Report data safe exporting and sharing method based on intelligent auditing and behavior analysis
By employing intelligent auditing and behavioral analysis methods, and utilizing multimodal deep neural network models and risk quantification models, the system addresses the issues of low efficiency and insufficient security in data export and sharing within intelligent reporting systems, thereby achieving refined data protection and efficient, secure data sharing.
Patent Information
- Application Number
- CN202511849650.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-09
- Publication Date
- 2026-02-27
AI Technical Summary
Existing intelligent reporting systems are inefficient and insecure in terms of data export and sharing, especially in terms of insufficient protection of sensitive data and lack of a sound auditing mechanism.
By employing a method based on intelligent auditing and behavioral analysis, sensitive data is identified through a multimodal deep neural network model, compliance pre-audit is conducted using an audit rule engine, and security approval is performed through a risk quantification model, ultimately achieving efficient compressed storage and secure sharing of data.
It improves the security and efficiency of data export and sharing, ensures that data complies with industry regulations before export, and achieves refined protection and efficient storage management of sensitive data.
Smart Images
Figure CN121579435A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of data processing technology, and in particular relates to a method for securely exporting and sharing report data based on intelligent auditing and behavior analysis. Background Technology
[0002] Currently, several technologies exist for data processing and export sharing in the data reporting field. For example, some intelligent reporting systems can perform basic data collection, organization, and simple export functions. Within an intelligent reporting system, the data source module is responsible for collecting raw data from various business systems. This data may come from different sources and business processes, such as sales data, inventory data, and human resource data. The data source module aggregates this scattered data into the reporting system through interfaces or database connections with various business systems. The report generation module organizes and processes the collected data, generating various reports according to preset report templates and rules. For example, it generates monthly sales reports and quarterly inventory reports. The report generation module typically provides data processing functions such as data filtering, sorting, and summarizing to meet the reporting needs of different users. The export module exports the generated report data to common file formats such as Excel, CSV, and PDF, facilitating user access and sharing of report data in other scenarios. Users can click the export button, select the export format and save the report data to their local machine or a specified network location.
[0003] Existing intelligent reporting systems typically involve a data source module acquiring data, a report generation module processing it to create reports, and then an export module exporting the report data. However, these systems have many limitations in data export and sharing, resulting in low export efficiency. Furthermore, there are no robust auditing mechanisms or security measures to ensure data security during the export and utilization process, especially regarding the insufficient handling of sensitive data, leading to low data protection security. Summary of the Invention
[0004] This invention provides a method for securely exporting and sharing report data based on intelligent auditing and behavior analysis, which can improve the security of securely exporting and sharing report data based on intelligent auditing and behavior analysis.
[0005] To achieve the above objectives, the present invention provides a device for securely exporting and sharing report data based on intelligent auditing and behavior analysis, comprising: The data source module is used to acquire heterogeneous report data from multiple sources; The sensitive data marking module is used to receive multi-source heterogeneous report data obtained by the data source module, and to determine the sensitivity level of data items in the multi-source heterogeneous report data based on a pre-built multimodal deep neural network model, and to associate the sensitivity level determination result with the corresponding multi-source heterogeneous report data. The business table review module is used to perform a compliance pre-review of multi-source heterogeneous report data marked with a sensitivity level using the review rule engine, and obtain the compliance review results. The data export application and approval module is used to quantify the risk of compliance audit results using a preset risk quantification model, and to determine whether to export multi-source heterogeneous report data based on the risk quantification results. The data collection module is used to perform data compression processing on the exported multi-source heterogeneous report data and store the compressed multi-source heterogeneous report data into the preset target data resource configuration system. The data sharing application module is used to respond to data sharing requests from users, match target data reports in the preset target data resource configuration system according to the data sharing request, and distribute the target data reports to the users who need them.
[0006] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the above-described method for securely exporting and sharing report data based on intelligent auditing and behavior analysis.
[0007] To address the aforementioned issues, the present invention also provides a computer-readable storage medium storing at least one computer program, which is executed by a processor in an electronic device to implement the aforementioned method for secure export and sharing of report data based on intelligent auditing and behavior analysis.
[0008] This invention's data source module is used to acquire multi-source heterogeneous report data. By supporting the access of multi-source heterogeneous data (from different systems and in different formats), it achieves comprehensive data aggregation, solving the problems of scattered data sources and inconsistent formats. Furthermore, based on a pre-built multimodal deep neural network model, it determines the sensitivity level of data items in the multi-source heterogeneous report data, enabling refined identification and labeling of sensitive data and improving data protection security. Additionally, the business table review module uses a review rule engine to perform compliance pre-review of multi-source heterogeneous report data marked with sensitivity levels, ensuring that the data complies with industry regulations before export. Finally, the data export application and approval module uses a preset risk quantification model for compliance review. The results are used to quantify risks, and based on these results, a decision is made on whether to export multi-source heterogeneous report data. This enables secure control and intelligent approval during the export process, improving export efficiency and security. Furthermore, the data collection module performs data compression on the exported multi-source heterogeneous report data, enabling efficient data storage and centralized management, and improving resource utilization. Finally, the data sharing request module responds to data sharing requests from users, matches target data reports in the preset target data resource configuration system based on the request, and distributes the target data reports to the requesting users. This ensures a secure response to user sharing requests, enhancing the controllability, compliance, and security of data sharing. Attached Figure Description
[0009] Figure 1 This is a flowchart illustrating a method for securely exporting and sharing report data based on intelligent auditing and behavior analysis, provided in an embodiment of the present invention. Figure 2 A functional module diagram of a report data secure export and sharing device based on intelligent auditing and behavior analysis provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device that implements the method for securely exporting and sharing report data based on intelligent auditing and behavior analysis, according to an embodiment of the present invention.
[0010] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0011] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0012] This application provides a method for securely exporting and sharing report data based on intelligent auditing and behavioral analysis. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, this method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.
[0013] Reference Figure 1 The diagram shown is a flowchart illustrating a method for securely exporting and sharing report data based on intelligent auditing and behavior analysis, according to an embodiment of the present invention. In this embodiment, the method for securely exporting and sharing report data based on intelligent auditing and behavior analysis includes: S1, the data source module, is used to obtain multi-source heterogeneous report data.
[0014] Understandably, the data source module is the entry point for the entire system, used to uniformly access and collect report data from different sources.
[0015] Understandably, multi-source heterogeneous report data refers to a collection of report data that comes from multiple data sources and has an inconsistent structure.
[0016] Specifically, acquiring multi-source heterogeneous report data includes: Send a protocol message to the target address and compare the returned message with the preset protocol feature fingerprint database. If the match is successful, the data source interface type is obtained. Extract report data based on the data source interface type, parse the data structure of the report data, and use the depth-first traversal algorithm and hash fingerprint algorithm to remove duplicates of redundant substructures to obtain multi-source heterogeneous report data.
[0017] Understandably, the target address refers to the network address or connection endpoint of the data source interface that needs to be accessed.
[0018] Understandably, a protocol message refers to a request or response data packet constructed according to a specific communication protocol (such as HTTP, SOAP, FTP, JDBC).
[0019] Understandably, the pre-built protocol feature fingerprint library refers to a pre-built set of protocol features used to identify different data source interface types.
[0020] Understandably, depth-first traversal is a graph or tree structure traversal algorithm that prioritizes traversing a branch to the bottom before backtracking to the upper level to continue traversing other branches.
[0021] Understandably, a hash fingerprint algorithm refers to generating a unique fingerprint value for a data structure or field using a hash function (such as MD5 or SHA-256).
[0022] Understandably, redundant substructures refer to the set of identical or equivalent child nodes / fields that appear repeatedly in the report data structure.
[0023] S2, Sensitive Data Marking Module, is used to receive multi-source heterogeneous report data obtained by the data source module, and to determine the sensitivity level of data items in the multi-source heterogeneous report data based on a pre-built multimodal deep neural network model, and to associate the sensitivity level determination result with the corresponding multi-source heterogeneous report data.
[0024] Understandably, the sensitive data tagging module refers to identifying and tagging sensitive information in report data.
[0025] Specifically, the sensitivity level determination of data items in multi-source heterogeneous report data based on the pre-built multimodal deep neural network model includes: the pre-built multimodal deep neural network model includes an RNN model for processing text data in multi-source heterogeneous report data, a CNN model for processing image data in multi-source heterogeneous report data, an FCN model for processing structured data in multi-source heterogeneous report data, a feature fusion layer, and a classification output layer.
[0026] Understandably, an RNN (Recurrent Neural Network) model is a type of recurrent neural network that excels at processing sequential data. For example, an RNN model can identify whether a text field contains sensitive information (such as "ID card number" or "bank card number").
[0027] Understandably, a CNN (Convolutional Neural Network) model refers to a convolutional neural network that processes image-based data. For example, a CNN model can identify whether a report contains sensitive image information.
[0028] Understandably, the FCN (Fully Connected Network) model refers to a fully connected neural network that can process structured data. For example, the FCN model can identify whether structured fields (such as "salary amount" or "customer number") are sensitive data.
[0029] Understandably, the feature fusion layer refers to a network layer that fuses features extracted from different sub-models (RNN, CNN, FCN).
[0030] Understandably, the classification output layer refers to the final output layer of the model, which is used to map the fused features to specific classification results.
[0031] Furthermore, the RNN model employs a BiLSTM model to capture contextual semantics and an Attention mechanism to focus on sensitive keywords; the CNN model uses ResNet50 to extract visual features and an OCR algorithm to recognize text content in multi-source heterogeneous report data; ResNet50 extracts global image features, the OCR layer recognizes text in the image, and the text sequence is input into a reused text model for sensitivity level determination; the FCN model analyzes field attributes in structured data.
[0032] Understandably, the BiLSTM model refers to a bidirectional long short-term memory network.
[0033] Understandably, ResNet50 refers to a deep convolutional neural network with 50 layers, belonging to the Residual Network (ResNet) family.
[0034] Understandably, the OCR layer refers to the optical character recognition technology layer, which is used to automatically recognize and convert text information in report images into a processable text sequence.
[0035] Furthermore, the feature fusion layer includes a modal interaction attention network, wherein the feature fusion layer uses the modal interaction attention network to map each single modal feature to a unified semantic space, and captures intermodal correlations through a cross-modal interaction attention layer.
[0036] Understandably, in this embodiment of the invention, the feature fusion layer uses a modal interaction attention network to map each single modal feature to a unified semantic space, and captures the intermodal correlation through a cross-modal interaction attention layer, fusing the three cross-modal enhanced features into a unified semantic feature vector for subsequent decision-level fusion.
[0037] Furthermore, the classification output layer includes a decision-level dynamic weight fusion network, wherein the classification output layer calculates dynamic weights based on the confidence level, historical accuracy, and data integrity of each modality output, and uses the decision-level dynamic weight fusion network to weight and fuse the judgment results of each modality to obtain the sensitivity level judgment result.
[0038] Understandably, the decision-level dynamic weighted fusion network is a multi-model fusion method that weights and combines the outputs of different sub-models in the final decision-making stage.
[0039] Furthermore, by using a decision-level dynamic weighted fusion network to weight and fuse the judgment results of each modality, the following formula can be used for weighted fusion: in, For image data weights, For image data modalities, Weights for text data, For text data modality, For structured data weights, For structured data modalities.
[0040] S3, the business table audit module, is used to perform compliance pre-audit on multi-source heterogeneous report data marked with sensitivity levels using the audit rule engine, and obtain compliance audit results.
[0041] Understandably, the audit rule engine refers to the rule-driven logic processing core used to perform compliance checks. It can contain multiple sets of predefined rule bases and matching mechanisms, and can be flexibly expanded according to different business scenarios.
[0042] Specifically, the compliance pre-audit of multi-source heterogeneous report data marked with sensitivity levels using an audit rule engine to obtain compliance audit results includes: The audit rule engine is used to scan multi-source heterogeneous report data. After the scan is completed, rule matching is performed to obtain a set of matching rules. The multi-source heterogeneous report data is reviewed using each rule in the matching rule set, and the compliance review result is obtained after the review is completed.
[0043] For example, to perform a compliance pre-audit on multi-source heterogeneous report data marked with sensitivity levels using an audit rule engine and obtain compliance audit results, the following implementation steps can be adopted: Step 1: If the business form passes the preliminary review, the system will automatically mark it as "approved" and send it to subsequent processes, such as the data export and sharing module, for further data processing and analysis tasks. Step 2: If the business table fails the preliminary review, the system will mark the business table as "to be modified" and send it back to the business party for correction. Step 3: After modifying the business report data according to the error prompts in the pre-review report, the business party can resubmit it for review.
[0044] S4, the data export application and approval module, is used to quantify the risk of compliance audit results using a preset risk quantification model, and determine whether to export multi-source heterogeneous report data based on the risk quantification results.
[0045] Understandably, a pre-defined risk quantification model refers to a mathematical or statistical model that is built and configured in advance in the system to transform compliance audit results into measurable risk values.
[0046] S5, the data collection module, is used to perform data compression processing on the exported multi-source heterogeneous report data, and store the compressed multi-source heterogeneous report data into the preset target data resource configuration system.
[0047] Understandably, data compression processing of exported multi-source heterogeneous report data can be performed using efficient compression algorithms, such as LZ4 or Zstandard algorithms, where LZ4 is a lightweight compression algorithm.
[0048] Understandably, the preset target data resource configuration system refers to a pre-configured data storage and management platform used to receive, store, and distribute processed multi-source heterogeneous report data.
[0049] S6, the data sharing application module, is used to respond to data sharing requests from users, match target data reports in the preset target data resource configuration system according to the data sharing request, and distribute the target data reports to the users who need them.
[0050] For example, matching a target data report in a preset target data resource configuration system according to a data sharing request can be achieved by the following implementation steps: searching for matching data resources in the preset target data resource configuration system based on the data requester's application information (such as data type, purpose of use, etc.).
[0051] This invention's data source module is used to acquire multi-source heterogeneous report data. By supporting the access of multi-source heterogeneous data (from different systems and in different formats), it achieves comprehensive data aggregation, solving the problems of scattered data sources and inconsistent formats. Furthermore, based on a pre-built multimodal deep neural network model, it determines the sensitivity level of data items in the multi-source heterogeneous report data, enabling refined identification and labeling of sensitive data and improving data protection security. Additionally, the business table review module uses a review rule engine to perform compliance pre-review of multi-source heterogeneous report data marked with sensitivity levels, ensuring that the data complies with industry regulations before export. Finally, the data export application and approval module uses a preset risk quantification model for compliance review. The results are used to quantify risks, and based on these results, a decision is made on whether to export multi-source heterogeneous report data. This enables secure control and intelligent approval during the export process, improving export efficiency and security. Furthermore, the data collection module performs data compression on the exported multi-source heterogeneous report data, enabling efficient data storage and centralized management, and improving resource utilization. Finally, the data sharing request module responds to data sharing requests from users, matches target data reports in the preset target data resource configuration system based on the request, and distributes the target data reports to the requesting users. This ensures a secure response to user sharing requests, enhancing the controllability, compliance, and security of data sharing.
[0052] like Figure 2 The diagram shown is a functional block diagram of a report data secure export and sharing device based on intelligent auditing and behavior analysis provided in an embodiment of the present invention.
[0053] The report data secure export and sharing device 100 based on intelligent auditing and behavior analysis described in this invention can be installed in an electronic device. Depending on the functions implemented, the report data secure export and sharing device 100 based on intelligent auditing and behavior analysis may include a data source module 101, a sensitive data marking module 102, a business table auditing module 103, a data export application and approval module 104, a data collection module 105, and a data sharing application module 106.
[0054] The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.
[0055] In this embodiment, the functions of each module / unit are as follows: The data source module 101 is used to acquire multi-source heterogeneous report data.
[0056] The sensitive data marking module 102 is used to receive multi-source heterogeneous report data obtained by the data source module, and to determine the sensitivity level of data items in the multi-source heterogeneous report data based on a pre-built multimodal deep neural network model, and to associate the sensitivity level determination result with the corresponding multi-source heterogeneous report data.
[0057] The business table audit module 103 is used to perform a compliance pre-audit on multi-source heterogeneous report data marked with a sensitivity level using an audit rule engine, and obtain a compliance audit result.
[0058] The data export application and approval module 104 is used to quantify the risk of the compliance audit results using a preset risk quantification model, and to determine whether to export multi-source heterogeneous report data based on the risk quantification results.
[0059] The data collection module 105 is used to perform data compression processing on the exported multi-source heterogeneous report data, and store the compressed multi-source heterogeneous report data into a preset target data resource configuration system.
[0060] The data sharing application module 106 is used to respond to the data sharing request of the user, match the target data report in the preset target data resource configuration system according to the data sharing request, and send the target data report to the user.
[0061] like Figure 3 The diagram shown is a structural schematic of an electronic device that implements a method for securely exporting and sharing report data based on intelligent auditing and behavior analysis, according to an embodiment of the present invention.
[0062] The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13. It may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a method program for securely exporting and sharing report data based on intelligent auditing and behavior analysis.
[0063] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a method for securely exporting and sharing report data based on intelligent auditing and behavior analysis), and calls data stored in the memory 11 to perform various functions of the electronic device and process data.
[0064] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 11 can include both internal and external storage units of the electronic device. The memory 11 can be used not only to store application software and various types of data installed on the electronic device, such as the code of a method for securely exporting and sharing report data based on intelligent auditing and behavior analysis, but also to temporarily store data that has been output or will be output.
[0065] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.
[0066] The communication interface 13 is used for communication between the aforementioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), or optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.
[0067] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.
[0068] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.
[0069] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.
[0070] The program for securely exporting and sharing report data based on intelligent auditing and behavior analysis, stored in the memory 11 of the electronic device, is a combination of multiple instructions. When run in the processor 10, it can achieve the following: The data source module is used to acquire heterogeneous report data from multiple sources; The sensitive data marking module is used to receive multi-source heterogeneous report data obtained by the data source module, and to determine the sensitivity level of data items in the multi-source heterogeneous report data based on a pre-built multimodal deep neural network model, and to associate the sensitivity level determination result with the corresponding multi-source heterogeneous report data. The business table review module is used to perform a compliance pre-review of multi-source heterogeneous report data marked with a sensitivity level using the review rule engine, and obtain the compliance review results. The data export application and approval module is used to quantify the risk of compliance audit results using a preset risk quantification model, and to determine whether to export multi-source heterogeneous report data based on the risk quantification results. The data collection module is used to perform data compression processing on the exported multi-source heterogeneous report data and store the compressed multi-source heterogeneous report data into the preset target data resource configuration system. The data sharing application module is used to respond to data sharing requests from users, match target data reports in the preset target data resource configuration system according to the data sharing request, and distribute the target data reports to the users who need them.
[0071] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.
[0072] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).
[0073] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: The data source module is used to acquire heterogeneous report data from multiple sources; The sensitive data marking module is used to receive multi-source heterogeneous report data obtained by the data source module, and to determine the sensitivity level of data items in the multi-source heterogeneous report data based on a pre-built multimodal deep neural network model, and to associate the sensitivity level determination result with the corresponding multi-source heterogeneous report data. The business table review module is used to perform a compliance pre-review of multi-source heterogeneous report data marked with a sensitivity level using the review rule engine, and obtain the compliance review results. The data export application and approval module is used to quantify the risk of compliance audit results using a preset risk quantification model, and to determine whether to export multi-source heterogeneous report data based on the risk quantification results. The data collection module is used to perform data compression processing on the exported multi-source heterogeneous report data and store the compressed multi-source heterogeneous report data into the preset target data resource configuration system. The data sharing application module is used to respond to data sharing requests from users, match target data reports in the preset target data resource configuration system according to the data sharing request, and distribute the target data reports to the users who need them.
[0074] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.
[0075] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0076] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.
[0077] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0078] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the invention. No appended diagram markings in the claims should be construed as limiting the scope of the claims.
[0079] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.
[0080] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.
[0081] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.
[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims
1. A device for securely exporting and sharing report data based on intelligent auditing and behavioral analysis, characterized in that: The device includes: The data source module is used to acquire heterogeneous report data from multiple sources; The sensitive data marking module is used to receive multi-source heterogeneous report data obtained by the data source module, and to determine the sensitivity level of data items in the multi-source heterogeneous report data based on a pre-built multimodal deep neural network model, and to associate the sensitivity level determination result with the corresponding multi-source heterogeneous report data. The business table review module is used to perform compliance pre-review on multi-source heterogeneous report data marked with sensitivity levels using the review rule engine, and obtain compliance review results; The data export application and approval module is used to quantify the risk of compliance audit results using a preset risk quantification model, and to determine whether to export multi-source heterogeneous report data based on the risk quantification results. The data collection module is used to perform data compression processing on the exported multi-source heterogeneous report data and store the compressed multi-source heterogeneous report data into the preset target data resource configuration system. The data sharing application module is used to respond to data sharing requests from users, match target data reports in the preset target data resource configuration system according to the data sharing request, and distribute the target data reports to the users who need them.
2. The report data secure export and sharing device based on intelligent auditing and behavior analysis as described in claim 1, characterized in that, The acquisition of multi-source heterogeneous report data includes: Send a protocol message to the target address and compare the returned message with the preset protocol feature fingerprint database. If the match is successful, the data source interface type is obtained. Extract report data based on the data source interface type, parse the data structure of the report data, and use the depth-first traversal algorithm and hash fingerprint algorithm to remove duplicates of redundant substructures to obtain multi-source heterogeneous report data.
3. The report data secure export and sharing device based on intelligent auditing and behavior analysis as described in claim 1, characterized in that, The sensitivity level determination of data items in multi-source heterogeneous report data based on the pre-constructed multimodal deep neural network model includes: the pre-constructed multimodal deep neural network model includes an RNN model for processing text data in multi-source heterogeneous report data, a CNN model for processing image data in multi-source heterogeneous report data, an FCN model for processing structured data in multi-source heterogeneous report data, a feature fusion layer, and a classification output layer.
4. The report data secure export and sharing device based on intelligent auditing and behavior analysis as described in claim 3, characterized in that, The RNN model uses a BiLSTM model to capture contextual semantics and an Attention mechanism to focus on sensitive keywords; the CNN model uses ResNet50 to extract visual features and an OCR algorithm to recognize text content in multi-source heterogeneous report data; ResNet50 extracts global image features, the OCR layer recognizes text in the image, and the text sequence is input into a reused text model for sensitivity level determination; the FCN model analyzes field attributes in structured data.
5. The report data secure export and sharing device based on intelligent auditing and behavior analysis as described in claim 3, characterized in that, The feature fusion layer includes a modal interaction attention network, wherein the feature fusion layer uses the modal interaction attention network to map each single modal feature to a unified semantic space, and captures the intermodal correlation through the cross-modal interaction attention layer.
6. The report data secure export and sharing device based on intelligent auditing and behavior analysis as described in claim 3, characterized in that, The classification output layer includes a decision-level dynamic weight fusion network, wherein the classification output layer calculates dynamic weights based on the confidence level, historical accuracy and data completeness of each modality output, and uses the decision-level dynamic weight fusion network to weight and fuse the judgment results of each modality.
7. The method for securely exporting and sharing report data based on intelligent auditing and behavior analysis as described in claim 1, characterized in that, The compliance pre-audit of multi-source heterogeneous report data marked with sensitivity levels using an audit rule engine yields compliance audit results, including: The audit rule engine is used to scan multi-source heterogeneous report data. After the scan is completed, rule matching is performed to obtain a set of matching rules. The multi-source heterogeneous report data is reviewed using each rule in the matching rule set, and the compliance review result is obtained after the review is completed.
8. A method for securely exporting and sharing report data based on intelligent auditing and behavior analysis, implemented using the report data secure export and sharing device based on intelligent auditing and behavior analysis as described in any one of claims 1 to 7, the method comprising: The data source module is used to acquire heterogeneous report data from multiple sources; The sensitive data marking module is used to receive multi-source heterogeneous report data obtained by the data source module, and to determine the sensitivity level of data items in the multi-source heterogeneous report data based on a pre-built multimodal deep neural network model, and to associate the sensitivity level determination result with the corresponding multi-source heterogeneous report data. The business table review module is used to perform compliance pre-review on multi-source heterogeneous report data marked with sensitivity levels using the review rule engine, and obtain compliance review results; The data export application and approval module is used to quantify the risk of compliance audit results using a preset risk quantification model, and to determine whether to export multi-source heterogeneous report data based on the risk quantification results. The data collection module is used to perform data compression processing on the exported multi-source heterogeneous report data and store the compressed multi-source heterogeneous report data into the preset target data resource configuration system. The data sharing application module is used to respond to data sharing requests from users, match target data reports in the preset target data resource configuration system according to the data sharing request, and distribute the target data reports to the users who need them.
9. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the report data secure export and sharing method based on intelligent auditing and behavior analysis as described in claim 8.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for secure export and sharing of report data based on intelligent auditing and behavior analysis as described in claim 8.