Verification method and device for information in image, equipment, medium and product

Abstract

The invention discloses a verification method and device for information in an image, equipment, a medium and a product. The method comprises the following steps: acquiring a first image of a service system; positioning a preset area of the first image to obtain position information of the preset area; based on the position information, a second image of the first target area is intercepted, and the preset area comprises the first target area; identifying character information in the second image to obtain image key information; whether the image key information meets a first preset condition or not is verified, a first verification result is obtained, and the first verification result comprises first prompt information. The information of the key area is verified, so that the waste of resources and time is reduced, the verification efficiency is improved, and the accuracy of the verification result can be improved.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a method, device, equipment, medium and product for verifying information in an image. Background Art

[0002] With the development of computer technology, users in various industries will save documents, images and other business-related information in their business systems. When checking certain information, it is necessary to filter out this information from the business system and check it, including the verification of information in the image.

[0003] In the prior art, images are usually obtained from business systems, and the text in the images is recognized and verified line by line. However, it is not necessary to verify every line of information in the image. This line-by-line verification method not only wastes time and resources, has low verification efficiency, but also may miss some key information and fail to recognize it, resulting in inaccurate verification results. Summary of the invention

[0004] The embodiment of the present application provides a method, device, equipment, medium and product for verifying information in an image. For a first image acquired, a second image corresponding to a key area is first located and intercepted, text information in the second image is identified, image key information is obtained, and the image key information is verified to see whether it meets a first preset condition, and a first verification result is obtained. In other words, verifying the information in the key area not only reduces the waste of resources and time, improves the efficiency of verification, but also improves the accuracy of the verification result.

[0005] In a first aspect, an embodiment of the present application provides a method for verifying information in an image, comprising:

[0006] Acquire a first image of the business system;

[0007] Positioning a preset area of ​​the first image to obtain position information of the preset area;

[0008] Based on the position information, intercepting a second image of a first target area, the preset area including the first target area;

[0009] Recognize text information in the second image to obtain key information of the image;

[0010] Verify whether the key image information meets the first preset condition, and obtain a first verification result, wherein the first verification result includes first prompt information.

[0011] In one possible implementation, obtaining a first image of a business system includes:

[0012] Acquire a third image of the business system and a document category corresponding to the third image;

[0013] A first image of a target document category is selected from the third images, and the document category includes the target document category.

[0014] In a possible embodiment, the first preset condition is a preset condition corresponding to the first target attribute category; based on the position information, a second image of a preset area of ​​the first target is captured, and the preset area includes the first target area, including:

[0015] Get the attribute category corresponding to the preset area;

[0016] Based on the position information, a second image of a first target area corresponding to a first target attribute category is captured, and the attribute category includes the first target attribute category.

[0017] In a possible embodiment, it also includes:

[0018] Verify whether the second target attribute category of the second target area meets the second preset condition corresponding to the second target attribute category, and obtain a second verification result, the second verification result includes second prompt information, and the second target area is an area other than the first target area in the preset area.

[0019] In a possible implementation, recognizing text information in the second image to obtain key image information includes:

[0020] identifying a font category of text in the second image;

[0021] According to the text recognition rules corresponding to the font category, the text information in the second image is recognized to obtain the key information of the image.

[0022] In a possible implementation, recognizing text information in the second image to obtain key image information includes:

[0023] When it is detected that the image direction of the second image is not the target direction, adjusting the image direction of the second image to the target direction to obtain a fourth image;

[0024] Recognize text information in the fourth image to obtain image key information.

[0025] In a second aspect, an embodiment of the present application provides a device for verifying information in an image, comprising:

[0026] An acquisition module, used for acquiring a first image of a business system;

[0027] A positioning module, used to locate a preset area of ​​the first image and obtain position information of the preset area;

[0028] An interception module, used for intercepting a second image of a first target area based on the position information, wherein the preset area includes the first target area;

[0029] A recognition module, used for recognizing text information in the second image to obtain key image information;

[0030] The verification module is used to verify whether the key information of the image meets the first preset condition and obtain a first verification result, which includes a first prompt information.

[0031] In one possible implementation, the acquisition module is specifically used for:

[0032] Acquire a third image of the business system and a document category corresponding to the third image;

[0033] A first image of a target document category is selected from the third images, and the document category includes the target document category.

[0034] In a possible implementation, the first preset condition is a preset condition corresponding to the first target attribute category; the interception module is specifically used for:

[0035] Get the attribute category corresponding to the preset area;

[0036] Based on the position information, a second image of a first target area corresponding to a first target attribute category is captured, and the attribute category includes the first target attribute category.

[0037] In a possible embodiment, it also includes:

[0038] The verification module is also used to verify whether the second target attribute category of the second target area meets the second preset condition corresponding to the second target attribute category, and obtain a second verification result. The second verification result includes second prompt information. The second target area is an area in the preset area except the first target area.

[0039] In one possible implementation, the identification module is specifically used for:

[0040] identifying a font category of text in the second image;

[0041] According to the text recognition rules corresponding to the font category, the text information in the second image is recognized to obtain the key information of the image.

[0042] In one possible implementation, the identification module is specifically used for:

[0043] When it is detected that the image direction of the second image is not the target direction, adjusting the image direction of the second image to the target direction to obtain a fourth image;

[0044] Recognize text information in the fourth image to obtain image key information.

[0045] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising:

[0046] a processor and a memory storing computer program instructions;

[0047] When the processor executes the computer program instructions, any one of the above methods for verifying information in an image is implemented.

[0048] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, any of the above-mentioned methods for verifying information in an image is implemented.

[0049] In a fifth aspect, an embodiment of the present application provides a computer program product, characterized in that when the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute any of the above-mentioned methods for verifying information in an image.

[0050] The verification method, device, equipment, medium and product of information in an image of an embodiment of the present application, the method includes: acquiring a first image of a business system; locating a preset area of ​​the first image to obtain location information of the preset area; based on the location information, intercepting a second image of a first target area, the preset area includes the first target area; identifying text information in the second image to obtain image key information; verifying whether the image key information meets a first preset condition to obtain a first verification result, the first verification result includes a first prompt information. In this way, for the acquired first image, first locate and intercept the second image corresponding to the key area, identify the text information in the second image to obtain the image key information, verify whether the image key information meets the first preset condition, and obtain a first verification result. In other words, verifying the information in the key area not only reduces the waste of resources and time, improves the efficiency of verification, but also improves the accuracy of the verification results. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0052] Figure 1 It is a structural schematic diagram of a system for verifying information in an image provided by an embodiment of the present application;

[0053] Figure 2 is a flow chart of a method for verifying information in an image provided by another embodiment of the present application;

[0054] Figure 3 is a flowchart of a method for verifying information in an image provided by another embodiment of the present application;

[0055] Figure 4 This is a flow chart of a method for verifying information in an image provided by another embodiment of the present application.

[0056] Figure 5 is a flowchart of a method for verifying information in an image provided by yet another embodiment of the present application;

[0057] Figure 6 is a schematic diagram of the structure of a device for verifying information in an image provided by yet another embodiment of the present application;

[0058] Figure 7 It is a structural diagram of an electronic device provided in yet another embodiment of the present application. DETAILED DESCRIPTION

[0059] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0060] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0061] It should be noted that the acquisition, storage, use and processing of data in the embodiments of the present application are in compliance with the relevant provisions of national laws and regulations.

[0062] With the development of computer technology, users in various industries will save documents, images and other business-related information in their business systems. When checking certain information, it is necessary to filter out this information from the business system and check it, including the verification of information in the image.

[0063] In the prior art, images are usually obtained from business systems, and the text in the images is recognized and verified line by line. However, it is not necessary to verify every line of information in the image. This line-by-line verification method not only wastes time and resources, has low verification efficiency, but also may miss some key information and fail to recognize it, resulting in inaccurate verification results.

[0064] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment, medium and product for verifying information in an image. The method for verifying information in an image provided by the embodiments of the present application is applied to a verification system for information in an image. For example, in the financial field, the verification system for information in an image can be an intelligent verification system for the integrity of credit authorization information. Figure 1 As shown, the verification system 100 for information in an image includes a data acquisition module 110, a key information positioning detection module 120, a text recognition module 130, a review and verification module 140, and a result display and feedback module 150. The verification method for information in an image provided in the embodiment of the present application first locates the key area of ​​the first image acquired by the data acquisition module 110 using the key information positioning detection module 120, and intercepts the second image corresponding to the key area, and uses the text recognition module 130 to recognize the text information in the second image to obtain the key information of the image, and uses the review and verification module 140 to verify whether the key information of the image meets the first preset condition, and the obtained first verification result is displayed using the result display and feedback module 150. In other words, verifying the information in the key area not only reduces the waste of resources and time, improves the efficiency of verification, but also improves the accuracy of the verification result.

[0065] The following is an introduction to the method for verifying information in an image provided by an embodiment of the present application. Figure 2 As shown, the method for verifying information in an image provided by an embodiment of the present application includes the following steps.

[0066] S210: Acquire a first image of the business system.

[0067] Here, it is necessary to verify the information in the first image, such as identity information, authorization information and date.

[0068] As an example, in the scenario of intelligent verification of the integrity of credit investigation authorization information, the first image can be a scanned copy of an ID card and a scanned copy (or electronic version) of the authorization letter.

[0069] S220: Position a preset area of ​​the first image to obtain position information of the preset area.

[0070] Here, the preset area may be pre-set, and is the area where the information in the first image is located. The position information is the position information of the area where the information in the first image is located.

[0071] In some embodiments, the position of information in the image of the same document category is relatively fixed in the original document. For example, the position of the name, ID number and validity period on the ID card, and the multiple authorization items, the name of the signer, the signing date, etc. on the authorization letter. The preset area is the area where the name, ID number and validity period on the ID card, and the multiple authorization items, the name of the signer, the signing date, etc. on the authorization letter are located.

[0072] As an example, the original document refers to the original ID card and the original authorization letter.

[0073] S230. Based on the position information, capture a second image of the first target area, where the preset area includes the first target area.

[0074] Here, the first target area is set in advance. The first target area is the area where the information that needs to be recognized is located in the first image. The second image is a sub-image captured from the first image.

[0075] In some embodiments, a first target area is selected from a preset area, and a region where information is located in the first image is cropped based on position information of the first target area to obtain at least one sub-image of the first image.

[0076] S240: Identify text information in the second image to obtain key image information.

[0077] In some embodiments, the text information in each second image is identified to obtain the key information of the image. For example, the key information of the image includes the name, ID number and validity period on the ID card, the name of the signatory and the signing date on the authorization letter, and the name, ID number and validity period on the ID card, the name of the signatory and the signing date on the authorization letter, etc.

[0078] S250: Verify whether the key image information meets a first preset condition, and obtain a first verification result, wherein the first verification result includes a first prompt information.

[0079] Here, the first preset condition is set in advance and is used to verify the information in the first image.

[0080] In some embodiments, the verification may include, but is not limited to, consistency verification, integrity verification, compliance verification, timeliness verification, etc. For example, the name, ID number, and validity period on the ID card in the recognized second image are compared with the name, ID number, and validity period in the first preset condition. If they are consistent, the consistency verification is passed; the name of the signatory and the signing date on the authorization letter are checked for integrity. If the name of the signatory and the signing date are recognized from the second image, the integrity verification is passed; the name on the ID card in the recognized second image is checked for consistency with the name of the signatory in the authorization letter recognized from the second image, and so on.

[0081] In some embodiments, the first prompt information includes a verification pass prompt information and a verification fail prompt information. Specifically, the verification pass prompt information includes prompt information that the first target image key information passes. The verification fail prompt information includes prompt information that the second target image key information fails. The image key information includes the first target image key information and the second target image key information.

[0082] In some embodiments, the first verification result is displayed.

[0083] In some embodiments, a verification report of the first verification result is generated to point out existing problems or confirm the compliance of the materials, and provide necessary correction suggestions. It is used to guide the next step of operation or directly notify the user to supplement or modify the materials. It should be noted that when the first prompt information is a prompt information of verification failure, the prompt information of the failure of the key information of the first target image can be used as a correction suggestion to prompt the user that the key information of the first target image has not passed the verification and remind the user to make corrections. For example, the name on the ID card in the identified second image is inconsistent with the name in the first preset condition, and the first prompt information includes the name verification failure.

[0084] As an example, in the scenario of intelligent verification of the integrity of credit authorization information, the first preset condition includes credit reporting business rules and relevant rules designed by laws and regulations, which are used to confirm the accuracy, completeness and compliance of credit reporting information.

[0085] In this way, for the acquired first image, the second image corresponding to the key area is first located and intercepted, the text information in the second image is identified, the image key information is obtained, and the image key information is verified to see whether it meets the first preset condition to obtain the first verification result. In other words, verifying the information in the key area not only reduces the waste of resources and time, improves the efficiency of verification, but also improves the accuracy of the verification result.

[0086] Based on this, in some embodiments, such as Figure 3 As shown, the above S210 may specifically include:

[0087] S211, obtaining a third image and a document category corresponding to the third image from a business system;

[0088] S212: Select a first image of a target document category from the third images, where the document category includes the target document category.

[0089] Here, the target document categories are set in advance, such as identity cards and authorization letters.

[0090] In some embodiments, the data acquisition module of the verification system for information in an image includes a data acquisition unit and a complex document classification unit. The data acquisition unit is used to acquire a third image of the business system, and the complex document classification unit is used to acquire a document category corresponding to the third image.

[0091] Specifically, a third image is obtained from the business system at regular intervals or in real time. The third image includes a large number of images. The third image is classified using a trained complex document classification model (such as the YOLOv8n-cls model), such as distinguishing different document categories such as identity cards, credit reports, and authorization letters.

[0092] In some embodiments, the training process of the trained complex document classification model includes:

[0093] Obtain historical image samples from the business system, display the historical image samples, and input the historical image samples and the annotation information into the initial complex document classification model when receiving the user's annotation information for the historical image samples. Here, the annotation information may include, but is not limited to, document categories. Determine the predicted document category of the historical image samples using the initial relationship between the image and the preset document category in the initial complex document classification model, adjust the initial relationship between the image and the document category based on the predicted document category of the historical image samples and the document category in the annotation information, and the test image samples until the training stop condition of the initial complex document classification model is met, and obtain a trained complex document classification model. For example, preset document categories include identity cards, credit reports, and authorization letters, etc.

[0094] In this way, even if there are a large number of images in the business system, the images that need to be verified can be screened out from a large number of images according to the document category, without the need for manual screening, which improves the verification efficiency and can be applied to most scenarios that require verification of information in images.

[0095] Based on this, in some embodiments, the first preset condition is a preset condition corresponding to the first target attribute category; Figure 4 As shown, the above S230 may specifically include:

[0096] S231, obtaining the attribute category corresponding to the preset area;

[0097] S232: Based on the position information, intercept a second image of the first target area corresponding to the first target attribute category, where the attribute category includes the first target attribute category.

[0098] Here, the first target attribute category is set in advance, such as the name, ID number, validity period on the ID card, and the name of the signatory and signing date on the authorization letter, etc., which are attribute categories that require text recognition.

[0099] In some embodiments, a preset area corresponds to an attribute category and a location information respectively.

[0100] In some embodiments, a trained key information location detection model (such as a YOLOv8n-obb model) can also be used to locate the preset area, and the second image can be captured based on the obtained location information and attribute categories. That is, the key information location detection model provides a minimized and accurate sub-image to be identified, as well as the attribute category of the preset area provided for the subsequent review and verification module.

[0101] In some embodiments, the training process of the trained key information location detection model includes:

[0102] Obtain historical image samples from the business system, display the historical image samples, and input the historical image samples and the annotation information into the initial key information positioning detection model when receiving the annotation information of the historical image samples from the user. Here, the annotation information may include, but is not limited to, the attribute category and location information of the preset area. Determine the predicted location information and the preset attribute category of the preset area of ​​the historical image sample by using the initial relationship between the preset area and the preset location information, and the initial relationship between the preset area and the preset attribute category in the initial key information positioning detection model, and adjust the initial relationship between the preset area and the preset location information, and the initial relationship between the preset area and the preset attribute category according to the predicted location information of the preset area of ​​the historical image sample and the location information in the annotation information, and the predicted attribute category of the preset area of ​​the historical image sample and the attribute category in the annotation information, and the test image sample until the training stop condition of the initial key information positioning detection model is met, and the trained key information positioning detection model is obtained.

[0103] In this way, the information in the image is screened according to the attribute category, the second image is intercepted for the information that needs to be verified by capturing the sub-image according to the attribute category, and some information that does not need to be captured by capturing the sub-image for verification is excluded, thereby improving the efficiency of verification.

[0104] Based on this, in some embodiments, such as Figure 5 As shown, corresponding to the above S230 to S250, the method may further include:

[0105] S233, verify whether the second target attribute category of the second target area meets the second preset condition corresponding to the second target attribute category, and obtain a second verification result, the second verification result includes second prompt information, and the second target area is an area in the preset area except the first target area.

[0106] Here, the second target attribute category is the attribute category of some preset areas that do not need to capture sub-images for verification, such as preset areas including special symbols, for example, the area where multiple authorization items are located on the authorization letter, the second target attribute category is the authorization item, which may include a check box.

[0107] In some embodiments, it is not necessary to intercept partial information of the sub-image for verification, and verification is performed directly according to the attribute category, such as multiple authorization items on the authorization letter. It should be noted that when different authorization items are checked, the second target attribute category of the second target area is different.

[0108] In this way, for some information that does not need to be intercepted for verification, text recognition is not performed, but verification is performed directly according to the attribute category, which improves the efficiency and accuracy of the verification.

[0109] Based on this, in some embodiments, the above S240 may specifically include:

[0110] identifying a font category of text in the second image;

[0111] According to the text recognition rules corresponding to the font category, the text information in the second image is recognized to obtain the key information of the image.

[0112] In some embodiments, font classification is performed by a trained key information font classification model (such as a YOLOv8n-cls model) to distinguish between printed fonts and handwritten fonts. The text information in the second image is identified by the text recognition rules in the trained multiple key information recognition models (such as the SVTR-LCNet model) to obtain the image key information. It is understandable that the text recognition rules in the multiple key information recognition models correspond to multiple font categories, such as printed fonts and handwritten fonts.

[0113] In some embodiments, the training process of the trained key information font classification model includes:

[0114] Obtain historical image samples from the business system, display the historical image samples, and input the historical image samples and the annotation information into the initial key information font classification model when receiving the annotation information of the historical image samples from the user. Here, the annotation information may include, but is not limited to, font categories. The predicted font category of the historical image samples is determined by using the initial relationship between the image and the preset font category in the initial key information font classification model, and the initial relationship between the image and the font category is adjusted according to the predicted font category of the historical image samples and the font category in the annotation information, as well as the test image samples, until the training stop condition of the initial key information font classification model is met, and a trained key information font classification model is obtained.

[0115] In some embodiments, the training process of the trained multiple key information recognition models includes:

[0116] Obtain historical image samples from the business system, display the historical image samples, and input the historical image samples and the annotation information into the initial multiple key information recognition model when receiving the user's annotation information for the historical image samples. Here, the annotation information may include, but is not limited to, font categories and actual text information. The initial multiple key information recognition model is used to perform text recognition on the historical image samples according to different font categories to obtain predicted text information, and the initial relationship between the image and document categories is adjusted according to the predicted text information and the actual text information of the historical image samples and the test image samples until the training stop condition of the initial multiple key information recognition model is met, thereby obtaining a trained multiple key information recognition model.

[0117] In this way, for text recognition of information in multiple font categories, text recognition is performed separately according to the text recognition rules corresponding to the font categories, so as to reduce the negative impact of different font recognitions and improve the recognition accuracy.

[0118] Based on this, in some embodiments, the above S240 may specifically:

[0119] When it is detected that the image direction of the second image is not the target direction, adjusting the image direction of the second image to the target direction to obtain a fourth image;

[0120] Recognize text information in the fourth image to obtain image key information.

[0121] In some embodiments, a key information direction classification model (such as a MobileNetV3 model) is trained and used to determine the image direction of the second image. When it is detected that the image direction of the second image is not the target direction, the image direction of the second image is adjusted to the target direction to obtain a fourth image. Here, the target direction is the positive direction.

[0122] In this way, after converting the image into a positive direction, text recognition is performed, which improves the accuracy of the recognition result.

[0123] In the embodiments provided in the present application, through fully automated processing, including screening images according to document categories, distinguishing attribute categories, and distinguishing font categories, etc., by designing an automated process of multiple deep learning models to accurately locate and identify multiple fonts, high-precision recognition of important information is ensured, and fast and accurate recognition and verification of information in images are achieved, which significantly improves the verification efficiency, reduces human errors, and ensures the compliance of the business. In addition, by integrating advanced deep learning models, such as complex document classification models (such as YOLOv8n-cls models), key information location detection models (such as YOLOv8n-obb models), key information font classification models (such as YOLOv8n-cls models), multiple key information recognition models (such as SVTR-LCNet models) and key information direction classification models (such as MobileNetV3 models), complex document classification models are applied to realize complex file classification, and key information location detection models are used to perform key information location detection, which can efficiently and accurately distinguish and identify information in images of various document categories, and improve the intelligence level of the verification system of information in images.

[0124] As an example, in the scenario of intelligent verification of credit authorization information integrity, the YOLOv8n-cls model is used to classify the credit materials provided by various customers, such as distinguishing between ID cards, credit reports, authorization letters, etc., to ensure that the subsequent processing process can adopt appropriate processing strategies for different document types. The YOLOv8n-obb model is constructed and applied to the key information location detection of ID cards and authorization letters, such as name, certificate number, authorization items, etc., to accurately circle the location of this information, laying the foundation for subsequent information extraction and recognition. The YOLOv8n-cls model is used for font classification to determine the font category used for key information, providing support for subsequent text recognition. Secondly, the MobileNetV3 model is used to determine the direction classification of key information to ensure that the information can be accurately recognized regardless of whether it is forward or inverted. For text recognition of key information in multiple fonts, the SVTR-LCNet model is used to reduce the negative impact of different font recognition. This model has strong text recognition capabilities and can effectively read and recognize images containing key information, including text on ID cards and authorization letters. By associating the identity and authorization together for verification, the verification result is obtained, and a prompt message indicating that the verification has failed is given for key image information that does not meet the preset conditions. Multiple links such as key information positioning detection, font classification, direction classification and font recognition are integrated to form a complete process system. This avoids the emergence of information islands and the inability to achieve cross-document logical verification and compliance assessment during the verification process, so as to ensure that every detail is fully considered and verified, greatly improving the detection and recognition accuracy of key information in identity cards and credit authorization letters, ensuring the accuracy of information extraction, and realizing a comprehensive and efficient intelligent verification of the integrity of credit authorization materials covering multiple dimensions.

[0125] Among them, the deep learning model is used to realize the automatic identification and verification of various key credit information, without the need for manual document selection and reducing the complexity of operation, which significantly improves the verification speed and efficiency, greatly shortens the time of information verification, and reduces human resource costs. Through the deep learning model trained on the credit authorization material data, it can accurately identify and verify personal information and authorization information (such as name and authorization item), reduce errors caused by human negligence or misunderstanding, and improve the accuracy of information verification. In the face of the growing business volume and complex and changing document formats, it has good scalability and adaptability, can flexibly respond to the verification needs of various credit authorization materials, meet the needs of the rapid development of the financial industry, and can automatically verify the integrity of credit authorization materials, the completeness of signing information, and the compliance requirements according to business needs, to ensure that the entire authorization process complies with regulatory requirements. This not only improves the compliance of credit authorization, but also strengthens risk management and reduces potential legal risks. The automated process enables resources to be reasonably allocated, allowing the review team to focus on more complex non-standardized issues and optimize the use of human resources. In addition, with the continuous updating of technology, the embodiments provided in this application can quickly adapt to new regulatory requirements or business changes, maintaining a high degree of flexibility and adaptability.

[0126] In summary, the embodiments provided in this application can not only greatly improve the efficiency and accuracy of personal credit authorization information verification, but also effectively control compliance risks, optimize resource allocation, and bring a safer, more efficient, and compliant service experience to financial institutions. That is, based on the key information identified through analysis, the verification results can be automatically generated through verification, providing decision support for manual verification and effectively improving the verification accuracy. Verification rules can also be customized according to different types of credit reporting services to ensure that each submitted credit authorization material meets the compliance requirements of the relevant business, reducing the manual burden and ensuring the standardization of business handling.

[0127] The embodiments provided in this application can be further extended to document review work in other fields, such as corporate credit assessment, application for scientific research funds in the fields of medical care, education, etc. In addition, with the development of artificial intelligence technology, it is possible to continuously improve its recognition accuracy of various key information by learning more types of financial documents to adapt to a wider range of application scenarios. For example, it can be used in the identity verification process when opening an account, and quickly identify and verify the submitted ID card to improve work efficiency, reduce human errors, and strengthen risk control. For corporate credit assessment, before conducting commercial cooperation with an enterprise, banks and financial institutions need to verify the company's business license, financial statements and other documents to ensure that the information involved is true and correct, and can efficiently extract and compare these key information, helping the company's credit assessment process to be more objective, fair and efficient.

[0128] Based on the method for verifying information in an image provided in the above embodiment, the present application also provides a specific implementation of a device for verifying information in an image. Please refer to the following embodiment.

[0129] See also Figure 6 , the image information verification device 300 provided in the embodiment of the present application includes:

[0130] An acquisition module 310 is used to acquire a first image of a business system;

[0131] A positioning module 320, used to locate a preset area of ​​the first image and obtain position information of the preset area;

[0132] The capture module 330 is used to capture a second image of a first target area based on the position information, wherein the preset area includes the first target area;

[0133] The recognition module 340 is used to recognize text information in the second image and obtain key information of the image;

[0134] The verification module 350 is used to verify whether the key image information meets the first preset condition and obtain a first verification result, which includes a first prompt information.

[0135] Based on this, in some embodiments, the acquisition module 310 may be specifically used for:

[0136] Acquire a third image of the business system and a document category corresponding to the third image;

[0137] A first image of a target document category is selected from the third images, and the document category includes the target document category.

[0138] Based on this, in some embodiments, the first preset condition is a preset condition corresponding to the first target attribute category; the interception module 330 can be specifically used for:

[0139] Get the attribute category corresponding to the preset area;

[0140] Based on the position information, a second image of a first target area corresponding to a first target attribute category is captured, and the attribute category includes the first target attribute category.

[0141] Based on this, in some embodiments, the apparatus 300 may further include:

[0142] The verification module is also used to verify whether the second target attribute category of the second target area meets the second preset condition corresponding to the second target attribute category, and obtain a second verification result. The second verification result includes second prompt information. The second target area is an area in the preset area except the first target area.

[0143] Based on this, in some embodiments, the identification module 340 may be specifically used for:

[0144] identifying a font category of text in the second image;

[0145] According to the text recognition rules corresponding to the font category, the text information in the second image is recognized to obtain the key information of the image.

[0146] Based on this, in some embodiments, the identification module 340 may be specifically used for:

[0147] When it is detected that the image direction of the second image is not the target direction, adjusting the image direction of the second image to the target direction to obtain a fourth image;

[0148] Recognize text information in the fourth image to obtain image key information.

[0149] The various modules of the device for verifying information in an image provided in the embodiment of the present application can realize the functions of the various steps of the method for verifying information in an image provided above and can achieve the corresponding technical effects, which will not be repeated here for the sake of concise description.

[0150] Based on the same inventive concept, an embodiment of the present application also provides an electronic device.

[0151] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0152] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0153] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0154] The memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 402 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 402 is a non-volatile solid-state memory.

[0155] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present disclosure.

[0156] The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any one of the methods for verifying information in an image in the above embodiments.

[0157] In one example, the electronic device may further include a communication interface 403 and a bus 410. Figure 7 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0158] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0159] The bus 410 includes hardware, software or both, coupling the components of the electronic device to each other. For example, but not limitation, the bus may include an accelerated graphics port (Accelerated Graphics Port, AGP) or other graphics bus, an enhanced industry standard architecture (Extended Industry Standard Architecture, EISA) bus, a front side bus (Front Side Bus, FSB), a hypertransport (Hyper Transport, HT) interconnection, an industry standard architecture (Industry Standard Architecture, ISA) bus, an infinite bandwidth interconnection, a low pin count (Linear Predictive Coding, LPC) bus, a memory bus, a micro channel architecture (MicroChannel Architecture, MCA) bus, a peripheral component interconnect (Peripheral Component Interconnect, PCI) bus, a PCI-Express (Peripheral Component Interconnect-X, PCI-X) bus, a serial advanced technology attachment (Serial Advanced Technology Attachment, SATA) bus, a video electronics standard association local (VESA Local Bus, VLB) bus or other suitable buses or a combination of two or more of these. Where appropriate, the bus 410 may include one or more buses. Although the embodiments of the present application describe and illustrate a specific bus, the present application considers any suitable bus or interconnection. The electronic device can execute the method for verifying information in an image in the embodiments of the present invention, thereby implementing the above-mentioned method for verifying information in an image.

[0160] In addition, in combination with the verification method of information in an image in the above-mentioned embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the verification methods of information in an image in the above-mentioned embodiment is implemented.

[0161] The present application also provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes each process of implementing any one of the above-mentioned methods for verifying information in an image.

[0162] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0163] The functional blocks shown in the structural block diagram described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (Read-Only Memory, ROM), flash memory, erasable read-only memory (Erasable ReadOnly Memory, EROM), floppy disks, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical discs, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0164] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0165] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0166] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for verifying information in an image, characterized in that: include: Acquire a first image of the business system; Positioning a preset area of ​​the first image to obtain position information of the preset area; Based on the position information, intercepting a second image of a first target area, the preset area including the first target area; Recognize text information in the second image to obtain key image information; Verify whether the key image information meets a first preset condition to obtain a first verification result, wherein the first verification result includes first prompt information.

2. The method for verifying information in an image according to claim 1, characterized in that: The obtaining of the first image of the business system includes: Acquire a third image of the business system and a document category corresponding to the third image; A first image of a target document category is selected from the third images, and the document categories include the target document category.

3. The method for verifying information in an image according to claim 1, characterized in that: The first preset condition is a preset condition corresponding to the first target attribute category; based on the position information, intercepting a second image of a preset area of ​​the first target, the preset area including the first target area, includes: Obtaining the attribute category corresponding to the preset area; Based on the position information, a second image of a first target area corresponding to the first target attribute category is captured, and the attribute category includes the first target attribute category.

4. The method for verifying information in an image according to claim 3, characterized in that: Also includes: Verify whether the second target attribute category of the second target area meets the second preset condition corresponding to the second target attribute category, and obtain a second verification result, wherein the second verification result includes second prompt information, and the second target area is an area in the preset area except the first target area.

5. The method for verifying information in an image according to claim 1, characterized in that: The identifying text information in the second image to obtain key image information includes: identifying the font category of the text in the second image; According to the text recognition rules corresponding to the font category, the text information in the second image is recognized to obtain the image key information.

6. The method for verifying information in an image according to claim 1, characterized in that: The identifying text information in the second image to obtain key image information includes: When it is detected that the image direction of the second image is not the target direction, adjusting the image direction of the second image to the target direction to obtain a fourth image; Identify text information in the fourth image to obtain image key information.

7. A device for verifying information in an image, characterized in that: include: An acquisition module, used for acquiring a first image of a business system; A positioning module, used to locate a preset area of ​​the first image and obtain position information of the preset area; A capture module, configured to capture a second image of a first target area based on the position information, wherein the preset area includes the first target area; A recognition module, used for recognizing text information in the second image to obtain key image information; The verification module is used to verify whether the key image information meets a first preset condition and obtain a first verification result, wherein the first verification result includes a first prompt information.

8. The device for verifying information in an image according to claim 7, characterized in that: The acquisition module is specifically used for: Acquire a third image of the business system and a document category corresponding to the third image; A first image of a target document category is selected from the third images, and the document categories include the target document category.

9. The device for verifying information in an image according to claim 7, characterized in that: The first preset condition is a preset condition corresponding to the first target attribute category; the interception module is specifically used for: Obtaining the attribute category corresponding to the preset area; Based on the position information, a second image of a first target area corresponding to the first target attribute category is captured, and the attribute category includes the first target attribute category.

10. The device for verifying information in an image according to claim 9, characterized in that: Also includes: The verification module is further used to verify whether the second target attribute category of the second target area meets the second preset condition corresponding to the second target attribute category, and obtain a second verification result, wherein the second verification result includes second prompt information, and the second target area is an area in the preset area except the first target area.

11. The device for verifying information in an image according to claim 7, characterized in that: The identification module is specifically used for: identifying the font category of the text in the second image; According to the text recognition rules corresponding to the font category, the text information in the second image is recognized to obtain the image key information.

12. The device for verifying information in an image according to claim 7, characterized in that: The identification module is specifically used for: When it is detected that the image direction of the second image is not the target direction, adjusting the image direction of the second image to the target direction to obtain a fourth image; Identify text information in the fourth image to obtain image key information.

13. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for verifying information in an image as described in any one of claims 1-6 is implemented.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for verifying information in an image according to any one of claims 1 to 6 is implemented.

15. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the method for verifying information in an image as described in any one of claims 1 to 6.

Images