Banking business demand book generation method and device, equipment, medium and product

Abstract

The invention provides a bank business demand book generation method and device, equipment, a medium and a product, and relates to the field of artificial intelligence. The method comprises the following steps: acquiring a business demand and a corresponding business demand book template; generating a demand book first draft based on the business demand book template and the business demand; extracting a demand compliance keyword according to the demand book first draft, and determining business compliance knowledge based on the demand compliance keyword and a keyword knowledge base; wherein the keyword knowledge base comprises a plurality of keywords and an association relationship between each keyword and the business requirement document; and according to the business compliance knowledge, detecting whether the first manuscript of the demand book is compliant, and under the condition that the first manuscript of the demand book is compliant, generating a business demand book. According to the scheme, the first manuscript of the demand book is generated by matching the corresponding business template according to the business demand, the industry compliance knowledge is determined based on the keyword knowledge base, the compliance of the first manuscript of the demand book is detected, and the generation efficiency and quality of the business demand book are greatly improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and in particular to a method, apparatus, device, medium, and product for generating banking business requirements documents. Background Technology

[0002] A business requirements document can transform abstract business objectives into specific, quantifiable requirements, helping different roles such as business stakeholders, technical teams, and designers to reach a unified understanding of the task objectives and avoid deviations in development direction due to differences in subjective perception. In the financial industry, the requirements document can serve as a document to prove that "system development complies with regulatory requirements," helping companies pass audits and compliance checks.

[0003] Currently, the traditional method of generating business requirements documents relies on the experience of financial experts to write them manually. This manual writing method consumes a lot of time, and the standardization of the content is affected by individual writing habits, resulting in insufficient industry standards for the generated business requirements documents.

[0004] Therefore, generating business requirements documents in this way is neither efficient nor of high quality. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, medium, and product for generating banking business requirements documents, in order to solve the technical problems of low efficiency and quality in generating banking business requirements documents.

[0006] Firstly, this application provides a method for generating a banking business requirements document, comprising: obtaining business requirements and a corresponding business requirements document template; generating a draft requirements document based on the business requirements document template and the business requirements; extracting compliance keywords from the draft requirements document, and determining business compliance knowledge based on the compliance keywords and a keyword knowledge base; wherein, the keyword knowledge base includes multiple keywords and the relationship between each keyword and the business requirements document; detecting whether the draft requirements document is compliant based on the business compliance knowledge, and generating the business requirements document if the draft requirements document is compliant.

[0007] In some examples, before obtaining business requirements and the corresponding business requirement document template, the process includes: obtaining business requirement documents to build a business requirement knowledge base; calling natural language processing tools to extract keywords from the business requirement documents to obtain corresponding keywords; wherein, the business requirement documents include business requirement document templates, business compliance knowledge, business architecture assets, and financial knowledge; establishing relationships based on the business requirement documents and corresponding keywords, and building a keyword knowledge base based on the relationships and keywords.

[0008] In some examples, obtaining business requirements and corresponding business requirement templates includes: obtaining business requirements uploaded by users; retrieving historical business requirements from the business requirement knowledge base based on the business requirements, calculating the similarity between the historical business requirements and the current business requirement, and determining whether the similarity is greater than a preset value; if the similarity is greater than the preset value, then using the business requirement template corresponding to the historical business requirements as the business requirement template for the current business requirement; if the similarity is not greater than the preset value, then retrieving the corresponding business requirement template from the business requirement knowledge base based on the current business requirement.

[0009] In some examples, a preliminary draft of the requirements document is generated based on the business requirements template and the business requirements. This includes: extracting keywords based on the business requirements to obtain financial knowledge keywords and business architecture asset keywords; determining the corresponding financial knowledge based on the financial knowledge keywords and keyword knowledge base, and filling the financial knowledge into the business requirements template according to the filling rules of the business requirements template to obtain the basic draft of the requirements document; determining the corresponding business architecture assets based on the business architecture asset keywords and keyword knowledge base; obtaining the corresponding step rule information from the business requirements knowledge base based on the business architecture assets; and generating the preliminary draft of the requirements document based on the basic draft of the requirements document, the business architecture assets, and the corresponding step rule information.

[0010] In some examples, the business requirements document is sent to the user and the user's feedback business requirements document is obtained; the user's feedback business requirements document is compared with the original business requirements document; if the user's feedback business requirements document is inconsistent with the original business requirements document, the modified content in the user's feedback business requirements document is recorded to optimize the regenerated business requirements document of the same type.

[0011] In some examples, if the initial draft of the requirements document is not compliant, the initial draft of the requirements document is modified based on business compliance knowledge to generate a business requirements document.

[0012] In some examples, a business requirements knowledge base is connected to the banking system; if the business requirements in the banking system are updated, the business requirements knowledge base is updated accordingly; a private domain knowledge graph is constructed based on the business requirements knowledge base; the private domain knowledge graph is used to record all the contents of the business requirements knowledge base.

[0013] Secondly, this application provides an apparatus for generating a banking business requirements document, comprising: an acquisition module for acquiring business requirements and a corresponding business requirements document template; and generating a draft requirements document based on the business requirements document template and the business requirements; a processing module for extracting compliance keywords from the draft requirements document, and determining business compliance knowledge based on the compliance keywords and a keyword knowledge base; wherein the keyword knowledge base includes multiple keywords and the association between each keyword and the business requirements document; and a generation module for detecting whether the draft requirements document is compliant based on the business compliance knowledge, and generating the business requirements document if the draft requirements document is compliant.

[0014] In some examples, the processing module is also used to: acquire business requirement documents to build a business requirement knowledge base; call natural language processing tools to extract keywords from the business requirement documents to obtain corresponding keywords; wherein, the business requirement documents include business requirement templates, business compliance knowledge, business architecture assets, and financial knowledge; establish associations based on the business requirement documents and corresponding keywords, and build a keyword knowledge base based on the associations and keywords.

[0015] In some examples, the acquisition module is also used to: acquire business requirements uploaded by users; acquire historical business requirements from the business requirements knowledge base based on the business requirements, calculate the similarity between the historical business requirements and the current business requirements, and determine whether the similarity is greater than a preset value; if the similarity is greater than the preset value, then use the business requirements template corresponding to the historical business requirements as the business requirements template for the current business requirements; if the similarity is not greater than the preset value, then acquire the corresponding business requirements template from the business requirements knowledge base based on the current business requirements.

[0016] In some examples, the acquisition module is also used to: extract keywords based on business requirements to obtain financial knowledge keywords and business architecture asset keywords; determine the corresponding financial knowledge based on the financial knowledge keywords and keyword knowledge base, and fill the financial knowledge into the business requirements document template according to the filling rules of the business requirements document template to obtain the basic draft of the requirements document; determine the corresponding business architecture assets based on the business architecture asset keywords and keyword knowledge base; obtain the corresponding step rule information from the business requirements knowledge base according to the business architecture assets; and generate the initial draft of the requirements document based on the basic draft of the requirements document, the business architecture assets, and the corresponding step rule information.

[0017] In some examples, the generation module is also used to: send business requirements documents to users and obtain feedback business requirements documents from users; compare the feedback business requirements documents with the original business requirements documents; if the feedback business requirements documents are inconsistent with the original business requirements documents, record the modifications made in the feedback business requirements documents to optimize the generation of the same type of business requirements documents.

[0018] In some examples, the generation module is also used to: if the initial draft of the requirements document is not compliant, modify the initial draft of the requirements document according to business compliance knowledge, and generate a business requirements document.

[0019] In some examples, the processing module is also used to: connect the business requirements knowledge base to the banking system; update the business requirements knowledge base according to the updated business requirements if the business requirements in the banking system are updated; and construct a private domain knowledge graph based on the business requirements knowledge base; wherein the private domain knowledge graph is used to record all the contents of the business requirements knowledge base.

[0020] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the aforementioned method.

[0021] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the aforementioned method.

[0022] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0023] This application provides a method, apparatus, equipment, medium, and product for generating banking business requirements documents. The method involves acquiring business requirements and corresponding business requirements document templates; generating a draft requirement document based on the templates and the requirements; extracting compliance keywords from the draft; determining business compliance knowledge based on these keywords and a keyword knowledge base; verifying the compliance of the draft requirement document based on this knowledge; and generating the final business requirements document if it is compliant. This solution significantly improves the efficiency and quality of business requirements document generation by matching business requirements to corresponding business templates, determining industry compliance knowledge based on a keyword knowledge base, and verifying the compliance of the draft. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0025] Figure 1 A flowchart illustrating a method for generating a banking business requirements document provided in this application. Figure 1 ;

[0026] Figure 2 A schematic diagram of the initial draft of the requirements document provided for this application;

[0027] Figure 3 A schematic diagram illustrating a method for generating a banking business requirements document provided in this application;

[0028] Figure 4 A schematic diagram of a knowledge base system provided for this application;

[0029] Figure 5 A flowchart illustrating a method for generating a banking business requirements document provided in this application. Figure 2 ;

[0030] Figure 6 A flowchart illustrating a method for generating a banking business requirements document provided in this application. Figure 3 ;

[0031] Figure 7 A schematic diagram of a device for generating a banking business requirements document provided in this application;

[0032] Figure 8 This is a schematic diagram of the structure of an electronic device provided in this application.

[0033] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0034] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0035] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize or refuse.

[0036] Furthermore, this application involves a technical solution for conducting big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, and electronic terminal operation data), and employing artificial intelligence technology for automated decision-making. Based on the automated decision-making results, it makes decisions that significantly impact individual rights and interests, providing users with corresponding access points to choose whether to agree to or reject the automated decision results. If the user chooses to reject, the process proceeds to an expert decision-making process. It should be noted that the method, apparatus, equipment, medium, and product for generating banking business requirements provided in this application can be used in the field of artificial intelligence, or in any field other than artificial intelligence. The application areas of the method, apparatus, equipment, medium, and product for generating banking business requirements in this application are not limited.

[0037] In the context of digital transformation, business requirements documents, as a crucial link connecting business objectives and technological implementation, are increasingly demonstrating their core value. Business requirements documents can transform abstract business goals into concrete, quantifiable requirements, helping different roles such as business stakeholders, technical teams, and designers to reach a unified understanding of the task objectives and avoiding deviations in development direction due to differences in subjective perception. In the financial industry, requirements documents can serve as documentation proving that "system development complies with regulatory requirements," helping companies pass audits and compliance checks.

[0038] However, the current traditional model for generating business requirements documents still relies heavily on manual writing and the accumulated experience of financial experts. This manual writing method is time-consuming, and due to the lack of standardized templates and automated verification mechanisms, the documents written by different experts vary in terms of terminology consistency, formatting, and logical rigor, resulting in a lack of industry standardization in the generated business requirements documents.

[0039] Therefore, generating business requirements documents in this way is neither efficient nor of high quality.

[0040] To address the current technical issues of low efficiency and quality in generating business requirement documents, this application provides a method, apparatus, equipment, medium, and product for generating banking business requirement documents. The method involves acquiring business requirements and corresponding business requirement document templates; generating a draft requirement document based on the templates and the requirements; extracting compliance keywords from the draft; determining business compliance knowledge based on these keywords and a keyword knowledge base; verifying the compliance of the draft requirement document based on this knowledge; and generating the final business requirement document if it is compliant. This solution significantly improves the efficiency and quality of business requirement document generation by matching business requirements to corresponding business templates, determining industry compliance knowledge based on a keyword knowledge base, and verifying the compliance of the draft.

[0041] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0042] Example 1

[0043] Figure 1 A flowchart illustrating a method for generating a banking business requirements document provided in this application. Figure 1 ,like Figure 1 As shown in the embodiment of this application, the method for generating a banking business requirements document includes:

[0044] S101, Obtain business requirements and corresponding business requirement document templates; and generate a draft requirement document based on the business requirement document templates and business requirements.

[0045] Among them, the business requirements document template is a pre-designed document structure template; specifically, the business requirements and the corresponding business requirements document template are obtained, and a draft of the requirements document is generated based on the business requirements document template and the business requirements. Figure 2 A schematic diagram of the initial draft of the requirements document provided for this application, such as Figure 2 As shown, fill in the content of the business requirements template according to business needs; for example, fill in the "Project Introduction" in the template according to business needs, and fill in the content as "In order to promote the digital transformation of xxx, improve the management efficiency of xxx, improve the automation, digitalization and intelligence level of each link of xxx, and provide xxx with more suitable, more agile, more accurate and intelligent system support, this project is proposed."

[0046] S102, Extract compliance keywords from the initial draft of the requirements document, and determine business compliance knowledge based on the compliance keywords and the keyword knowledge base; wherein, the keyword knowledge base includes multiple keywords and the relationship between each keyword and the business requirements document;

[0047] Among these, business compliance knowledge refers to the compliance knowledge of the business requirements document. Essentially, it requires that the document comply with laws, regulations, and internal company rules in all dimensions, including content, processes, and entities, to prevent legal risks and ensure the legal and compliant operation of the business. The generated draft requirements document also needs to be tested for compliance. This involves extracting compliance keywords from the draft and determining the business compliance knowledge based on these keywords and a keyword knowledge base. For example, if the business requirements document is about "mobile banking products," the keyword obtained is "login password." Based on the keyword "login password" and the keyword knowledge base, the determined business compliance knowledge is the compliance knowledge related to "login password" in the "Mobile Banking Product Design Specifications."

[0048] S103, based on business compliance knowledge, check whether the initial draft of the requirements document is compliant, and if the initial draft of the requirements document is compliant, generate the business requirements document.

[0049] In practical applications, the acquired business compliance knowledge is used to check whether the initial draft of the requirements document is compliant. If the initial draft is compliant, its content is transformed into a business requirements document based on the rules. Furthermore, after the content in the initial draft has been checked using business compliance knowledge, supplementary content and helpful tips are provided based on the results. Figure 3 A schematic diagram illustrating a method for generating a banking business requirements document provided in this application, as shown below. Figure 3 As shown, after the initial draft of the requirements document complies with the inspection, the content of the initial draft is converted into rules to generate a business requirements document; and supplementary suggestions are provided. Specifically, the content in the dotted box in the figure represents the suggested supplementary content. For example, based on the requirement in the "Mobile Banking Product Design Specification" that "after the login password is entered incorrectly, xxx should be performed", relevant rules are generated to supplement the initial draft of the requirements document; and a friendly reminder is generated: "Please confirm whether relevant rule descriptions need to be added to this business rule. If so, please refer to the following example: [] Figure 3 [The content within the dashed box].

[0050] In this embodiment, the present application provides a method for generating a banking business requirements document. This involves obtaining business requirements and a corresponding business requirements document template; generating a draft requirements document based on the template and the requirements; extracting compliance keywords from the draft; determining business compliance knowledge based on these keywords and a keyword knowledge base; verifying the compliance of the draft requirements document based on this knowledge; and generating the final business requirements document if it is compliant. This solution significantly improves the efficiency and quality of business requirements document generation by matching the business requirements to the corresponding business template, determining industry compliance knowledge based on a keyword knowledge base, and verifying the compliance of the draft.

[0051] In some examples, before obtaining the business requirements and the corresponding business requirements document template, the following steps are also included:

[0052] Acquire business requirements documents to build a business requirements knowledge base; use natural language processing tools to extract keywords from the business requirements documents to obtain corresponding keywords; the business requirements documents include business requirements templates, business compliance knowledge, business architecture assets, and financial knowledge;

[0053] Establish relationships based on business requirements documents and corresponding keywords, and build a keyword knowledge base based on these relationships and keywords.

[0054] The constructed business requirements knowledge base includes a core requirements knowledge base, a supplementary requirements knowledge base, a requirements compliance knowledge base, and a financial business knowledge base. Specifically, the core requirements knowledge base includes business requirements document templates and historical business requirements; the supplementary requirements knowledge base includes business requirements policies, quality control requirements, and business architecture assets; the requirements compliance knowledge base includes regulatory laws, compliance requirements, and industry standards; and the financial business knowledge base includes business knowledge and operation manuals for various business areas.

[0055] The process involves: acquiring business requirement documents to build a business requirement knowledge base; using natural language processing (NLP) tools to extract keywords from the business requirement documents; for example, extracting the keyword "loan" from a loan business requirement template; establishing a relationship between "loan" and the loan business requirement template; similarly, extracting keywords from the business requirement documents corresponding to the requirement auxiliary knowledge base, requirement compliance knowledge base, and financial business knowledge base, and establishing relationships between them; and building a keyword knowledge base based on the obtained relationships and keywords.

[0056] Figure 4 A schematic diagram of a knowledge base system provided for this application, such as Figure 4 As shown, the upper layer is a keyword knowledge base, and the lower layer consists of four types of knowledge bases. In practical applications, when generating business requirements documents, such as during compliance testing, specific business compliance knowledge is retrieved from the corresponding requirement compliance knowledge base based on the keywords and their relationships in the keyword knowledge base.

[0057] By constructing a keyword knowledge base and a business requirement knowledge base, and establishing relationships, disordered information is transformed into a structured knowledge network. This enables precise location of required documents when retrieving documents, avoiding the inefficient operation of traversing the entire text and greatly saving time.

[0058] In some examples, business requirements and corresponding business requirement document templates are obtained, including:

[0059] Obtain business requirements uploaded by users; retrieve historical business requirements from the business requirements knowledge base based on the business requirements, calculate the similarity between historical business requirements and the current business requirements, and determine whether the similarity is greater than a preset value.

[0060] If the similarity is greater than the preset value, the business requirement template corresponding to the historical business requirement will be used as the business requirement template for the current business requirement.

[0061] If the similarity is not greater than the preset value, the corresponding business requirement template will be retrieved from the business requirement knowledge base according to the business requirements.

[0062] Specifically, the preset similarity value is set according to requirements, for example, to 80%. For instance, if a user uploads a business requirement of "generating a business requirement document for credit card installment payment processing," based on the keyword "credit card processing," historical business requirements related to credit card processing are retrieved from the business requirement knowledge base using the keyword knowledge base. The similarity between the historical business requirement and the current business requirement is calculated to be 95%. Since the similarity is greater than the preset value of 80%, the template for the business requirement document corresponding to that historical business requirement can be directly used as the template for the current credit card processing business requirement document.

[0063] By comparing with historical business requirements, for business requirements with a similarity higher than the preset value, the requirement template of the historical business requirement can be directly used. The template can be based on the standard framework already included in the template, such as scenario, objectives, functional modules, technical requirements, acceptance criteria, etc., without the need to reorganize the document structure. At the same time, the historical template may already contain content to meet regulatory requirements, which can be reused to directly cover the basic compliance points, saving time for compliance testing of the initial draft of the requirement document and improving the efficiency of generating business requirement documents.

[0064] In some examples, Figure 5 A flowchart illustrating a method for generating a banking business requirements document provided in this application. Figure 2 ,like Figure 5 As shown, based on the business requirements template and business requirements, a draft requirements document is generated, including:

[0065] S501, extract keywords based on business needs to obtain financial knowledge keywords and business architecture asset keywords;

[0066] Building on the previous example, if a user uploads a business requirement document for "generating a business requirement document for credit card installment payment processing", keyword extraction can be performed to obtain the financial knowledge keyword "installment payment" and the business architecture asset keywords "credit card, installment payment".

[0067] S502. Based on financial knowledge keywords and keyword knowledge base, determine the corresponding financial knowledge, and fill in the financial knowledge into the business requirements template according to the filling rules of the business requirements template to obtain the basic draft of the requirements document.

[0068] Based on financial knowledge keywords and keyword knowledge base, the corresponding financial knowledge is obtained from the financial business knowledge base in the business requirements knowledge base. Then, according to the filling rules of the business requirements template, such as the business rules section and the business process section, the financial knowledge is filled into the business rules section and the business process section of the business requirements template to obtain the basic draft of the requirements document.

[0069] S503: Based on business architecture asset keywords and keyword knowledge base, determine the corresponding business architecture assets; obtain the corresponding step rule information from the business requirement knowledge base according to the business architecture assets; generate the initial draft of the requirement document based on the basic draft of the requirement document, the business architecture assets, and the corresponding step rule information.

[0070] Based on the business architecture asset keywords and keyword knowledge base, the corresponding business architecture assets are determined; the business areas, activities, and tasks involved in credit card installment payments are filled in, and relevant step rule information is retrieved from the core requirement knowledge base according to the architecture assets. The content of the basic requirement document is identified, and the step rule information is trimmed into paragraphs before the requirement content is filled in to generate the first draft of the requirement document.

[0071] In practical applications, Figure 6 A flowchart illustrating a method for generating a banking business requirements document provided in this application. Figure 3 ,like Figure 6 As shown, users upload business requirements to the system. After matching templates based on the received business requirements, the system determines the financial knowledge required to fill in the template and generates a basic draft of the requirements document. After positioning the asset structure of the basic draft of the requirements document, a first draft of the requirements document is generated. The first draft of the requirements document undergoes compliance testing. If it meets the compliance requirements, a business requirements document is generated and fed back to the user.

[0072] By acquiring relevant financial knowledge, the template is supplemented and filled in to obtain the basic draft of the requirements document, avoiding fragmented information. The asset structure of the basic draft of the requirements document is positioned, configuration defects in the basic draft are identified and corrected, so that the generated initial draft of the requirements document has long-term feasibility.

[0073] In some examples, the business requirements document is sent to the user and the user's feedback business requirements document is obtained; the user's feedback business requirements document is compared with the original business requirements document.

[0074] If the business requirement document provided by the user is inconsistent with the original business requirement document, the modifications made in the user's feedback document will be recorded and used to optimize the regenerated business requirement document of the same type.

[0075] Based on the above example, the generated business requirements document is fed back to the user for review and correction. The processed business requirements document is then fed back to the system, and the user-submitted document is compared with the original document. If the user-submitted document differs from the original, the modifications made in the user-submitted document are recorded. By obtaining user feedback, it is possible to identify any deficiencies in the generated business requirements document. When deficiencies are found, the user's modifications are recorded. This modified content can be directly utilized when the user needs to generate the same type of business requirements document again, thereby improving the quality of the generated document.

[0076] In some examples, if the initial draft of the requirements document is not compliant, the initial draft of the requirements document is modified based on business compliance knowledge to generate a business requirements document.

[0077] When reviewing the initial draft of the requirements document based on business compliance knowledge, if the content of the initial draft does not conform to the corresponding business compliance knowledge, it will be modified based on that knowledge to generate the final business requirements document. For example, in the initial draft, the section on "Customer Eligibility Criteria" states: "A loan application can be made by providing a business license and the user's ID card; no other documents such as financial statements are required." The section on "Purpose of Loan Funds" states: "Loan funds can be freely disposed of by the customer." According to the acquired business compliance knowledge, the "Interim Measures for the Management of Working Capital Loans," banks should comprehensively assess the borrower's repayment ability. A business license and user's ID card alone cannot complete an effective assessment, and the lack of financial statements and other documents violates regulations. Furthermore, the measures explicitly require that working capital loans have a designated purpose and cannot be freely disposed of to prevent loan funds from flowing into restricted areas such as the stock market and real estate market.

[0078] Based on compliance knowledge, the business requirements document was revised. Specifically, it was supplemented to include "in addition to the business license and user's ID card, financial statements, bank statements, tax records, and other materials for the past year are also required so that the bank can assess the company's operating status and repayment ability," ensuring compliance with regulatory requirements for risk assessment. The wording of the "Purpose of Loan Funds" section was adjusted to "Loan funds can only be used for the company's daily production and operation turnover, including raw material procurement, equipment maintenance, etc. Customers must specify the purpose of funds when applying and provide supporting documentation after the loan is disbursed," to meet regulatory requirements for controlling the flow of loan funds.

[0079] By systematically and rigorously revising the initial drafts of requirement documents that do not comply with business compliance, a final business requirement document that meets the standards is formed, ensuring that the generated business requirement document complies with industry norms.

[0080] In some examples, the business requirements knowledge base is connected to the banking system; if the business requirements in the banking system are updated, the business requirements knowledge base is updated accordingly.

[0081] A private domain knowledge graph is constructed based on the business requirements knowledge base; the private domain knowledge graph is used to record all the contents of the business requirements knowledge base.

[0082] In practical applications, connecting the business requirements knowledge base with the banking system enables timely acquisition of changing industry knowledge, ensuring the real-time nature of the knowledge base content. Simultaneously, a private knowledge graph is constructed based on the business requirements knowledge base to record all its contents, ensuring the traceability of the generated business requirements documents.

[0083] For example, regarding the document "Work Mechanism for the Rectification of the 'Card Breaking' Action in Preventing and Combating Telecommunications and Internet Fraud" in the Requirements Compliance Knowledge Base, as of June 30, 2025, the version stored in the Requirements Compliance Knowledge Base is the updated third version; the first and second versions of the same document are stored in the private domain knowledge graph, while the Requirements Compliance Knowledge Base only stores the third version. When a user needs to query business requirements documents related to this content, they can retrieve historical content from the private domain knowledge graph for viewing.

[0084] Example 2

[0085] Figure 7 A schematic diagram of a device for generating banking business requirements is provided for this application, as shown in the figure. Figure 7 As shown in the embodiment of this application, the apparatus 700 for generating banking business requirements includes:

[0086] The acquisition module 701 is used to acquire business requirements and corresponding business requirement document templates; and to generate a draft requirement document based on the business requirement document templates and business requirements.

[0087] Processing module 702 is used to extract compliance keywords from the initial draft of the requirements document, and to determine business compliance knowledge based on the compliance keywords and the keyword knowledge base; wherein, the keyword knowledge base includes multiple keywords and the relationship between each keyword and the business requirements document;

[0088] The generation module 703 is used to check whether the initial draft of the requirements document is compliant based on business compliance knowledge, and to generate the business requirements document if the initial draft of the requirements document is compliant.

[0089] The apparatus for generating banking business requirements provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0090] Figure 8 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 8 As shown, the electronic device 80 provided in this embodiment includes at least one processor 801 and a memory 802. Optionally, the device 80 further includes a communication component 803. The processor 801, memory 802, and communication component 803 are connected via a bus 804.

[0091] In a specific implementation, at least one processor 801 executes computer execution instructions stored in memory 802, causing at least one processor 801 to perform the above-described method.

[0092] The specific implementation process of processor 801 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0093] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method; its implementation principle and technical effect are similar and will not be described in detail here.

[0094] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the technical solution of the above method embodiments. Its implementation principle and technical effects are similar, and will not be repeated here.

[0095] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0096] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated 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 steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0097] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0098] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0099] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0100] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 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 methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0101] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0102] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0103] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for generating a banking business requirements document, characterized in that, include: Obtain business requirements and corresponding business requirement document templates; Based on the business requirements template and the business requirements, a draft of the requirements document is generated. Based on the initial draft of the requirements document, compliance keywords were extracted, and business compliance knowledge was determined based on the compliance keywords and the keyword knowledge base; wherein, the keyword knowledge base includes multiple keywords and the relationship between each keyword and the business requirements document; Based on the aforementioned business compliance knowledge, the initial draft of the requirements document is checked for compliance, and if the initial draft of the requirements document is compliant, a business requirements document is generated.

2. The method according to claim 1, characterized in that, Before obtaining the business requirements and the corresponding business requirements template, the process also includes: Obtain business requirements documents and build a business requirements knowledge base; use natural language processing tools to extract keywords from the business requirements documents to obtain corresponding keywords; wherein, the business requirements documents include business requirements templates, business compliance knowledge, business architecture assets, and financial knowledge; Establish a relationship based on the business requirements document and the corresponding keywords, and construct a keyword knowledge base based on the relationship and the keywords.

3. The method according to claim 2, characterized in that, The process of obtaining business requirements and corresponding business requirement templates includes: Obtain the business requirements uploaded by the user; retrieve historical business requirements from the business requirements knowledge base based on the business requirements, calculate the similarity between the historical business requirements and the current business requirements, and determine whether the similarity is greater than a preset value; If the similarity is greater than a preset value, then the business requirement template corresponding to the historical business requirement will be used as the business requirement template for the business requirement. If the similarity is not greater than a preset value, then the corresponding business requirement template is obtained from the business requirement knowledge base according to the business requirements.

4. The method according to claim 3, characterized in that, The process of generating a draft requirement document based on the business requirement document template and the business requirements includes: Based on the business requirements, keywords were extracted to obtain financial knowledge keywords and business architecture asset keywords. Based on the financial knowledge keywords and the keyword knowledge base, the corresponding financial knowledge is determined, and the financial knowledge is filled into the business requirements template according to the filling rules of the business requirements template to obtain the basic draft of the requirements document; Based on the business architecture asset keywords and the keyword knowledge base, the corresponding business architecture assets are determined; the corresponding step rule information is obtained from the business requirement knowledge base according to the business architecture assets; and the initial draft of the requirement document is generated according to the basic draft of the requirement document, the business architecture assets, and the corresponding step rule information.

5. The method according to claim 1, characterized in that, The method further includes: Send the business requirements document to the user and obtain the user's feedback business requirements document; compare the user's feedback business requirements document with the original business requirements document; If the business requirement document provided by the user is inconsistent with the original business requirement document, the modifications made in the user-provided business requirement document will be recorded to optimize the regenerated business requirement document of the same type.

6. The method according to claim 1, characterized in that, The method further includes: If the initial draft of the requirements document is not compliant, the initial draft of the requirements document shall be modified according to the business compliance knowledge to generate a business requirements document.

7. The method according to any one of claims 1-6, characterized in that, Also includes: Connect the aforementioned business requirements knowledge base to the banking system; If the business requirements in the banking system are updated, the business requirements knowledge base is updated accordingly. A private domain knowledge graph is constructed based on the business requirements knowledge base; wherein, the private domain knowledge graph is used to record all the contents of the business requirements knowledge base.

8. A device for generating a banking business requirements document, characterized in that, include: The acquisition module is used to acquire business requirements and corresponding business requirement templates. Based on the business requirements template and the business requirements, a draft of the requirements document is generated. The processing module is used to extract compliance keywords from the initial draft of the requirements document, and to determine business compliance knowledge based on the compliance keywords and the keyword knowledge base; wherein, the keyword knowledge base includes multiple keywords and the association between each keyword and the business requirements document; The generation module is used to check whether the initial draft of the requirements document is compliant based on the business compliance knowledge, and generate the business requirements document if the initial draft of the requirements document is compliant.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images