Data processing method and device, storage medium and electronic equipment

Abstract

The invention discloses a data processing method and device, a storage medium and electronic equipment. The method comprises the following steps: in response to a target service request, obtaining a service data file and identity information of a target object; determining image features and character features according to the business data file, inputting the image features and the character features into a target multi-modal recognition model, and determining a file category and a file authenticity attribute; under the condition that the file category is a preset target file category and the authenticity attribute of the file is true, determining an associated object having a business relationship with the target object through the identity information, and obtaining associated business information which represents business data related to the target object; and executing a target auditing operation by using the business data file and the associated business information, and determining whether the target object can obtain a virtual resource corresponding to the target business request or not. The technical problem that the response speed of the service request is low due to the fact that the data processing flow is long is solved.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a data processing method and device, a storage medium, and an electronic device. Background Art

[0002] In related technologies, when processing business requests from various entities, traditional data processing processes often involve manual review and multi-step information verification, which not only increases the complexity of operations, but also leads to the extension of data processing processes. Especially when faced with a large number of real-time business requests, this manual processing method is difficult to meet the needs of efficient information processing, thus causing technical problems such as slow response speed.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a data processing method and device, a storage medium, and an electronic device to at least solve the technical problem that the data processing process is long, resulting in a slow response speed to business requests.

[0005] According to one aspect of an embodiment of the present application, a data processing method is provided, comprising: in response to a target business request, obtaining a business data file and identity information of a target object; determining image features and text features according to the business data file, inputting the image features and the text features into a target multimodal recognition model, and determining a file category and a file authenticity attribute, wherein the target multimodal recognition model is pre-trained with sample image features and sample text features; when the file category is a preset target file category and the file authenticity attribute is true, determining an associated object having a business relationship with the target object through the identity information, and obtaining associated business information of the associated object, wherein the associated business information represents business data related to the target object; performing a target audit operation using the business data file and the associated business information to determine whether the target object can obtain a virtual resource corresponding to the target business request.

[0006] According to another aspect of an embodiment of the present application, a data processing device is also provided, including: an acquisition module, used to obtain a business data file and identity information of a target object in response to a target business request; a determination module, used to determine image features and text features according to the business data file, input the image features and the text features into a target multimodal recognition model, and determine the file category and the file authenticity attribute, wherein the target multimodal recognition model is pre-trained by sample image features and sample text features; an association module, used to determine an associated object having a business relationship with the target object through the identity information when the file category is a preset target file category and the file authenticity attribute is true, and obtain associated business information of the associated object, wherein the associated business information represents business data related to the target object; an audit module, used to perform a target audit operation using the business data file and the associated business information to determine whether the target object can obtain the virtual resources corresponding to the target business request.

[0007] Optionally, the device is used to determine image features and text features based on the business data file in the following manner, input the image features and the text features into a target multimodal recognition model, and determine the file category and file authenticity attributes: obtain a business image from the business data file; use an image feature extraction module to extract the image features of the business image; identify the text area in the business image to obtain the text features.

[0008] Optionally, the device is also used to: use an attention mechanism to fuse the image features and the text features to obtain multimodal feature information; input the multimodal feature information into a classifier in the target multimodal recognition model to obtain the file category and the authenticity attribute.

[0009] Optionally, the device is also used to: determine an inclined image with a tilt attribute and a first non-tilted image without the tilt attribute from the business image; perform a Hough transform operation on the inclined image to obtain a second non-tilted image; use the image feature extraction module in the target multimodal recognition model to extract the image features of the first non-tilted image and the second non-tilted image; identify the text area in the business image to obtain the text feature.

[0010] Optionally, the device is used to determine an associated object having a business relationship with the target object through the identity information and obtain associated business information of the associated object when the file category is a preset target file category and the file authenticity attribute is true in the following manner: determine a target business according to the target business request; query a business information repository according to the type of the target business to determine the target file category required to process the target business, wherein the business information repository includes several business types and business file categories corresponding to each business type; compare the target file category with the file category to determine whether the file category is the target file category.

[0011] Optionally, the device is used to determine an associated object having a business relationship with the target object through the identity information and obtain associated business information of the associated object in the following manner when the file category is a preset target file category and the file authenticity attribute is true: use the identity information to perform a business association query operation on the target object to determine a first associated object and a second associated object, wherein the first associated object represents an object having a direct business relationship with the target object, and the second associated object represents an object having an indirect business relationship with the target object, and the associated objects include the first associated object and the second associated object; obtain first associated business information of the first associated object, and obtain second associated business information of the second associated object, wherein the first associated business information is used to indicate a business situation associated between the target object and the first associated object, and the second associated business information is used to indicate a business situation associated between the target object and the second associated object, and the associated business information includes the first associated business information and the second associated business information.

[0012] Optionally, the device is used to perform a target audit operation using the business data file and the associated business information to determine whether the target object can obtain the virtual resources corresponding to the target business request in the following manner: perform the target audit operation using the business data file and the associated business information to obtain a first audit result; if the first audit result indicates that the business data file and the associated business information do not meet the business preset conditions, generate a first prompt message, wherein the first prompt message indicates that the target object is prohibited from obtaining the virtual resources corresponding to the target business request; perform the target audit operation using the business data file and the associated business information to obtain a second audit result; if the second audit result indicates that the business data file and the associated business information meet the business preset conditions, issue the virtual resources to the target object and generate a second prompt message, wherein the second prompt message indicates that the target object is allowed to obtain the virtual resources corresponding to the target business request.

[0013] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned data processing method when running.

[0014] According to another aspect of the embodiments of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the above data processing method.

[0015] According to another aspect of the embodiments of the present application, there is further provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the data processing method through the computer program.

[0016] In an embodiment of the present application, in response to a target business request, a business data file and identity information of a target object are obtained; image features and text features are determined according to the business data file, and the image features and text features are input into a target multimodal recognition model to determine the file category and the authenticity attribute of the file, wherein the target multimodal recognition model is pre-trained by sample image features and sample text features; when the file category is a preset target file category and the authenticity attribute of the file is true, an associated object having a business relationship with the target object is determined by the identity information, and associated business information of the associated object is obtained, wherein the associated business information represents business data related to the target object; a target review operation is performed using the business data file and the associated business information to determine whether the target object can obtain the virtual resources corresponding to the target business request, and the purpose of accelerating the processing of business requests is achieved through automated and intelligent file recognition and review, thereby achieving the technical effect of efficient data processing and immediate response, thereby solving the technical problem of a long data processing flow leading to a slow response speed to business requests. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a schematic diagram of an application environment of an optional data processing method according to an embodiment of the present application;

[0019] Figure 2 is a flowchart of an optional data processing method according to an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of an optional data processing method according to an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of another optional data processing method according to an embodiment of the present application;

[0022] Figure 5 is a schematic structural diagram of an optional data processing device according to an embodiment of the present application;

[0023] Figure 6 is a schematic diagram of the structure of an optional data processing product according to an embodiment of the present application;

[0024] Figure 7 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] The present application is described below in conjunction with embodiments:

[0028] According to one aspect of an embodiment of the present application, a data processing method is provided. Optionally, in this embodiment, the data processing method can be applied to Figure 1 In the hardware environment composed of the server 101 and the terminal device 103 shown in FIG. Figure 1As shown, the server 101 is connected to the terminal 103 via a network, and can be used to provide services for the terminal device or an application 107 installed on the terminal device. The application can be a video application, an instant messaging application, a browser application, an educational application, a game application, etc. A database 105 may be set up on the server or independently of the server to provide data storage services for the server 101, for example, a game data storage server. The above-mentioned network may include, but is not limited to, a wired network and a wireless network, wherein the wired network includes, for example, a local area network, a metropolitan area network, and a wide area network; the wireless network includes, for example, Bluetooth, WIFI, and other networks that implement wireless communication; the terminal device 103 may be a terminal configured with an application program, and may include, but is not limited to, at least one of the following: a mobile phone (such as an Android phone, an iOS phone, etc.), a laptop computer, a tablet computer, a PDA, a MID (Mobile Internet Devices), a PAD, a desktop computer, a smart TV, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, an aircraft, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a mixed reality (MR) terminal, and other computer devices; the above-mentioned server may be a single server, a server cluster consisting of multiple servers, or a cloud server.

[0029] Combination Figure 1 As shown, the above data processing method can be executed by an electronic device, which can be a terminal device or a server. The above data processing method can be implemented by the terminal device or the server respectively, or by the terminal device and the server together.

[0030] The above is only an example and is not specifically limited in this embodiment.

[0031] Optionally, as an optional implementation, as Figure 2 As shown, the above data processing method includes:

[0032] S202, in response to the target service request, obtaining the service data file and identity information of the target object;

[0033] S204, determining image features and text features according to the business data file, inputting the image features and text features into a target multimodal recognition model to determine the file category and the authenticity of the file, wherein the target multimodal recognition model is pre-trained with sample image features and sample text features;

[0034] S206, when the file category is a preset target file category and the file authenticity attribute is true, determine an associated object having a business relationship with the target object through the identity information, and obtain associated business information of the associated object, wherein the associated business information represents business data related to the target object;

[0035] S208, performing a target review operation using the business data file and the associated business information to determine whether the target object can obtain the virtual resources corresponding to the target business request.

[0036] Optionally, in the embodiment of the present application, the target business request refers to the demand for specific business operations proposed by the target object, including but not limited to business scenarios such as account opening, loan application, and authority modification, and the business data file specifically refers to documents related to the target business request, including but not limited to account opening application, identity document, financial statement, etc. Identity information refers to the identification information of the target object, such as an individual's ID number, a unified social credit code of an enterprise, etc., which is used to confirm the entity identity of the target object.

[0037] It should be noted that in different business scenarios, the specific content of the target document category and the associated business information may vary. For example, in an account opening scenario, the target document category may include an account opening application, a legal representative's identity certificate, etc., while in a loan application scenario, the target document category may be a loan application form, an asset certification document, etc. This application does not limit this.

[0038] Exemplarily, the system first responds to the target business request, and then automatically obtains the business data file and identity information submitted by the target object; thereafter, the system analyzes the image features and text features of the file, and uses a pre-trained multimodal recognition model to determine the category and authenticity of the file; after confirming that the file category is correct and authentic, the system automatically identifies the related business data, i.e., associated business information, based on the identity information of the target object; finally, the system uses the business data file and associated business information to perform a target review operation to determine whether the target object meets the conditions for obtaining virtual resources, which may be permission for business operations, electronic versions of certification documents, etc.

[0039] In an exemplary embodiment, taking the application scenario of account opening business as an example, when an enterprise makes a request to open an account, the system responds and collects relevant business data files and enterprise identity information, analyzes the image and text features of the files through a deep learning model, and determines the authenticity and category of the files; the system further identifies the legal representative and the enterprise's historical transaction records and other related business information through the enterprise identity information, and finally, combined with the business data files and related business information, the system completes the review of the account opening request and determines whether the enterprise meets the conditions for opening an account.

[0040] In general, the use of automated and intelligent document processing and review processes has achieved efficient and accurate technical results in business request processing, achieving the goal of shortening data processing time and speeding up business request response speed. It not only improves system operation efficiency, but also significantly improves user experience and ensures the continuity and timeliness of business operations.

[0041] Through the embodiments of the present application, in response to a target business request, the business data file and identity information of the target object are obtained; image features and text features are determined according to the business data file, and the image features and text features are input into a target multimodal recognition model to determine the file category and the file authenticity attribute, wherein the target multimodal recognition model is pre-trained by sample image features and sample text features; when the file category is a preset target file category and the file authenticity attribute is true, the associated object having a business relationship with the target object is determined by the identity information, and the associated business information of the associated object is obtained, wherein the associated business information represents the business data related to the target object; the business data file and the associated business information are used to perform a target review operation to determine whether the target object can obtain the virtual resources corresponding to the target business request, and the purpose of accelerating the processing of business requests is achieved through automated and intelligent file recognition and review, thereby achieving the technical effect of efficient data processing and immediate response, and further solving the technical problem of a long data processing flow leading to a slow response speed to business requests.

[0042] As an optional solution, the method of determining image features and text features based on the business data file, inputting the image features and text features into a target multimodal recognition model, and determining the file category and file authenticity attributes includes: obtaining a business image from the business data file; extracting the image features of the business image using an image feature extraction module; and identifying the text area in the business image to obtain the text features.

[0043] Optionally, in an embodiment of the present application, the above-mentioned business data file refers to various files submitted by an entity in a business request, including but not limited to identity documents, application forms, supporting documents, etc.; business images refer to the visible image part in the business data file, which may cover identity card pictures, signature samples, corporate certificate scans, etc.; text features refer to feature information extracted from the text content in the business image, including the content, format, layout, etc. of the text; image features refer to feature information extracted from the non-text part of the business image, such as the pixel distribution, shape features, color features, etc. of the image.

[0044] It should be noted that the function of the image feature extraction module can be implemented using a variety of deep learning architectures, such as using residual networks (ResNet) and convolutional neural networks (CNN) to extract image features, or using specific image processing algorithms (such as edge detection and color analysis) to enhance the recognition of features. The recognition of text areas and the acquisition of text features can be completed by Transformer and optical character recognition (OCR) technology, which can accurately extract readable text information from the text part in the image. This application does not limit this specific implementation method, and any technical solution that can achieve the above functions is within the scope of protection of the present invention.

[0045] For example, the system separates the business image from the submitted business data file, sends the image to the image feature extraction module for processing, and applies OCR technology to the text area in the image to obtain text features. Subsequently, the extracted image features and text features are input into the pre-trained multimodal recognition model, and the category and authenticity of the business document are determined through analysis and judgment of the model.

[0046] In an exemplary embodiment, taking the application scenario of a loan application business as an example, when an individual submits a loan application, the system extracts the ID card image and income certificate image from the business data file submitted by the individual as the business image; using the image feature extraction module, the system accurately identifies the image features of the ID card and income certificate; through OCR technology, the system obtains and analyzes the text information on the ID card and the numbers and text content in the income certificate, and then these image features and text features are input into the multimodal recognition model. Based on the pattern of the training data set, the model quickly determines the category and authenticity of the document, providing a basis for loan review.

[0047] Through the embodiment of the present application, a multimodal fusion recognition strategy of image features and text features is adopted to achieve fast and accurate business document classification and authenticity verification, thereby achieving the purpose of optimizing business processing procedures and improving audit efficiency. This technical means can significantly reduce the reliance on manual audits, speed up the response speed of business requests, and ensure the efficiency and security of business operations.

[0048] As an optional solution, the method also includes: using an attention mechanism to fuse the image features and the text features to obtain multimodal feature information; inputting the multimodal feature information into a classifier in the target multimodal recognition model to obtain the file category and the authenticity attribute.

[0049] Optionally, in the embodiment of the present application, the above-mentioned attention mechanism refers to a mechanism in a deep learning model for highlighting important feature information and suppressing irrelevant information, including but not limited to self-attention, conditional attention, etc. Image features and text features refer to visual and text feature data extracted from business images and business documents, respectively, which can characterize the characteristics of file content.

[0050] It should be noted that the fusion strategy can be implemented in a variety of ways, such as weighted averaging, gating mechanism, multi-layer attention network, etc., to ensure the effective combination of image features and text features. This application does not limit this specific fusion method, and any technical solution that can achieve feature information integration is applicable to the present invention.

[0051] For example, the system first independently obtains the image features and text features of the business data file, and then uses the attention mechanism to fuse the two features, and by assigning weights at the feature level, it highlights the feature information that is more relevant to file classification and authenticity verification, and obtains comprehensive multimodal feature information. Finally, this multimodal feature information is input into the classifier of the target multimodal recognition model to determine the file category and authenticity attributes.

[0052] In an exemplary embodiment, taking the application scenario of account opening business as an example, the system extracts the features of the ID card image and the features of the text content on the application form from the account opening application document. Then, the attention mechanism is used to weight these features to ensure that the weight of key information such as ID card number and name is higher than that of background images or irrelevant text, forming multimodal feature information. Finally, the fused information is input into the classifier of the target multimodal recognition model to quickly and accurately identify the category of the document (such as ID card, account opening application form) and judge its authenticity, providing instant review services for account opening.

[0053] Through the embodiments of the present application, multimodal feature fusion and recognition under the attention mechanism are adopted to achieve efficient classification and authenticity verification of business documents, achieve the purpose of improving the speed and accuracy of business request processing, and can significantly shorten the document review cycle and reduce the error rate. At the same time, it can enhance the system's intelligent analysis capabilities and provide support for efficient and intelligent business management.

[0054] As an optional scheme, the method also includes: determining an inclined image with a tilt attribute and a first non-tilted image without the tilt attribute from the business image; performing a Hough transform operation on the inclined image to obtain a second non-tilted image; using an image feature extraction module in the target multimodal recognition model to extract the image features of the first non-tilted image and the second non-tilted image; and identifying the text area in the business image to obtain the text features.

[0055] Optionally, in an embodiment of the present application, the above-mentioned business image refers to image data obtained from a business data file submitted by an entity, including but not limited to scanned copies of identity cards, contract photos, financial statement images, etc.; the tilt attribute refers to the presence of rotation or tilt in the image, and the first non-tilted image specifically refers to a business image that is not tilted; the second non-tilted image refers to the result of processing the tilted image through image correction technology to restore it to a non-tilted state.

[0056] It should be noted that the Hough transform operation is an algorithm for detecting geometric shapes such as straight lines and circles in an image, and is also applicable to image correction. By finding edge straight lines in a tilted image, the image rotation angle is calculated, and then the image rotation operation is applied to adjust the image to the correct direction. This application does not limit the specific parameter settings and implementation details of the Hough transform, and any technical solution that can effectively correct the tilt of an image can be applied to the present invention.

[0057] Exemplarily, the system identifies tilted images and non-tilted images from the business documents submitted by the entity, performs Hough transform operation on the tilted image to correct it, and obtains a second non-tilted image. Then, the first non-tilted image and the second non-tilted image are sent to the image feature extraction module in the target multimodal recognition model to extract image features. At the same time, text recognition technology is applied to the text areas in all business images to obtain text features, providing comprehensive feature information for subsequent document classification and authenticity verification.

[0058] In an exemplary embodiment, taking the application scenario of loan approval as an example, when an individual submits a loan application, the system identifies that the ID card image is tilted (i.e., tilted image) from the various images uploaded by the individual, while the loan contract image is not tilted (the first non-tilted image). The system then performs a Hough transform operation on the ID card image to restore it to its normal state (the second non-tilted image). Subsequently, all non-tilted images are input into the multimodal recognition model to extract image features, and the text area in the image is identified to obtain text features. Finally, the model gives the category and authenticity of the document based on the image features and text features, providing an accurate basis for loan approval.

[0059] Through the embodiment of the present application, Hough transform is used to correct image tilt, which achieves accurate extraction of image features and text features, and achieves the purpose of improving the accuracy and efficiency of file recognition. This technical solution optimizes the image preprocessing stage, ensures the smooth progress of the subsequent automatic recognition and review process, and has a significant effect on improving the automation level of business processes and user experience.

[0060] As an optional solution, when the file category is a preset target file category and the file authenticity attribute is true, determining an associated object having a business relationship with the target object through the identity information, and obtaining associated business information of the associated object, includes: determining a target business according to the target business request; querying a business information repository according to the type of the target business to determine the target file category required to process the target business, wherein the business information repository includes several business types and business file categories corresponding to each business type; comparing the target file category with the file category to determine whether the file category is the target file category.

[0061] Optionally, in the embodiment of the present application, the above-mentioned target business request refers to a specific business operation requirement proposed by an entity, including but not limited to account opening, loan application, permission change, etc. The target file category refers to a file category that is related to and necessary for the target business request. For example, in the account opening business, the target file category may include an account opening application form, a legal representative's identity document, etc. The business information repository refers to a database that centrally stores various business types and their required file categories, which may include but not limited to relational databases, non-relational databases, file systems and other storage methods.

[0062] It should be noted that the data structure and query algorithm in the business information repository can be diversified, such as using a hash table to achieve fast query, or using a tree structure to store file requirements of different business types to adapt to efficient processing in different business scenarios. This application does not limit this.

[0063] Exemplarily, the system first parses the target business request to determine the specific business type; then, it queries the business information repository for a list of file requirements corresponding to the business type, i.e., the target file category; then, it compares the file category identified by the system with the target file category to check whether the file is complete and correct, to ensure the smooth progress of subsequent business processes.

[0064] In an exemplary embodiment, taking the application scenario of corporate bank account opening as an example, when a company submits an account opening request, the system first identifies the business request as "corporate account opening". Subsequently, the system queries the business information repository to obtain the document requirements related to the "corporate account opening" business, that is, the target document category, including the company's business license, legal representative's ID card, account opening application, etc. Next, the system compares the actual received document category (that is, the identified document category) with the queried target document category to confirm whether the documents submitted by the company fully meet the requirements.

[0065] Through the embodiments of the present application, a business information repository query and file category comparison mechanism is adopted to achieve accurate matching and file verification of business requests, thereby achieving the purpose of ensuring the compliance and efficiency of business processes. It can not only avoid file omissions or errors, but also speed up the progress of business review and improve the overall business processing automation level and user experience.

[0066] As an optional solution, when the file category is a preset target file category and the file authenticity attribute is true, determining the associated object having a business relationship with the target object through the identity information, and obtaining the associated business information of the associated object, includes: using the identity information to perform a business association query operation on the target object to determine a first associated object and a second associated object, wherein the first associated object represents an object having a direct business relationship with the target object, and the second associated object represents an object having an indirect business relationship with the target object, and the associated objects include the first associated object and the second associated object; obtaining first associated business information of the first associated object, and obtaining second associated business information of the second associated object, wherein the first associated business information is used to indicate the associated business situation between the target object and the first associated object, and the second associated business information is used to indicate the associated business situation between the target object and the second associated object, and the associated business information includes the first associated business information and the second associated business information.

[0067] Optionally, in the embodiment of the present application, the above-mentioned business association query operation refers to analyzing the business relationship between the target object and other objects based on identity information through database query or other data processing methods; the first associated object and the second associated object respectively refer to entities that are directly or indirectly related to the target object in business, including but not limited to individual customers, corporate customers, business partners, etc. Associated business information refers to information reflecting the business transactions between the target object and the associated object, covering business type, transaction history, credit status, etc.

[0068] It should be noted that the specific algorithms and implementation methods of business association queries can be diverse, such as association relationship analysis based on graph databases, business network models established using social network analysis technology, etc. This application does not limit this, and any technical solution that can effectively determine associated objects and obtain associated business information is applicable.

[0069] Exemplarily, in the embodiment of the present invention, the system uses the identity information of the target object to perform a business association query, and by analyzing the business history data, determines the first associated object (such as the legal representative, direct business partner) and the second associated object (such as the enterprise shareholder, other enterprises in the indirect business chain) that are directly associated with the target object. Subsequently, the system extracts the business information related to the first associated object and the second associated object from the stored business data to evaluate the business status and credit level of the target object.

[0070] In an exemplary embodiment, taking the application scenario of enterprise credit approval as an example, when an enterprise submits a loan application, the system first performs a business association query based on the identity information of the enterprise (such as the enterprise's unified social credit code) to identify the first associated object directly associated with it (such as the legal representative, the company with direct financial transactions) and the second associated object indirectly associated with it (such as the enterprise's shareholders, other enterprises in the supply chain). Then, the system obtains the first associated business information such as the credit record and financial statements of the first associated object from the enterprise credit database, and collects the second associated business information such as the transaction history and credit rating of the second associated object. This information will be used to comprehensively assess the enterprise's loan risks and provide comprehensive support for credit decisions.

[0071] Through the embodiments of the present application, a business association query and data collection mechanism based on identity information is adopted to achieve in-depth insight into the business relationship network of the target object, achieve the purpose of accurately assessing business risks and optimizing the credit approval process, and can improve the level of intelligence in business processing and ensure the accuracy and timeliness of decision-making.

[0072] As an optional scheme, the use of the business data file and the associated business information to perform a target audit operation to determine whether the target object can obtain the virtual resources corresponding to the target business request includes: using the business data file and the associated business information to perform the target audit operation to obtain a first audit result; when the first audit result indicates that the business data file and the associated business information do not meet the business preset conditions, generating a first prompt message, wherein the first prompt message indicates that the target object is prohibited from obtaining the virtual resources corresponding to the target business request; using the business data file and the associated business information to perform the target audit operation to obtain a second audit result; when the second audit result indicates that the business data file and the associated business information meet the business preset conditions, issuing the virtual resources to the target object and generating a second prompt message, wherein the second prompt message indicates that the target object is allowed to obtain the virtual resources corresponding to the target business request.

[0073] Optionally, in an embodiment of the present application, the above-mentioned target review operation refers to an automatic review process for compliance, credit status, etc. of the target object based on business data files and related business information, including but not limited to credit review, account opening review, authority change review, etc. Business preset conditions refer to the rules and standards that must be met when conducting the target business, which can cover but not be limited to identity authentication, credit scoring, business compliance checks, etc. The first prompt message and the second prompt message are feedback information for audit failure and audit pass, respectively, to guide subsequent operations of the target object.

[0074] It should be noted that the specific implementation of the audit operation can be diversified, such as a rule-based audit process, a machine learning model audit, or a combination of the two. This application does not limit this, and any technical solution that can automatically complete the business audit is applicable.

[0075] Exemplarily, the system uses business data files and associated business information to conduct target audits, and the audit process involves multiple checks, such as identity information verification, credit rating assessment, business-related risk analysis, etc. After the audit is completed, the system generates a corresponding prompt message based on the audit results. If all conditions are met, a second prompt message is generated to allow access to virtual resources, otherwise a first prompt message is generated to prohibit access to virtual resources.

[0076] In an exemplary embodiment, taking the business scenario of bank account opening as an example, when an entity submits an account opening application, the system first performs an account opening review based on the business data file (account opening application, legal representative's ID card, etc.) and related business information (such as the legal representative's credit record, the company's operating conditions). At this time, the system will check whether the legal representative's identity information is true, whether the company's credit status meets the business preset conditions, etc. If the review finds that the legal representative's ID card is false or the company has a bad credit record, a first prompt message is generated to inform the entity that the account opening application is rejected. On the contrary, if all checks meet the preset conditions, the system will generate a second prompt message to confirm that the account opening application has passed the review, and automatically allocate virtual bank account resources to the entity, and the entity will then obtain account opening authority.

[0077] Through the embodiments of the present application, an automated review process and an intelligent decision-making mechanism are adopted to achieve rapid response and compliance checks to business requests, thereby achieving the purpose of improving review efficiency and ensuring business security. It can effectively reduce the error rate of manual review, while shortening the review cycle and providing entities with a more convenient service experience.

[0078] In an exemplary embodiment, the data processing method proposed in this application can be applied to the review and submission of bank expenditures for corporate accounts. Specifically, in the prior art, when a bank opens a basic deposit account, a temporary deposit account, etc. for an enterprise, it shall submit a copy or image of the relevant materials to the local bank system within 2 working days. At the end of the day, the bank branch staff needs to screen, copy, and bag the paper account materials that need to be submitted to the upper-level business system on that day, and then have them reviewed by branch specialists and manually scanned to generate image files and upload them to the upper-level business system according to the regulations of the upper-level business system. Every day, the number of documents reported by business personnel is large, the operations are highly repetitive, the process operation time is long, and a large amount of human resources are consumed. There may be a risk of misjudgment due to human factors.

[0079] Taking the above technical problems into consideration, the embodiment of the present application adopts Python programming language. When the business personnel handle account business for the enterprise, the account opening application, the identity document of the head of the unit, the business license and other documents provided are stored locally through a scanner. Then, the document verification system based on Python's residual network (ResNet) and Transformer's multimodal large language model (MLLMs) is used to identify and classify the document images provided by the user. After comparing the information of each file with the corresponding rules, manual intervention is performed to complete the missing files, and the files are uploaded to the target business system through a Python-based program at the end of the day. The specific implementation steps include but are not limited to:

[0080] S1, when the enterprise (target object) handles the account business, the bank staff manually scans the documents to the local area through a scanner, including the account opening application, the identity card of the head of the unit, the business license and other documents;

[0081] S2, a document verification system based on residual network (ResNet) and Transformer multimodal large language model (MLLMs) processes the above business information files. The neural network uses multimodal fusion technology, innovatively uses trans-membrane feature extraction, and uses a variety of different neural networks to extract text and image features, which can capture document information more comprehensively and perform feature fusion between the extraction layer and the decision layer, overcoming information loss or misunderstanding of context and improving the accuracy of the task;

[0082] For example, Figure 3 is a schematic diagram of an optional data processing method according to an embodiment of the present application. The overall process is as follows Figure 3 shown.

[0083] The first step is to use Hough transform to correct the tilted image and process the image through the residual network (ResNet) to extract the image features;

[0084] The second step is to process the image through Transformer to extract and analyze text features;

[0085] The third step is to combine the image features extracted by the residual network (ResNet) with the text features extracted by the Transformer, and use a fusion network or attention mechanism to associate the data of the two modalities;

[0086] For example, Figure 4 is a schematic diagram of another optional data processing method according to an embodiment of the present application, wherein the file category is determined as follows: Figure 4 shown.

[0087] The fourth step is to send the fused features into a classifier (such as a simple linear convolutional neural network (CNN)) to make an authenticity judgment and obtain the identified file category.

[0088] For example, when opening a basic deposit account, an account opening application, a business license or the identity document of the legal representative or the head of the unit, and basic deposit account information are required. When making changes, a change application, a business license or the identity document of the legal representative or the head of the unit, and basic deposit account information are required. When closing a temporary account of a non-temporary institution, an account cancellation application and a temporary account opening permit are required.

[0089] S3, document inspection: first, the document is marked through the data processing link (such as document type, document owner / ownership, document authenticity, etc.), the first step is to train a neural network model based on existing real documents, the second step is to obtain a set of images of the documents to be identified, and judge their authenticity and document category through the trained neural network, and the third step is to compare the category of the obtained document image with the category of the document required for the corresponding business. At the same time, the copy of the ID card scanned by the business personnel through the scanner during the business handling is checked online, and the superior unit of the enterprise is checked. If there is a superior unit, it will prompt to supplement the relevant documents of the superior unit.

[0090] S4, file submission: The business files of corporate accounts generated on the day are submitted through Python-based programs at the end of the day.

[0091] In general, in the embodiments of the present application, file recognition and classification are automatically classified and marked through Python-based multimodal large language model technology, which can automatically verify the identity card in the business document online, automatically check whether the enterprise has a superior unit, and automatically report the enterprise account business file to the higher-level business system.

[0092] Furthermore, all steps of the embodiment of the present application are automated, and the comparison process and the upload process are compared by artificial intelligence throughout, avoiding errors and problems caused by human operation and reducing the error rate. The embodiment of the present application can quickly and automatically classify business documents of corporate accounts and compare them according to business rules, which can improve work efficiency and save a lot of human resources. Furthermore, compared with traditional models, multimodal large language models can use transfer learning mechanisms for the recognition of other certificates when business changes occur (such as adding other certificates), continuously update and expand the types of certificates supported by the system, and increase the training speed and scalability of the system.

[0093] It is understandable that in the specific implementation of this application, related data such as user information is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0094] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0095] According to another aspect of the embodiment of the present application, a data processing device for implementing the above data processing method is also provided. Figure 5 As shown, the device comprises:

[0096] The acquisition module 502 is used to obtain the business data file and identity information of the target object in response to the target business request;

[0097] A determination module 504 is used to determine image features and text features according to the business data file, input the image features and text features into a target multimodal recognition model, and determine the file category and the authenticity of the file, wherein the target multimodal recognition model is pre-trained with sample image features and sample text features;

[0098] The association module 506 is used to determine the associated object having a business relationship with the target object through the identity information when the file category is a preset target file category and the file authenticity attribute is true, and obtain the associated business information of the associated object, wherein the associated business information represents business data related to the target object;

[0099] The audit module 508 is used to perform a target audit operation using the business data file and the associated business information to determine whether the target object can obtain the virtual resources corresponding to the target business request.

[0100] As an optional solution, the above-mentioned device is used to determine image features and text features based on a business data file in the following manner, input the image features and text features into a target multimodal recognition model, and determine the file category and file authenticity attributes: obtain a business image from the business data file; use an image feature extraction module in the target multimodal recognition model to extract image features of the business image; identify the text area in the business image to obtain text features.

[0101] As an optional solution, the above-mentioned device is also used to: use an attention mechanism to fuse image features and text features to obtain multimodal feature information; input the multimodal feature information into a classifier in a target multimodal recognition model to obtain a file category and authenticity attributes.

[0102] As an optional solution, the above-mentioned device is also used to: determine an oblique image with a tilt attribute and a first non-oblique image without a tilt attribute from a business image; perform a Hough transform operation on the oblique image to obtain a second non-oblique image; use an image feature extraction module in a target multimodal recognition model to extract image features of the first non-oblique image and the second non-oblique image; identify text areas in the business image to obtain text features.

[0103] As an optional solution, the above-mentioned device is used to determine the associated object having a business relationship with the target object through identity information and obtain the associated business information of the associated object in the following manner when the file category is a preset target file category and the file authenticity attribute is true: determine the target business according to the target business request; query the business information repository according to the type of the target business to determine the target file category required to process the target business, wherein the business information repository includes several business types and the business file category corresponding to each business type; compare the target file category and the file category to determine whether the file category is the target file category.

[0104] As an optional solution, the above-mentioned device is used to determine the associated object having a business relationship with the target object through identity information and obtain the associated business information of the associated object in the following manner when the file category is a preset target file category and the file authenticity attribute is true: use the identity information to perform a business association query operation on the target object to determine a first associated object and a second associated object, wherein the first associated object represents an object having a direct business relationship with the target object, and the second associated object represents an object having an indirect business relationship with the target object, and the associated objects include the first associated object and the second associated object; obtain first associated business information of the first associated object, and obtain second associated business information of the second associated object, wherein the first associated business information is used to indicate the associated business situation between the target object and the first associated object, and the second associated business information is used to indicate the associated business situation between the target object and the second associated object, and the associated business information includes the first associated business information and the second associated business information.

[0105] As an optional solution, the above-mentioned device is used to perform a target review operation using business data files and associated business information in the following manner to determine whether the target object can obtain the virtual resources corresponding to the target business request: use the business data files and associated business information to perform a target review operation to obtain a first review result; when the first review result indicates that the business data files and the associated business information do not meet the business preset conditions, generate a first prompt message, wherein the first prompt message indicates that the target object is prohibited from obtaining the virtual resources corresponding to the target business request; use the business data files and the associated business information to perform a target review operation to obtain a second review result; when the second review result indicates that the business data files and the associated business information meet the business preset conditions, issue virtual resources to the target object and generate a second prompt message, wherein the second prompt message indicates that the target object is allowed to obtain the virtual resources corresponding to the target business request.

[0106] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0107] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0108] According to one aspect of the present application, a computer program product is provided. The computer program product includes a computer program.

[0109] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0110] Figure 6 The structure block diagram of a computer system for implementing an electronic device according to an embodiment of the present application is schematically shown.

[0111] It should be noted that Figure 6 The computer system 600 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0112] like Figure 6 As shown, the computer system 600 includes a central processing unit 601 (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory 602 (ROM) or the program loaded from the storage part 608 to the random access memory 603 (RAM). Various programs and data required for system operation are also stored in the random access memory 603. The central processing unit 601, the read-only memory 602 and the random access memory 603 are connected to each other through a bus 604. The input / output interface 605 (Input / Output interface, i.e., I / O interface) is also connected to the bus 604.

[0113] The following components are connected to the input / output interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a local area network card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

[0114] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processor 601, various functions defined in the system of the present application are executed.

[0115] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processor 601, various functions provided by the embodiment of the present application are performed.

[0116] According to another aspect of the embodiment of the present application, an electronic device for implementing the above data processing method is also provided. The electronic device may be Figure 1 The terminal device or server shown in the figure. This embodiment is described by taking the electronic device as a terminal device as an example. Figure 7 As shown, the electronic device includes a memory 702 and a processor 704. The memory 702 stores a computer program, and the processor 704 is configured to execute the steps in any of the above method embodiments through the computer program.

[0117] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0118] Optionally, in this embodiment, the above-mentioned processor can be configured to execute the methods in each embodiment of the present application through a computer program.

[0119] Alternatively, a person skilled in the art may understand that: Figure 7 The structure shown is for illustration only. Figure 7 The structure of the electronic device is not limited. Figure 7 More or fewer components (such as network interfaces, etc.) as shown in, or with Figure 7 Different configurations are shown.

[0120] Among them, the memory 702 can be used to store software programs and modules, such as program instructions / modules corresponding to the data processing method and device in the embodiments of the present application. The processor 704 executes various functional applications and data processing by running the software programs and modules stored in the memory 702, that is, realizing the above-mentioned data processing method. The memory 702 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 702 may further include a memory remotely located relative to the processor 704, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 702 can be specifically, but not limited to, used to store information such as business data files and identity information. As an example, such as Figure 7 As shown, the memory 702 may include but is not limited to the acquisition module 502, determination module 504, association module 506, and review module 508 in the data processing device. In addition, it may also include but is not limited to other module units in the data processing device, which will not be repeated in this example.

[0121] Optionally, the transmission device 706 is used to receive or send data via a network. Specific examples of the network may include a wired network and a wireless network. In one example, the transmission device 706 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 706 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0122] In addition, the electronic device further includes: a display 708 for displaying the business data file and identity information; and a connection bus 710 for connecting various module components in the electronic device.

[0123] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. The nodes may form a peer-to-peer network, and any form of computing device, such as a server, terminal or other electronic device, may become a node in the blockchain system by joining the peer-to-peer network.

[0124] According to one aspect of the present application, a computer-readable storage medium is provided, and a processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the data processing method provided in various optional implementations of the above-mentioned data processing aspects.

[0125] Optionally, in this embodiment, the above-mentioned computer-readable storage medium can be configured to store data for executing the methods in various embodiments of the present application.

[0126] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0127] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0128] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for one or more electronic devices to execute all or part of the steps of the methods described in each embodiment of the present application.

[0129] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0130] In the several embodiments provided in the present application, it should be understood that the disclosed application can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0131] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0133] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A data processing method, characterized in that: include: In response to the target business request, obtain the business data file and identity information of the target object; Determining image features and text features according to the business data file, inputting the image features and the text features into a target multimodal recognition model to determine the file category and the authenticity of the file, wherein the target multimodal recognition model is pre-trained with sample image features and sample text features; When the file category is a preset target file category and the file authenticity attribute is true, determining an associated object having a business relationship with the target object through the identity information, and obtaining associated business information of the associated object, wherein the associated business information represents business data related to the target object; A target audit operation is performed using the business data file and the associated business information to determine whether the target object can obtain the virtual resource corresponding to the target business request.

2. The method according to claim 1, characterized in that The determining of image features and text features according to the business data file, inputting the image features and text features into a target multimodal recognition model, and determining the file category and the authenticity of the file includes: Acquire a business image from the business data file; Extracting the image features of the business image using an image feature extraction module; The text area in the business image is identified to obtain the text features.

3. The method according to claim 2, characterized in that The method further comprises: Using an attention mechanism to fuse the image features and the text features to obtain multimodal feature information; The multimodal feature information is input into a classifier in the target multimodal recognition model to obtain the document category and the authenticity attribute.

4. The method according to claim 2, characterized in that: The method further comprises: Determine from the service image an oblique image having an oblique attribute and a first non-oblique image not having the oblique attribute; Performing a Hough transform operation on the oblique image to obtain a second non-oblique image; Extracting the image features of the first non-oblique image and the second non-oblique image using an image feature extraction module in the target multimodal recognition model; The text area in the business image is identified to obtain the text features.

5. The method according to claim 1, characterized in that When the file category is a preset target file category and the file authenticity attribute is true, determining an associated object having a business relationship with the target object through the identity information, and obtaining associated business information of the associated object, includes: Determine a target service according to the target service request; Querying a business information repository according to the type of the target business to determine the target file category required for processing the target business, wherein the business information repository includes a plurality of business types and business file categories corresponding to each business type; The target file category is compared with the file category to determine whether the file category is the target file category.

6. The method according to claim 1, characterized in that When the file category is a preset target file category and the file authenticity attribute is true, determining an associated object having a business relationship with the target object through the identity information, and obtaining associated business information of the associated object, includes: Using the identity information to perform a business association query operation on the target object, determining a first associated object and a second associated object, wherein the first associated object represents an object having a direct business relationship with the target object, and the second associated object represents an object having an indirect business relationship with the target object, and the associated objects include the first associated object and the second associated object; Acquire first associated business information of the first associated object, and acquire second associated business information of the second associated object, wherein the first associated business information is used to indicate a business situation associated between the target object and the first associated object, and the second associated business information is used to indicate a business situation associated between the target object and the second associated object, and the associated business information includes the first associated business information and the second associated business information.

7. The method according to claim 1, characterized in that The using the business data file and the associated business information to perform a target audit operation to determine whether the target object can obtain the virtual resource corresponding to the target business request includes: Using the business data file and the associated business information to perform the target audit operation, obtaining a first audit result; if the first audit result indicates that the business data file and the associated business information do not meet the business preset condition, generating a first prompt message, wherein the first prompt message indicates that the target object is prohibited from obtaining the virtual resource corresponding to the target business request; Use the business data file and the associated business information to perform the target audit operation and obtain a second audit result; when the second audit result indicates that the business data file and the associated business information meet the business preset conditions, issue the virtual resources to the target object and generate a second prompt message, wherein the second prompt message indicates that the target object is allowed to obtain the virtual resources corresponding to the target business request.

8. A data processing device, characterized in that: include: An acquisition module, used to obtain the business data file and identity information of the target object in response to the target business request; a determination module, configured to determine image features and text features according to the business data file, input the image features and text features into a target multimodal recognition model, and determine the file category and the authenticity of the file, wherein the target multimodal recognition model is pre-trained with sample image features and sample text features; an association module, configured to determine, when the file category is a preset target file category and the file authenticity attribute is true, an associated object having a business relationship with the target object through the identity information, and obtain associated business information of the associated object, wherein the associated business information represents business data related to the target object; The audit module is used to perform a target audit operation using the business data file and the associated business information to determine whether the target object can obtain the virtual resources corresponding to the target business request.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein the computer program can be executed by an electronic device to perform the method described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

11. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images