Business data auditing method and device based on large model, equipment and medium

Abstract

The invention provides a business data auditing method and device based on a large model, equipment and a medium, and the method comprises the steps: obtaining an auditing key point list for a target business in response to the initiation of a target business transaction, and traversing the auditing key point list in response to the start of business data auditing for the target business, obtaining the auditing key points of the auditing key point list, obtaining cue words corresponding to the auditing key points from a preset cue word bank based on the auditing key points, determining service data of the target service, supplementing the cue words based on the service data, calling a preset large model to process the cue words, and obtaining auditing suggestions of the auditing key points corresponding to the cue words. According to the method and the device, manual auditing is not needed, the dependence on manpower is reduced, the business auditing risk is reduced, meanwhile, the auditing efficiency is improved, and the missing in the auditing process is reduced.

Description

Technical Field

[0001] This application relates to the field of financial technology, and more specifically, to a business data auditing method, apparatus, equipment, and medium based on a large model. Background Technology

[0002] In the process of international settlement operations, it is necessary to review the business in accordance with business rules, international practices, management regulations, and business processing management methods.

[0003] Currently, the existing business review process relies heavily on manual processing. Reviewers use their professional knowledge and experience to examine the business and, when necessary, log into various essential systems to query data to determine whether the business is genuine, reasonable, and compliant.

[0004] However, the review process for international settlement transactions relies heavily on manual labor, which places high demands on the professional knowledge and experience of the reviewers. Furthermore, the diverse range of practices and regulations involved in international settlements makes it difficult for reviewers to fully grasp the information and update their experience in a timely manner, thus creating risks in the review process. In addition, the numerous aspects involved in international settlement reviews mean that reviewers typically rely on various tools for research and analysis, which is inefficient and prone to omissions. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a business data auditing method, apparatus, device and medium based on a large model. The method obtains audit points through a list of audit points for the target business, obtains corresponding prompts based on the audit points, supplements the prompts based on business data, and calls the large model to process the supplemented prompts to obtain audit opinions. This eliminates the need for manual auditing, reduces reliance on human intervention, lowers business auditing risks, improves auditing efficiency, and reduces omissions in the auditing process.

[0006] In a first aspect, embodiments of this application provide a business data auditing method based on a large model, the method comprising: In response to the initiation of a target business transaction, obtain a list of key review points for the target business; In response to the commencement of business data review for the target business, the review checklist is traversed to obtain the review checklist points. Based on the audit criteria, the system retrieves the corresponding prompt words from a preset prompt word library, determines the business data of the target business, and supplements the prompt words based on the business data. The preset large model is invoked to process the prompt words, and the review comments corresponding to the review points of the prompt words are obtained.

[0007] In one possible implementation, obtaining the audit checklist for the target business includes: Obtain basic information about the target business, and identify the business scenario of the target business based on the basic information about the target business; Based on the business scenario of the target business, obtain a list of key points for the review of the business scenario.

[0008] In one possible implementation, determining the business data of the target service and supplementing the prompt words based on the business data includes: The business data of the target business is determined, and the target placeholder of the prompt word is determined based on the business scenario; wherein, the target placeholder is a placeholder that needs to be supplemented. The target business data corresponding to the target placeholder is determined and the placeholder is replaced based on the target business data to supplement the prompt word.

[0009] In one possible implementation, the step of calling a preset large model to process the prompt words and obtain the review comments on the review points includes: The prompt word is input into the large model so that the large model triggers the review points corresponding to the prompt word upon being notified by the prompt word; Based on the aforementioned audit points, the audit opinions are obtained.

[0010] In one possible implementation, the business data auditing method based on large models further includes: Real-time monitoring of the business review process to identify any abnormal situations during the process; The abnormal situation is identified and handled.

[0011] In one possible implementation, handling the abnormal situation includes: Obtain the mapping table between the abnormal situations and the warning methods; The category of the abnormal situation is determined, and the warning method for the abnormal situation is obtained by matching the category of the abnormal situation in the mapping table; The abnormal situation is warned based on the aforementioned warning method.

[0012] In one possible implementation, the business data auditing method based on large models further includes: Determine whether all audit points have received audit comments; If all audit points receive audit comments, summarize and provide feedback on the audit comments for those audit points.

[0013] Secondly, embodiments of this application also provide a business data auditing device based on a large model, the device comprising: The first acquisition module is used to obtain a list of key review points for the target business in response to the initiation of the target business transaction; The second acquisition module is used to traverse the list of audit points and acquire the audit points of the list of audit points in response to the start of business data audit for the target business. The third acquisition module is used to acquire the prompt words corresponding to the audit points from a preset prompt word library based on the audit points, determine the business data of the target business, and supplement the prompt words based on the business data; The fourth acquisition module is used to call a preset large model to process the prompt words and obtain the review opinions of the review points corresponding to the prompt words.

[0014] In one possible implementation, the first acquisition module is specifically used for: Obtain basic information about the target business, and identify the business scenario of the target business based on the basic information about the target business; Based on the business scenario of the target business, obtain a list of key points for the review of the business scenario.

[0015] In one possible implementation, the third acquisition module is specifically used for: The business data of the target business is determined, and the target placeholder of the prompt word is determined based on the business scenario; wherein, the target placeholder is a placeholder that needs to be supplemented; The target business data corresponding to the target placeholder is determined and the placeholder is replaced based on the target business data to supplement the prompt word.

[0016] In one possible implementation, the fourth acquisition module is specifically used for: The prompt word is input into the large model so that the large model triggers the review points corresponding to the prompt word upon being notified by the prompt word; Based on the aforementioned audit points, the audit opinions are obtained.

[0017] In one possible implementation, the large-model-based business data auditing device includes: The monitoring module is used to monitor the business review process in real time and detect any abnormal situations during the business review process. The processing module is used to identify the abnormal situation and process it.

[0018] In one possible implementation, the processing module is specifically used for: Obtain the mapping table between the abnormal situations and the warning methods; The category of the abnormal situation is determined, and the warning method for the abnormal situation is obtained by matching the category of the abnormal situation in the mapping table; The abnormal situation is warned based on the aforementioned warning method.

[0019] In one possible implementation, the large-model-based business data auditing device includes: The judgment module is used to determine whether all review points have received review comments; The summary module is used to summarize and provide feedback on the review comments for all review points if review comments are received.

[0020] Thirdly, embodiments of this application provide an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the business data auditing method based on a large model as described in any of the first aspects.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the business data auditing method based on a large model as described in any of the first aspects.

[0022] This application provides a business data auditing method, apparatus, device, and medium based on a large model. In response to the initiation of a target business transaction, it obtains a list of audit points for the target business. In response to the commencement of business data auditing for the target business, it iterates through the audit point list to obtain the audit points. Based on the audit points, it retrieves corresponding prompt words from a preset prompt word library, determines the business data of the target business, supplements the prompt words based on the business data, and calls a preset large model to process the prompt words, obtaining audit opinions for the corresponding audit points. This application obtains audit points from the target business's audit point list, retrieves corresponding prompt words based on the audit points, supplements the prompt words based on the business data, and calls a large model to process the supplemented prompt words to obtain audit opinions. This eliminates the need for manual auditing, reduces reliance on human intervention, lowers business auditing risks, improves auditing efficiency, and reduces omissions during the auditing process.

[0023] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a business data auditing method based on a large model, provided according to an embodiment of this application; Figure 2 This is a schematic diagram of the business scenario identification process; Figure 3 This is a diagram illustrating the business review process; Figure 4 This is a schematic diagram of the structure of a business data review device based on a large model provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0027] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0028] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0029] Considering that international settlement operations require review of transactions in accordance with business rules, international practices, management regulations, and business processing management methods.

[0030] Currently, the existing business review process relies heavily on manual processing. Reviewers use their professional knowledge and experience to examine the business and, when necessary, log into various essential systems to query data to determine whether the business is genuine, reasonable, and compliant.

[0031] However, the review process for international settlement transactions relies heavily on manual labor, which places high demands on the professional knowledge and experience of the reviewers. Furthermore, the diverse range of practices and regulations involved in international settlements makes it difficult for reviewers to fully grasp the information and update their experience in a timely manner, thus creating risks in the review process. In addition, the numerous aspects involved in international settlement reviews mean that reviewers typically rely on various tools for research and analysis, which is inefficient and prone to omissions.

[0032] To address this issue, this application provides a business data auditing method, apparatus, device, and medium based on a large model. The method obtains audit points from a list of audit points for the target business, retrieves corresponding prompts based on these points, supplements the prompts with business data, and then uses a large model to process the supplemented prompts to obtain audit opinions. This eliminates the need for manual auditing, reducing reliance on human intervention, lowering business auditing risks, improving auditing efficiency, and minimizing omissions during the auditing process.

[0033] Figure 1 This is a flowchart of a business data auditing method based on a large model, provided according to an embodiment of this application. For example... Figure 1 As shown, the business data auditing method based on a large model in this application embodiment may specifically include: S101. In response to the initiation of the target business transaction, obtain a list of key audit points for the target business.

[0034] S102. In response to the start of business data review for the target business, the review point list is traversed to obtain the review points of the review point list.

[0035] S103. Based on the audit key points, retrieve the corresponding prompt words from the preset prompt word library, determine the business data of the target business, and supplement the prompt words based on the business data.

[0036] S104. Call the preset large model to process the prompt words and obtain the review comments of the review points corresponding to the prompt words.

[0037] In the above-mentioned business data review method based on a large model, the review points are obtained through the review point list of the target business, the corresponding prompts are obtained based on the review points, and the prompts are supplemented based on business data. The large model is then called to process the supplemented prompts to obtain the review opinions. No manual review is required, which reduces the dependence on human labor, lowers the risk of business review, improves the review efficiency, and reduces omissions in the review process. The exemplary steps described above in the embodiments of this application are illustrated below with specific examples: S101, in response to the initiation of the target business transaction, obtain a list of key audit points for the target business.

[0038] In this embodiment of the application, the target business is the business whose business data needs to be reviewed, and the review checklist is a list of various key points for reviewing the business data of the target business, i.e., a list of parameters for the business scenario review checklist of the target business. For example, a single personal remittance cannot exceed US$50,000. When the target business transaction is initiated, the review checklist of the target business is obtained for subsequent processing. For example, such as... Figure 2 As shown, after initiating a business transaction, a list of key review points is obtained.

[0039] Optionally, when obtaining the list of key audit points for the target business, basic information about the target business is obtained, and the business scenario of the target business is identified based on this basic information. A list of key audit points for the business scenario is then obtained based on the business scenario. The basic information about the target business includes at least the business type and industry-standard criteria. For example, such as... Figure 2 As shown, business scenarios are identified based on basic business information, and parameters for the business scenario review checklist are obtained.

[0040] S102, in response to the start of business data review for the target business, iterate through the review point list and obtain the review points of the review point list.

[0041] In this embodiment of the application, the audit points are those determined by the audit point list. For example, in the aforementioned audit point list, if a single personal remittance does not exceed US$50,000, the corresponding audit point could be that a single personal remittance does not exceed US$50,000. When the business data audit of the target business begins, the audit point list obtained in step S101 is traversed to obtain the audit points corresponding to the audit point list for subsequent processing. For example, as... Figure 3 As shown, after the business review begins, the review checklist is iterated to obtain the review check points.

[0042] S103: Based on the audit key points, retrieve the corresponding prompt words from the preset prompt word library, determine the business data of the target business, and supplement the prompt words based on the business data.

[0043] In this embodiment, the prompt word library is a pre-set large model prompt word library, which is also a large model prompt word template library. The prompt words are prompt words specific to the large model, i.e., prompt word templates. Based on the review points obtained in step S102, the prompt words corresponding to the review points are obtained from the prompt word library, and the prompt words are supplemented based on the business data of the target business to obtain the supplemented prompt words for subsequent processing. For example, such as... Figure 3 As shown, prompts are retrieved from the prompt word library according to the review criteria, and additional prompts are added to improve the prompts.

[0044] As one possible implementation, when determining the business data of the target business and supplementing the prompt words based on the business data, the business data of the target business is determined, and the target placeholder for the prompt words is determined based on the business scenario; the target business data corresponding to the target placeholder is determined, and the placeholder is replaced based on the target business data to supplement the prompt words. Here, the target placeholder is the placeholder that needs to be supplemented.

[0045] It's important to note that when retrieving prompts from the prompt word library based on the review criteria, what's essentially being retrieved is a prompt word template. At this stage, it's not yet bound to the target business's data because the prompts need to be supplemented—that is, the context needs to be organized. Specifically, placeholders for the prompts are extracted based on business elements. These placeholders need to be supplemented, i.e., replaced with specific business data. Replacing the specific business data associated with the placeholders completes the supplementation and improvement of the prompts. For example, like... Figure 3 As shown.

[0046] As one possible implementation, the prompt words are input into the large model, so that the large model triggers the review points corresponding to the prompt words when informed by the prompt words; and the review opinions of the review points are obtained based on the review points.

[0047] Specifically, after supplementing the prompt words with specific business data of the target business, the prompt words are input into the large model. The large model reviews each prompt word, that is, it triggers the review points corresponding to the prompt words, and obtains the review opinions based on the review points.

[0048] S104, call the preset large model to process the prompt words and obtain the review comments of the review points corresponding to the prompt words.

[0049] In this embodiment of the application, the review comments refer to the feedback on the key review points. This is achieved by calling the prompts obtained in the large model processing step S103, and conducting the review under the guidance of these prompts to obtain the review comments on the key review points. For example, such as... Figure 3 As shown, the large model is invoked to obtain feedback on the review comments.

[0050] The business data review method based on a large model provided in this application, in response to the initiation of a target business transaction, obtains a list of review points for the target business. In response to the commencement of business data review for the target business, it iterates through the list of review points to obtain the review points themselves. Based on these review points, it retrieves corresponding prompt words from a preset prompt word library, determines the business data of the target business, supplements the prompt words based on the business data, and calls a preset large model to process the prompt words, thereby obtaining the review opinion for the corresponding review points. This business data review method based on a large model obtains review points from the list of review points for the target business, retrieves corresponding prompt words based on the review points, supplements the prompt words based on the business data, and calls a large model to process the supplemented prompt words to obtain the review opinion. It eliminates the need for manual review, reduces reliance on human intervention, lowers business review risks, improves review efficiency, and reduces omissions during the review process. Furthermore, the business review process is monitored in real time to identify and handle any anomalies.

[0051] It should be noted that abnormal situations in the business review process are monitored and identified in real time, and then dealt with once an abnormal situation is identified.

[0052] Optionally, obtain a mapping table of abnormal situations and warning methods; determine the category of abnormal situation, and match the warning method of abnormal situation in the mapping table based on the category of abnormal situation; issue a warning for abnormal situation based on the warning method.

[0053] Furthermore, determine whether all audit points have received audit comments; if all audit points have received audit comments, summarize the audit comments for the audit points and provide feedback.

[0054] Specifically, it is necessary to determine whether all audit points have received audit comments; if so, all audit comments should be summarized. For example, such as... Figure 3 As shown, iterate through the review points to see if they have been completed. For example, if there are 10 review points, iterate 10 times. When it is determined that all review points have been processed in the large model, summarize the review comments.

[0055] Therefore, this application proposes a business scenario identification and review mechanism and a mechanism for generating international settlement business review information based on a large model and prompt words. Specifically, business scenarios are divided according to business types and industry standards. Review points are sorted out according to the scenarios. Based on the sorted business scenario review points, prompt words for the large model are sorted out. Based on the business-adapted scenarios, the corresponding business scenario prompt words are called in the large model. Based on the feedback from the large model, the business review results are summarized to form review opinions.

[0056] It should be noted that this application provides a business data auditing method based on a large model, that is, a business auditing method based on a large model.

[0057] Figure 4 This is a schematic diagram of the structure of a business data review device based on a large model, according to an embodiment of this application; as shown below. Figure 4 As shown, the business data auditing device 400 based on a large model in this application embodiment may specifically include: The first acquisition module 401 is used to obtain a list of key review points for the target business in response to the initiation of the target business transaction.

[0058] The second acquisition module 402 is used to traverse the audit point list and obtain the audit points in response to the start of business data audit for the target business.

[0059] The third acquisition module 403 is used to acquire the prompt words corresponding to the audit points from a preset prompt word library based on the audit points, determine the business data of the target business, and supplement the prompt words based on the business data.

[0060] The fourth acquisition module 404 is used to call the preset large model to process the prompt words and obtain the review opinions of the review points corresponding to the prompt words.

[0061] In one possible implementation, the first acquisition module is specifically used for: Obtain basic information about the target business, and identify the business scenario of the target business based on the basic information of the target business; Based on the business scenarios of the target business, obtain a list of key points for the review of the business scenarios.

[0062] In one possible implementation, the third acquisition module is specifically used for: Identify the business data for the target business, and determine the target placeholders for the prompt words based on the business scenario; where the target placeholders are the placeholders that need to be supplemented. The target business data corresponding to the target placeholder is determined, and the placeholder is replaced based on the target business data to supplement the prompt words.

[0063] In one possible implementation, the fourth acquisition module is specifically used for: Input the prompt words into the large model so that the large model can trigger the review points corresponding to the prompt words when informed by the prompt words; The audit comments were obtained based on the audit points.

[0064] In one possible implementation, the business data auditing device based on a large model includes: The monitoring module is used to monitor the business review process in real time and detect any abnormal situations during the business review process. The processing module is used to identify and handle abnormal situations.

[0065] In one possible implementation, the processing module is specifically used for: Obtain a mapping table of abnormal situations and warning methods; Determine the category of the abnormal situation, and match the abnormal situation warning method in the mapping table based on the category of the abnormal situation; Early warning is issued based on the early warning method to detect abnormal situations.

[0066] In one possible implementation, the business data auditing device based on a large model includes: The judgment module is used to determine whether all review points have received review comments; The summary module is used to summarize and provide feedback on the review comments for all review points if review comments are received.

[0067] The business data review device based on a large model provided in this application, in response to the initiation of a target business transaction, obtains a list of review points for the target business. In response to the commencement of business data review for the target business, it iterates through the list of review points to obtain the review points themselves. Based on these review points, it retrieves corresponding prompt words from a preset prompt word library, determines the business data of the target business, supplements the prompt words based on the business data, and calls a preset large model to process the prompt words, thereby obtaining the review opinion for the corresponding review points. This business data review device based on a large model obtains review points from the list of review points for the target business, retrieves corresponding prompt words based on the review points, supplements the prompt words based on the business data, and calls a large model to process the supplemented prompt words to obtain the review opinion. This eliminates the need for manual review, reduces reliance on human intervention, lowers business review risks, improves review efficiency, and reduces omissions during the review process.

[0068] like Figure 5 As shown in the embodiment of this application, an electronic device 500 includes a processor 501, a memory 502, and a bus. The memory 502 stores machine-readable instructions that can be executed by the processor 501. When the electronic device is running, the processor 501 communicates with the memory 502 via the bus, and the processor 501 executes the machine-readable instructions to perform the steps of the business data auditing method based on the large model described above.

[0069] Specifically, the memory 502 and processor 501 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 501 runs the computer program stored in the memory 502, it can execute the above-mentioned business data auditing method based on the large model.

[0070] Corresponding to the above-described business data auditing method based on a large model, this application embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-described business data auditing method based on a large model.

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0072] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0073] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0074] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the deployment methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0075] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A business data auditing method based on a large model, characterized in that, The method includes: In response to the initiation of a target business transaction, obtain a list of key review points for the target business; In response to the commencement of business data review for the target business, the review checklist is traversed to obtain the review checklist points. Based on the audit criteria, the system retrieves the corresponding prompt words from a preset prompt word library, determines the business data of the target business, and supplements the prompt words based on the business data. The pre-defined large model is invoked to process the supplemented prompt words, and the review comments corresponding to the review points of the prompt words are obtained.

2. The method according to claim 1, characterized in that, The process of obtaining the audit checklist for the target business includes: Obtain basic information about the target business, and identify the business scenario of the target business based on the basic information about the target business; Based on the business scenario of the target business, obtain a list of key points for the review of the business scenario.

3. The method according to claim 2, characterized in that, The process of determining the business data for the target service and supplementing the prompt words based on the business data includes: The business data of the target business is determined, and the target placeholder of the prompt word is determined based on the business scenario; wherein, the target placeholder is a placeholder that needs to be supplemented. The target business data corresponding to the target placeholder is determined and the placeholder is replaced based on the target business data to supplement the prompt word.

4. The method according to claim 3, characterized in that, The process of calling a preset large model to process the prompt words and obtain the review comments on the review points includes: The prompt word is input into the large model so that the large model triggers the review points corresponding to the prompt word upon being notified by the prompt word; Based on the aforementioned audit points, the audit opinions are obtained.

5. The method according to claim 4, characterized in that, The method further includes: Real-time monitoring of the business review process to identify any abnormal situations during the process; The abnormal situation is identified and handled.

6. The method according to claim 5, characterized in that, The handling of the abnormal situation includes: Obtain the mapping table between the abnormal situations and the warning methods; The category of the abnormal situation is determined, and the warning method for the abnormal situation is obtained by matching the category of the abnormal situation in the mapping table; The abnormal situation is warned based on the aforementioned warning method.

7. The method according to claim 1, characterized in that, The method further includes: Determine whether all audit points have received audit comments; If all audit points receive audit comments, summarize and provide feedback on the audit comments for those audit points.

8. A business data auditing device based on a large model, characterized in that, The device includes: The first acquisition module is used to obtain a list of key review points for the target business in response to the initiation of the target business transaction; The second acquisition module is used to traverse the list of audit points and acquire the audit points of the list of audit points in response to the start of business data audit for the target business. The third acquisition module is used to acquire the prompt words corresponding to the audit points from a preset prompt word library based on the audit points, determine the business data of the target business, and supplement the prompt words based on the business data; The fourth acquisition module is used to call a preset large model to process the prompt words and obtain the review opinions of the review points corresponding to the prompt words.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the business data auditing method based on a large model as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the business data auditing method based on a large model as described in any one of claims 1 to 7.

Images