An audit management method, system and device based on a knowledge graph and a storage medium

Abstract

The application provides a knowledge graph-based audit management method, system and device and a storage medium, comprising obtaining an audit task and a pre-constructed audit knowledge graph; obtaining element information of the audit task according to the audit task; matching audit data corresponding to the element information from the audit knowledge graph; and processing the audit task according to the audit data. The technical scheme of the application realizes automatic processing and intelligent management of the audit task by using the knowledge graph technology and intelligent processing method, can accurately understand the business requirements of the audit task, efficiently realizes the audit data matching of the audit task, reduces manual intervention, improves the audit efficiency, enhances the flexibility and adaptability, realizes the intelligent and automatic audit management, and improves the audit quality.

Description

Technical Field

[0001] This application relates to the field of audit management technology, and more specifically, to an audit management method, system, device, and computer-readable storage medium based on knowledge graphs. Background Technology

[0002] Traditional audit management systems have numerous limitations that severely impact the efficiency and quality of audit work. These systems typically rely on manual setup of audit processes and manual collection and analysis of data, resulting in long audit cycles and high costs. More importantly, they struggle to adapt to constantly changing regulatory environments and business needs, lacking the necessary flexibility and adaptability.

[0003] Currently available audit management systems are often limited to specific areas, with fixed functions and audit content, failing to meet the requirements of flexible and rapid auditing. This rigid design makes the system ill-suited to handle diverse audit tasks and evolving business environments. Furthermore, due to the varying structures and types of audit data from multiple sources, collecting relevant audit data for different audit business types becomes exceptionally difficult. This not only increases the workload of auditors but may also lead to incomplete or inaccurate data analysis.

[0004] Existing audit management systems also have significant shortcomings in the allocation of auditors. Most systems use random allocation, failing to consider key factors such as the professional skills, experience, work efficiency, and workload of different auditors. This crude allocation method not only fails to fully utilize the professional advantages of the audit team but may also lead to uneven task distribution, thereby affecting the overall audit efficiency and quality. Summary of the Invention

[0005] In view of the above problems, the present invention provides a knowledge graph-based bank audit management method, system, device, and storage medium to overcome or at least partially solve the above problems. The technical solution is as follows:

[0006] An audit management method based on knowledge graphs includes:

[0007] Obtain audit tasks and a pre-built audit knowledge graph;

[0008] Based on the audit task, obtain the element information of the audit task;

[0009] Match the audit data corresponding to the element information from the audit knowledge graph;

[0010] The audit task is processed based on the audit data.

[0011] Furthermore, this application also proposes that the step of extracting the element information of the audit task according to the audit task includes: determining the business type corresponding to the audit task according to the audit task; generating a template based on the business type requirements corresponding to the business type, processing the audit task, and obtaining the element information corresponding to the audit task.

[0012] Furthermore, this application also proposes that the business type requirement generation template is pre-set.

[0013] Furthermore, this application also proposes a method for pre-constructing the audit knowledge graph, comprising: acquiring financial audit data and business type requirement information from various data sources; determining the first relationship data between the data corresponding to the financial audit data; determining the second relationship data between the requirements corresponding to the business type requirement information; determining the third relationship data between the data corresponding to the financial audit data and the business type requirement information; and generating the audit knowledge graph based on the first relationship data, the second relationship data, and the third relationship data.

[0014] Furthermore, this application also proposes that the process of the audit task based on the audit data includes: assigning auditors according to the audit data and the business type requirements.

[0015] Furthermore, this application also proposes that the audit data includes auditor competency model data and current workload data; the business type requirements include audit task difficulty level data and priority level data.

[0016] Furthermore, this application also proposes a knowledge graph-based audit management system, comprising: an acquisition module for acquiring audit tasks and a pre-constructed audit knowledge graph; a first processing module for obtaining element information of the audit task based on the audit task; a second processing module for matching audit data corresponding to the element information based on the audit knowledge graph; and a third processing module for processing the audit task based on the audit data.

[0017] Furthermore, this application also proposes that the third processing module includes: an audit risk processing unit, used to identify potential risk points of the audit task based on the audit data; and an auditor allocation unit, used to allocate auditors based on the audit data and the business type requirements.

[0018] Furthermore, this application also proposes a knowledge graph-based audit management device, including a processor and a memory; the memory stores computer programs thereon; the processor is used to execute one or more programs stored in the memory to implement the steps of the above-mentioned knowledge graph-based audit management method.

[0019] Furthermore, this application also proposes a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps of the knowledge graph-based audit management method described above.

[0020] Beneficial effects

[0021] This invention provides a knowledge graph-based audit management method, system, device, and storage medium, including acquiring an audit task and a pre-constructed audit knowledge graph; obtaining element information of the audit task based on the audit task; matching audit data corresponding to the element information from the audit knowledge graph; and processing the audit task based on the audit data. The technical solution of this invention, by utilizing knowledge graph technology and intelligent processing methods, achieves automated processing and intelligent management of audit tasks. It can accurately understand the business requirements of the audit task, efficiently match audit data for the audit task, reduce manual intervention, improve audit efficiency, enhance audit quality, increase flexibility and adaptability, and achieve intelligent and automated audit management. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating an embodiment of a knowledge graph-based audit management method according to the present invention.

[0024] Figure 2 This is a schematic diagram of the structure of a knowledge graph-based audit management system according to an embodiment of the present invention. Detailed Implementation

[0025] The following description, in conjunction with the accompanying drawings, illustrates an audit management method based on a knowledge graph in an embodiment of this application. The terminology used in the implementation section of this application is for explaining specific embodiments of this application only and is not intended to limit this application.

[0026] The terms "first," "second," etc., used in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of units is not necessarily limited to those units, but may include other units not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0027] See Figure 1 This paper provides a schematic diagram of an audit management method based on knowledge graphs. This method can be applied to existing network environments such as servers and cloud servers. This embodiment uses the application of this method to a server as an example for illustration. The audit management method based on knowledge graphs in this embodiment includes the following steps:

[0028] S101. Obtain audit tasks and a pre-built audit knowledge graph;

[0029] In this step, the audit task can be an audit task input by an external system connected to the current server, for example, an audit task submitted by an external system through a user interface or application.

[0030] In practical applications, within banking systems, this audit task is usually defined and generally includes the audit purpose, audit scope, audit standards and criteria, and audit engagement type. It can be presented in the form of a form or other existing methods, without any restrictions. This audit task is generally expressed in unstructured natural language.

[0031] In other embodiments, this application also proposes a method for pre-constructing an audit knowledge graph: obtaining financial audit data and business type requirement information from various data sources; determining the first relationship data between the data corresponding to the financial audit data; determining the second relationship data between the requirements corresponding to the business type requirement information; determining the third relationship data between the data corresponding to the financial audit data and the business type requirement information; and generating an audit knowledge graph based on the first relationship data, the second relationship data, and the third relationship data.

[0032] In practical applications, obtaining financial audit data and business type requirement information from various data sources is fundamental. By determining the first relationship between financial audit data and other data, the correlation between financial data can be clarified. By determining the second relationship between business type requirement information and other requirements, the correlation between business requirements can be clarified. By determining the third relationship between financial audit data and business type requirement information and other requirements, the connection between financial data and business requirements can be achieved. An audit knowledge graph constructed based on these relationship data can effectively integrate financial audit data and business type requirement information, thus solving the problem of how to construct an audit knowledge graph that can effectively integrate financial audit data and business type requirement information.

[0033] The acquisition of financial audit data and business type requirement information from various data sources can be achieved in several ways. For example, data can be automatically retrieved from different data sources via API interfaces, such as ERP systems, financial systems, and databases, or data can be manually imported into the system. Determining the first relationship between financial audit data and other data can be achieved through data analysis and mining techniques, such as using association rule mining algorithms to identify the relationships between financial data. Determining the second relationship between business type requirement information and other requirements can be achieved through business requirement analysis and modeling techniques, such as using requirement matrix analysis to identify the relationships between different business requirements. Determining the third relationship between financial audit data and business type requirement information and other requirements can be achieved through multidimensional data association analysis techniques, such as using multidimensional association analysis algorithms to identify the relationships between financial data and business requirements. This application, by generating an audit knowledge graph, can effectively integrate financial audit data and business type requirement information, solving the problem of data integration difficulties in traditional audit management systems and improving audit efficiency and accuracy. Compared with existing technologies, the advantage of this application lies in its ability to automatically process and integrate multi-source data, providing a flexible and efficient audit solution.

[0034] S102. Based on the audit task, obtain the element information of the audit task;

[0035] In this step, the business type corresponding to the audit task is determined. A template is generated based on the business type requirements corresponding to that task, and the audit task is processed to obtain the element information corresponding to the audit task. This element information includes various data and requirements related to the audit task.

[0036] In other embodiments, step S102 includes:

[0037] S112. Determine the business type corresponding to the audit task based on the audit task;

[0038] S122. Generate a template based on the business type requirements corresponding to the business type, process the audit task, and obtain the element information corresponding to the audit task.

[0039] In this step, the technical solution of this application is implemented in the following way: First, an audit task is obtained, and the business type corresponding to the audit task is determined. Then, a template is generated based on the business type requirements corresponding to the business type. Specifically, a corresponding template can be generated through a pre-set template library, or a template can be dynamically generated according to real-time requirements. Next, the generated template is used to process the audit task, thereby obtaining the element information corresponding to the audit task. As a preferred implementation, the generation of the template can take into account the characteristics and requirements of the business type to ensure the relevance and effectiveness of the template.

[0040] The technical solution of this application effectively solves the problem of extracting element information from audit tasks by identifying business types and generating corresponding templates. Compared with existing technologies, the advantages of this application are that it improves the efficiency and accuracy of audit task processing, reduces the need for manual intervention, adapts to the needs of different business types, and has strong flexibility and adaptability. Therefore, this application has significant application value in audit management systems.

[0041] In other implementations, the business type requirement generation template is pre-set.

[0042] In practical applications, corresponding templates have been pre-set for different business type requirements. These pre-set templates are invoked during actual audit task processing, thereby improving the efficiency and accuracy of audit task processing. By generating templates based on pre-set business type requirements, different types of audit tasks can be quickly matched and processed, reducing the time and potential errors associated with manual template setting. These pre-set templates can be directly invoked when processing audit tasks, ensuring consistency and standardization in audit task processing, thus solving the technical problem of how to generate templates corresponding to business type requirements.

[0043] Specifically, the pre-set business type requirement generation template can include, but is not limited to, financial audit templates, compliance audit templates, performance audit templates, etc. Each template contains the audit elements, audit standards, audit steps, etc., required for that business type. Generally, this can be achieved in the following ways:

[0044] 1. By analyzing historical audit data and business requirements, extract common requirements for different business types and pre-set corresponding templates;

[0045] 2. Utilize expert experience and industry standards to develop templates that meet the needs of specific business types;

[0046] 3. Automatically generate and optimize business type requirement templates through machine learning algorithms.

[0047] In another implementation, the pre-set business type requirement generation template can be dynamically adjusted and optimized according to actual needs. For example, if new requirements or issues are discovered during the audit process, the template can be updated in a timely manner to ensure its timeliness and accuracy.

[0048] S103. Match the audit data corresponding to the element information from the audit knowledge graph;

[0049] In this step, audit data corresponding to element information is matched from the audit knowledge graph. Audit data includes information such as auditor competency model data and current workload data. Through matching, data relevant to the audit task can be quickly found for further processing.

[0050] S104. Process the audit task based on the audit data.

[0051] In this step, audit tasks are processed based on audit data. Specifically, auditors can be assigned according to the audit data and the needs of the business type. For example, the allocation of auditors considers not only the difficulty and priority of the audit tasks, but also factors such as the auditors' professional skills, experience, work efficiency, and current workload. This allows for a more scientific and rational allocation of auditors, improving audit efficiency.

[0052] In another embodiment, step S104 includes:

[0053] Auditors are assigned based on the audit data and the business type requirements.

[0054] In this step, auditors are assigned based on audit data and business type requirements. By matching audit data with business type requirements, auditors are rationally allocated, enabling the audit task to be completed efficiently. This technical solution utilizes information from audit data and business type requirements to ensure a more scientific and rational allocation of auditors, thereby improving audit efficiency and solving the inefficiency problem caused by random allocation of auditors in traditional audit management systems.

[0055] In practical applications, this can be done in several ways: One approach is to allocate auditors based on a comprehensive assessment of their competency model data, current workload data, and the difficulty and priority levels of audit tasks. Another approach is to process audit tasks using pre-set business type requirement templates to obtain corresponding element information, thereby allocating personnel. Alternatively, an audit knowledge graph can be constructed to obtain financial audit data and business type requirement information from various data sources, generating an audit knowledge graph that serves as the basis for personnel allocation.

[0056] In another implementation, the audit data includes auditor competency model data and current workload data; the business type requirement includes the audit task difficulty level data and priority level data.

[0057] In practical applications, auditor competency model data can be obtained by analyzing and modeling data such as auditors' historical work records, professional skills, and training experience. Current workload data can be updated in real time using information such as the number and complexity of tasks currently being processed by auditors. Audit task difficulty level data can be categorized based on factors such as task complexity and the business areas involved, while priority level data can be set based on factors such as task urgency and business needs. For example, when assigning audit tasks, the system first filters auditors who meet the task requirements from the auditor competency model data based on the task's difficulty and priority level. Then, based on the current workload data, it selects auditors with lower workloads for task assignment. This ensures that the assigned auditors not only have the ability to complete the tasks but also can work under a reasonable workload, avoiding auditor overwork or resource waste.

[0058] Compared to traditional random allocation methods, this application introduces auditor competency model data and current workload data, combined with audit task difficulty and priority level data, to achieve a more scientific and reasonable auditor allocation method. This significantly improves audit efficiency and quality, ensuring that audit tasks are completed in a timely and efficient manner.

[0059] In one embodiment, such as Figure 2 As shown, a knowledge graph-based audit management system is provided, including:

[0060] Module 501 is used to acquire audit tasks and pre-built audit knowledge graphs;

[0061] The first processing module 502 is used to obtain the element information of the audit task based on the audit task.

[0062] The second processing module 503 is used to match audit data corresponding to element information based on the audit knowledge graph.

[0063] The third processing module 504 is used to process audit tasks based on audit data.

[0064] In practical applications, the acquisition module 501 acquires the audit task and a pre-built audit knowledge graph through external or internal data transmission. The first processing module 502 extracts key element information from the text-described audit task using natural language processing technology, and employs data cleaning and standardization techniques to ensure the accuracy and consistency of the element information. The second processing module 503 utilizes graph database technology to perform fast and efficient data matching based on the pre-built audit knowledge graph. The third processing module 504 combines machine learning algorithms to automatically generate audit reports or execute specific operational steps for the audit task based on the matched audit data.

[0065] The functions of each module of the knowledge graph-based audit management system provided in the above embodiments of this application can be implemented through the above methods and steps. Therefore, the specific working process and beneficial effects of each unit in the knowledge graph-based audit management system provided in the embodiments of this application will not be repeated here.

[0066] In other embodiments, the third processing module 503 includes:

[0067] The audit risk processing unit 513 is used to identify potential risk points of the audit task based on the audit data.

[0068] Auditor allocation unit 523 is used to allocate auditors according to audit data and the business type requirements.

[0069] In practical applications, the audit risk processing unit 513 can be implemented by training historical audit data using machine learning algorithms to establish a risk identification model, and then inputting current audit data into the model for risk assessment. The auditor allocation unit 523 can automatically match the most suitable auditors based on preset rules or algorithms, considering factors such as auditors' professional skills, experience, and current workload. For example, an auditor competency model can be constructed, and the allocation of auditors can be dynamically adjusted by combining current workload data and business type requirements. This application, by introducing the audit risk processing unit 513 and the auditor allocation unit 523, achieves the identification of potential risk points in audit tasks and the reasonable allocation of auditors. Compared with existing technologies, this application can more accurately identify risk points in audit tasks, avoid the subjectivity and uncertainty of manual judgment, and improve the efficiency and quality of audit work while reducing audit costs through the reasonable allocation of auditors.

[0070] The present invention also provides a server, including a processor and a memory;

[0071] The memory stores computer programs.

[0072] The processor is used to execute one or more programs stored in the memory to implement the steps of the knowledge graph-based audit management method in the above embodiments.

[0073] The present invention also provides a computer-readable storage medium storing one or more programs, which can be executed by one or more processors to implement the steps of the knowledge graph-based audit management method in the above embodiments.

[0074] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0075] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0076] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0077] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A knowledge graph-based audit management method, characterized in that, The method comprises the following steps: obtaining an audit task and a pre-constructed audit knowledge graph; obtaining element information of the audit task according to the audit task; matching audit data corresponding to the element information from the audit knowledge graph; processing the audit task according to the audit data; the step of extracting the element information of the audit task according to the audit task comprises the following steps: determining a business type corresponding to the audit task according to the audit task; processing the audit task by generating a business type demand template based on the business type demand template, to obtain element information corresponding to the audit task, wherein the business type demand template at least includes a financial audit template, a compliance audit template and a performance audit template, the financial audit template, the compliance audit template and the performance audit template all include audit elements, audit standards and audit steps required by the business type, and the element information includes multiple types of data and multiple types of requirements, each type of data and each type of requirement is related to the audit task; the method for pre-construction of the audit knowledge graph comprises the following steps: obtaining financial audit data and business type demand information in each data source; determining data corresponding to the financial audit data and first relationship data of the data; determining the second relationship data of the demand corresponding to the demand information of the business type; determining the third relationship data of the data and the demand corresponding to the financial audit data and the business type demand information; generating the audit knowledge graph based on the first relationship data, the second relationship data and the third relationship data. 2.The knowledge graph-based audit management method of claim 1, wherein, The business type demand generation template is pre-set.

3. The knowledge graph-based audit management method according to claim 1, wherein the step of processing the audit task according to the audit data comprises: allocating an audit personnel according to the audit data and the business type demand.

4. The knowledge graph-based audit management method according to claim 3, wherein the audit data includes audit personnel capability model data and current workload data; the business type demand includes audit task difficulty level data and priority level data.

5. A knowledge graph based audit management system, characterized in that, The method comprises the following steps: an acquisition module for acquiring an audit task and a pre-constructed audit knowledge graph; a first processing module for obtaining element information of the audit task according to the audit task; a second processing module for matching audit data corresponding to the element information based on the audit knowledge graph; a third processing module for processing the audit task according to the audit data; the first processing module comprises the following steps: determining a business type corresponding to the audit task according to the audit task; Based on the business type requirement generation template corresponding to the business type, the audit task is processed to obtain the element information corresponding to the audit task. The business type requirement generation template includes at least a financial audit template, a compliance audit template, and a performance audit template. The financial audit template, the compliance audit template, and the performance audit template all include the audit elements, audit standards, and audit steps required for the business type. The element information includes multiple types of data and multiple types of requirements, and each type of data and each type of requirement is related to the audit task. The system also includes: Obtain financial audit data and business type requirements from various data sources; Determine the first relationship data between the data corresponding to the financial audit data; Determine the second relationship data between the requirements and the requirements corresponding to the business type requirement information; Determine the third-party relationship data between the financial audit data and the business type requirement information; The audit knowledge graph is generated based on the first relation data, the second relation data, and the third relation data. 6.A knowledge graph-based audit management apparatus, characterized by comprising: Including processor and memory; The memory stores computer programs thereon; The processor is used to execute one or more programs stored in the memory to implement the steps of the knowledge graph-based audit management method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps of the knowledge graph-based audit management method as described in any one of claims 1 to 4.

Images