickets in the same functional area exceeds the preset number;
[0027] If the amount is greater than the value, extract the bill amount data within the same functional area and calculate the total bill amount.
[0028] If the total amount of bills is greater than the preset total amount of bills, the number of bills in the same functional area will be integrated according to the preset total amount of bills until the number of bills is less than or equal to the preset number and the total amount of bills is less than or equal to the preset total amount of bills.
[0029] Optionally, in the intelligent invoice management method described in this application embodiment, the step of acquiring invoice images and preprocessing the invoice images to obtain clear invoice image information includes:
[0030] Scan the ticket image, segment the ticket image into regions, and obtain several sub-regions;
[0031] Several sub-regions are subjected to grayscale value processing, noise reduction binarization processing, or tilt correction processing to obtain the preprocessing results of several sub-regions;
[0032] The preprocessing results of several sub-regions are integrated and superimposed to obtain the processing information of the entire region;
[0033] The processed image information of the ticket is obtained based on the information processed across the entire area.
[0034] Optionally, in the intelligent invoice management method described in the embodiments of this application, the invoice text features include one or more of the following: address, account number, bank, invoice date, buyer's name and ID card number or organization code, certificate number, machine-printed code, machine-printed number, machine number, price excluding tax, seller's name, value-added tax amount, value-added tax rate or levy rate, buyer's taxpayer identification number, seller's taxpayer identification number or telephone number, invoice number, acceptor, and face value.
[0035] Optionally, in the intelligent invoice management method described in this application embodiment, the step of extracting invoice text features based on the processed clear invoice image information includes:
[0036] Obtain the invoice text information and associate the obtained invoice text information with the invoice;
[0037] Obtain search information and create search keywords or search text based on the search information;
[0038] The target ticket is obtained by traversing the tickets in the database using the search keywords or key text.
[0039] Retrieve, review, or print the target documents.
[0040] Optionally, the intelligent invoice management method described in this application embodiment further includes: configuring invoice information access type, issuing access operation, and calling program to extract invoice data information;
[0041] Determine the encryption level of the invoice information based on the invoice information;
[0042] Obtain the access permission level and compare it with the encryption level;
[0043] If the access permission level is greater than or equal to the encryption level, the caller can directly extract the ticket information.
[0044] If the access permission level is lower than the encryption level, a forced access request is generated, and access permission level adjustment request information is obtained;
[0045] The deviation rate is obtained by comparing the access permission level adjustment application information with the preset application information.
[0046] Determine whether the deviation rate is greater than a preset deviation rate threshold;
[0047] If so, the application for grade adjustment will be rejected, and the invoice information will be sealed.
[0048] If not, then the application for grade adjustment is approved.
[0049] Optionally, the intelligent invoice management method described in the embodiments of this application further includes:
[0050] Obtain the invoice query parameters and query the corresponding invoice information based on the year and amount range;
[0051] Enter the search criteria, and the system will display the search results that meet the criteria, as well as the invoice information in real time.
[0052] Modify the invoice information according to the information displayed on the invoice, switch the invoice display interface, modify the invoice information, and click the submit button to save the modified information after the modification is completed;
[0053] Select the invoice information you want to delete in the invoice details display interface and delete it.
[0054] Optionally, the intelligent invoice management method described in the embodiments of this application further includes:
[0055] Obtain the invoice text information and compare and verify it with preset text information;
[0056] If a text error occurs, verify the location and message of the error text, and generate correction information.
[0057] The ticket data is corrected by modifying the information to obtain the correct text information, which is then entered into the database.
[0058] Secondly, embodiments of this application provide an intelligent invoice management system, which includes: a memory and a processor. The memory includes a program for an intelligent invoice management method, and when the program for the intelligent invoice management method is executed by the processor, it performs the following steps:
[0059] Acquire ticket images, preprocess the ticket images to obtain clear ticket image information;
[0060] Extract the text features of the invoice based on the clear image information of the processed invoice;
[0061] Input the textual features of the invoice into the invoice management model to generate invoice annotation information;
[0062] The invoice image is annotated using the invoice annotation information to obtain the annotated image;
[0063] Establish comparison parameters, and compare several labeled ticket images using the comparison parameters to obtain similarity information;
[0064] The similarity information is compared with the preset similarity information to obtain the similarity deviation rate;
[0065] Determine whether the similarity deviation rate is greater than a preset deviation rate threshold;
[0066] If so, the two corresponding tickets will be categorized and stored in different categories of databases;
[0067] If not, store the tickets in the same category database.
[0068] Optionally, the intelligent invoice management system described in this application embodiment further includes: configuring invoice information access type, issuing access operation, and calling program to extract invoice data information;
[0069] Determine the encryption level of the invoice information based on the invoice information;
[0070] Obtain the access permission level and compare it with the encryption level;
[0071] If the access permission level is greater than or equal to the encryption level, the caller can directly extract the ticket information.
[0072] If the access permission level is lower than the encryption level, a forced access request is generated, and access permission level adjustment request information is obtained;
[0073] The deviation rate is obtained by comparing the access permission level adjustment application information with the preset application information.
[0074] Determine whether the deviation rate is greater than a preset deviation rate threshold;
[0075] If so, the application for grade adjustment will be rejected, and the invoice information will be sealed.
[0076] If not, then the application for grade adjustment is approved.
[0077] Thirdly, embodiments of this application also provide a computer-readable storage medium, which includes an intelligent invoice management method program. When the intelligent invoice management method program is executed by a processor, it implements the steps of the intelligent invoice management method as described in any of the preceding claims.
[0078] As can be seen from the above, the intelligent invoice management method, system, and medium provided in this application collect invoice images, preprocess the invoice images to obtain clear invoice image information; extract invoice text features based on the processed clear invoice image information and input them into the invoice management model to generate invoice annotation information; annotate the invoice images using the invoice annotation information to obtain annotated images; establish comparison parameters, compare several annotated invoice images using the comparison parameters to obtain similarity information; compare the similarity information with preset similarity information to obtain a similarity deviation rate; determine whether the similarity deviation rate is greater than a preset deviation rate threshold; if it is greater, classify the corresponding two invoices; if it is less, store the invoices in the same category database. This technology can standardize and efficiently establish and manage invoice information databases, facilitate further retrieval or querying of invoices in the future, and effectively improve the management quality and efficiency of invoice management.
[0079] 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, claims, and drawings. Attached Figure Description
[0080] 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.
[0081] Figure 1 A flowchart of the intelligent invoice management method provided in the embodiments of this application;
[0082] Figure 2 A flowchart illustrating the over-limit reminder process for the intelligent invoice management method provided in this application embodiment;
[0083] Figure 3 A flowchart illustrating the method for extracting text features of a smart invoice management method provided in this application embodiment;
[0084] Figure 4 A flowchart illustrating the invoice information access process of the intelligent invoice management method provided in this application embodiment;
[0085] Figure 5 This is a schematic diagram of the structure of the intelligent invoice management system provided in an embodiment of this application. Detailed Implementation
[0086] 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.
[0087] 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.
[0088] Please refer to Figure 1 , Figure 1 This is a flowchart of an intelligent invoice management method according to some embodiments of this application. The intelligent invoice management method is used in terminal devices, such as computers and mobile terminals. The intelligent invoice management method includes the following steps:
[0089] S101, acquire the ticket image, preprocess the ticket image to obtain clear ticket image information;
[0090] S102, Extract the text features of the invoice based on the processed and clear invoice image information;
[0091] S103, Input the text features of the invoice into the invoice management model to generate invoice annotation information;
[0092] S104, Annotate the ticket image using the ticket annotation information to obtain the annotated image;
[0093] S105, Establish comparison parameters, and compare several labeled ticket images using the comparison parameters to obtain similarity information;
[0094] S106, compare the similarity information with the preset similarity information to obtain the similarity deviation rate;
[0095] S107, Determine whether the similarity deviation rate is greater than the preset deviation rate threshold;
[0096] If so, the two corresponding tickets will be categorized and stored in different categories of databases;
[0097] If not, store the tickets in the same category database.
[0098] It should be noted that each invoice is marked with a unique label, which can be used for quick identification when retrieving invoice information. In addition, invoice information of different categories can be stored separately.
[0099] According to an embodiment of the present invention, the step of acquiring the invoice image and preprocessing the invoice image to obtain clear invoice image information includes:
[0100] The ticket image is segmented according to its functions to obtain multiple sub-region images displaying different functions;
[0101] Extract feature values from sub-region images, differentiate functions between different sub-regions, and filter tickets.
[0102] Store the same functional information for all tickets in the same partition.
[0103] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating an over-limit reminder for a smart invoice management method according to some embodiments of this application. According to an embodiment of the present invention, the step of extracting feature values from sub-region images, distinguishing functions between different sub-regions, and filtering invoice functions includes:
[0104] S201, the document filtering function, categorizes documents according to predetermined categories;
[0105] S202, sum the amounts of the same type of bills to obtain the total amount of the bills;
[0106] S203, determine whether the total amount of the bills is greater than the preset total amount of bills;
[0107] S204 If the amount is greater than the limit, an over-limit reminder for invoices will be issued.
[0108] According to an embodiment of the present invention, the document filtering function categorizes documents according to predetermined categories, including:
[0109] The tickets are categorized according to their functions, stored in the same functional area, and their quantities are updated.
[0110] Determine whether the number of tickets in the same functional area exceeds the preset number;
[0111] If the amount is greater than the value, extract the bill amount data within the same functional area and calculate the total bill amount.
[0112] If the total amount of bills is greater than the preset total amount of bills, the number of bills in the same functional area will be integrated according to the preset total amount of bills until the number of bills is less than or equal to the preset number and the total amount of bills is less than or equal to the preset total amount of bills.
[0113] According to an embodiment of the present invention, acquiring a ticket image and preprocessing the ticket image to obtain clear ticket image information includes:
[0114] Scan the ticket image, segment the ticket image into regions, and obtain several sub-regions;
[0115] Several sub-regions are subjected to grayscale value processing, noise reduction binarization processing, or tilt correction processing to obtain the preprocessing results of several sub-regions;
[0116] The preprocessing results of several sub-regions are integrated and superimposed to obtain the processing information of the entire region;
[0117] The processed image information of the ticket is obtained based on the information processed across the entire area.
[0118] According to embodiments of the present invention, in the intelligent invoice management method of this application, the invoice text features include one or more of the following: address, account number, bank, invoice date, buyer's name and ID card number or organization code, certificate number, machine-printed code, machine-printed number, machine number, price excluding tax, seller's name, value-added tax amount, value-added tax rate or levy rate, buyer's taxpayer identification number, seller's taxpayer identification number or telephone number, invoice number, acceptor, and face value.
[0119] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating a method for extracting text features from invoices using an intelligent invoice management method, as described in some embodiments of this application. According to embodiments of the present invention, extracting text features from invoices based on processed, clear invoice image information includes:
[0120] S301, Obtain the document text information and associate the obtained document text information with the document;
[0121] S302, Obtain search information and establish search keywords or search text based on the search information;
[0122] S303: By searching for keywords or key text, the tickets in the database are traversed to obtain the target ticket;
[0123] S304, retrieve, view or print the target document.
[0124] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the ticket information access process of an intelligent ticket management method according to some embodiments of this application. According to embodiments of the present invention, it further includes:
[0125] S401, configure the ticket information access type, issue an access operation, and call the program to extract ticket data information;
[0126] S402, determine the encryption level of the bill information based on the bill information;
[0127] S403, Obtain the access permission level and compare the access permission level with the encryption level;
[0128] If the access permission level is greater than or equal to the encryption level, the caller can directly extract the ticket information.
[0129] If the access permission level is lower than the encryption level, a forced access request is generated, and access permission level adjustment request information is obtained;
[0130] S404, compare the access permission level adjustment application information with the preset application information to obtain the deviation rate;
[0131] S405, determine whether the deviation rate is greater than the preset deviation rate threshold;
[0132] If so, the application for grade adjustment will be rejected, and the invoice information will be sealed.
[0133] If not, then the application for grade adjustment is approved.
[0134] It should be noted that, in order to ensure the security of invoice information, access to invoice information in the database can only be performed when the required access permissions are met. If the access permissions are not met, an alarm can be triggered to alert the user of the data intrusion, or a higher access permission can be requested to extract and retrieve the invoice information from the database.
[0135] According to an embodiment of the present invention, it further includes:
[0136] Obtain the invoice query parameters and query the corresponding invoice information based on the year and amount range;
[0137] Enter the search criteria, and the system will display the search results that meet the criteria, as well as the invoice information in real time.
[0138] Modify the invoice information according to the information displayed on the invoice, switch the invoice display interface, modify the invoice information, and click the submit button to save the modified information after the modification is completed;
[0139] Select the invoice information you want to delete in the invoice details display interface and delete it.
[0140] It should be noted that the status of negotiable instruments is constantly changing. For negotiable instruments in abnormal states that have ceased circulation, such as those that are lost, damaged, or expired, the status of the negotiable instruments needs to be modified so that they can be withdrawn from circulation.
[0141] According to an embodiment of the present invention, it further includes:
[0142] Obtain the invoice text information and compare and verify it with preset text information;
[0143] If a text error occurs, verify the location and message of the error text, and generate correction information.
[0144] The ticket data is corrected by modifying the information to obtain the correct text information, which is then entered into the database.
[0145] According to an embodiment of the present invention, it further includes:
[0146] Obtain the ticket image information, perform binarization processing on the ticket image, and obtain a binarized image;
[0147] The binarized image is subjected to specified text detection, localization, and segmentation to obtain the specified text image;
[0148] Perform character segmentation on the specified text image to obtain a character image.
[0149] Extract character image feature values and perform recognition processing on the feature values to obtain character recognition information;
[0150] The character recognition information is integrated into the ticket text information.
[0151] According to an embodiment of the present invention, it further includes:
[0152] The invoice text information is categorized according to whether it has been cancelled, and the number of invoice text information that has not been cancelled is obtained;
[0153] Determine whether the number of unredeemed invoice text information is greater than a preset threshold; if so, trigger an invoice reconciliation prompt message.
[0154] The invoice verification notification information is sent to the preset invoice verification terminal.
[0155] It should be noted that after the invoice text information is sent to the database for storage, it is further classified in the corresponding database according to whether it has been cancelled, resulting in cancelled invoice text information and uncancelled invoice text information. The number of uncancelled invoice text information is recorded. When the number of uncancelled invoice text information exceeds a preset threshold, an invoice cancellation prompt is triggered, prompting the corresponding invoice cancellation terminal to cancel the uncancelled invoice text information. The preset threshold is set by those skilled in the art according to actual needs.
[0156] According to an embodiment of the present invention, it further includes:
[0157] Obtain the time information when the text information of unverified invoices was sent to the database;
[0158] Get the current time information;
[0159] Based on the current time information and the time information of the unverified invoice text information sent to the database, the time value of the unverified invoice text information stored in the database is obtained;
[0160] Determine whether the time value of the unverified invoice text information stored in the database is greater than a preset time threshold. If so, send the corresponding unverified invoice text information to the preset invoice verification terminal for verification prompt.
[0161] It should be noted that when the text information of the unverified invoice is sent to the database, the time information of the corresponding unverified invoice text information sent to the database is recorded. The current time information is subtracted from the time information of the unverified invoice text information sent to the database to obtain the storage time value of the corresponding unverified invoice text information in the database. For example, if the preset time threshold is 3 days, then when the storage time value of the corresponding unverified invoice text information in the database is greater than 3 days, the corresponding unverified invoice text information is directly sent to the corresponding invoice verification terminal for invoice verification.
[0162] According to an embodiment of the present invention, it further includes:
[0163] The invoice text information is compared and analyzed with the text in the preset illegal text database to determine whether the invoice text information contains illegal text. If so, the corresponding invoice text information is set as illegal invoice text information.
[0164] The text information of the illegal invoice was deleted.
[0165] It should be noted that the preset violation text library stores a large amount of violation text information and text violation rules. When the invoice text information contains text that is also in the preset violation text library, it indicates that the corresponding invoice text information is a violation text and is set as a violation invoice text information.
[0166] According to an embodiment of the present invention, it further includes:
[0167] Set the ticket corresponding to the illegal ticket text information as an illegal ticket;
[0168] Extract the source user information of the irregular invoices;
[0169] Based on the source user information of the violation ticket, obtain the number of times the corresponding violation ticket was provided by the source user;
[0170] Determine whether the number of times the source user of the illegal ticket has provided illegal tickets exceeds a preset threshold. If so, trigger a warning message.
[0171] The user information that triggered the alert will be sent to the preset management terminal for display.
[0172] It should be noted that the text information of the illegal receipts is summarized, and the source user of each illegal receipt text information is extracted. The number of times the corresponding source user provides illegal receipts is recorded. For example, if the preset threshold is 3 times, when the number of times the source user provides illegal receipts is greater than 3 times, an alert message is triggered, and the source user information that triggered the alert message is sent to the preset management terminal to trace the illegal receipts.
[0173] Please refer to Figure 5 , Figure 5 This is a second aspect of an intelligent invoice management method in some embodiments of this application. An embodiment of this application provides an intelligent invoice management system 5, which includes: a memory 51 and a processor 52. The memory 51 includes a program for the intelligent invoice management method. When the program for the intelligent invoice management method is executed by the processor, it implements the following steps:
[0174] Acquire ticket images, preprocess the ticket images to obtain clear ticket image information;
[0175] Extract the text features of the invoice based on the clear image information of the processed invoice;
[0176] Input the textual features of the invoice into the invoice management model to generate invoice annotation information;
[0177] The invoice image is annotated using the invoice annotation information to obtain the annotated image;
[0178] Establish comparison parameters, and compare several labeled ticket images using the comparison parameters to obtain similarity information;
[0179] The similarity information is compared with the preset similarity information to obtain the similarity deviation rate;
[0180] Determine whether the similarity deviation rate is greater than the preset deviation rate threshold;
[0181] If so, the two corresponding tickets will be categorized and stored in different categories of databases;
[0182] If not, store the tickets in the same category database.
[0183] It should be noted that each invoice is marked with a unique label, which can be used for quick identification when retrieving invoice information. In addition, invoice information of different categories can be stored separately.
[0184] According to an embodiment of the present invention, the method further includes: configuring the invoice information access type, issuing an access operation, and calling a program to extract invoice data information;
[0185] Determine the encryption level of the invoice information based on the invoice information;
[0186] Obtain the access permission level and compare it with the encryption level;
[0187] If the access permission level is greater than or equal to the encryption level, the caller can directly extract the ticket information.
[0188] If the access permission level is lower than the encryption level, a forced access request is generated, and access permission level adjustment request information is obtained;
[0189] The deviation rate is obtained by comparing the access permission level adjustment application information with the preset application information.
[0190] Determine whether the deviation rate is greater than the preset deviation rate threshold;
[0191] If so, the application for grade adjustment will be rejected, and the invoice information will be sealed.
[0192] If not, then the application for grade adjustment is approved.
[0193] It should be noted that, in order to ensure the security of invoice information, access to invoice information in the database can only be performed when the required access permissions are met. If the access permissions are not met, an alarm can be triggered to alert the user of the data intrusion, or a higher access permission can be requested to extract and retrieve the invoice information from the database.
[0194] According to an embodiment of the present invention, acquiring a ticket image and preprocessing the ticket image to obtain clear ticket image information includes:
[0195] Scan the ticket image, segment the ticket image into regions, and obtain several sub-regions;
[0196] Several sub-regions are subjected to grayscale value processing, noise reduction binarization processing, or tilt correction processing to obtain the preprocessing results of several sub-regions;
[0197] The preprocessing results of several sub-regions are integrated and superimposed to obtain the processing information of the entire region;
[0198] The processed image information of the ticket is obtained based on the information processed across the entire area.
[0199] According to embodiments of the present invention, in the intelligent invoice management method of this application, the invoice text features include one or more of the following: address, account number, bank, invoice date, buyer's name and ID card number or organization code, certificate number, machine-printed code, machine-printed number, machine number, price excluding tax, seller's name, value-added tax amount, value-added tax rate or levy rate, buyer's taxpayer identification number, seller's taxpayer identification number or telephone number, invoice number, acceptor, and face value.
[0200] According to an embodiment of the present invention, extracting document text features based on the processed, clear document image information includes:
[0201] Obtain the invoice text information and associate the obtained invoice text information with the invoice;
[0202] Obtain search information and create search keywords or search text based on the search information;
[0203] The target ticket is obtained by traversing the tickets in the database by searching keywords or key text.
[0204] Retrieve, review, or print the target documents.
[0205] According to an embodiment of the present invention, it further includes:
[0206] Obtain the invoice query parameters and query the corresponding invoice information based on the year and amount range;
[0207] Enter the search criteria, and the system will display the search results that meet the criteria, as well as the invoice information in real time.
[0208] Modify the invoice information according to the information displayed on the invoice, switch the invoice display interface, modify the invoice information, and click the submit button to save the modified information after the modification is completed;
[0209] Select the invoice information you want to delete in the invoice details display interface and delete it.
[0210] It should be noted that the status of negotiable instruments is constantly changing. For negotiable instruments in abnormal states that have ceased circulation, such as those that are lost, damaged, or expired, the status of the negotiable instruments needs to be modified so that they can be withdrawn from circulation.
[0211] According to an embodiment of the present invention, it further includes:
[0212] Obtain the invoice text information and compare and verify it with preset text information;
[0213] If a text error occurs, verify the location and message of the error text, and generate correction information.
[0214] The ticket data is corrected by modifying the information to obtain the correct text information, which is then entered into the database.
[0215] According to an embodiment of the present invention, it further includes:
[0216] Obtain the ticket image information, perform binarization processing on the ticket image, and obtain a binarized image;
[0217] The binarized image is subjected to specified text detection, localization, and segmentation to obtain the specified text image;
[0218] Perform character segmentation on the specified text image to obtain a character image.
[0219] Extract character image feature values and perform recognition processing on the feature values to obtain character recognition information; integrate the character recognition information into invoice text information.
[0220] According to an embodiment of the present invention, the step of acquiring the invoice image and preprocessing the invoice image to obtain clear invoice image information includes:
[0221] The ticket image is segmented according to its functions to obtain multiple sub-region images displaying different functions;
[0222] Extract feature values from sub-region images, differentiate functions between different sub-regions, and filter tickets.
[0223] Store the same functional information for all tickets in the same partition.
[0224] According to an embodiment of the present invention, the step of extracting feature values of sub-region images, distinguishing functions of different sub-regions, and filtering tickets includes:
[0225] The document filtering function categorizes documents according to predefined categories;
[0226] The total amount of the bills is obtained by summing the amounts of the same type of bills.
[0227] Determine whether the total amount of the bills is greater than the preset total amount of bills;
[0228] If the amount exceeds the limit, an over-limit notification will be issued.
[0229] According to an embodiment of the present invention, the document filtering function categorizes documents according to predetermined categories, including:
[0230] The tickets are categorized according to their functions, stored in the same functional area, and their quantities are updated.
[0231] Determine whether the number of tickets in the same functional area exceeds the preset number;
[0232] If the amount is greater than the value, extract the bill amount data within the same functional area and calculate the total bill amount.
[0233] If the total amount of bills is greater than the preset total amount of bills, the number of bills in the same functional area will be integrated according to the preset total amount of bills until the number of bills is less than or equal to the preset number and the total amount of bills is less than or equal to the preset total amount of bills.
[0234] A third aspect of the present invention provides a computer-readable storage medium including an intelligent invoice management method program, which, when executed by a processor, implements the steps of the intelligent invoice management method as described above.
[0235] This invention discloses an intelligent invoice management method, system, and medium. The method involves acquiring invoice images, preprocessing the images to obtain clear image information, extracting textual features from the processed images and inputting them into an invoice management model to generate invoice annotation information, annotating the images with this information, establishing comparison parameters, comparing several annotated invoice images to obtain similarity information, comparing the similarity information with preset similarity information to obtain a similarity deviation rate, determining whether the deviation rate exceeds a preset threshold, classifying the corresponding invoices if it does, and storing the invoices in the same category database if it does not. This method enables standardized and efficient database establishment and management of invoice information, facilitating future retrieval and querying of invoices, and effectively improving the management quality and efficiency of invoice management.
[0236] 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 illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.
[0237] The units described above as separate components may or may not be physically separate. The components shown 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 to achieve the purpose of this embodiment according to actual needs.
[0238] 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.
[0239] 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.
[0240] 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. An intelligent invoice management method, characterized in that, include: Acquire ticket images, preprocess the ticket images to obtain clear ticket image information; Extract the text features of the invoice based on the clear image information of the processed invoice; Input the textual features of the invoice into the invoice management model to generate invoice annotation information; The invoice image is annotated using the invoice annotation information to obtain the annotated image; Establish comparison parameters, and compare several labeled ticket images using the comparison parameters to obtain similarity information; The similarity information is compared with the preset similarity information to obtain the similarity deviation rate; Determine whether the similarity deviation rate is greater than a preset deviation rate threshold; If so, the two corresponding tickets will be categorized and stored in different categories of databases; If not, store the tickets in the same category database; Configure the invoice information access type, issue an access operation, and call the program to extract invoice data information; Determine the encryption level of the invoice information based on the invoice information; Obtain the access permission level and compare it with the encryption level; If the access permission level is greater than or equal to the encryption level, the calling program directly extracts the ticket information; If the access permission level is lower than the encryption level, a forced access request is generated, and access permission level adjustment request information is obtained; The deviation rate is obtained by comparing the access permission level adjustment application information with the preset application information. Determine whether the deviation rate is greater than a preset deviation rate threshold; If so, the application for grade adjustment will be rejected, and the invoice information will be sealed. If not, the application for grade adjustment is approved; The invoice text information is compared and analyzed with the text in the preset illegal text database to determine whether there is any illegal text in the invoice text information. If so, the corresponding invoice text information is set as illegal invoice text information. Delete the text information of the illegal invoice; Set the ticket corresponding to the illegal ticket text information as an illegal ticket; Extract the source user information of the irregular invoices; Based on the source user information of the violation ticket, obtain the number of times the corresponding violation ticket was provided by the source user; Determine whether the number of times the source user of the illegal ticket has provided illegal tickets exceeds a preset threshold. If so, trigger a warning message. The source user information corresponding to the triggered warning message will be sent to the preset management terminal for display.
2. The intelligent invoice management method according to claim 1, characterized in that, The process of acquiring the ticket image and preprocessing it to obtain clear ticket image information includes: The ticket image is segmented according to its functions to obtain multiple sub-region images displaying different functions; Extract feature values from sub-region images, differentiate functions between different sub-regions, and filter tickets. Store the same functional information for all tickets in the same partition.
3. The intelligent invoice management method according to claim 2, characterized in that, The extraction of feature values from sub-region images, the differentiation of functions in different sub-regions, and the filtering of invoices include: The document filtering function categorizes documents according to predefined categories; The total amount of the bills is obtained by summing the amounts of the same type of bills. Determine whether the total amount of the bills is greater than the preset total amount of bills; If the amount exceeds the limit, an over-limit notification will be issued.
4. The intelligent invoice management method according to claim 3, characterized in that, The document filtering function categorizes documents according to predetermined categories, including: The tickets are categorized according to their functions, stored in the same functional area, and their quantities are updated. Determine whether the number of tickets in the same functional area exceeds the preset number; If the amount is greater than the value, extract the bill amount data within the same functional area and calculate the total bill amount. If the total amount of bills is greater than the preset total amount of bills, the number of bills in the same functional area will be integrated according to the preset total amount of bills until the number of bills is less than or equal to the preset number and the total amount of bills is less than or equal to the preset total amount of bills.
5. The intelligent invoice management method according to claim 4, characterized in that, The step of extracting document text features based on the processed, clear document image information includes: Obtain the invoice text information and associate the obtained invoice text information with the invoice; Obtain search information and create search keywords or search text based on the search information; The target ticket is obtained by traversing the tickets in the database using the search keywords or key text. Retrieve, review, or print the target documents.
6. The intelligent invoice management method according to claim 5, characterized in that, Also includes: Obtain the invoice text information and compare and verify it with preset text information; If a text error occurs, verify the location and message of the error text, and generate correction information. The ticket data is corrected by modifying the information to obtain the correct text information, which is then entered into the database.
7. An intelligent invoice management system, characterized in that, The system includes: a memory and a processor, wherein the memory includes a program for an intelligent ticket management method, and when the program for the intelligent ticket management method is executed by the processor, it performs the following steps: Acquire ticket images, preprocess the ticket images to obtain clear ticket image information; Extract the text features of the invoice based on the clear image information of the processed invoice; Input the textual features of the invoice into the invoice management model to generate invoice annotation information; The invoice image is annotated using the invoice annotation information to obtain the annotated image; Establish comparison parameters, and compare several labeled ticket images using the comparison parameters to obtain similarity information; The similarity information is compared with the preset similarity information to obtain the similarity deviation rate; Determine whether the similarity deviation rate is greater than a preset deviation rate threshold; If so, the two corresponding tickets will be categorized and stored in different categories of databases; If not, store the tickets in the same category database; Configure the invoice information access type, issue an access operation, and call the program to extract invoice data information; Determine the encryption level of the invoice information based on the invoice information; Obtain the access permission level and compare it with the encryption level; If the access permission level is greater than or equal to the encryption level, the calling program directly extracts the ticket information; If the access permission level is lower than the encryption level, a forced access request is generated, and access permission level adjustment request information is obtained; The deviation rate is obtained by comparing the access permission level adjustment application information with the preset application information. Determine whether the deviation rate is greater than a preset deviation rate threshold; If so, the application for grade adjustment will be rejected, and the invoice information will be sealed. If not, the application for grade adjustment is approved; The invoice text information is compared and analyzed with the text in the preset illegal text database to determine whether there is any illegal text in the invoice text information. If so, the corresponding invoice text information is set as illegal invoice text information. Delete the text information of the illegal invoice; Set the ticket corresponding to the illegal ticket text information as an illegal ticket; Extract the source user information of the irregular invoices; Based on the source user information of the violation ticket, obtain the number of times the corresponding violation ticket was provided by the source user; Determine whether the number of times the source user of the illegal ticket has provided illegal tickets exceeds a preset threshold. If so, trigger a warning message. The source user information corresponding to the triggered warning message will be sent to the preset management terminal for display.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes an intelligent invoice management method program, which, when executed by a processor, implements the steps of the intelligent invoice management method as described in any one of claims 1 to 6.