Visiting record-based information verification method and device, equipment and storage medium

By generating visit records and verifying bill information using OCR technology, the problem of difficult to verify the authenticity of entertainment expense details in the catering reimbursement process is solved, and the reliability and management efficiency of bill reimbursement are improved.

CN119477574APending Publication Date: 2025-02-18KANG JIAN INFORMATION TECH (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411356776.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-26
Publication Date
2025-02-18

AI Technical Summary

Technical Problem

In the existing catering reimbursement process, the authenticity of the entertainment expense details is difficult to verify, resulting in the risk of false reimbursement or inflated reimbursement expenses.

Method used

Through the information verification method based on the visit record, the user's current location information and service needs are used to generate the visit record information, and the ticket information is extracted in combination with the preset optical character recognition (OCR) technology to verify the validity of the ticket.

Benefits of technology

It improves the reliability of bill reimbursement, reduces the risks of false reimbursement and inflated expenses, and better monitors and manages the reimbursement process through an intelligent review process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119477574A_ABST
    Figure CN119477574A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent decision making, is applied to the field of financial science and technology businesses, and discloses an information verification method, device and equipment based on a visit record and a storage medium, the method comprises the following steps: generating visit record information based on user current position information and current business requirements of a target user; various bill information in the target bill is extracted through the OCR technology, and whether the target bill is a valid bill is verified through the visit record information and the bill information; and under the condition that the target bill is determined to be the effective bill, issuing notification information that reimbursement audit is passed to the target user. By means of the mode, the accuracy of bill information extraction is improved by applying the OCR technology, and the authenticity and effectiveness of the bill can be effectively verified in combination with verification of the visit record information. Through the intelligent auditing process, risks possibly occurring in the reimbursement process can be better monitored and managed, and then the reliability of bill reimbursement is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent decision-making technology, which is applied to the field of financial technology business, and in particular to an information verification method, device, equipment and storage medium based on visit records. Background Art

[0002] In various fields, entertainment expenses have always been an important part of invoice reimbursement, and the review of catering reimbursement has always been an important part of financial audit and cost control. In the existing catering reimbursement process, the materials required mainly include electronic invoices, personal consumption records, and entertainment expense details (the main contents of which include the entertainment time, entertainment organization, and list of entertainers). Electronic invoices plus personal consumption records ensure the authenticity of consumption; combined with the list of people in the entertainment expense details, it ensures that the entertainment expenses meet the per capita consumption stipulated by the company.

[0003] With the rapid development of artificial intelligence technology, the authenticity of catering expense reimbursement can be guaranteed based on the provided materials and manual comparison. However, there are still some loopholes, which leads to the risk of false reimbursement or inflated reimbursement expenses.

[0004] Among the three types of materials provided by the existing process (electronic invoices, personal consumption records, and entertainment expense details), electronic invoices and personal consumption records have relatively mature verification methods and are difficult to forge. Therefore, the main problem of loopholes in the existing process lies in the entertainment expense details. In real scenarios, the entertainment expense details are filled out by the account manager and approved and signed by the superior approver. However, due to the particularity of the entertainment occasion and the habit of centralized reimbursement, the approver has almost no way to verify the authenticity of each entertainment, which brings the risk of false reporting of catering expenses. Therefore, how to improve the reliability of bill reimbursement through artificial intelligence technology has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a method, device, equipment and storage medium for information verification based on visit records, so as to improve the reliability of bill reimbursement through artificial intelligence technology.

[0006] In a first aspect, the present application provides an information verification method based on a visit record, the method comprising:

[0007] Generate visit record information based on the target user's current location information and current business needs;

[0008] Extract various ticket information in the target ticket by using preset optical character recognition (OCR) technology, and verify whether the target ticket is a valid ticket by using the visit record information and various ticket information;

[0009] When it is determined that the target bill is the valid bill, a notification message indicating that the reimbursement review has been passed is sent to the target user.

[0010] In a second aspect, the present application further provides an information verification device based on a visit record, the device comprising:

[0011] A visit record information generation module is used to generate visit record information based on the user's current location information and current business needs of the target user;

[0012] The bill verification module is used to extract various bill information in the target bill by using the preset optical character recognition (OCR) technology, and verify whether the target bill is a valid bill by using the visit record information and various bill information;

[0013] The notification information sending module is used to send notification information of reimbursement approval to the target user when it is determined that the target bill is the valid bill.

[0014] In a third aspect, the present application also provides a computer device, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the above-mentioned information verification method based on visit records when executing the computer program.

[0015] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the information verification method based on the visit record as described above.

[0016] The present application discloses a method, device, equipment and storage medium for information verification based on visit records, wherein the method for information verification based on visit records includes generating visit record information based on the current location information and current business needs of the target user; extracting various bill information in the target bill by using a preset optical character recognition (OCR) technology, and verifying whether the target bill is a valid bill through the visit record information and various bill information; and sending a notification message of reimbursement approval to the target user when it is determined that the target bill is a valid bill. In the above manner, the present application improves the accuracy of extracting bill information by applying OCR technology, and can effectively verify the authenticity and validity of the bill by combining the verification of visit record information. Through an intelligent audit process, the risks that may arise in the reimbursement process can be better monitored and managed, thereby improving the reliability of bill reimbursement. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is a schematic flow chart of an information verification method based on visit records provided in the first embodiment of the present application;

[0019] Figure 2 is a schematic flow chart of an information verification method based on visit records provided in the second embodiment of the present application;

[0020] Figure 3 is a schematic flow chart of an information verification method based on visit records provided in the third embodiment of the present application;

[0021] Figure 4 A schematic block diagram of an information verification device based on visit records provided in an embodiment of the present application;

[0022] Figure 5 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0025] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0026] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] The embodiments of the present application provide a method, device, equipment and storage medium for information verification based on visit records. The information verification method based on visit records can be applied to a server. By applying OCR technology, the accuracy of extracting bill information is improved. Combined with the verification of visit record information, the authenticity and validity of the bill can be effectively verified. Through an intelligent review process, the risks that may arise in the reimbursement process can be better monitored and managed, thereby improving the reliability of bill reimbursement. The server can be an independent server or a server cluster.

[0028] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0029] See also Figure 1 , Figure 1 This is a schematic flow chart of an information verification method based on visit records provided by the first embodiment of the present application. The information verification method based on visit records can be applied to a server to improve the accuracy of extracting bill information by applying OCR technology. Combined with the verification of visit record information, the authenticity and validity of the bill can be effectively verified. Through an intelligent audit process, the risks that may arise in the reimbursement process can be better monitored and managed, thereby improving the reliability of bill reimbursement.

[0030] like Figure 1 As shown, the information verification method based on the visit record specifically includes steps S10 to S30.

[0031] Step S10: Generate visit record information based on the current location information and current business needs of the target user;

[0032] Specifically, the data of on-site clock-in for visits is obtained. The scene of catering reception is usually generated by visits. The visit record requires the account manager to clock in twice in real time through the mobile app at the beginning and end of the visit, and automatically associate the customer based on the geographical location for the account manager to fill in. The operation is convenient, but it can effectively guarantee the authenticity. At the same time, the data that can be generated can be used by the business development department to manage the visits in a refined manner, adjust the type of visits according to business needs, and promote business development. With the visit record to ensure the authenticity of the visit, all catering consumption records cannot be reimbursed if there is no visit on the same day, which can effectively avoid the risk point of "the reception did not actually take place".

[0033] Step S20, extracting various ticket information in the target ticket by using a preset optical character recognition (OCR) technology, and verifying whether the target ticket is a valid ticket by using the visit record information and the various ticket information;

[0034] Specifically, OCR (Optical Character Recognition) technology is used to automatically recognize text information on invoices and other documents. Since receipts usually contain various information, such as date, time, product name, price, etc., and the formats may vary from merchant to merchant, OCR will improve the image quality through technologies such as denoising, contrast enhancement, and sharpening, and then perform regional segmentation, layout understanding, and finally perform character recognition to format information in different formats. In terms of OCR recognition models, in order to improve the generalization ability of the model, different types of samples will be collected for training, including receipts of different sizes, different colors, and different materials, so as to achieve the adaptability of OCR recognition technology to different receipts. The introduction of OCR technology can quickly compare the recognized formatted data while reducing the input cost to complete the verification of reimbursement information.

[0035] Step S30: When it is determined that the target bill is the valid bill, a notification message indicating that the reimbursement has been approved is sent to the target user.

[0036] Specifically, it connects to a third-party verification platform to verify the target bills online, prevents fake bills from being reimbursed, and ensures the safety of funds. It connects to the bill authenticity query interface to verify the consumption record based on the consumption record serial number extracted by text recognition to ensure the authenticity of the consumption.

[0037] In one embodiment, the user's current GPS location information is obtained through the user's smart device (such as a smart phone or tablet). The type and content of the visit record information to be generated are determined according to the user's business needs. The visit record information is automatically generated using the user's location information and business needs, including the visit time, location, purpose, etc. The user takes a photo of the bill or uploads a scanned copy of the bill through the smart device.

[0038] Use the preset OCR technology to process the receipt image, including image preprocessing (denoising, binarization, tilt correction, etc.). Use OCR technology to extract text information from the receipt image, including the receipt number, date, amount, consumption details, etc. Compare the extracted receipt information with the visit record information to verify the validity of the receipt. This may include checking whether the receipt date is consistent with the visit date, whether the location on the receipt matches the user's location information, etc.

[0039] Compare the bill information with the visit record information to verify the authenticity and compliance of the bill. Based on the verification results, determine whether the bill is a valid bill. If the bill is confirmed to be valid, the system will automatically generate a notification message that the reimbursement review has been passed.

[0040] The present embodiment discloses a method, device, equipment and storage medium for information verification based on visit records, wherein the method for information verification based on visit records includes generating visit record information based on the current location information and current business needs of the target user; extracting various bill information in the target bill by using a preset optical character recognition (OCR) technology, and verifying whether the target bill is a valid bill through the visit record information and various bill information; and sending a notification message of reimbursement approval to the target user when it is determined that the target bill is a valid bill. In the above manner, the present application improves the accuracy of extracting bill information by applying OCR technology, and can effectively verify the authenticity and validity of the bill by combining the verification of visit record information. Through an intelligent audit process, the risks that may arise in the reimbursement process can be better monitored and managed, thereby improving the reliability of bill reimbursement.

[0041] See also Figure 2 , Figure 2 This is a schematic flow chart of an information verification method based on visit records provided by the second embodiment of the present application. The information verification method based on visit records can be applied to a server to generate visit records by combining user location information and business needs to ensure the accuracy of information. By using OCR technology to accurately identify bill information, human errors can be reduced, and risks that may occur during the reimbursement process can be better monitored and managed, thereby improving the reliability of bill reimbursement.

[0042] based on Figure 1 The embodiment shown, this embodiment Figure 2 As shown, step S20 includes step S201 to step S202.

[0043] Step S201, performing image segmentation and image denoising processing on the target bill by using the preset OCR technology to generate at least one target bill image block;

[0044] Step S202, identifying the text information in each of the target bill blocks, and using the text information as the bill information, wherein the text information includes current reimbursement amount information, current number of reimbursements information, and current payment serial number information.

[0045] In one embodiment, a filtering algorithm (such as Gaussian filtering, median filtering, etc.) is used to remove noise from the image. The grayscale value of the bill image is converted into a binary (usually black and white) image to facilitate text recognition. This is usually achieved by setting a threshold, with pixels above the threshold set to white and pixels below the threshold set to black.

[0046] Analyze the text lines in the image, detect their tilt angles, and apply affine transformation to correct the image to make the text lines horizontal. Use the OCR engine to perform text recognition on the pre-processed bill image to identify key information on the bill, such as bill number, date, amount, consumption details, etc.

[0047] If the ticket contains location information (such as store name, address, etc.), the location information API is used to parse these locations and compare them with the user location information in the visit record. This may require converting the text location to longitude and latitude and performing spatial distance calculations. If all verifications pass, the ticket is considered valid and a notification message indicating that the reimbursement review has passed is generated. If the verification fails, the reason for the failure is recorded and a notification message indicating that the reimbursement review has not passed may be generated, with a detailed explanation of the failure.

[0048] The present embodiment discloses a method, device, equipment and storage medium for information verification based on visit records, wherein the method for information verification based on visit records includes generating visit record information based on the current location information and current business needs of the target user; performing image segmentation and image denoising on the target bill through the preset OCR technology to generate at least one target bill block; identifying the text information in each target bill block, and using the text information as the bill information, wherein the text information includes the current reimbursement amount information, the current number of reimbursements information and the current payment serial number information, and verifying whether the target bill is a valid bill through the visit record information and each of the bill information; in the case where it is determined that the target bill is the valid bill, sending a notification message of reimbursement approval to the target user. In the above manner, the present application generates visit records by combining user location information and business needs to ensure the accuracy of information. Accurately identify bill information through OCR technology, reduce human errors, better monitor and manage the risks that may occur in the reimbursement process, and thus improve the reliability of bill reimbursement.

[0049] See also Figure 3 , Figure 3This is a schematic flow chart of an information verification method based on visit records provided in the third embodiment of the present application. The information verification method based on visit records can be applied to a server to improve the accuracy of extracting bill information by applying OCR technology. Combined with the verification of visit record information, the authenticity and validity of the bill can be effectively verified. Through an intelligent audit process, the risks that may arise in the reimbursement process can be better monitored and managed, thereby improving the reliability of bill reimbursement.

[0050] based on Figure 2 The embodiment shown, this embodiment Figure 3 As shown, step S201 includes steps S2011 to S2014.

[0051] Step S2011, performing denoising processing on the target bill by using a Gaussian filtering method, and determining the text area and image area of ​​the target bill by physical layout analysis and logical layout analysis;

[0052] Specifically, each tile is denoised to remove noise in the image, such as spots, scratches or blur. Common denoising methods include Gaussian filtering, median filtering or bilateral filtering. The original bill image is divided into multiple smaller tiles, which helps to improve the accuracy and efficiency of OCR recognition. Segmentation methods include but are not limited to algorithms based on edge detection, threshold segmentation or region growing.

[0053] Step S2012, performing image segmentation processing on the text area through the horizontal projection histogram and the vertical direction histogram to generate at least one text area block;

[0054] Step S2013: performing image segmentation processing on the image area by using a preset edge recognition algorithm to generate at least one image area block;

[0055] Step S2014: determine each of the text area tiles and each of the image area tiles as the target bill tiles.

[0056] In one embodiment, key information is extracted from the recognition results, such as the current reimbursement amount, number of people reimbursed, and payment serial number. This information will be used as part of the bill information. The size and method of image segmentation may affect the accuracy and efficiency of OCR recognition and need to be adjusted according to actual conditions. The extracted text information is verified to ensure its accuracy. This may include checking the format of the number, verifying the rationality of the amount, etc.

[0057] The present embodiment discloses a method, device, equipment and storage medium for information verification based on visit records. The method for information verification based on visit records includes generating visit record information based on the current location information and current business needs of the target user; performing denoising on the target bill by Gaussian filtering method, and determining the text area and image area of ​​the target bill by physical layout analysis and logical layout analysis; performing image segmentation on the text area by horizontal projection histogram and vertical direction histogram to generate at least one text area block; performing image segmentation on the image area by a preset edge recognition algorithm to generate at least one image area block; determining each of the text area blocks and each of the image area blocks as the target bill block; identifying the text information in each of the target bill blocks, and using the text information as the bill information, wherein the text information includes the current reimbursement amount information, the current number of reimbursement information and the current payment serial number information, and verifying whether the target bill is a valid bill by using the visit record information and each of the bill information; and sending a notification message of reimbursement review passing to the target user when it is determined that the target bill is the valid bill. Through the above method, this application accurately identifies bill information through filtering methods, reduces human errors, strengthens financial management by verifying the validity of bills, avoids financial risks, and promptly issues notifications of reimbursement review and approval, thereby improving user satisfaction and the reliability of bill reimbursement.

[0058] In a more preferred embodiment, based on Figure 2 In the embodiment shown, in this embodiment, step S20 includes:

[0059] Obtaining a preset reimbursement rule, and determining standard reimbursement amount information based on the visit record information and the preset reimbursement rule;

[0060] Based on the visit record information and the current number of people reimbursed, generate a verification result of the number of people reimbursed;

[0061] Generate a reimbursement amount verification result based on the standard reimbursement amount information and the current reimbursement amount information;

[0062] When both the verification result of the number of people reimbursed and the verification result of the reimbursement amount are passed, the target bill is determined to be the valid bill.

[0063] In one embodiment, the data on the number of visitors is obtained, and the person requesting reimbursement needs to fill in the number of visitors in advance in the visit record function, which can effectively avoid the scenario where the person requesting reimbursement tampers with the number of visitors based on the consumption amount.

[0064] When reimbursing catering bills, you can obtain per capita catering data from a third-party Internet platform to assist in reviewing the authenticity of the per capita catering data in catering bills. If the person making the reimbursement reserves too many people in the visiting number link, the final per capita consumer will be too low, which will eventually trigger an automatic warning in the system, prompting the approval personnel to manually review the dish details of the catering bill.

[0065] The present embodiment discloses a method, device, equipment and storage medium for information verification based on visit records, wherein the method for information verification based on visit records includes generating visit record information based on the current location information and current business needs of the target user; extracting various bill information in the target bill by preset optical character recognition (OCR) technology, and obtaining preset reimbursement rules, and determining the standard reimbursement amount information based on the visit record information and the preset reimbursement rules; generating the reimbursement number verification result based on the visit record information and the current reimbursement number information; generating the reimbursement amount verification result based on the standard reimbursement amount information and the current reimbursement amount information; determining the target bill as the valid bill when both the reimbursement number verification result and the reimbursement amount verification result are passed; and sending the target user a notification message of reimbursement review passing when determining that the target bill is the valid bill. In the above manner, the present application improves the accuracy of extracting bill information by applying OCR technology, and can effectively verify the authenticity and validity of the bill by combining the verification of visit record information. Through the intelligent audit process, the risks that may occur in the reimbursement process can be better monitored and managed, thereby improving the reliability of bill reimbursement.

[0066] In a more preferred embodiment, the preset reimbursement rules are obtained, and based on the visit record information and the preset reimbursement rules, the standard reimbursement amount information is determined, including:

[0067] Determine the current number of people reimbursed according to the visit record information;

[0068] According to the preset insurance rules, determine the per capita consumption information matching the visit record information;

[0069] The product of the current number of people being reimbursed and the per capita consumption information is calculated, and the product is used as the standard reimbursement amount information.

[0070] Specifically, extract the current number of people being reimbursed from the visit record information. This is usually a number that indicates the number of people who participated in the visit and need to be reimbursed. Get the preset insurance rules. These rules include per capita consumption limits for different visit types, different locations, or different activity types. Match the visit record information (such as visit type, location, activity type, etc.) with the preset insurance rules to determine the per capita consumption information that matches the current visit record.

[0071] Multiply the current number of people being reimbursed by the per capita consumption information, that is, the standard reimbursement amount information = the current number of people being reimbursed x the per capita consumption information.

[0072] In a more preferred embodiment, step S20 further includes:

[0073] Verify the current payment serial number information through a third-party authentication platform to generate a payment serial number verification result;

[0074] When the payment serial number verification result is passed, the target bill is determined to be the valid bill.

[0075] Based on the above embodiment, in this embodiment, after step S30, the following steps are further included:

[0076] If the verification result of the number of people to be reimbursed, the verification result of the amount to be reimbursed and / or the verification result of the payment serial number are failed, the target bill is determined to be an invalid bill;

[0077] In the case that the target ticket is the invalid ticket, an alarm prompt is generated and sent to the target user.

[0078] Specifically, the bill information and visit record information are compared to verify the authenticity and compliance of the bill. Based on the verification results, it is determined whether the bill is a valid bill. If the bill is confirmed to be valid, the system will automatically generate a notification message that the reimbursement review has been passed.

[0079] See also Figure 4 , Figure 4 The embodiment of the present application provides a schematic block diagram of an information verification device based on a visit record, and the information verification device based on a visit record is used to execute the aforementioned information verification method based on a visit record. The information verification device based on a visit record can be configured on a server.

[0080] like Figure 4 As shown, the information verification device 400 based on the visit record includes:

[0081] The visit record information generating module 410 is used to generate the visit record information based on the user's current location information and current business requirements of the target user;

[0082] The bill verification module 420 is used to extract various bill information in the target bill by using a preset optical character recognition (OCR) technology, and verify whether the target bill is a valid bill by using the visit record information and various bill information;

[0083] The notification information sending module 430 is used to send notification information of reimbursement approval to the target user when it is determined that the target bill is the valid bill.

[0084] Furthermore, the bill verification module 420 includes:

[0085] A target bill image block generation submodule, configured to perform image segmentation and image denoising on the target bill using the preset OCR technology to generate at least one target bill image block;

[0086] The bill information determination submodule is used to identify the text information in each of the target bill blocks and use the text information as the bill information, wherein the text information includes the current reimbursement amount information, the current number of reimbursements information and the current payment serial number information.

[0087] Furthermore, the target bill block generation submodule includes:

[0088] A denoising unit, used for denoising the target bill by using a Gaussian filtering method, and determining a text area and an image area of ​​the target bill by using a physical layout analysis and a logical layout analysis;

[0089] A text area block generating unit, configured to perform image segmentation processing on the text area through a horizontal projection histogram and a vertical direction histogram to generate at least one text area block;

[0090] An image region block generating unit, configured to perform image segmentation processing on the image region by using a preset edge recognition algorithm to generate at least one image region block;

[0091] The target bill block determining unit is used to determine each of the text area blocks and each of the image area blocks as the target bill block.

[0092] Furthermore, the bill verification module 420 includes:

[0093] A standard reimbursement amount information determination submodule, used to obtain a preset reimbursement rule, and determine the standard reimbursement amount information based on the visit record information and the preset reimbursement rule;

[0094] A submodule for generating verification results of the number of people reimbursed, for generating verification results of the number of people reimbursed based on the visit record information and the current number of people reimbursed;

[0095] A reimbursement amount verification result generation submodule, used to generate a reimbursement amount verification result based on the standard reimbursement amount information and the current reimbursement amount information;

[0096] The valid bill determination submodule is used to determine that the target bill is the valid bill if the verification result of the number of people reimbursed and the verification result of the reimbursement amount are both passed.

[0097] Furthermore, the standard reimbursement amount information determination submodule includes:

[0098] A current reimbursement number information determining unit, used to determine the current reimbursement number information according to the visit record information;

[0099] a per capita consumption information determination unit, configured to determine per capita consumption information matching the visit record information according to preset insurance rules;

[0100] The standard reimbursement amount information determination unit is used to calculate the product of the current number of reimbursement persons and the per capita consumption information, and use the product as the standard reimbursement amount information.

[0101] Furthermore, the bill verification module 420 further includes:

[0102] A payment serial number verification result generation submodule is used to verify the current payment serial number information through a third-party authentication platform and generate a payment serial number verification result;

[0103] The valid bill determination submodule is used to determine that the target bill is the valid bill if the payment serial number verification result is passed.

[0104] Furthermore, the information verification device 400 based on the visit record includes:

[0105] An invalid bill determination module, configured to determine that the target bill is an invalid bill if the verification result of the number of people to be reimbursed, the verification result of the reimbursement amount and / or the verification result of the payment serial number are failed;

[0106] The alarm prompt sending module is used to generate an alarm prompt when the target bill is the invalid bill, and send the alarm prompt to the target user.

[0107] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0108] The above-mentioned device can be implemented in the form of a computer program. Figure 5 Runs on the computer device shown.

[0109] See also Figure 5 , Figure 5 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0110] See also Figure 5 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0111] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any information verification method based on the access record.

[0112] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0113] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any information verification method based on the access record.

[0114] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0115] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0116] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0117] Generate visit record information based on the target user's current location information and current business needs;

[0118] Extract various ticket information in the target ticket by using preset optical character recognition (OCR) technology, and verify whether the target ticket is a valid ticket by using the visit record information and various ticket information;

[0119] When it is determined that the target bill is the valid bill, a notification message indicating that the reimbursement review has been passed is sent to the target user.

[0120] In one embodiment, various bill information in the target bill is extracted by using a preset optical character recognition (OCR) technology to achieve:

[0121] Performing image segmentation and image denoising on the target bill by using the preset OCR technology to generate at least one target bill image block;

[0122] The text information in each of the target bill blocks is identified, and the text information is used as the bill information, wherein the text information includes current reimbursement amount information, current number of reimbursements information, and current payment serial number information.

[0123] In one embodiment, the preset OCR technology is used to perform image segmentation and image denoising on the target bill to generate at least one target bill image block, which is used to achieve:

[0124] De-noising the target bill by using a Gaussian filtering method, and determining the text area and image area of ​​the target bill by using physical layout analysis and logical layout analysis;

[0125] Performing image segmentation processing on the text area through a horizontal projection histogram and a vertical direction histogram to generate at least one text area block;

[0126] Performing image segmentation processing on the image area by using a preset edge recognition algorithm to generate at least one image area block;

[0127] Each of the text area tiles and each of the image area tiles are determined as the target bill tile.

[0128] In one embodiment, the visit record information and each item of the ticket information are used to verify whether the target ticket is a valid ticket, so as to achieve:

[0129] Obtaining a preset reimbursement rule, and determining standard reimbursement amount information based on the visit record information and the preset reimbursement rule;

[0130] Based on the visit record information and the current number of people reimbursed, generate a verification result of the number of people reimbursed;

[0131] Generate a reimbursement amount verification result based on the standard reimbursement amount information and the current reimbursement amount information;

[0132] When both the verification result of the number of people reimbursed and the verification result of the reimbursement amount are passed, the target bill is determined to be the valid bill.

[0133] In one embodiment, a preset reimbursement rule is obtained, and based on the visit record information and the preset reimbursement rule, standard reimbursement amount information is determined to achieve:

[0134] Determine the current number of people reimbursed according to the visit record information;

[0135] According to the preset insurance rules, determine the per capita consumption information matching the visit record information;

[0136] The product of the current number of people being reimbursed and the per capita consumption information is calculated, and the product is used as the standard reimbursement amount information.

[0137] In one embodiment, the visit record information and each item of the ticket information are used to verify whether the target ticket is a valid ticket, so as to achieve:

[0138] Verify the current payment serial number information through a third-party authentication platform to generate a payment serial number verification result;

[0139] When the payment serial number verification result is passed, the target bill is determined to be the valid bill.

[0140] In one embodiment, various ticket information in the target ticket is extracted by using a preset optical character recognition (OCR) technology, and after verifying whether the target ticket is a valid ticket by using the visit record information and the various ticket information, it is used to achieve:

[0141] If the verification result of the number of people to be reimbursed, the verification result of the amount to be reimbursed and / or the verification result of the payment serial number are failed, the target bill is determined to be an invalid bill;

[0142] In the case that the target ticket is the invalid ticket, an alarm prompt is generated and sent to the target user.

[0143] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any one of the information verification methods based on visit records provided in the embodiments of the present application.

[0144] The computer-readable storage medium may be an internal storage unit of the computer device described in the above embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device.

[0145] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An information verification method based on visit records, characterized in that: include: Generate visit record information based on the target user's current location information and current business needs; Extract various ticket information in the target ticket by using preset optical character recognition (OCR) technology, and verify whether the target ticket is a valid ticket by using the visit record information and various ticket information; When it is determined that the target bill is the valid bill, a notification message indicating that the reimbursement review has been passed is sent to the target user.

2. The information verification method based on visit records according to claim 1 is characterized in that: The method of extracting various bill information from the target bill by using the preset optical character recognition (OCR) technology includes: Performing image segmentation and image denoising on the target bill by using the preset OCR technology to generate at least one target bill image block; The text information in each of the target bill blocks is identified, and the text information is used as the bill information, wherein the text information includes current reimbursement amount information, current number of reimbursements information, and current payment serial number information.

3. The information verification method based on visit records according to claim 2 is characterized in that: The step of performing image segmentation and image denoising on the target bill by using the preset OCR technology to generate at least one target bill image block includes: De-noising the target bill by using a Gaussian filtering method, and determining the text area and image area of ​​the target bill by using physical layout analysis and logical layout analysis; Performing image segmentation processing on the text area through a horizontal projection histogram and a vertical direction histogram to generate at least one text area block; Performing image segmentation processing on the image area by using a preset edge recognition algorithm to generate at least one image area block; Each of the text area tiles and each of the image area tiles are determined as the target bill tile.

4. The information verification method based on visit records according to claim 2 is characterized in that: The ticket information is the current reimbursement amount information and the current number of reimbursement persons information. The verification of whether the target ticket is a valid ticket by using the visit record information and each item of the ticket information includes: Obtaining a preset reimbursement rule, and determining standard reimbursement amount information based on the visit record information and the preset reimbursement rule; Based on the visit record information and the current number of people reimbursed, generate a verification result of the number of people reimbursed; Based on the standard reimbursement amount information and the current reimbursement amount information, generating a reimbursement amount verification result; When both the verification result of the number of people reimbursed and the verification result of the reimbursement amount are passed, the target bill is determined to be the valid bill.

5. The information verification method based on visit records according to claim 4 is characterized in that: The obtaining of the preset reimbursement rules and determining the standard reimbursement amount information based on the visit record information and the preset reimbursement rules includes: Determine the current number of people reimbursed according to the visit record information; According to preset insurance rules, determine per capita consumption information that matches the visit record information; The product of the current number of people being reimbursed and the per capita consumption information is calculated, and the product is used as the standard reimbursement amount information.

6. The information verification method based on visit records according to claim 5 is characterized in that: The bill information is the current payment serial number information, and the verification of whether the target bill is a valid bill by using the visit record information and each item of the bill information includes: Verify the current payment serial number information through a third-party authentication platform to generate a payment serial number verification result; When the payment serial number verification result is passed, the target bill is determined to be the valid bill.

7. The information verification method based on visit records according to claim 6 is characterized in that: After extracting various ticket information in the target ticket by using the preset optical character recognition (OCR) technology and verifying whether the target ticket is a valid ticket by using the visit record information and various ticket information, the method includes: If the verification result of the number of people to be reimbursed, the verification result of the amount to be reimbursed and / or the verification result of the payment serial number are failed, the target bill is determined to be an invalid bill; In the case that the target ticket is the invalid ticket, an alarm prompt is generated and sent to the target user.

8. An information verification device based on visit records, characterized in that: include: A visit record information generation module is used to generate visit record information based on the user's current location information and current business needs of the target user; The bill verification module is used to extract various bill information in the target bill by using the preset optical character recognition (OCR) technology, and verify whether the target bill is a valid bill by using the visit record information and various bill information; The notification information sending module is used to send notification information of reimbursement approval to the target user when it is determined that the target bill is the valid bill.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the information verification method based on the visit record as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the information verification method based on the visit record as described in any one of claims 1 to 7.