Intelligentization-based business auditing operation method and apparatus, and electronic device

Abstract

The invention relates to the technical field of auditing systems, and particularly provides an intellectualization-based business auditing operation method and device and electronic equipment, and the method comprises the steps: obtaining fund flow information of a preset time period in an enterprise, carrying out the information extraction of the fund flow information, and obtaining the fund flow information; and the abnormal probability corresponding to each preset abnormal type is calculated based on the extraction result, and an audit report in a preset time period is generated based on the abnormal probability and output, so that the effect of solving the problem that the current small enterprises or newborn enterprises cannot know the current company operation condition in time at present is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of audit systems, and in particular to an intelligent business audit operation method, device and electronic equipment. Background Art

[0002] Auditing is an independent, objective and impartial review and evaluation of a company's financial statements, internal controls and business processes. Its main purpose is to help companies understand the true current situation within the company and reduce their operating risks. However, due to the complexity of current audit work, which requires a large number of full-time auditors, most companies that are listed companies and companies of a certain size with a complete organizational structure now have their own independent internal audits. For smaller or emerging companies, due to issues such as labor costs (including costs arising from personnel turnover and experience), their internal audits are basically non-existent or superficial. This results in some smaller or emerging companies being unable to understand the current operating conditions of the company in a timely and accurate manner, posing greater operating risks. Summary of the Invention

[0003] In view of this, this application aims to propose an intelligent business audit operation method to solve the current problem that small or start-up companies cannot understand the current company operation status in a timely manner.

[0004] In order to achieve the above-mentioned purpose, the technical solution of this application is implemented as follows:

[0005] An intelligent business audit method, comprising:

[0006] Obtain capital flow information within the enterprise for a preset time period;

[0007] Extracting information from the fund flow information, and calculating the abnormality probability corresponding to each preset abnormality type based on the extraction results;

[0008] An audit report for the preset time period is generated based on the abnormal probability and outputted.

[0009] In another possible implementation, extracting the funds flow information includes:

[0010] determining the information type of the capital flow information based on the field information of the capital flow information;

[0011] Determining a corresponding extraction method based on the information type;

[0012] The fund flow information is extracted based on the extraction method.

[0013] In another possible implementation, the calculating the abnormality probability corresponding to each preset abnormality type based on the extraction result includes:

[0014] Inputting the extraction results into a preset probability calculation model;

[0015] The abnormality probability corresponding to each preset abnormality type is determined based on the probability calculation model.

[0016] In another possible implementation, the preset probability calculation model is determined by the following method:

[0017] Construct a Bayesian network based on the preset anomaly types, preset audit rules, and historical data corresponding to each preset anomaly type;

[0018] Obtain multiple sample data and the exception type corresponding to each sample data;

[0019] Based on the multiple sample data and the corresponding anomaly types, the Bayesian network is trained to obtain a preset probability calculation model.

[0020] In another possible implementation, the method further includes:

[0021] Output the audit report to the after-sales platform;

[0022] Obtaining the manual determination result of the audit report by the after-sales platform;

[0023] Extracting sample data and corresponding anomaly types from the audit report based on the manual determination result;

[0024] The extracted sample data and the corresponding anomaly types are saved in the preset sample library.

[0025] In another possible implementation, the fund flow information includes a plurality of sub-flow information, each sub-flow information corresponds to an abnormality probability, and the generating and outputting of the audit report for the preset time period based on the abnormality probability includes:

[0026] Classifying the plurality of sub-flow information into abnormal levels based on the abnormal probability to obtain an abnormal level corresponding to each sub-flow information;

[0027] An audit report for the preset time period is generated based on the abnormality level and outputted.

[0028] Compared with the existing technology, this application has the following advantages:

[0029] The intelligent business audit operation method described in this application obtains the capital flow information of a preset time period within the enterprise, so as to facilitate the subsequent information extraction of the capital flow information, and calculates the abnormality probability corresponding to each preset abnormality type based on the extraction results. After calculating the abnormality probability, in order to facilitate the user to clearly understand the operating conditions within the current preset time period, an audit report for the preset time period can be generated and output based on the abnormality probability, thereby achieving the effect of solving the current problem that small or start-up enterprises cannot understand the current company's operating conditions in a timely manner.

[0030] In the second aspect, the present application proposes an intelligent business audit operation device, comprising an acquisition module, a calculation module and a generation module;

[0031] The acquisition module is used to obtain the capital flow information of the enterprise within a preset time period;

[0032] A calculation module, configured to extract information from the fund flow information and calculate an abnormality probability corresponding to each preset abnormality type based on the extraction result;

[0033] A generation module is used to generate and output an audit report for the preset time period based on the abnormal probability.

[0034] In a third aspect, the present application also provides an electronic device, which adopts the following technical solution;

[0035] An electronic device, comprising:

[0036] at least one processor;

[0037] Memory;

[0038] At least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, and the at least one application needs to be configured to execute an intelligent-based business audit operation method as described in any one of the first aspects.

[0039] In a fourth aspect, the present application provides a computer-readable medium, which adopts the following technical solution:

[0040] A computer-readable medium having a computer program thereon, which, when executed in a computer, causes the computer to execute an intelligent business audit operation method described in any one of the first aspects.

[0041] In summary, this application has the following beneficial effects:

[0042] Obtain the cash flow information within the enterprise for a preset time period to facilitate subsequent information extraction of the cash flow information, and calculate the abnormality probability corresponding to each preset abnormality type based on the extraction results. After calculating the abnormality probability, in order to facilitate users to clearly understand the operating conditions within the current preset time period, an audit report for the preset time period can be generated and output based on the abnormality probability, thereby achieving the effect of solving the current problem of small or start-up enterprises being unable to understand the current company's operating conditions in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0044] Figure 1 A flowchart of an intelligent business audit method according to an embodiment of the present application;

[0045] Figure 2 This is a structural diagram of an intelligent business audit operation device according to an embodiment of the present application;

[0046] Figure 3 This is a structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0047] It should be noted that, unless there is any conflict, the embodiments and features in the embodiments of this application can be combined with each other.

[0048] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0049] In the description of this application, it should be noted that if terms such as "upper," "lower," "inner," and "outer" appear to indicate orientation or positional relationships, these are based on the orientation or positional relationships shown in the accompanying drawings and are intended solely to facilitate the description of this application and simplify the description. They do not indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, if terms such as "first" and "second" appear, they are used solely for descriptive purposes and should not be construed as indicating or implying relative importance.

[0050] Furthermore, in the description of this application, unless otherwise explicitly defined, the terms "mounted," "connected," "connect," and "connector" should be interpreted broadly. For example, they can refer to fixed, removable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediary; and internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this application based on the specific circumstances.

[0051] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0052] Example 1

[0053] This embodiment relates to an intelligent business auditing method, which obtains the internal cash flow information of the enterprise and then generates an audit report based on the cash flow information, thereby avoiding the problem that the enterprise is unable to timely and truly understand the current operating conditions of the enterprise due to the cost of employees with higher audit experience, and has greater operating risks.

[0054] Among the relevant technologies, due to the extensive audit expertise and the large amount of materials that need to be reviewed, many audit tasks currently involve a lot of repetitive work, resulting in a large waste of manpower costs. To solve this problem, many preliminary audit tasks have adopted RPA (robotic process automation) technology. However, although RPA technology can solve these repetitive tasks with clear rules and structure, it still requires a lot of subjective judgment in the audit work, and the subjective judgment part requires the audit specialist to have certain business capabilities. This has led to many small or start-up companies not having internal audits.

[0055] In view of this, in order to help these small or newly established enterprises to clearly understand the real situation inside the enterprise, combined with Figure 1 As shown in , the intelligent business audit operation method of this embodiment mainly includes the following steps.

[0056] Step S101: Obtain capital flow information within a preset time period within the enterprise.

[0057] In step S101, the preset time period is a pre-set time period that can be adjusted by internal enterprise users as needed. For example, it can be the most recent month, a certain month to a certain month, or the last few days, etc., without limitation. Fund flow information includes information such as the direction of fund flow, specific operator, and fund amount. Specifically, the fund flow information can be directly extracted from the financial module by connecting to the enterprise ERP system (such as Kingdee) through an API interface, or by collecting the operation log of the financial system (such as SAP log) to extract the fund flow information. It can also be extracted through web crawler technology, or it can be obtained through manual input by enterprise employees.

[0058] Furthermore, in order to ensure that the acquired cash flow information is authentic and reliable, the embodiment of the present application first establishes a two-way SSL authentication for the acquiring device (electronic device) and the enterprise ERP system server before acquiring the cash flow information through the API interface to ensure that the acquired cash flow information is authentic and reliable; and when a small business does not use the enterprise ERP system, the way to obtain the cash flow information at this time is to extract it through the operation log of the mobile financial system and / or web crawler technology. In this case, in order to ensure data reliability, the embodiment of the present application also provides a blockchain technology optional installation function. Small businesses can save the financial system data or other office data on the blockchain according to their own situation to ensure that the operation log and other data cannot be changed, thereby increasing the reliability of the acquired cash flow information.

[0059] Step S102: extract the capital flow information and calculate the abnormality probability corresponding to each preset abnormality type based on the extraction result.

[0060] In step S102, since the acquired cash flow information may not only include the features required for calculating the anomaly probability described below, but may also include some unnecessary information, such as sequence numbers and file titles, information extraction is performed on the cash flow information before calculating the anomaly probability to improve the speed and accuracy of the subsequent calculation of the anomaly probability. When extracting information from the cash flow information, since there are many ways to obtain cash flow information, the acquired cash flow information may be structured data or natural language. Therefore, when extracting information from the cash flow information, it is necessary to first determine the information type of the cash flow information. Specifically, the information type can be determined based on the field information of the cash flow information. If the field information is in a fixed format, the information type of the cash flow information is determined to be structured data. If the field information does not have a fixed format, the information type of the cash flow information is determined to be natural language. For asset flow information in structured data, the extraction method is full extraction, and the extraction result is the entire content of the asset flow information. For asset flow information in natural language, a trained FinBERT model can be used for extraction.

[0061] The preset exception types are exception types set in advance, covering all exceptions that are likely to occur in audit work on the market. When new exception types exist, after-sales personnel can add the new exception types to the preset exception types.

[0062] When calculating the abnormality probability, the extraction result can be input into a preset probability calculation model, and then the abnormality probability corresponding to each preset abnormality type can be determined according to the probability calculation model, wherein the preset probability calculation model is a calculation model trained in advance: specifically, based on the preset abnormality type, the preset audit rules and the historical data corresponding to each preset abnormality type, a Bayesian network is constructed, and then multiple sample data and the abnormality type corresponding to each sample data are obtained, and the constructed Bayesian network is trained using the obtained multiple sample data and the corresponding abnormality type, so as to obtain the preset probability calculation model.

[0063] Among them, the preset audit rules include audit expertise, laws and regulations, standards for judging whether there are anomalies, and descriptions of the situations corresponding to each anomaly type. The preset audit rules can be supplemented based on the audit experience of the audit specialist. The historical data corresponding to each preset anomaly type refers to the previously confirmed asset flow information. Each anomaly type can only correspond to one historical data, which is only for the purpose of building a preliminary Bayesian network model. The Bayesian network model is then trained through multiple sample data and the anomaly type corresponding to each sample data to obtain a preset probability calculation model.

[0064] Step S103: Generate and output an audit report for a preset time period based on the abnormality probability.

[0065] In step S103, the abnormality level can be divided according to user needs. It is assumed that in the embodiment of the present application, the abnormality level is divided into three levels, the abnormality probability interval corresponding to the third level is (70%, 100%], the abnormality probability corresponding to the second level is (30%, 70%], and the abnormality probability corresponding to the first level is [0%, 30%]. The capital flow information includes multiple sub-flow information. It is assumed that the acquired capital flow information includes employee a's business trip reimbursement of 500 yuan with authorization, and employee b's payment of 50,000 yuan to factory a without authorization. That is, the capital flow information at this time contains two sub-flow information, namely, sub-flow information a: employee a's business trip reimbursement of 500 yuan with authorization and employee b's payment of 50,000 yuan to factory a without authorization. And sub-flow information b: Employee b transferred RMB 50,000 to factory a without authorization. When calculating the abnormal probability corresponding to the asset flow information, two abnormal probabilities will be calculated. Assume that the abnormal probability corresponding to sub-flow information a is 80%, and the abnormal probability corresponding to sub-flow information b is 60%, that is, the abnormal level corresponding to sub-flow information a is the third level, and the abnormal level corresponding to sub-flow information b is the second level. The higher the level corresponding to the sub-flow information, the greater the risk of this sub-flow information. Therefore, when generating an audit report, the sub-flow information with a higher abnormal level can be output in the front part of the audit report. Furthermore, in the audit report, the abnormal levels can also be distinguished by different colors and / or font sizes.

[0066] Furthermore, the after-sales platform can output the generated audit report to the after-sales platform for enterprises that have created preset probability calculation models, so that the after-sales platform can subsequently perform manual judgment on the obtained audit report and obtain manual judgment results. The manual judgment results include the normal rate of judgment of abnormal types in the audit report, so that it is convenient to subsequently select those sample data and corresponding abnormal types whose normal rate reaches the preset threshold from the manual judgment results, and save those selected sample data and corresponding abnormal types in the sample library, so that the preset probability calculation model can be re-trained through the sample data and corresponding abnormal types in the sample library. By continuously training the preset probability calculation model multiple times, the effect of optimizing the preset probability calculation model is achieved, so that the preset probability calculation model can be more in line with the actual situation of the enterprise, and the accuracy of the subsequently generated audit report is higher.

[0067] Furthermore, since the audit report includes a lot of confidential information, and at the same time in order to reduce the burden on small business electronic devices, the storage time of each generated audit report will be evaluated. When the storage time of the audit report reaches the preset time, the audit report and the original data corresponding to the audit report (for example: cash flow information, intermediate files generated when calculating the probability of abnormality of cash flow information, and data generated during manual judgment) will be automatically deleted, thereby achieving the effect of enhancing security; further, since there may be unscrupulous personnel recovering data to understand the situation of the enterprise, therefore, if it is detected that the storage time of an audit report is longer than the preset time, it means that the audit report may have been maliciously restored, and a prompt message will be output to the terminal device of the person with the highest authority in the enterprise, so as to promptly remind the person with the highest authority in the enterprise that there is an abnormality.

[0068] The intelligent business auditing method of this embodiment adopts the above design. Small enterprises or start-ups download the software that carries the above method and grant the corresponding permissions to the software, so that the software can automatically obtain the capital flow information of the preset time period within the enterprise, and further calculate the abnormality probability corresponding to the current preset abnormality type based on the capital flow information, and then generate an audit report for the preset time period, so that small enterprises or start-ups no longer need to bear the high cost of hiring audit specialists to clearly understand the current company's operations.

[0069] Example 2

[0070] This embodiment relates to an intelligent business audit operation device 20, combined with Figure 2 As shown in , the device 20 includes an acquisition module 201, a calculation module 202 and a generation module 203, wherein,

[0071] Acquisition module 201, used to obtain capital flow information within a preset time period within the enterprise;

[0072] Calculation module 202, configured to extract information from the capital flow information and calculate the abnormality probability corresponding to each preset abnormality type based on the extraction result;

[0073] The generation module 203 is used to generate and output an audit report for a preset time period based on the abnormality probability.

[0074] By adopting the above technical solution, the acquisition module 201 obtains the capital flow information of the preset time period within the enterprise, so that the subsequent calculation module 202 can extract the capital flow information and calculate the abnormality probability corresponding to each preset abnormality type based on the extraction result. After calculating the abnormality probability, in order to facilitate the user to clearly understand the operation status within the current preset time period, the generation module 203 can generate and output an audit report for the preset time period based on the abnormality probability, thereby achieving the effect of solving the current problem that small enterprises or start-ups cannot timely understand the current company operation status.

[0075] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the intelligent business audit operation device 20 described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0076] Example 3

[0077] This embodiment relates to an electronic device, Figure 3 As shown in FIG, the electronic device 30 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 30 may further include a transceiver 304. It should be noted that in actual applications, the number of transceivers 304 is not limited to one, and the structure of the terminal device 30 does not constitute a limitation on the embodiments of the present application.

[0078] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0079] The bus 302 may include a path for transmitting information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or one type of bus.

[0080] The memory 303 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0081] The memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 703 to implement the content shown in the above method embodiment.

[0082] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers and the like are also possible. Figure 3 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0083] An embodiment of the present application provides a computer-readable medium having a computer program stored thereon. When the computer-readable medium is run on a computer, the computer can execute the corresponding content of the aforementioned method embodiment. Compared with the related art, the cash flow information of a preset time period within the enterprise is obtained, so that the cash flow information can be subsequently extracted, and the abnormality probability corresponding to each preset abnormality type is calculated based on the extraction result. After the abnormality probability is calculated, in order to facilitate the user to clearly understand the operating conditions within the current preset time period, an audit report for the preset time period can be generated and output based on the abnormality probability, thereby achieving the effect of solving the current problem that small enterprises or start-ups cannot timely understand the current company's operating conditions.

[0084] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0085] The above are only some of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A business audit method based on intelligence, characterized in that: The method comprises: Obtain capital flow information within the enterprise for a preset time period; Extracting information from the fund flow information, and calculating the abnormality probability corresponding to each preset abnormality type based on the extraction results; An audit report for the preset time period is generated based on the abnormal probability and outputted.

2. The intelligent business audit method according to claim 1, characterized in that: The extracting of the capital flow information includes: determining the information type of the capital flow information based on the field information of the capital flow information; Determining a corresponding extraction method based on the information type; The fund flow information is extracted based on the extraction method.

3. The intelligent business auditing method according to claim 1 is characterized in that: The calculation of the abnormality probability corresponding to each preset abnormality type based on the extraction result includes: Inputting the extraction results into a preset probability calculation model; The abnormality probability corresponding to each preset abnormality type is determined based on the probability calculation model.

4. The intelligent business auditing method according to claim 3 is characterized in that: The preset probability calculation model is determined by the following method: Construct a Bayesian network based on the preset anomaly types, preset audit rules, and historical data corresponding to each preset anomaly type; Obtain multiple sample data and the exception type corresponding to each sample data; Based on the multiple sample data and the corresponding anomaly types, the Bayesian network is trained to obtain a preset probability calculation model.

5. The intelligent business auditing method according to claim 1 is characterized in that: The method further comprises: Output the audit report to the after-sales platform; Obtaining the manual determination result of the audit report by the after-sales platform; Extracting sample data and corresponding anomaly types from the audit report based on the manual determination result; The extracted sample data and the corresponding anomaly types are saved in the preset sample library.

6. The intelligent business auditing method according to claim 1 is characterized in that: The fund flow information includes a plurality of sub-flow information, each sub-flow information corresponds to an abnormality probability, and the generating and outputting of the audit report for the preset time period based on the abnormality probability includes: Classifying the plurality of sub-flow information into abnormal levels based on the abnormal probability to obtain an abnormal level corresponding to each sub-flow information; An audit report for the preset time period is generated based on the abnormality level and outputted.

7. An intelligent business audit operation device, applied to an intelligent business audit operation method according to any one of claims 1 to 6, characterized in that: include: The acquisition module is used to obtain the capital flow information of the enterprise within a preset time period; A calculation module, configured to extract information from the fund flow information and calculate an abnormality probability corresponding to each preset abnormality type based on the extraction result; A generation module is used to generate and output an audit report for the preset time period based on the abnormal probability.

8. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, and the at least one application needs to be configured to execute an intelligent-based business audit operation method according to any one of claims 1 to 6.

9. A computer-readable medium having a computer program thereon, characterized in that When the computer program is executed in a computer, the computer is caused to execute an intelligent business auditing method according to any one of claims 1 to 6.

Images