Auditing project data management method, system and equipment for digital intelligent power grid construction and medium

Abstract

The invention relates to an auditing project data management method for digital intelligent power grid construction, which is applied to a data auditing device, the device comprises a power grid cloud server and a project auditing sub-terminal, and the method comprises the following steps: obtaining a user operation instruction of the project auditing sub-terminal through the power grid cloud server, generating user operation record information based on the user operation instruction; constructing an audit resource knowledge base, wherein the audit resource knowledge base comprises project archive information, standard data resource information and basic regulation retrieval information; extracting the user operation record information through an SQL (Structured Query Language) on the basis of the regulation retrieval information and the standard data resource information to obtain feature data information; and carrying out association relationship analysis on the feature data information to generate audit evaluation information. Through the content, high efficiency, intelligence and standardization of data management of the digital intelligent power grid construction auditing project are realized, powerful support is provided for auditing work, auditing quality and efficiency can be improved, and healthy development of a digital intelligent power grid is promoted.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to an audit project data management method, system, equipment, and medium for digital intelligent power grid construction. Background Art

[0002] With the acceleration of the digital transformation of power grids, power grid audits face numerous challenges, including processing massive amounts of data, monitoring complex business processes, and checking regulatory compliance. Traditional audit methods and tools, when handling audit tasks in the context of digital grid construction, suffer from inefficiency, lack of accuracy, and weak data correlation, making them unable to meet the demands of modern power grid audits. Therefore, there is an urgent need for a system and method that can efficiently, accurately, and flexibly manage audit project data to improve audit efficiency and quality and ensure the compliance and security of power grid construction. Summary of the Invention

[0003] Based on this, it is necessary to provide an audit project data management method, system, equipment and medium for the construction of digital power grids to address the problems of low efficiency, insufficient accuracy and weak data correlation of traditional power grid audit methods and tools.

[0004] An audit project data management method for digital power grid construction is applied to a data audit device, the device including a power grid cloud server and a project audit sub-terminal. The method includes:

[0005] Obtaining user operation instructions of the project audit sub-terminal through the power grid cloud server, and generating user operation record information based on the user operation instructions;

[0006] Constructing an audit resource knowledge base, which includes project archive information, standard data resource information, and basic law and regulation retrieval information;

[0007] Based on the regulatory retrieval information and standard data resource information, the user operation record information is extracted through SQL to obtain feature data information;

[0008] Perform correlation analysis on the characteristic data information to generate audit evaluation information.

[0009] In one preferred embodiment, obtaining the user operation instruction of the project audit sub-terminal through the power grid cloud server and generating user operation record information based on the user operation instruction includes:

[0010] generating bitmap response data based on the acquired user operation instruction, wherein the bitmap response data includes bitmap data and operation identification data;

[0011] The bitmap data is converted into image data and combined with the operation identification data to generate the user operation record data.

[0012] In one preferred embodiment, the generating of bitmap response data based on the acquired user operation instruction includes:

[0013] Convert the user operation instruction into structured data information based on OCR recognition technology;

[0014] In one preferred embodiment, the method for obtaining the basic legal regulations search information includes:

[0015] Obtain regulatory texts on target websites through web crawlers;

[0016] The obtained regulatory text is subjected to keyword extraction and classification based on natural language processing technology, and updated into the basic regulatory retrieval information.

[0017] The above implementation method uses web crawlers to obtain the latest regulatory texts and applies natural language processing technology to extract and classify keywords, ensuring the timeliness and accuracy of basic regulatory retrieval information, enabling audit work to be carried out in accordance with the latest regulatory requirements, and enhancing audit compliance.

[0018] In one preferred embodiment, the extracting of the user operation record information by SQL to obtain feature data information includes:

[0019] Acquire application scenarios based on the user operation records, and write regularized query statements using SQL based on the application scenarios;

[0020] A regularized query statement is written based on SQL, and feature extraction is performed on the user operation record information according to the application scenario to obtain feature data information.

[0021] In one preferred embodiment, the performing of correlation analysis on the characteristic data information to generate audit evaluation information includes:

[0022] Construct an audit entity relationship network based on a graph database;

[0023] Perform association analysis on the feature information based on the audit entity relationship network.

[0024] In one preferred embodiment, generating audit evaluation information includes:

[0025] Output visual evaluation report;

[0026] Output audit warning information based on warning rules.

[0027] The above-mentioned embodiments of the present invention realize the efficient, intelligent and standardized data management of the digital power grid construction audit project through the above-mentioned contents, provide strong support for the audit work, help improve the audit quality and efficiency, and promote the healthy development of the digital power grid.

[0028] An audit project data management system for digital power grid construction, applied to a data audit device, comprising a power grid cloud server and a project audit sub-terminal. The system includes:

[0029] a data acquisition module, configured to obtain user operation instructions of the project audit sub-terminal through the power grid cloud server, and generate user operation record information based on the user operation instructions;

[0030] A resource construction module is used to construct an audit resource knowledge base, which includes project archive information, standard data resource information and basic law and regulation retrieval information;

[0031] A data analysis module is used to extract the user operation record information through SQL based on the regulatory retrieval information and standard data resource information to obtain characteristic data information;

[0032] The information generation module is used to perform correlation analysis on the characteristic data information and generate audit evaluation information.

[0033] The above-mentioned embodiments of the present invention realize the efficient, intelligent and standardized data management of the digital power grid construction audit project through the above-mentioned contents, provide strong support for the audit work, help improve the audit quality and efficiency, and promote the healthy development of the digital power grid.

[0034] An electronic device, comprising:

[0035] at least one processor; and a memory communicatively connected to the at least one processor; wherein,

[0036] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned audit project data management method for digital power grid construction.

[0037] The above-mentioned embodiments of the present invention realize the efficient, intelligent and standardized data management of the digital power grid construction audit project through the above-mentioned contents, provide strong support for the audit work, help improve the audit quality and efficiency, and promote the healthy development of the digital power grid.

[0038] A computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the audit project data management method described above when executed.

[0039] The above-mentioned embodiments of the present invention realize the efficient, intelligent and standardized data management of the digital power grid construction audit project through the above-mentioned contents, provide strong support for the audit work, help improve the audit quality and efficiency, and promote the healthy development of the digital power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The present invention discloses a flowchart of an audit project data management method for digital intelligent power grid construction in accordance with the first preferred embodiment of the present invention;

[0041] Figure 2 A flowchart of the subdivided steps of step S10 of an audit project data management method for digital intelligent power grid construction is disclosed as a first preferred embodiment of the present invention;

[0042] Figure 3 A flowchart of the subdivided steps of step S20 of an audit project data management method for digital smart grid construction is disclosed as a first preferred embodiment of the present invention;

[0043] Figure 4 A flowchart of the subdivided steps of step S30 of an audit project data management method for digital smart grid construction is disclosed as a first preferred embodiment of the present invention;

[0044] Figure 5 A module diagram of an audit project data management system for digital smart grid construction is disclosed as a second preferred embodiment of the present invention;

[0045] Figure 6 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0047] It should be noted that when an element is referred to as being "disposed on" another element, it may be directly on the other element or there may be an element centered thereon. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an element centered thereon. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only implementations.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0049] like Figure 1 As shown, the first preferred embodiment of this embodiment discloses an audit project data management method for the construction of a digital power grid. The method is applied to a data audit device, which includes a power grid cloud server and a project audit sub-terminal. The power grid cloud server obtains project data and generates user operation record data based on the project data; wherein, the project data is the data for interaction between the cloud server and the client through the power grid cloud server; the project audit subsystem audits the user operation record data according to a pre-defined security audit strategy to obtain an audit result.

[0050] The above-mentioned audit project data management method for digital power grid construction includes the following steps:

[0051] S10: Acquire user operation instructions of the project audit sub-terminal through the power grid cloud server, and generate user operation record information based on the user operation instructions;

[0052] In this step, the above-mentioned user operation instructions can come from various input methods of the audit sub-terminal, including but not limited to: graphical interface operations: such as mouse clicking, dragging, and form filling; command line instructions: such as audit script execution, data export commands; API calls: audit tasks triggered by third-party systems through RESTful APIs.

[0053] The above generates user operation record information based on the user operation instructions. For unstructured instructions (such as natural language input), a pre-trained NLP model (such as BERT) is used to extract the operation intent and map it to standardized operation types (such as "data query" and "risk tag"). For structured instructions (such as JSON format), key fields are parsed using regular expressions or XPath.

[0054] Specifically, combined Figure 1 and Figure 2 As shown, the above step S10 includes the following subdivision steps:

[0055] S11: generating bitmap response data based on the acquired user operation instruction, wherein the bitmap response data includes bitmap data and operation identification data;

[0056] In this embodiment, when a user triggers an operation, the cloud server captures the screen image of the audit sub-terminal in real time through a remote desktop protocol (such as RDP or VNC) to generate original bitmap data.

[0057] In more detail, in the above-mentioned subdivision step S11, the user operation instructions are converted into structured data information based on OCR recognition technology; specifically, it includes text cleaning, semantic segmentation and structured mapping. The above-mentioned text cleaning is used to remove irrelevant characters (such as special symbols, garbled characters) and merge broken texts.

[0058] In this subdivision step, the bitmap data of the user operation instruction can be preprocessed to improve the OCR recognition accuracy: for example, using Gaussian filtering to eliminate image noise (such as interfering pixels caused by screen flickering); using binarization processing to convert the image into black and white mode (such as using the Otsu algorithm adaptive threshold); using contrast adjustment to enhance the distinction between text and background (such as histogram equalization), etc.

[0059] S12: Convert the bitmap data into image data, and combine it with the operation identification data to generate the user operation record data.

[0060] In this subdivision step, the bitmap data is parsed to extract the corresponding metadata, and the metadata embedding technology and conversion technology are used to generate the corresponding image data.

[0061] S20: Construct an audit resource knowledge base, which includes project archive information, standard data resource information, and basic law and regulation retrieval information.

[0062] Project archive information is generated when constructing the audit resource knowledge base; at the same time, when constructing the audit resource knowledge base, the project archive information is used to build standard table data resources for intelligent audit data mining and data modeling.

[0063] When building audit archive management within audit management, archived project files are automatically collected into the project archive module, published audit report information and documents are automatically collected into the audit report module, and data from closed audit project drawers is automatically collected into the data module, thereby forming audit data assets. Unstructured and semi-structured audit evidence is recognized as structured data using optical character recognition.

[0064] When constructing the legal and regulatory database for audit resource management, a basic retrieval database is established for audit analysis and audit judgment.

[0065] Combine Figure 1 and Figure 3 As shown, the method for obtaining the basic legal regulations search information in step S20 includes the following subdivision steps:

[0066] S21: Obtain regulatory texts on target websites through web crawlers;

[0067] In this subdivision step, different types of web crawler tools can be used for different types of target websites. For example, for government static websites, the crawling tools used are Scrapy+XPath; for dynamic rendering websites, the crawling tools used are Selenium / Playwright; for legal databases, API interfaces are used, and Requests+JSON parsing is used for parsing.

[0068] S22: Extract and classify keywords from the obtained regulatory text based on natural language processing technology, and update the keywords into the basic regulatory search information.

[0069] In this subdivision step, the regulatory text obtained in the above-mentioned subdivision step S21 is pre-processed using natural language processing technology, followed by keyword extraction, and then text classification, and finally updated to the above-mentioned basic regulatory retrieval information.

[0070] The above text preprocessing cleans the data of noise and standardizes the text format, providing high-quality input for subsequent NLP tasks. The above keyword extraction extracts core keywords from the preprocessed legal text. Specifically, through the statistical TF-IDF, high-frequency borrowing and high-distinction words are extracted, and based on the TextRank of the graph model, a graph model is constructed through word co-occurrence to calculate the importance of nodes. Semantic extraction based on the pre-trained model generates word vectors, and keyword extraction is performed through clustering. In this embodiment, by classifying the laws and regulations according to dimensions such as business field and effectiveness level, structured storage is facilitated.

[0071] In this step, we use web crawlers to obtain the latest regulatory texts and apply natural language processing technology to extract and classify keywords, ensuring the timeliness and accuracy of basic regulatory retrieval information, enabling audit work to be carried out in accordance with the latest regulatory requirements, and enhancing audit compliance.

[0072] S30: Based on the regulatory search information and the standard data resource information, the user operation record information is extracted through SQL to obtain feature data information;

[0073] In this step, standard table data resources and the basic retrieval library are used to build SQL analysis for self-service analysis to obtain focused or feature data.

[0074] When building SQL analysis for self-service analysis, we will carry out the construction of intelligent audit application scenarios such as procurement bidding, contract management, and engineering material management. We will write SQL statements based on SQL analysis to analyze and mine data and ultimately obtain focused or feature data.

[0075] Combine Figure 1 and Figure 4 As shown, the above step S30 includes the following subdivision steps:

[0076] S31: Acquire an application scenario based on the user operation record, and write a regularized query statement using SQL based on the application scenario;

[0077] The audit scenario type is determined based on the context of the operation record. Application scenarios can refer to different audit task types, such as electricity bill audits, equipment inspections, or security compliance audits. Each scenario may require different data characteristics. For example, an electricity bill audit may focus on the frequency of data export operations, while a security audit may focus on permission changes or abnormal logins.

[0078] S32: Compile a regularized query statement based on SQL, and perform feature extraction on the user operation record information according to the application scenario to obtain feature data information.

[0079] Feature extraction is performed based on the SQL statements written. It's important to note that user operation records can be stored in a database, in a structured data table containing information such as user ID, operation type, timestamp, and project ID. Feature extraction can include counting a user's operation count, operation frequency within a specific time period, and identifying high-risk operations.

[0080] S40: Perform correlation analysis on the characteristic data information to generate audit evaluation information.

[0081] Specifically, the above step S40 includes constructing an audit entity relationship network based on a graph database; and performing association relationship analysis on the feature information based on the audit entity relationship network.

[0082] Generating audit assessment information includes: outputting a visual assessment report; and outputting audit warning information based on warning rules.

[0083] This correlation analysis can be performed using advanced data analysis algorithms, such as statistical methods like the Pearson correlation coefficient and the Spearman correlation coefficient, as well as deep learning models based on graph neural networks, to analyze the correlations of feature data. By calculating the correlations between different features and constructing a feature correlation map, direct and indirect correlations between features can be identified. For example, the Pearson correlation coefficient can be used to measure the degree of linear correlation between two variables. Its value ranges from -1 to 1, with r = 1 indicating a perfect positive correlation, r = -1 indicating a perfect negative correlation, and r = 0 indicating no correlation. Graph neural network-based models are better able to handle complex nonlinear relationships and high-order correlations, improving the accuracy of correlation identification.

[0084] The above audit assessment information is generated based on the relationships obtained through analysis, combined with audit rules and models. This includes the assessment of audit risk and the analysis of the impact on financial statement items, providing decision support for auditors.

[0085] For example, when auditing and evaluating a company's financial data, various data from its balance sheet, income statement, cash flow statement, and other financial statements can be collected as feature data. After preprocessing and feature selection, the Pearson correlation coefficient is used to calculate correlations between different financial indicators, such as the correlation between total assets and net assets, and the correlation between operating income and total profit, to construct a financial indicator correlation map. Simultaneously, a graph neural network-based model is used to further explore the deep-level correlations between financial indicators. Based on these correlations and combined with audit rules, audit assessment information is generated, such as assessing the company's financial risk and determining whether there are any abnormal financial behaviors, providing valuable reference for auditors.

[0086] In addition to the above, this step presents the audit assessment information in an intuitive visual form to generate an assessment report. The report can include charts, graphs, data tables and other forms to help auditors quickly understand the assessment results. At the same time, based on the preset early warning rules, the audit assessment information is monitored, and when anomalies or potential risks are found, audit early warning information is output in a timely manner. The early warning rules can include various conditions such as financial indicator thresholds and risk event patterns to ensure that auditors can take timely measures. In this embodiment, the above-mentioned preset early warning rules are based on the timely discovery and reporting of potential risks and abnormal situations in the audit process so that auditors can take prompt measures.

[0087] Generating visual assessment reports and audit warning information enables auditors to quickly and intuitively understand audit results and potential risks, improving the efficiency and scientific nature of audit decisions, helping to promptly discover and resolve problems in the construction of digital power grids, and ensuring the smooth progress and compliance of projects.

[0088] The above-mentioned embodiments of the present invention realize the efficient, intelligent and standardized data management of the digital power grid construction audit project through the above-mentioned contents, provide strong support for the audit work, help improve the audit quality and efficiency, and promote the healthy development of the digital power grid.

[0089] like Figure 5 As shown, the second preferred embodiment of the present invention discloses an audit project data management system 100 for the construction of a digital power grid, which is applied to a data audit device. The device includes a power grid cloud server and a project audit sub-terminal. The system 100 includes a data acquisition module 110, a resource construction module 120, a data analysis module 130 and an information generation module 140.

[0090] The above-mentioned data acquisition module 110 is used to obtain user operation instructions of the project audit sub-terminal through the power grid cloud server, and generate user operation record information based on the user operation instructions; convert the bitmap data into image data, and combine it with the operation identification data to generate the user operation record data.

[0091] The above user operation instructions can come from various input methods of the audit sub-terminal, including but not limited to: graphical interface operations: such as mouse clicking, dragging, and form filling; command line instructions: such as audit script execution and data export commands; API calls: audit tasks triggered by third-party systems through RESTful APIs.

[0092] The above generates user operation record information based on the user operation instructions. For unstructured instructions (such as natural language input), a pre-trained NLP model (such as BERT) is used to extract the operation intent and map it to standardized operation types (such as "data query" and "risk tag"). For structured instructions (such as JSON format), key fields are parsed using regular expressions or XPath.

[0093] Specifically, the above-mentioned data acquisition module 110 generates bitmap response data based on the acquired user operation instructions, and the bitmap response data includes bitmap data and operation identification data; in this embodiment, when the user triggers the operation, the cloud server captures the screen image of the audit sub-terminal in real time through the remote desktop protocol (such as RDP or VNC) to generate original bitmap data.

[0094] In more detail, the user operation instructions are converted into structured data information based on OCR recognition technology; specifically, text cleaning, semantic segmentation and structured mapping are included. The above text cleaning is used to remove irrelevant characters (such as special symbols, garbled characters) and merge broken texts.

[0095] The bitmap data of user operation instructions can be preprocessed to improve OCR recognition accuracy: for example, using Gaussian filtering to eliminate image noise (such as interfering pixels caused by screen flickering); using binarization to convert the image to black and white (such as using the Otsu algorithm with adaptive thresholding); and using contrast adjustment to enhance the distinction between text and background (such as histogram equalization). By parsing the bitmap data, the corresponding metadata is extracted, and metadata embedding and conversion technologies are used to generate the corresponding image data.

[0096] The resource construction module 120 is used to construct an audit resource knowledge base, which includes project archive information, standard data resource information and basic law retrieval information;

[0097] The resource construction module 120 generates project archive information when constructing the audit resource knowledge base. Simultaneously, this information is used to build standard table data resources for intelligent audit data mining and data modeling. When constructing the audit archive management component of audit management, archived project archives are automatically collected into the project archive module, published audit reports and documents are automatically collected into the audit report module, and data from closed audit project drawers is automatically collected into the data module, thereby forming audit data assets. Optical character recognition is used to convert unstructured and semi-structured audit evidence into structured data.

[0098] When constructing the legal and regulatory database for audit resource management, a basic retrieval database is established for audit analysis and audit judgment.

[0099] The above-mentioned resource construction module 120 acquires basic legal retrieval information in the following ways: obtaining legal texts on the target website through a web crawler; using different types of web crawler tools for different types of target websites, for example, for government static websites, the crawling tool used is Scrapy+XPath; for dynamically rendered websites, the crawling tool used is Selenium / Playwright; and for legal databases, the API interface is used, and parsed using Requests+JSON parsing.

[0100] The resource construction module 120 extracts and classifies keywords from the obtained legal text based on natural language processing technology, and updates the keywords to the basic legal search information.

[0101] Specifically, for the legal text obtained by the resource construction module 120, natural language processing technology is used to pre-process the text, followed by keyword extraction, and then text classification, and finally updated to the basic legal retrieval information. The above text pre-processing cleans the data of noise and standardizes the text format to provide high-quality input for subsequent NLP tasks. The above keyword extraction extracts core keywords from the legal text after the above pre-processing. Specifically, through the statistical TF-IDF, high-frequency borrowing and high-distinction vocabulary is extracted, and based on the TextRank of the graph model, a graph model is constructed through word co-occurrence to calculate the importance of nodes. Semantic extraction based on the pre-trained model generates word vectors, and subject words are extracted through clustering. In this embodiment, by classifying the laws and regulations according to dimensions such as business areas and effectiveness levels, structured storage is facilitated. With the help of web crawlers to obtain the latest legal texts, and using natural language processing technology to extract and classify keywords, the timeliness and accuracy of the basic legal retrieval information are guaranteed, so that the audit work can be carried out in accordance with the latest regulatory requirements, and the compliance of the audit is enhanced.

[0102] The data analysis module 130 is used to extract the user operation record information based on the regulatory retrieval information and the standard data resource information through SQL to obtain characteristic data information;

[0103] The data analysis module 130 utilizes standard table data resources and a basic retrieval library to construct a self-service SQL analysis to obtain focused or feature data.

[0104] When building SQL analysis for self-service analysis, we will carry out the construction of intelligent audit application scenarios such as procurement bidding, contract management, and engineering material management. We will write SQL statements based on SQL analysis to analyze and mine data and ultimately obtain focused or feature data.

[0105] Specifically, the above-mentioned data analysis module 130 obtains the application scenario based on the user operation record, and writes a regularized query statement through SQL based on the application scenario; writes a regularized query statement based on SQL, and extracts features of the user operation record information according to the application scenario to obtain feature data information.

[0106] The audit scenario type is determined based on the context of the operation record. Application scenarios can refer to different audit task types, such as electricity bill audits, equipment inspections, or security compliance audits. Each scenario may require different data characteristics. For example, an electricity bill audit may focus on the frequency of data export operations, while a security audit may focus on permission changes or abnormal logins.

[0107] Feature extraction is performed based on the SQL statements written. It's important to note that user operation records can be stored in a database, in a structured data table containing information such as user ID, operation type, timestamp, and project ID. Feature extraction can include counting a user's operation count, operation frequency within a specific time period, and identifying high-risk operations.

[0108] The information generation module 140 is used to perform correlation analysis on the characteristic data information to generate audit evaluation information.

[0109] Specifically, the information generation module 140 includes constructing an audit entity relationship network based on a graph database; and performing correlation analysis on the feature information based on the audit entity relationship network.

[0110] Generating audit assessment information includes: outputting a visual assessment report; and outputting audit warning information based on warning rules.

[0111] This correlation analysis can be performed using advanced data analysis algorithms, such as statistical methods like the Pearson correlation coefficient and the Spearman correlation coefficient, as well as deep learning models based on graph neural networks, to analyze the correlations of feature data. By calculating the correlations between different features and constructing a feature correlation map, direct and indirect correlations between features can be identified. For example, the Pearson correlation coefficient can be used to measure the degree of linear correlation between two variables. Its value ranges from -1 to 1, with r = 1 indicating a perfect positive correlation, r = -1 indicating a perfect negative correlation, and r = 0 indicating no correlation. Graph neural network-based models are better able to handle complex nonlinear relationships and high-order correlations, improving the accuracy of correlation identification.

[0112] The above audit assessment information is generated based on the relationships obtained through analysis, combined with audit rules and models. This includes the assessment of audit risk and the analysis of the impact on financial statement items, providing decision support for auditors.

[0113] For example, when auditing and evaluating a company's financial data, various data from its balance sheet, income statement, cash flow statement, and other financial statements can be collected as feature data. After preprocessing and feature selection, the Pearson correlation coefficient is used to calculate correlations between different financial indicators, such as the correlation between total assets and net assets, and the correlation between operating income and total profit, to construct a financial indicator correlation map. Simultaneously, a graph neural network-based model is used to further explore the deep-level correlations between financial indicators. Based on these correlations and combined with audit rules, audit assessment information is generated, such as assessing the company's financial risk and determining whether there are any abnormal financial behaviors, providing valuable reference for auditors.

[0114] In addition to the above, this step presents the audit assessment information in an intuitive visual form to generate an assessment report. The report can include charts, graphs, data tables and other forms to help auditors quickly understand the assessment results. At the same time, based on the preset early warning rules, the audit assessment information is monitored, and when anomalies or potential risks are found, audit early warning information is output in a timely manner. The early warning rules can include various conditions such as financial indicator thresholds and risk event patterns to ensure that auditors can take timely measures. In this embodiment, the above-mentioned preset early warning rules are based on the timely discovery and reporting of potential risks and abnormal situations in the audit process so that auditors can take prompt measures.

[0115] Generating visual assessment reports and audit warning information enables auditors to quickly and intuitively understand audit results and potential risks, improving the efficiency and scientific nature of audit decisions, helping to promptly discover and resolve problems in the construction of digital power grids, and ensuring the smooth progress and compliance of projects.

[0116] The above-mentioned embodiments of the present invention realize the efficient, intelligent and standardized data management of the digital power grid construction audit project through the above-mentioned contents, provide strong support for the audit work, help improve the audit quality and efficiency, and promote the healthy development of the digital power grid.

[0117] Figure 6 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0118] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0119] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0120] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the audit project data management method.

[0121] A computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the audit project data management method described above when executed.

[0122] In some embodiments, the audit project data management method can be implemented as a computer program that is tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the audit project data management method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the audit project data management method in any other appropriate manner (e.g., by means of firmware).

[0123] The audit project data management device provided by the embodiment of the present invention can execute the audit project data management method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0124] It should be noted that the computer storage medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer storage medium other than a computer-readable storage medium that can transmit, propagate, or convey a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer storage medium may be conveyed using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0125] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0126] The computer storage medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0127] The computer storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0128] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. An audit project data management method for digital power grid construction, applied to a data audit device, the device comprising a power grid cloud server and a project audit sub-terminal, characterized in that: The method comprises: Obtaining user operation instructions of the project audit sub-terminal through the power grid cloud server, and generating user operation record information based on the user operation instructions; Constructing an audit resource knowledge base, which includes project archive information, standard data resource information, and basic law and regulation retrieval information; Based on the regulatory retrieval information and standard data resource information, the user operation record information is extracted through SQL to obtain feature data information; Perform correlation analysis on the characteristic data information to generate audit evaluation information.

2. The audit project data management method for digital intelligent grid construction according to claim 1 is characterized in that: The obtaining of the user operation instruction of the project audit sub-terminal through the power grid cloud server and generating user operation record information based on the user operation instruction includes: generating bitmap response data based on the acquired user operation instruction, wherein the bitmap response data includes bitmap data and operation identification data; The bitmap data is converted into image data and combined with the operation identification data to generate the user operation record data.

3. The audit project data management method for digital intelligent grid construction according to claim 1 is characterized in that: The generating of bitmap response data based on the acquired user operation instruction includes: The user operation instructions are converted into structured data information based on OCR recognition technology.

4. The audit project data management method for digital intelligent grid construction according to claim 1 is characterized in that: Methods for obtaining the basic regulations search information include: Obtain regulatory texts on target websites through web crawlers; The obtained regulatory text is subjected to keyword extraction and classification based on natural language processing technology, and updated into the basic regulatory retrieval information.

5. The audit project data management method for digital intelligent grid construction according to claim 1 is characterized in that: The extracting of the user operation record information by SQL to obtain feature data information includes: Acquire application scenarios based on the user operation records, and write regularized query statements using SQL based on the application scenarios; A regularized query statement is written based on SQL, and feature extraction is performed on the user operation record information according to the application scenario to obtain feature data information.

6. The audit project data management method for digital intelligent grid construction according to claim 1 is characterized in that: The performing of correlation analysis on the characteristic data information to generate audit evaluation information includes: Construct an audit entity relationship network based on a graph database; Perform association analysis on the feature information based on the audit entity relationship network.

7. The audit project data management method for digital intelligent grid construction according to claim 1 is characterized in that: Generating audit assessment information includes: Output visual evaluation report; Output audit warning information based on warning rules.

8. An audit project data management system for digital power grid construction, applied to a data audit device, the device comprising a power grid cloud server and a project audit sub-terminal, characterized in that: The system comprises: a data acquisition module, configured to obtain user operation instructions of the project audit sub-terminal through the power grid cloud server, and generate user operation record information based on the user operation instructions; A resource construction module is used to construct an audit resource knowledge base, which includes project archive information, standard data resource information and basic law and regulation retrieval information; A data analysis module is used to extract the user operation record information through SQL based on the regulatory retrieval information and standard data resource information to obtain characteristic data information; The information generation module is used to perform correlation analysis on the characteristic data information and generate audit evaluation information.

9. An electronic device, characterized in that: The electronic device comprises: 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, and the computer program is executed by the at least one processor so that the at least one processor can execute the audit project data management method for digital power grid construction as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the audit project data management method according to any one of claims 1 to 7 when executed.

Images