Monitoring and printing method and device

Abstract

Embodiments of the present invention disclose a seal supervision method and apparatus, which can be applied to the financial field or other technical fields. The method includes: extracting a seal area image from a stamped page, inputting the seal area image into a preset first recognition model to obtain a first recognition result; inputting the seal area image after removing the seal into a preset second recognition model to obtain a second recognition result; if the second recognition result indicates the existence of signature text, generating signature compliance area information according to the position information, and extracting a signature compliance area image from the stamped page according to the signature compliance area information; inputting the signature compliance area image into a preset third recognition model to obtain a third recognition result; if the signature text recognized by the third recognition model is consistent with the seal text recognized by the first recognition model, generating correct seal usage information. The present invention helps to improve the accuracy and efficiency of seal supervision.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and in particular, to an imprint monitoring method and device. Background Art

[0002] Currently, the work of imprint monitoring is usually completed manually by the imprint monitoring personnel. For the imprint monitoring personnel, it is necessary to manually determine every day whether the imprints on a large number of stamped pages are accurate and compliant. Completing the imprint monitoring work solely by manual labor is extremely laborious and error-prone, and it is difficult to ensure accuracy and efficiency, and a large amount of labor costs need to be invested.

[0003] Therefore, the prior art lacks a more efficient and accurate imprint monitoring method. Summary of the Invention

[0004] In order to solve at least one of the above technical problems in the background art, the present invention proposes an imprint monitoring method and device.

[0005] To achieve the above object, according to one aspect of the present invention, there is provided an imprint monitoring method, which includes:

[0006] Determine the position information of the seal on the stamped page, extract the seal area image from the stamped page according to the position information, and input the seal area image into a preset first recognition model to obtain a first recognition result, where the first recognition model is used to recognize the seal characters in the seal area image;

[0007] Remove the seal from the seal area image, and input the seal area image after removing the seal into a preset second recognition model to obtain a second recognition result, where the second recognition model is used to recognize whether there is signature text in the seal area image after removing the seal;

[0008] If the second recognition result is that there is signature text, generate signature compliance area information according to the position information, and extract the signature compliance area image from the stamped page according to the signature compliance area information;

[0009] Input the signature compliance area image into a preset third recognition model to obtain a third recognition result, where the third recognition model is used to recognize the signature text in the signature compliance area image;

[0010] If the signature text recognized by the third recognition model is consistent with the seal characters recognized by the first recognition model, generate correct imprint information.

[0011] Optionally, before determining the position information of the seal on the stamped page, it further includes:

[0012] Obtain the original document to be stamped corresponding to the stamped page;

[0013] Compare the stamped page with each page in the original document to be stamped by means of similarity comparison to verify whether the stamped page is in the original document to be stamped;

[0014] The determination of the position information of the seal on the stamped page specifically includes:

[0015] If the stamped page is in the original document to be stamped, determine the position information of the seal on the stamped page.

[0016] Optionally, the seal supervision method further includes:

[0017] If there is a signature area on the stamped page, extract the signature area image from the stamped page;

[0018] Obtain the seal approval form corresponding to the stamped page, and identify the authorized person's name from the seal approval form;

[0019] Identify the text in the signature area image through a preset text recognition model. If the authorized person's name is in the text recognized by the text recognition model, generate signature compliance information.

[0020] Optionally, the seal supervision method further includes:

[0021] Generate stamped page compliance information according to the correct seal usage information and the signature compliance information.

[0022] Optionally, the seal supervision method further includes:

[0023] If the third recognition model fails to recognize the signature text, generate the first seal usage error information;

[0024] If the signature text recognized by the third recognition model is inconsistent with the seal text recognized by the first recognition model, generate the second seal usage error information.

[0025] Optionally, the position information includes: the coordinates of the four vertices of the seal area, where the seal area is a rectangular area;

[0026] The generation of the signature compliance area information according to the position information specifically includes:

[0027] Generate the coordinates of the four vertices of the signature compliance area according to the coordinates of the four vertices of the seal area and the width and height of the seal area, where the signature compliance area is a rectangular area.

[0028] To achieve the above object, according to another aspect of the present invention, there is provided a seal supervision device, which includes:

[0029] The seal text recognition unit is used to determine the position information of the seal on the stamped page, extract the seal area image from the stamped page according to the position information, and input the seal area image into a preset first recognition model to obtain a first recognition result, where the first recognition model is used to recognize the seal text in the seal area image;

[0030] The signature text determination unit is used to remove the seal from the seal area image, input the seal area image after removing the seal into a preset second recognition model to obtain a second recognition result, where the second recognition model is used to recognize whether there is a signature text in the seal area image after removing the seal;

[0031] The signature compliance area image extraction unit is used to, if the second recognition result is that there is a signature text, generate signature compliance area information according to the position information, and extract the signature compliance area image from the stamped page according to the signature compliance area information;

[0032] The signature text recognition unit is used to input the signature compliance area image into a preset third recognition model to obtain a third recognition result, where the third recognition model is used to recognize the signature text in the signature compliance area image;

[0033] The correct seal usage information generation unit is used to generate correct seal usage information if the signature text recognized by the third recognition model is consistent with the seal text recognized by the first recognition model.

[0034] Optionally, the seal supervision device further includes:

[0035] The original document to be sealed acquisition unit is used to acquire the original document to be sealed corresponding to the stamped page;

[0036] The stamped page verification unit is used to compare the stamped page with each page in the original document to be sealed by a similarity comparison method to verify whether the stamped page is in the original document to be sealed;

[0037] The seal text recognition unit is specifically used to determine the position information of the seal on the stamped page if the stamped page is in the original document to be sealed.

[0038] Optionally, the seal supervision device further includes:

[0039] The signature area image extraction unit is used to extract the signature area image from the stamped page if there is a signature area on the stamped page;

[0040] The authorized person name recognition unit is used to obtain the seal approval form corresponding to the stamped page and recognize the authorized person name from the seal approval form;

[0041] The signature compliance verification unit is used to recognize the text in the signature area image through a preset text recognition model. If the authorized person name is in the text recognized by the text recognition model, signature compliance information is generated.

[0042] To achieve the above object, according to another aspect of the present invention, there is also provided a computer device, including 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 steps of the above seal supervision method are implemented.

[0043] To achieve the above object, according to another aspect of the present invention, there is also provided a computer-readable storage medium, on which a computer program / instructions are stored. When the computer program / instructions are executed by a processor, the steps of the above seal supervision method are implemented.

[0044] To achieve the above object, according to another aspect of the present invention, there is also provided a computer program product, including a computer program / instructions. When the computer program / instructions are executed by a processor, the steps of the above seal supervision method are implemented.

[0045] The beneficial effects of the present invention are as follows: In the embodiments of the present invention, a preset recognition model is used to recognize the seal and the seal text, and then seal supervision is carried out according to the recognition results, achieving the beneficial effects of efficient and accurate seal supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings. In the drawings:

[0047] Figure 1 is the first flowchart of the seal supervision method in the embodiments of the present invention;

[0048] Figure 2 is the second flowchart of the seal supervision method in the embodiments of the present invention;

[0049] Figure 3 is the third flowchart of the seal supervision method in the embodiments of the present invention;

[0050] Figure 4 is the first structural block diagram of the seal supervision device in the embodiments of the present invention;

[0051] Figure 5 It is the second structural block diagram of the printing supervision device according to an embodiment of the present invention;

[0052] Figure 6 It is the third structural block diagram of the printing supervision device according to an embodiment of the present invention;

[0053] Figure 7 It is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed implementation manners

[0054] In order to enable those skilled in the art of the present technology to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0055] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] It should be noted that the terms "including" and "having" in the description and claims of the present invention and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0057] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0058] It should be noted that the acquisition, storage, use, processing, etc. of data in the technical solution of the present application all comply with the relevant regulations of national laws and regulations.

[0059] It should be noted that the printing supervision method and device of the present invention can be applied to the financial field and can also be applied to other technical fields.

[0060] The present invention proposes a seal supervision method and device based on artificial intelligence. The solution of the present invention can replace the process of manual seal supervision, help the seal supervisors determine whether the stamped page is in the original document to be sealed, whether the seal is compliant and accurate, and at the same time help the seal supervisors judge whether the document to be sealed needs to be signed. If signature is required, it is confirmed whether the relevant page signature or seal is consistent with the authorized person in the document to be sealed, saving labor and time costs. The intelligent seal supervision system cooperates with manual post-inspection, which can improve the seal supervision efficiency and accuracy.

[0061] Figure 1 is the first flowchart of the seal supervision method in the embodiment of the present invention. As Figure 1 shown, in an embodiment of the present invention, the seal supervision method of the present invention includes steps S101 to S105.

[0062] Step S101, determine the position information of the seal in the stamped page, extract the seal area image from the stamped page according to the position information, and input the seal area image into a preset first recognition model to obtain a first recognition result, where the first recognition model is used to recognize the seal characters in the seal area image.

[0063] In the embodiment of the present invention, the stamped page specifically refers to the stamped page image.

[0064] In an embodiment of the present invention, the first recognition result is the seal characters.

[0065] In an embodiment of the present invention, the present invention can input the stamped page image into a preset seal detection model to obtain the position information of the seal in the stamped page. In an embodiment of the present invention, the position information of the seal specifically includes: the coordinates of the four vertices of the seal area, where the seal area is a rectangular area.

[0066] In an embodiment of the present invention, the above-mentioned seal detection model can be obtained by training based on a preset machine learning model and using a preset training sample. The machine learning model can adopt various models in the prior art, for example, a convolutional neural network model and a YOLO (You Only Look Once) model, etc. The training sample used is the stamped page image with the position information of the seal marked.

[0067] In an embodiment of the present invention, the present invention specifically detects the coordinates of the four vertices (left, top, right, bottom) of each seal in the stamped page through the seal detection model, and saves the size (width, height) of each seal.

[0068] In an embodiment of the present invention, the present invention can use the crop method in the PIL package to crop and save all the seal area images according to the four coordinates.

[0069] In one embodiment of the present invention, after obtaining the seal area image, the present invention first removes other colors based on the color channel for the seal area image, and only retains the color of the seal (such as red), and identifies the text on the seal through the first recognition model.

[0070] In one embodiment of the present invention, the first recognition model may adopt a general text recognition model in the prior art. In another embodiment of the present invention, the first recognition model may be obtained by training based on a preset machine learning model and using a preset training sample. The machine learning model may adopt various models in the prior art, for example, CTPN (Connection Text Proposal Network) model, YOLO model, and CRNN (Convolutional Recurrent Neural Network) model, etc. The training sample used is a seal image marked with text content. In one embodiment of the present invention, the first recognition model may specifically use the CTPN+YOLO+CRNN (i.e., a model combined by CTPN, YOLO, and CRNN) training model.

[0071] Step S102, remove the seal in the seal area image, and input the seal area image after removing the seal into a preset second recognition model to obtain a second recognition result, where the second recognition model is used to identify whether there is signature text in the seal area image after removing the seal.

[0072] In one embodiment of the present invention, the present invention removes the color of the seal based on the color channel for the seal area image, and sends the seal area image after removing the color of the seal into the second recognition model to obtain a second recognition result.

[0073] In one embodiment of the present invention, the second recognition result includes: there is signature text and there is no signature text.

[0074] In one embodiment of the present invention, the second recognition model may adopt a general text recognition model in the prior art. In another embodiment of the present invention, the second recognition model may be obtained by training based on a preset machine learning model and using a preset training sample. The machine learning model may adopt various models in the prior art, for example, CTPN model, YOLO model, and CRNN (Convolutional Recurrent Neural Network) model, etc. The training sample used is an image sample marked with text content in the image. In one embodiment of the present invention, the second recognition model may specifically use the CTPN+YOLO+CRNN (i.e., a model combined by CTPN, YOLO, and CRNN) training model.

[0075] Step S103, if the second recognition result is that there is signature text, generate signature compliance area information according to the position information, and extract the signature compliance area image from the stamped page according to the signature compliance area information.

[0076] In an embodiment of the present invention, generating the signature compliance area information according to the position information in this step specifically includes: generating the coordinates of the four vertices of the signature compliance area according to the coordinates of the four vertices of the seal area and the width and height of the seal area, where the signature compliance area is a rectangular area.

[0077] In an embodiment of the present invention, this step can specifically extract the signature compliance area image from the seal area image after removing the seal according to the signature compliance area information.

[0078] In an embodiment of the present invention, the present invention can adjust the coordinates of the four vertices of the seal area according to the width and height of the seal area to generate the coordinates of the four vertices of the signature compliance area. Specifically, the present invention can first generate a horizontal coordinate adjustment parameter according to the width of the seal area, and generate a vertical coordinate parameter according to the height of the seal area, and then add the horizontal coordinate adjustment parameter to the horizontal coordinates of the coordinates of each vertex of the seal area and add the vertical coordinate parameter to the vertical coordinates respectively to obtain new four vertex coordinates, and the new four vertex coordinates are the coordinates of the four vertices of the signature compliance area.

[0079] In an embodiment of the present invention, the present invention crops the seal area image after removing the seal according to four new coordinates (left, top + height × m, right, bottom - height × n) to obtain the signature compliance area image, where both m and n are preset values, for example, both m and n are 0.2.

[0080] Step S104, input the signature compliance area image into a preset third recognition model to obtain a third recognition result, where the third recognition model is used to recognize the signature text in the signature compliance area image.

[0081] In an embodiment of the present invention, the third recognition result is specifically the signature text in the signature compliance area image.

[0082] In an embodiment of the present invention, the third recognition model can adopt a general text recognition model in the prior art. In another embodiment of the present invention, the third recognition model can be obtained by training based on a preset machine learning model and using a preset training sample. The machine learning model can adopt various models in the prior art, for example, CTPN model, YOLO model, and CRNN (Convolutional Recurrent Neural Network) model, etc. The training sample used is an image sample with the text content in the image marked. In an embodiment of the present invention, the third recognition model can specifically use a CTPN+YOLO+CRNN (i.e., a model combined by CTPN, YOLO, and CRNN) training model.

[0083] In one embodiment of the present invention, the first recognition model, the second recognition model, and the third recognition model may adopt the same character recognition model.

[0084] Step S105, if the signature text recognized by the third recognition model is consistent with the seal text recognized by the first recognition model, generate correct seal usage information.

[0085] In one embodiment of the present invention, if the third recognition model fails to recognize the signature text, generate a first seal usage error message. In the present invention, the first seal usage error message is used to indicate excessive blank space.

[0086] In one embodiment of the present invention, if the signature text recognized by the third recognition model is inconsistent with the seal text recognized by the first recognition model, generate a second seal usage error message. In the present invention, the second seal usage error message is used to indicate incorrect seal usage.

[0087] In one embodiment of the present invention, after generating the correct seal usage information, the present invention also returns the seal area image and the name of the stamped page together for subsequent manual screening.

[0088] Figure 2 This is the second flowchart of the seal supervision method according to the embodiment of the present invention. As Figure 2 shown, in one embodiment of the present invention, the seal supervision method of the present invention further includes step S201 and step S202.

[0089] Step S201, obtain the original file to be sealed corresponding to the stamped page.

[0090] Step S202, compare the stamped page with each page in the original file to be sealed by means of similarity comparison to verify whether the stamped page is in the original file to be sealed.

[0091] In one embodiment of the present invention, the determination of the position information of the seal in the stamped page in the above step S101 is specifically:

[0092] If the stamped page is in the original file to be sealed, determine the position information of the seal in the stamped page

[0093] In an embodiment of the present invention, the present invention can use the openCV package of python to remove the seal color (such as red) in the stamped page image based on the color channel. After that, the stamped page image after removing the seal color and each page in the original document to be stamped are compared for image similarity through a model trained by a siamese network. A similarity threshold is set (such as 0.8). When the similarity value of the two images is greater than 0.8, it can be determined that the stamped page is in the original document to be stamped. The similarity value and the stamped page in the stamped document are returned. At the same time, the name of the stamped page, the name of the original document to be stamped, and the page number of the stamped page in the original document to be stamped are also returned.

[0094] In an embodiment of the present invention, after verifying that the stamped page is in the original document to be stamped, the above step S101 is entered for processing.

[0095] Figure 3 It is the third flowchart of the seal supervision method of the embodiment of the present invention. As Figure 3 shown, in an embodiment of the present invention, the seal supervision method of the present invention further includes step S301 and step S303.

[0096] Step S301, if there is a signature area in the stamped page, extract the signature area image from the stamped page.

[0097] In an embodiment of the present invention, the present invention inputs the stamped page image into a text recognition model (a text recognition model trained by CTPN+CRNN can be used). For each line of text recognized, it is judged whether there are words such as signer and signature in the text. If so, it means that there is a signature area in the stamped page. In an embodiment of the present invention, the text recognition model here can adopt a general text recognition model in the prior art. In another embodiment of the present invention, the text recognition model here can be trained based on a preset machine learning model and using a preset training sample. The machine learning model can adopt various models in the prior art, such as the CTPN model, the YOLO model, and the CRNN (convolutional recurrent neural network) model, etc. The training sample used is the stamped page image with the text content in the image marked. In an embodiment of the present invention, the text recognition model here can specifically use the CTPN+CRNN (that is, a model combined by CTPN and CRNN) training model. In an embodiment of the present invention, the present invention crops the image with a preset line distance above and below the recognized words such as signer and signature from the stamped page image as the signature area image.

[0098] In an embodiment of the present invention, if there are no words such as signer and signature in the stamped page image, return the information that no signature is required and do not perform the processing of subsequent steps.

[0099] Step S302: Obtain the seal approval form corresponding to the stamped page, and identify the authorized person's name from the seal approval form.

[0100] In an embodiment of the present invention, the present invention inputs the seal approval form into a text recognition model, locates the line where the authorized person is located, and extracts the name of the person after the colon in the line where the authorized person is located to obtain the authorized person's name.

[0101] Step S303: Recognize the text in the signature area image through a preset text recognition model. If the authorized person's name is among the text recognized by the text recognition model, generate signature compliance information.

[0102] In an embodiment of the present invention, the present invention matches the authorized person's name with the text in the recognized signature area image. If the authorized person's name exists in the text of the signature area image, generate signature compliance information and return that a signature is required and the signatory is the same as the authorized person. If the authorized person's name does not exist in the text of the signature area image, return that there is no signature and it is non-compliant. In an embodiment of the present invention, when returning this result, the cropped signature area image and the stamped page name are also returned together for subsequent manual screening.

[0103] In an embodiment of the present invention, the above-mentioned stamped page, original document to be sealed, and seal approval form are all in image format. In the present invention, the seal supervisor inputs the stamped page, original document to be sealed, and seal approval form into the system. If the document is in word format, it can be converted from a word document to a pdf through the pandoc package of python, and then converted from pdf to a picture through the pymupdf or pdf2image package. If the document is in pdf format, it is converted from pdf to a picture through the pymupdf or pdf2image package. Thus, all three input files become in image format. The stamped page, original document to be sealed, and seal approval form described in the embodiments of the present invention are all in image format.

[0104] In an embodiment of the present invention, the seal supervision method of the present invention further includes:

[0105] Generate stamped page compliance information according to the seal usage correct information and the signature compliance information.

[0106] In an embodiment of the present invention, the stamped page compliance information is used to indicate that the stamped page conforms to the review rules and there is no problem.

[0107] It can be seen from the above embodiments that the seal supervision method of the present invention has at least achieved the following beneficial effects.

[0108] The present invention replaces the original manual seal supervision process, helps seal supervisors determine the accuracy and compliance of seal use, saves the manpower and time costs required for the original manual seal supervision, and the intelligent seal supervision system assists in post-event manual inspection, which can also improve the seal supervision efficiency and accuracy rate.

[0109] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0110] Based on the same inventive concept, an embodiment of the present invention also provides a seal supervision device, which can be used to implement the seal supervision method described in the above embodiment, as described in the following embodiment. Since the principle of the seal supervision device for solving problems is similar to that of the seal supervision method, the embodiments of the seal supervision device can refer to the embodiments of the seal supervision method, and the repeated parts will not be described again. As used below, the term "unit" or "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0111] Figure 4 is the first structural block diagram of the seal supervision device in the embodiment of the present invention, as Figure 4 shown, in an embodiment of the present invention, the seal supervision device of the present invention includes:

[0112] The seal text recognition unit 1 is used to determine the position information of the seal in the stamped page, extract the seal area image from the stamped page according to the position information, and input the seal area image into a preset first recognition model to obtain a first recognition result, where the first recognition model is used to recognize the seal text in the seal area image;

[0113] The signature text determination unit 2 is used to remove the seal in the seal area image, input the seal area image after removing the seal into a preset second recognition model to obtain a second recognition result, where the second recognition model is used to recognize whether there is a signature text in the seal area image after removing the seal;

[0114] The signature compliance area image extraction unit 3 is used to, if the second recognition result is that there is a signature text, generate signature compliance area information according to the position information, and extract the signature compliance area image from the stamped page according to the signature compliance area information;

[0115] The signature text recognition unit 4 is configured to input the signature compliance area image into a preset third recognition model to obtain a third recognition result, where the third recognition model is used to recognize the signature text in the signature compliance area image;

[0116] The correct seal usage information generation unit 5 is configured to generate correct seal usage information if the signature text recognized by the third recognition model is consistent with the seal text recognized by the first recognition model.

[0117] Figure 5 is the second structural block diagram of the seal supervision device according to an embodiment of the present invention. As Figure 5 shown, in an embodiment of the present invention, the seal supervision device of the present invention further includes:

[0118] The original file to be sealed acquisition unit 6 is configured to acquire the original file to be sealed corresponding to the sealed page;

[0119] The sealed page verification unit 7 is configured to compare the sealed page with each page in the original file to be sealed by a similarity comparison method to verify whether the sealed page is in the original file to be sealed.

[0120] In an embodiment of the present invention, the seal text recognition unit 1 is specifically configured to determine the position information of the seal on the sealed page if the sealed page is in the original file to be sealed.

[0121] Figure 6 is the third structural block diagram of the seal supervision device according to an embodiment of the present invention. As Figure 6 shown, in an embodiment of the present invention, the seal supervision device of the present invention further includes:

[0122] The signature area image extraction unit 8 is configured to extract the signature area image from the sealed page if there is a signature area on the sealed page;

[0123] The authorized person name recognition unit 9 is configured to obtain the seal approval form corresponding to the sealed page and recognize the authorized person name from the seal approval form;

[0124] The signature compliance verification unit 10 is configured to recognize the text in the signature area image through a preset text recognition model, and generate signature compliance information if the authorized person name is in the text recognized by the text recognition model.

[0125] In an embodiment of the present invention, the seal supervision device of the present invention further includes:

[0126] The sealed page compliance information generation unit is configured to generate sealed page compliance information according to the correct seal usage information and the signature compliance information.

[0127] In an embodiment of the present invention, the seal monitoring device of the present invention further includes:

[0128] A first seal - using error information generation unit, configured to generate first seal - using error information if the third recognition model fails to recognize the signature text.

[0129] A second seal - using error information generation unit, configured to generate second seal - using error information if the signature text recognized by the third recognition model is inconsistent with the seal text recognized by the first recognition model.

[0130] In an embodiment of the present invention, the position information includes: the coordinates of the four vertices of the seal area, where the seal area is a rectangular area.

[0131] A signature compliance area image extraction unit 3, specifically configured to generate the coordinates of the four vertices of the signature compliance area according to the coordinates of the four vertices of the seal area and the width and height of the seal area, where the signature compliance area is a rectangular area.

[0132] To achieve the above - mentioned object, according to another aspect of the present application, a computer device is further provided. As Figure 7 shown, the computer device includes a memory, a processor, a communication interface, and a communication bus. A computer program that can run on the processor is stored in the memory. When the processor executes the computer program, the steps in the method of the above - mentioned embodiment are implemented.

[0133] The processor may be a central processing unit (CPU). The processor may also be other general - purpose processors, digital signal processors (DSPs), application - specific integrated circuits (ASICs), field - programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., or a combination of the above - mentioned types of chips.

[0134] The memory, as a non - transient computer - readable storage medium, can be used to store non - transient software programs, non - transient computer - executable programs, and units, such as the corresponding program units in the above - mentioned method embodiments of the present invention. By running the non - transient software programs, instructions, and modules stored in the memory, the processor executes various functional applications and work data processing of the processor, that is, implements the method in the above - mentioned method embodiments.

[0135] The memory may include a program storage area and a data storage area. Among them, the program storage area can store the operating system and application programs required for at least one function; the data storage area can store data created by the processor and the like. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely provided with respect to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0136] The one or more units are stored in the memory and, when executed by the processor, execute the method in the above embodiments.

[0137] Specific details of the above computer device can be understood by referring to the corresponding relevant descriptions and effects in the above embodiments, and will not be elaborated here.

[0138] To achieve the above object, according to another aspect of the present application, there is also provided a computer-readable storage medium storing a computer program, and when the computer program is executed in a computer processor, it implements the steps in the above monitoring and printing method. Those skilled in the art can understand that to implement all or part of the processes in the above method embodiments, it can be completed by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disc, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (abbreviation: HDD), or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memories.

[0139] To achieve the above object, according to another aspect of the present application, there is also provided a computer program product including a computer program / instructions, and when the computer program / instructions are executed by a processor, they implement the steps of the above monitoring and printing method.

[0140] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to implement. In this way, the present invention is not limited to any specific combination of hardware and software.

[0141] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A printing supervision method, characterized in that, Including: Determine the position information of the seal on the sealed page, extract the seal area image from the sealed page according to the position information, and input the seal area image into a preset first recognition model to obtain a first recognition result, where the first recognition model is used to recognize the seal characters in the seal area image; Remove the seal from the seal area image, and input the seal area image after removing the seal into a preset second recognition model to obtain a second recognition result, where the second recognition model is used to recognize whether there are signature characters in the seal area image after removing the seal; If the second recognition result is that there are signature characters, generate signature compliance area information according to the position information, and extract the signature compliance area image from the sealed page according to the signature compliance area information; Input the signature compliance area image into a preset third recognition model to obtain a third recognition result, where the third recognition model is used to recognize the signature characters in the signature compliance area image; If the signature characters recognized by the third recognition model are the same as the seal characters recognized by the first recognition model, generate correct seal usage information; The position information includes: the coordinates of the four vertices of the seal area, where the seal area is a rectangular area; The generating the signature compliance area information according to the position information specifically includes: Generating the coordinates of the four vertices of the signature compliance area according to the coordinates of the four vertices of the seal area and the width and height of the seal area, where the signature compliance area is a rectangular area.

2. The printing supervision method according to claim 1, wherein Before determining the position information of the seal on the sealed page, it further includes: Obtain the original file to be sealed corresponding to the sealed page; Compare the sealed page with each page in the original file to be sealed by a similarity comparison method to verify whether the sealed page is in the original file to be sealed; The determining the position information of the seal on the sealed page specifically includes: If the sealed page is in the original file to be sealed, determine the position information of the seal on the sealed page.

3. The printing supervision method according to claim 1, wherein It further includes: If there is a signature area on the sealed page, extract the signature area image from the sealed page; Obtain the seal approval form corresponding to the sealed page, and recognize the authorized person's name from the seal approval form; Recognize the characters in the signature area image through a preset character recognition model. If the authorized person's name is in the characters recognized by the character recognition model, generate signature compliance information.

4. The printing supervision method according to claim 3, wherein It further includes: Generate sealed page compliance information according to the correct seal usage information and the signature compliance information.

5. The monitoring and printing method according to claim 1, characterized in that It further includes: If the third recognition model does not recognize the signature characters, generate a first incorrect seal usage information; If the signature characters recognized by the third recognition model are not the same as the seal characters recognized by the first recognition model, generate a second incorrect seal usage information.

6. An imprint monitoring device, characterized in that, Including: The seal text recognition unit is used to determine the position information of the seal on the stamped page, extract the seal area image from the stamped page according to the position information, and input the seal area image into a preset first recognition model to obtain a first recognition result, where the first recognition model is used to recognize the seal text in the seal area image; The signature text determination unit is used to remove the seal from the seal area image, input the seal area image after removing the seal into a preset second recognition model to obtain a second recognition result, where the second recognition model is used to recognize whether there is signature text in the seal area image after removing the seal; The signature compliance area image extraction unit is used to, if the second recognition result is that there is signature text, generate signature compliance area information according to the position information, and extract the signature compliance area image from the stamped page according to the signature compliance area information; The signature text recognition unit is used to input the signature compliance area image into a preset third recognition model to obtain a third recognition result, where the third recognition model is used to recognize the signature text in the signature compliance area image; The correct seal usage information generation unit is used to generate correct seal usage information if the signature text recognized by the third recognition model is consistent with the seal text recognized by the first recognition model; The position information includes: the coordinates of the four vertices of the seal area, where the seal area is a rectangular area; The signature compliance area image extraction unit is specifically used for: Generating the coordinates of the four vertices of the signature compliance area according to the coordinates of the four vertices of the seal area and the width and height of the seal area, where the signature compliance area is a rectangular area.

7. The printing supervision device according to claim 6, characterized in that, It further includes: The original file to be sealed acquisition unit is used to acquire the original file to be sealed corresponding to the stamped page; The stamped page verification unit is used to compare the stamped page with each page in the original file to be sealed by a similarity comparison method to verify whether the stamped page is in the original file to be sealed; The seal text recognition unit is specifically used to determine the position information of the seal on the stamped page if the stamped page is in the original file to be sealed.

8. The printing supervision device according to claim 6, wherein, It further includes: The signature area image extraction unit is used to extract the signature area image from the stamped page if there is a signature area on the stamped page; The authorized person name recognition unit is used to acquire the seal approval form corresponding to the stamped page and recognize the authorized person name from the seal approval form; The signature compliance verification unit is used to recognize the text in the signature area image through a preset text recognition model, and generate signature compliance information if the authorized person name is in the text recognized by the text recognition model.

9. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that, When the computer program / instructions are executed by the processor, it implements the steps of the method according to any one of claims 1 to 5.

11. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, it implements the steps of the method according to any one of claims 1 to 5.

Images