Intelligent Billing Management Method, Device, Computer Equipment and Storage Medium

Abstract

The present invention relates to the field of computer technology, and particularly to an intelligent bill management method, device, computer device and storage medium. The intelligent bill management method includes the following steps: obtaining a to-be-stored intelligent payment order and performing content recognition on the intelligent payment order; generating and displaying an information entry page according to the recognition result, and receiving the information entered by the user through the information entry page; binding the recognition result with the entered information and submitting it for review, and filing and storing it after the review is passed; generating a download link. The method provided by the present invention realizes the standardized processing of re-factoring materials by obtaining the intelligent payment order and performing content recognition, generating an information entry page according to the recognition result and submitting it for review. The processing process has a high degree of automation, reduces manual operations, has a high accuracy rate, and saves labor costs; and by generating a download link, it is convenient for later reference, which is simple and fast.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to an intelligent bill management method, device, computer device, and storage medium. Background Art

[0002] Factoring, also known as accounts receivable financing, is a financial term. It refers to the transfer of accounts receivable arising from a seller's current or future goods sales / service contracts with a buyer to a factor (a financial institution providing factoring services). The factor provides a series of comprehensive financial services such as financing, buyer credit assessment, sales account management, credit risk guarantee, and account collection.

[0003] Re-factoring is the re-transfer of creditor's rights on the basis of factoring. That is, after an enterprise transfers its accounts receivable creditor's rights arising from trade to a factor company, the factor company then transfers the rights and obligations after this transfer to other factors. Bank re-factoring is usually a way for a bank to provide financing to a commercial factor company after approving its credit line.

[0004] The re-factoring business of financial institutions requires a lot of intelligent payment document materials. The existing management of intelligent payment document materials is basically handled manually, lacking a unified standard process and corresponding technical means to improve the accuracy and efficiency of processing, and thus needs to be improved. Summary of the Invention

[0005] Based on this, it is necessary to provide an intelligent bill management method, device, computer device, and storage medium for the above problems.

[0006] An embodiment of the present invention is implemented as follows. An intelligent bill management method, the intelligent bill management method includes the following steps:

[0007] Obtain an intelligent payment document to be warehoused and perform content recognition on the intelligent payment document;

[0008] Generate and display an information entry page according to the recognition result, and receive the information entered by the user through the information entry page;

[0009] Bind the recognition result with the entered information and submit it for review. If the review is passed, file it for warehousing;

[0010] Generate a download link.

[0011] In one embodiment, the present invention provides an intelligent bill management device, the intelligent bill management device includes:

[0012] An identification module, configured to obtain an intelligent payment document to be warehoused and perform content recognition on the intelligent payment document;

[0013] A page generation module, configured to generate and display an information entry page according to the recognition result, and receive the information entered by the user through the information entry page;

[0014] An audit module, configured to bind the recognition result with the entered information and submit it for audit. If the audit is passed, it will be archived and stored in the database;

[0015] A sharing module, configured to generate a download link.

[0016] In one embodiment, the present invention provides a computer device, including a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor is caused to execute the steps of the above-mentioned intelligent bill management method.

[0017] In one embodiment, the present invention provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the processor is caused to execute the steps of the above-mentioned intelligent bill management method.

[0018] The method provided by the present invention realizes the standardized processing of factoring information by obtaining a smart payment bill and performing content recognition, generating an information entry page according to the recognition result and submitting it for audit. The processing process has a high degree of automation, reduces manual operations, has a high accuracy rate, and saves labor costs; and by generating a download link, it is convenient for later reference, which is simple and fast. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of the intelligent bill management method provided for one embodiment;

[0020] Figure 2 A structural block diagram of the intelligent bill management method device provided for one embodiment;

[0021] Figure 3 An internal structural block diagram of a computer device for one embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0023] It will be appreciated that the terms "first", "second", etc. used in the present invention may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of the present invention, the first xx script may be referred to as the second xx script, and similarly, the second xx script may be referred to as the first xx script.

[0024] As Figure 1 shown, in one embodiment, an intelligent bill management method is proposed, which may specifically include the following steps:

[0025] Obtain the intelligent payment order to be warehoused and perform content recognition on the intelligent payment order;

[0026] Generate and display an information entry page according to the recognition result, and receive the information entered by the user through the information entry page;

[0027] Bind the recognition result with the entered information and submit it for review. If the review is passed, file it in the warehouse;

[0028] Generate a download link.

[0029] In this embodiment, the intelligent payment order to be warehoused may specifically be in the form of text or electronic form. For the text form, to achieve its automated processing, it should also be converted into electronic form. In this embodiment, content recognition is performed on the intelligent payment order, that is, relevant information on the intelligent payment order is automatically read, so as to realize the automatic filing and sorting of the intelligent payment order.

[0030] In this embodiment, an information entry page is generated according to the recognition result for the user to enter relevant supplementary information. It will be appreciated that in the embodiments of the present invention, through the information entry page, the user can input relevant information through external input devices such as keyboards, or upload other electronic documents, pictures and other materials through relevant ports. These materials together constitute the main materials of the re-factoring business. In this embodiment, each intelligent payment order allows one re-factoring business to be added and does not allow multiple additions, providing a safe and effective guarantee for the re-factoring business of the fund provider.

[0031] In this embodiment, the entered information is bound to the recognition result and submitted for review as a data packet of a business. If the review is passed, it is automatically filed in the warehouse; after warehousing, a unique download link is generated, and the full set of materials of the same re-factoring business can be downloaded through this link subsequently.

[0032] The method provided by the present invention realizes the standardized processing of factoring materials by obtaining Zhifu bills, performing content recognition, generating an information entry page based on the recognition results, and submitting for review. The processing process has a high degree of automation, reduces manual operations, has a high accuracy rate, and saves labor costs. Moreover, by generating a download link, it is convenient for later reference, which is simple and fast.

[0033] In an embodiment of the present invention, the content recognition of the Zhifu bill includes the following steps:

[0034] Obtain the Zhifu bill image and preprocess the obtained image;

[0035] Upload the Zhifu bill image to the recognition system and obtain the recognition result returned by the recognition system.

[0036] In this embodiment, the Zhifu bill image can be obtained by scanning through a scanning device connected to the system; for non-paper documents, it can be directly read, or format-converted, or captured by screenshot, etc., which are optional specific implementation methods. In this embodiment, the purpose of preprocessing the image is to improve the accuracy of later recognition.

[0037] In this embodiment, upload the preprocessed image to the recognition system, and after the recognition system performs recognition processing, return the corresponding recognition result. In an embodiment of the present invention, preferably, the recognition system provides recognition service ports for multiple service providers, and realizes the automatic recognition of the Zhifu bill by selecting one or more service providers; the returned recognition result is preferably in text form.

[0038] In an embodiment of the present invention, the content recognition of the Zhifu bill includes the following steps:

[0039] Obtain the Zhifu bill image and preprocess the obtained image;

[0040] Upload the Zhifu bill image to the recognition system and obtain the recognition result returned by the recognition system;

[0041] Repeat the above steps to process the first 10% of the batch of Zhifu bill images;

[0042] According to the return results of the first 10% of the images, determine the optimal port combination for the batch of images according to the principle of the least quantity and the best continuity;

[0043] Batch process the remaining images according to the determined optimal port combination.

[0044] In this embodiment, the Zhifu bill image can be obtained by scanning through a scanning device connected to the system; for non-paper documents, it can be directly read, or format-converted, or captured by screenshot, etc., which are optional specific implementation methods. In this embodiment, the purpose of preprocessing the image is to improve the accuracy of later recognition.

[0045] In this embodiment, the preprocessed image is uploaded to the recognition system, and after the recognition system performs recognition processing, the corresponding recognition result is returned. In the embodiment of the present invention, preferably, the recognition system provides recognition service ports of multiple service providers, and the automatic recognition of intelligent payment bills is realized by selecting one or more service providers; the returned recognition result is preferably in text form.

[0046] In this embodiment, for a batch of recognition tasks, by processing the first 10% of the quantity, according to the returned recognition result, the optimal port combination for batch image recognition is determined based on the principle of the fewest ports and the best continuity. The fewest ports here means that, on the premise of ensuring the best accuracy of the recognition result, a combination of the fewest ports is adopted, and at the same time, according to the continuity principle, the optimal port combination is found among the port combinations with the same number of ports, and the remaining images are all processed quickly in batches according to the determined port combination.

[0047] The following is an example for illustration:

[0048] For a recognition task with 5 sub-images, this task is denoted as (sub-image 1, sub-image 2, sub-image 3, sub-image 4, sub-image 5); taking 5 service ports as an example, the combination of its returned results is (port 1 or port 3 or port 5; port 4 or port 5; port 2 or port 3 or port 5; port 1 or port 3 or port 4; port 4 or port 5), and several port combinations determined according to the principle of the fewest ports are (port 5; port 5; port 5; port 1 or port 3 or port 4; port 5) or (port 5; port 5; port 5; port 4; port 4 or port 5); further, according to the continuity principle, the determined port combination is (port 5; port 5; port 5; port 4; port 4), that is, for the first 3 sub-images, they are all processed by port 5, and for the subsequent 2 sub-images, they are all processed by port 4. In this way, the frequent jumping between different ports during the data sending and receiving process is avoided, and the data return speed is improved.

[0049] The specific steps to find the optimal port combination can be:

[0050] Determine all port combinations;

[0051] Arrange them in ascending order according to the number of ports included in each port combination;

[0052] For several combinations of ports with the smallest number of ports, calculate their continuity, and the combination with the highest continuity is taken as the optimal port combination; the continuity is equal to the sum of the number of times the elements continuously repeat in sequence in the combination. For example, for the combination (port 5; port 5; port 5; port 4; port 4), its connectivity is: (0 + 1 + 2) + (0 + 1) = 4, where (0 + 1 + 2) is the continuity generated by the continuous occurrence of port 5 three times; (0 + 1) is the continuity of the continuous occurrence of port 4 twice.

[0053] In an embodiment of the present invention, preprocessing the acquired image includes the following steps:

[0054] Desaturate the Zhifu bill image, and perform high-contrast processing on the desaturated image;

[0055] Identify the characteristic information of the Zhifu bill, and obtain the corresponding template according to the characteristic information;

[0056] Segment the preprocessed Zhifu bill into several sub-images according to the acquired template.

[0057] In this embodiment, the desaturation process can highlight the image contour. The desaturation process belongs to the prior art, and the specific desaturation algorithm refers to the prior art; increasing the contrast can be achieved by simultaneously increasing the dark and bright parts, which can be implemented with reference to the prior art, and this embodiment will not elaborate on this.

[0058] In this embodiment, for different types of Zhifu bills, by obtaining the corresponding template, the image is divided into several sub-images according to the template. The template contains the division scheme of the sub-images. The template is a general Zhifu bill corresponding to the corresponding type of Zhifu bill, and is divided into several blocks according to the content layout, recording the division rules of the sub-images of the same type of Zhifu bill.

[0059] In an embodiment of the present invention, uploading the Zhifu bill image to the recognition system and obtaining the recognition result returned by the recognition system specifically includes the following steps:

[0060] Send each sub-image to several recognition ports of the recognition system at the same time, and each recognition port is connected to a recognition service platform;

[0061] Obtain the recognition result returned by each recognition port for the same sub-image;

[0062] Calculate the coincidence rate of each returned result. For any returned result, the coincidence rate is equal to the ratio of the number of returned results that are exactly the same as this returned result to the total number of recognition ports;

[0063] Select the returned result with the largest coincidence rate as the returned result of the current sub-image.

[0064] In this embodiment, it is preferably sent to all idle ports simultaneously; comparing whether any two return results are the same can be determined by subtracting after binaryizing the data, or can be achieved by comparing the check codes (such as hash values, etc.) of the two return results.

[0065] In an embodiment of the present invention, the step of selecting the return result with the largest coincidence rate as the return result of the current sub-image is followed by the following steps:

[0066] Obtain the return results with the largest coincidence rate of all sub-images, and determine the recognition port group according to the return results with the largest coincidence rate of all sub-images:

[0067] S = (S1, S2, S3, …, S n )

[0068] Where: S is the recognition port group of any image; S1 to S n Are respectively the recognition ports corresponding to the return results with the largest coincidence rate of the 1st to nth sub-images, and each item in S1 to S n Has at least one element and at most m elements, where m is the total number of recognition ports;

[0069] Determine the optimal port combination of this image according to the principle of the least quantity and the best continuity;

[0070] Process other images according to the determined optimal port combination.

[0071] In this embodiment, the method of determining the optimal port combination of this image according to the principle of the least quantity and the best continuity refers to the foregoing, and will not be elaborated herein. In this embodiment, after determining the optimal port combination, batch processing of the remaining images is performed through this combination.

[0072] In an embodiment of the present invention, the step of generating and displaying an information entry page according to the recognition result specifically includes the following steps:

[0073] Obtain the return results of each sub-image of the Zhifu single image;

[0074] Fill the return result of each sub-image into the corresponding position of the preset information entry page;

[0075] Output the information entry page.

[0076] In this embodiment, according to the return results of each image of the Zhifu single, these results are filled into the corresponding positions of the preset information entry page to realize automatic page generation.

[0077] As Figure 2 shown, an embodiment of the present invention also provides an intelligent bill management device, which specifically may include:

[0078] An identification module, configured to obtain the Zhifu bill to be stored in the warehouse and perform content identification on the Zhifu bill;

[0079] A page generation module, configured to generate and display an information entry page according to the identification result, and receive the information entered by the user through the information entry page;

[0080] An audit module, configured to bind the identification result with the entered information and submit it for audit. If the audit is passed, it will be archived and stored in the warehouse;

[0081] A sharing module, configured to generate a download link.

[0082] In this embodiment, for the explanations of the functions and roles of each module of the above intelligent bill management device, reference can be made to the content of the method part of the present invention, and details will not be repeated here.

[0083] Figure 3 shows the internal structure diagram of a computer device in an embodiment. As Figure 3 shown, the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the intelligent bill management method provided by the embodiments of the present invention. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute the intelligent bill management method provided by the embodiments of the present invention. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0084] Those skilled in the art can understand that Figure 3 the structure shown in

[0085] is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. Figure 3 shown, and the computer program can run on the computer device as

[0086] In one embodiment, a computer device is provided. The computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0087] Obtain a Zhifu bill to be warehoused and perform content recognition on the Zhifu bill;

[0088] Generate and display an information entry page according to the recognition result, and receive the information entered by the user through the information entry page;

[0089] Bind the recognition result with the entered information and submit it for review. If the review is passed, file it for warehousing;

[0090] Generate a download link.

[0091] In one embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the processor is caused to execute the following steps:

[0092] Obtain a Zhifu bill to be warehoused and perform content recognition on the Zhifu bill;

[0093] Generate and display an information entry page according to the recognition result, and receive the information entered by the user through the information entry page;

[0094] Bind the recognition result with the entered information and submit it for review. If the review is passed, file it for warehousing;

[0095] Generate a download link.

[0096] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily have to be executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0097] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0098] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0099] The above embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims

1. An intelligent bill management method, characterized in that, The intelligent bill management method includes the following steps: Obtain the intelligent payment order to be warehoused and perform content recognition on the intelligent payment order; Generate and display an information entry page according to the recognition result, and receive the information entered by the user through the information entry page; Bind the recognition result with the entered information and submit it for review. If the review is passed, file it and warehousing; Generate a download link; Perform content recognition on the intelligent payment order, including the following steps: Obtain the intelligent payment order image and preprocess the obtained image; Upload the intelligent payment order image to the recognition system and obtain the recognition result returned by the recognition system; Repeat the above steps to process the first 10% of the batch of intelligent payment order images; According to the return results of the first 10% of the images, determine the optimal port combination of the batch of images according to the principle of the least quantity and the best continuity; Process the remaining images in batches according to the determined optimal port combination; Preprocess the obtained image, including the following steps: Desaturate the intelligent payment order image and perform high-contrast processing on the desaturated image; Identify the characteristic information of the intelligent payment order and obtain the corresponding template according to the characteristic information; Segment the preprocessed intelligent payment order into several sub-images according to the obtained template; The step of uploading the intelligent payment order image to the recognition system and obtaining the recognition result returned by the recognition system specifically includes the following steps: Send each sub-image to several recognition ports of the recognition system at the same time, and each recognition port is connected to a recognition service platform; Obtain the recognition results returned by each recognition port for the same sub-image; Calculate the coincidence rate of each return result. For any return result, the coincidence rate is equal to the ratio of the number of return results that are exactly the same as this return result to the total number of recognition ports; Select the return result with the largest coincidence rate as the return result of the current sub-image; After the step of selecting the return result with the largest coincidence rate as the return result of the current sub-image, the following steps are further included: Obtain the return results with the largest coincidence rate of all sub-images, and determine the recognition port group according to the return results with the largest coincidence rate of all sub-images: S = (S1, S2, S3, …, S n ) Where: S is the recognition port group of any image; S1 to Sn are the recognition ports corresponding to the return results with the largest coincidence rate of the 1st to nth sub-images respectively. Each item in S1 to Sn has at least one element and at most m elements, where m is the total number of recognition ports; Determine the optimal port combination of this image according to the principle of the least quantity and the best continuity; Process other images according to the determined optimal port combination.

2. The intelligent bill management method according to claim 1, wherein, The step of generating and displaying an information entry page according to the recognition result specifically includes the following steps: Obtain the return result of each sub-image of the intelligent payment order image; Fill the return result of each sub-image into the corresponding position of the preset information entry page; Output the information entry page.

3. An intelligent bill management device, characterized in that, The intelligent bill management device includes: A recognition module, which is used to obtain the intelligent payment order to be warehoused and perform content recognition on the intelligent payment order; A page generation module, which is used to generate and display an information entry page according to the recognition result, and receive the information entered by the user through the information entry page; A review module, which is used to bind the recognition result with the entered information and submit it for review. If the review is passed, file it and warehousing; A sharing module, which is used to generate a download link; Perform content recognition on the intelligent payment order, including the following steps: Obtain the Zhifu bill image and preprocess the obtained image; Upload the Zhifu bill image to the recognition system and obtain the recognition result returned by the recognition system; Repeat the above steps to process the first 10% of the batch of Zhifu bill images; According to the return results of the first 10% of the images, determine the optimal port combination of the batch of images according to the principle of the least quantity and the best continuity; Batch process the remaining images according to the determined optimal port combination; Preprocess the obtained image, including the following steps: Desaturate the Zhifu bill image and perform high-contrast processing on the desaturated image; Identify the characteristic information of the Zhifu bill and obtain the corresponding template according to the characteristic information; Segment the preprocessed Zhifu bill into several sub-images according to the obtained template; The step of uploading the Zhifu bill image to the recognition system and obtaining the recognition result returned by the recognition system specifically includes the following steps: Send each sub-image to several recognition ports of the recognition system at the same time, and each recognition port is connected to a recognition service platform; Obtain the recognition results returned by each recognition port for the same sub-image; Calculate the coincidence rate of each return result. For any return result, the coincidence rate is equal to the ratio of the number of return results that are exactly the same as this return result to the total number of recognition ports; Select the return result with the largest coincidence rate as the return result of the current sub-image; After the step of selecting the return result with the largest coincidence rate as the return result of the current sub-image, the following steps are further included: Obtain the return results with the largest coincidence rate of all sub-images and determine the recognition port group according to the return results with the largest coincidence rate of all sub-images: S = (S1, S2, S3, …, S n ) Where: S is the recognition port group of any image; S1 to Sn are the recognition ports corresponding to the return results with the largest coincidence rate of the 1st to nth sub-images respectively. Each item in S1 to Sn has at least one element and at most m elements, where m is the total number of recognition ports; Determine the optimal port combination of this image according to the principle of the least quantity and the best continuity; Process other images according to the determined optimal port combination.

4. A computer device, characterized in that, Including a memory and a processor, a computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the intelligent bill management method described in any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, the processor executes the steps of the intelligent bill management method described in any one of claims 1 to 2.

Images