Demand document generation method and device, equipment and medium
By identifying related sub-requirement documents in the reference sub-requirement document library and generating target requirement documents using multiple requirement analysis models, the problems of low efficiency and poor comprehensibility in requirement document generation are solved, achieving efficient, comprehensive, and easy-to-understand requirement document generation.
Patent Information
- Application Number
- CN202511711199.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-20
- Publication Date
- 2026-04-24
AI Technical Summary
In existing technologies, the generation of requirements documents is inefficient and not easily understood by personnel in other stages, leading to communication difficulties.
By obtaining the initial requirement document, related sub-requirement documents are identified in the pre-built reference sub-requirement document library, a candidate requirement information set is generated, and target requirement documents are generated based on multiple sets of requirement prompts using multiple requirement analysis models. This ensures that the requirement prompts of each requirement analysis model are not completely identical, so as to meet the requirements of multiple sets of requirements.
It improved the efficiency and comprehensibility of requirement documents, ensuring that the requirement documents fully meet the needs of various business roles and reducing the difficulty of understanding.
Smart Images
Figure CN121918796A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of computer technology, and in particular to a method, apparatus, device, and medium for generating requirements documents. Background Technology
[0002] With the development of computer technology, development scenarios such as application generation have emerged, and generating requirement documents that indicate development needs before development has become a common scenario.
[0003] In related technologies, development documents are manually written by product managers or developers. After being written, they are discussed and modified with technical personnel involved in various stages of the development process. However, this method of generating requirements documents, which relies on manual processes and interactions, results in low efficiency in document generation and makes the generated documents difficult for personnel in other stages to understand. Summary of the Invention
[0004] To solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides a method, apparatus, device and medium for generating requirements documents.
[0005] This disclosure provides a method for generating a requirement document, the method comprising: obtaining an initial requirement document; determining associated sub-requirement documents related to the initial requirement document in a pre-built reference sub-requirement document library; generating a candidate requirement information set based on the associated sub-requirement documents and the initial requirement document; obtaining multiple sets of requirement prompts corresponding to multiple predetermined requirement analysis models; and generating a target requirement document through the multiple requirement analysis models based on the multiple sets of requirement prompts and the candidate requirement information set, wherein the requirement prompts corresponding to each requirement analysis model are not completely identical, and the target requirement document satisfies the requirements corresponding to the multiple sets of requirement prompts.
[0006] This disclosure also provides a requirement document generation apparatus, comprising: a determining module, configured to acquire an initial requirement document and determine associated sub-requirement documents related to the initial requirement document in a pre-built reference sub-requirement document library; an information generation module, configured to generate a candidate requirement information set based on the associated sub-requirement documents and the initial requirement document; and a document generation module, configured to acquire multiple sets of requirement prompts corresponding to multiple pre-determined requirement analysis models, and generate a target requirement document based on the multiple sets of requirement prompts and the candidate requirement information set through the multiple requirement analysis models, wherein the sets of requirement prompts corresponding to each requirement analysis model are not completely identical, and the target requirement document satisfies the requirements corresponding to the multiple sets of requirement prompts.
[0007] This disclosure also provides an electronic device, the electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the requirement document generation method provided in this disclosure.
[0008] This disclosure also provides a computer-readable storage medium storing a computer program for executing a requirements document generation method as provided in this disclosure.
[0009] The technical solution provided in this disclosure has the following advantages compared with the prior art: The requirement document generation scheme provided in this disclosure involves obtaining an initial requirement document, determining associated sub-requirement documents from a pre-built reference sub-requirement document library, generating a candidate requirement information set based on the associated sub-requirement documents and the initial requirement document, obtaining multiple sets of requirement prompts corresponding to multiple predetermined requirement analysis models, and generating a target requirement document using multiple requirement analysis models based on the multiple sets of requirement prompts and the candidate requirement information set. The requirement prompts for each requirement analysis model are not entirely identical, and the target requirement document satisfies the requirements corresponding to the multiple sets of requirement prompts. This technical solution improves the efficiency of requirement document generation, the comprehensiveness of requirement expression, and ease of understanding. Attached Figure Description
[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.
[0011] Figure 1 A flowchart illustrating a method for generating a requirements document according to an embodiment of this disclosure; Figure 2 A flowchart illustrating another method for generating a requirements document provided in this embodiment of the disclosure; Figure 3 A flowchart illustrating another method for generating a requirements document provided in this embodiment of the disclosure; Figure 4 A schematic diagram of a requirements document generation apparatus provided in an embodiment of this disclosure; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation
[0012] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.
[0013] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.
[0014] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.
[0015] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.
[0016] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".
[0017] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
[0018] To address the aforementioned issues, this disclosure provides a method for generating requirements documents, which will be described below with reference to specific embodiments.
[0019] Figure 1 This is a flowchart illustrating a method for generating a requirements document according to an embodiment of this disclosure. The method can be executed by a requirements document generation device, which can be implemented in software and / or hardware, and is generally integrated into an electronic device. Figure 1 As shown, the method includes: Step 101: Obtain the initial requirements document and identify the associated sub-requirements document in the pre-built reference sub-requirements document library.
[0020] The initial requirements document is a requirement document written by relevant technical personnel who do not fully express the requirements. This initial requirements document can be a short text.
[0021] In one embodiment of this disclosure, before determining the associated sub-requirement document associated with the initial requirement document in a pre-built reference sub-requirement document library, multiple reference requirement documents are obtained. The reference requirement documents may include various associated technical documents in a business scenario. For example, in a development scenario, the reference requirement documents may include documents associated with the business scenario such as historical performance logs and technical white papers.
[0022] In this embodiment, each reference requirement document can be split to obtain multiple reference sub-requirement documents corresponding to each reference requirement document. This can be done by using the splitting function of a Retrieval-Augmented Generation (RAG) model, where each chunk of the RAG split is considered a sub-requirement document. Alternatively, each reference requirement document can be split by paragraph, with each resulting paragraph considered a reference sub-requirement document. In this embodiment, the reference sub-requirement document library can be constructed based on all the aforementioned reference sub-requirement documents.
[0023] In some possible embodiments, to improve matching efficiency, a large language model can be used to generate a summary corresponding to each reference sub-requirement document. After obtaining the initial requirement document, the initial requirement document is matched with the summary to determine the matched associated sub-requirement document.
[0024] In embodiments of this disclosure, the initial requirement document may also be directly matched with the reference sub-requirement document, and the matched associated sub-requirement document may be determined based on the matching similarity.
[0025] Step 102: Generate a set of candidate requirement information based on the associated sub-requirement documents and the initial requirement document.
[0026] In the embodiments of this disclosure, a set of candidate requirement information is generated based on the associated sub-requirement documents and the initial requirement document, that is, some associated sub-requirement documents are added to the initial requirement document to improve the information comprehensiveness of the requirement document.
[0027] In one embodiment of this disclosure, to further improve the comprehensiveness of the requirements document, a context sub-requirement document of the associated sub-requirement document can be determined in a reference sub-requirement document library. The context sub-requirement document may include explanations and other information related to the associated sub-requirement document. Therefore, using the context sub-requirement document as a supplementary document can further enrich the comprehensiveness of the requirements document. In this embodiment, business terms contained in the associated sub-requirement document, the initial requirements document, and the context sub-requirement document can also be identified. For example, based on a large language model, some highly specialized business terms (e.g., the business term "metaverse") can be identified, and business description information of the business terms can be obtained. A business characteristic knowledge base can be pre-constructed, containing a large amount of business description information for business terms. This business description information is used to explain the corresponding business terms. In one embodiment of this disclosure, when the business characteristic knowledge base does not contain business description information for business terms, the relevant user can be prompted to fill in the missing information, and the supplemented information is stored in the business characteristic knowledge base as business description information.
[0028] In this embodiment, a candidate requirement information set is formed based on the following sub-requirement documents, associated sub-requirement documents, initial requirement documents, and business description information. When performing query matching based on the summary of the sub-requirement documents, this candidate requirement information set may also include the summary of the corresponding sub-requirement, etc.
[0029] Step 103: Obtain multiple sets of requirement prompts corresponding to multiple predetermined requirement analysis models. Generate a target requirement document based on the multiple sets of requirement prompts and candidate requirement information set through multiple requirement analysis models. The requirement prompts corresponding to each requirement analysis model are not completely the same. The target requirement document satisfies the requirements corresponding to the multiple sets of requirement prompts.
[0030] It should be noted that, in order to meet multi-dimensional needs, multiple requirement analysis models can be pre-built. These multiple requirement analysis models can be viewed as intelligent agents representing each business role in the business scenario. Based on these multiple requirement analysis models, each can represent a different business role to refine the requirement document. For example, in a development business scenario, the multiple requirement analysis models could include a first analysis model representing the product manager, a second analysis model representing the tester, and a third analysis model representing the developer.
[0031] Each requirement analysis model corresponds to a set of requirement prompts. Each set of prompts is used from the perspective of the corresponding business role to express requirements regarding the content expressed in the requirement document. For example, when the business role is product manager, the corresponding set of prompts is used to determine whether the requirements are clearly expressed (e.g., are technical terms clearly explained?, are the development time limits clearly stated?). When the business role is tester, the corresponding set of prompts is used to determine whether the requirements meet the needs of actual business test cases in certain business scenarios (e.g., can rendering be achieved in an 8G scenario?). When the business role is developer, the corresponding set of prompts is used to determine whether the requirements meet certain business development requirements (e.g., is the workload of implementing the requirements within the preset workload range?).
[0032] In the embodiments of this disclosure, multiple sets of requirement prompts corresponding to multiple predetermined requirement analysis models are obtained. A target requirement document is generated by the multiple requirement analysis models based on the multiple sets of requirement prompts and the candidate requirement information set. The requirement prompts corresponding to each requirement analysis model are not completely the same, and the target requirement document satisfies the requirements corresponding to the multiple sets of requirement prompts.
[0033] In this technical solution, a target requirement document is generated by combining various requirement analysis models based on the multiple sets of requirement prompts and the candidate requirement information set. This ensures that the generated target requirement document can meet the needs of various business roles, avoids difficulties for business roles in understanding the requirement document, and guarantees the comprehensiveness of the information in the target requirement document.
[0034] It should be noted that the methods for generating target requirement documents using the multiple requirement analysis models based on the multiple sets of requirement prompts and the candidate requirement information set differ in different application scenarios, as shown in the following examples: For ease of explanation, the example provided will use multiple requirements analysis models, including a first analysis model, a second analysis model, and a third analysis model.
[0035] In one possible example, such as Figure 2 As shown, the target requirement document is generated through the multiple requirement analysis models based on the multiple sets of requirement prompts and the candidate requirement information set, including: Step 201: Generate a first information set using the first analysis model based on a set of corresponding demand prompts and candidate demand information sets.
[0036] In the embodiments of this disclosure, a first information set is generated by a first analysis model based on a corresponding set of demand prompts and a set of candidate demand information, wherein the information included in the first information set conforms to the corresponding demand according to the first analysis model.
[0037] In the embodiments of this disclosure, the first analysis model can be sorted according to a corresponding set of demand prompts to obtain a sorting result. The corresponding demand prompts are traversed in the sorting result from front to back. The traversed demand prompts and the first reference information set are input into the first analysis model to obtain the second reference information set output by the first analysis model. The second reference information set satisfies the demand corresponding to the corresponding demand prompt. When the traversed demand prompt is the first demand prompt in the sorting result, the first reference information set is a candidate demand information set. When the traversed demand prompt is not the first demand prompt in the sorting result, the first reference information set is the second reference information set previously output by the first analysis model. When the traversed demand prompt is the last demand prompt in the sorting result, the output second reference information set is the first information set.
[0038] In this embodiment, the corresponding requirement document is optimized layer by layer, like peeling an onion, based on the first analysis model and a set of corresponding requirement prompts.
[0039] The first analysis model can be a RAG model, etc. The first analysis model learns in advance whether the first set of reference information input satisfies the requirement corresponding to the requirement prompt word currently being traversed. If the requirement is satisfied, the first set of reference information input is not processed. If it is not satisfied, the requirement sub-document corresponding to the requirement prompt word currently being traversed is determined in the preset reference sub-requirement document library. The second information set is then organized according to the first set of reference information and the requirement sub-document.
[0040] Step 202: Generate a second information set using the second analysis model based on the corresponding set of demand prompts and the first information set.
[0041] In the embodiments of this disclosure, a second information set can be generated by a second analysis model based on a corresponding set of demand prompts and a first information set. The generation method of the second information set can refer to the generation method of the first information set, and will not be repeated here.
[0042] Step 203: Generate the target requirement document using the third analysis model based on the corresponding set of requirement prompts and the second information set.
[0043] In the embodiments of this disclosure, a target requirement document is generated by a third analysis model based on a corresponding set of requirement prompts and a second information set. The method of generating the target requirement document can refer to the method of generating the first information set, and will not be repeated here.
[0044] In one possible example, a first information set can be generated using a first analysis model based on a corresponding set of requirement prompts and candidate requirement information sets. A second information set can be generated using a second analysis model based on the same set of requirement prompts and candidate requirement information sets. A third information set can be generated using a third analysis model based on the same set of requirement prompts and candidate requirement information sets. Finally, the first, second, and third information sets can be merged to obtain the target requirement document. The methods for generating the first, second, and third information sets can all refer to the above embodiments.
[0045] Furthermore, after generating the target requirement document, in order to further ensure that the target requirement document can meet the requirements corresponding to each requirement analysis model, in one embodiment of this disclosure, such as... Figure 3 As shown, after generating the target requirement document based on multiple sets of requirement cue words and candidate requirement information through multiple requirement analysis models, the method further includes: Step 301: Determine the validation rules corresponding to the target requirement document, and validate the target requirement document according to the validation rules.
[0046] The validation rules are used as further extended validations for further target requirement documents.
[0047] Validation rules correspond to business scenarios. For example, when the business scenario is a development scenario, the corresponding validation rules may include validation of whether the constraints corresponding to the sub-requirements are included, validation of the completeness of semantic expression, and validation of the semantic completeness of each requirement. Validation rules may also include some general rules, such as whether technical terms are expressed consistently.
[0048] In one embodiment of this disclosure, the sub-requirement types included in the target requirement document can be identified. The sub-requirement types can be identified through large language models, etc. The sub-requirement types are related to the business scenario. For example, when the business scenario is a development scenario, the corresponding sub-requirement types include interface component display requirements, code execution time requirements, etc.
[0049] Furthermore, verification rules can be obtained based on the sub-requirement type. These rules can include one or more of the following: verification content, verification questions, etc. For example, a pre-defined correspondence can be queried to determine the rules corresponding to the sub-requirement type. Alternatively, a verification rule generation model can be pre-trained based on experimental data. The sub-requirement type and its corresponding sub-requirement information can be input into the pre-trained model to obtain the verification rules output by the model. The sub-requirement information corresponding to the sub-requirement type can be considered as the document information associated with the sub-requirement type in the target requirement document.
[0050] Step 302: When the target requirement document fails validation, modify the target requirement document according to the validation rules for failure to obtain the modified target requirement document.
[0051] In the embodiments of this disclosure, the target requirement document is not modified when it passes verification.
[0052] When the target requirement document fails validation, it is modified according to the validation rules to obtain a revised target requirement document. Modification can be done manually or using an AI model, and the revised document must conform to the corresponding validation rules.
[0053] In summary, the requirement document generation method of this disclosure involves obtaining an initial requirement document, determining associated sub-requirement documents from a pre-built reference sub-requirement document library, generating a candidate requirement information set based on the associated sub-requirement documents and the initial requirement document, obtaining multiple sets of requirement prompts corresponding to multiple predetermined requirement analysis models, and generating a target requirement document using multiple requirement analysis models based on the multiple sets of requirement prompts and the candidate requirement information set. The requirement prompts for each requirement analysis model are not entirely identical, and the target requirement document satisfies the requirements corresponding to the multiple sets of requirement prompts. This technical solution improves the efficiency of requirement document generation, the comprehensiveness of requirement expression, and ease of understanding.
[0054] To implement the above embodiments, this disclosure also proposes a requirements document generation apparatus.
[0055] Figure 4 This is a schematic diagram of a requirements document generation apparatus provided in an embodiment of the present disclosure. The apparatus can be implemented by software and / or hardware and is generally integrated into an electronic device. Figure 4 As shown, the device includes: a determining module 410, an information generating module 420, and a document generating module 430, wherein, The determination module 410 is used to obtain the initial requirement document and determine the associated sub-requirement documents related to the initial requirement document in the pre-built reference sub-requirement document library; The information generation module 420 is used to generate a set of candidate requirement information based on the associated sub-requirement documents and the initial requirement document; The document generation module 430 is used to obtain multiple sets of requirement prompts corresponding to multiple predetermined requirement analysis models, and generate a target requirement document based on the multiple sets of requirement prompts and candidate requirement information set through multiple requirement analysis models. The requirement prompts corresponding to each requirement analysis model are not completely the same, and the target requirement document satisfies the requirements corresponding to the multiple sets of requirement prompts.
[0056] The requirement document generation apparatus provided in this disclosure can execute the requirement document generation method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the execution method.
[0057] In one embodiment of this disclosure, it further includes: a construction module, configured to: Obtain multiple reference requirement documents, and break down each reference requirement document to obtain multiple reference sub-requirement documents corresponding to each reference requirement document; Build a reference sub-requirement document library based on all reference sub-requirement documents.
[0058] In one embodiment of this disclosure, the information generation module 420 is configured to: Identify the context sub-requirement document associated with the sub-requirement document in the reference sub-requirement document library; Identify business terms contained in related sub-requirement documents, initial requirement documents, and contextual sub-requirement documents; Obtain business description information for business terms; The candidate requirement information set is composed of the following sub-requirement documents, related sub-requirement documents, initial requirement documents, and business description information.
[0059] In one embodiment of this disclosure, when multiple requirement analysis models include a first analysis model, a second analysis model, and a third analysis model, the document generation module 430 is used to: The first analysis model generates a first information set based on a set of corresponding demand prompts and candidate demand information. The second analysis model generates a second information set based on a corresponding set of demand prompts and the first information set. The third analysis model generates the target requirement document based on a set of corresponding requirement prompts and a second set of information.
[0060] In one embodiment of this disclosure, the document generation module 430 is configured to: sort the first analysis model according to a corresponding set of demand prompts to obtain a sorting result; Following the order of the sorted results, the corresponding requirement prompts are traversed from front to back. The traversed requirement prompts and the first reference information set are then input into the first analysis model to obtain the second reference information set output by the first analysis model. The second reference information set satisfies the requirements corresponding to the respective requirement prompts. When the requested keyword encountered during iteration is the first requested keyword in the sorting results, the first reference information set is the candidate requested information set. When the requested keyword encountered during iteration is not the first requested keyword in the sorting results, the first reference information set is the second reference information set previously output by the first analysis model. When the requested keyword encountered during iteration is the last requested keyword in the sorting results, the output second reference information set is the first information set.
[0061] In one embodiment of this disclosure, a verification module is further included, for: Determine the validation rules corresponding to the target requirement document, and validate the target requirement document according to the validation rules; If the target requirement document fails validation, modify the target requirement document according to the validation rules to obtain the modified target requirement document.
[0062] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program / instructions, which, when executed by a processor, implements the requirement document generation method in the above embodiments.
[0063] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.
[0064] The following is a detailed reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing the electronic device 500 in the embodiments of this disclosure. The electronic device 500 in the embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.
[0065] like Figure 5As shown, electronic device 500 may include a processor (e.g., central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from memory 508 into random access memory (RAM) 503. RAM 503 also stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.
[0066] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.
[0067] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 509, or installed from memory 508, or installed from ROM 502. When the computer program is executed by processor 501, it performs the functions defined in the requirements document generation method of embodiments of this disclosure.
[0068] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.
[0069] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.
[0070] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.
[0071] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned method for generating the requirements document.
[0072] Electronic devices can be programmed with computer program code in one or more programming languages or combinations thereof to perform the operations of this disclosure. These programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as "C" or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0073] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0074] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.
[0075] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.
[0076] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0077] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.
[0078] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.
[0079] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.
Claims
1. A method for generating a requirements document, characterized in that, include: Obtain the initial requirements document, and determine the associated sub-requirements document in the pre-built reference sub-requirements document library that is associated with the initial requirements document; Based on the associated sub-requirement documents and the initial requirement document, a set of candidate requirement information is generated; Multiple sets of requirement prompts corresponding to multiple predetermined requirement analysis models are obtained. A target requirement document is generated based on the multiple sets of requirement prompts and the candidate requirement information set through the multiple requirement analysis models. The requirement prompts corresponding to each requirement analysis model are not completely the same, and the target requirement document satisfies the requirements corresponding to the multiple sets of requirement prompts.
2. The method as described in claim 1, characterized in that, Before determining the associated sub-requirement document related to the initial requirement document in the pre-built reference sub-requirement document library, the process includes: Obtain multiple reference requirement documents, and split each reference requirement document to obtain multiple reference sub-requirement documents corresponding to each reference requirement document; The reference sub-requirement document library is constructed based on all the aforementioned reference sub-requirement documents.
3. The method as described in claim 1 or 2, characterized in that, The step of generating a candidate requirement information set based on the associated sub-requirement document and the initial requirement document includes: Determine the context sub-requirement document of the associated sub-requirement document in the reference sub-requirement document library; Identify the business terms contained in the associated sub-requirement document, the initial requirement document, and the context sub-requirement document; Obtain the business description information of the business term; The candidate requirement information set is composed of the following sub-requirement documents, the associated sub-requirement documents, the initial requirement document, and the business description information.
4. The method as described in claim 1, characterized in that, When the plurality of requirement analysis models include a first analysis model, a second analysis model, and a third analysis model, the step of generating a target requirement document based on the plurality of requirement cue words and the candidate requirement information set through the plurality of requirement analysis models includes: The first information set is generated by the first analysis model based on the corresponding set of demand prompts and the candidate demand information set; The second analysis model generates a second information set based on a corresponding set of demand prompts and the first information set. The target requirement document is generated by the third analysis model based on a set of corresponding requirement prompts and the second information set.
5. The method as described in claim 4, characterized in that, The first information set is generated by the first analysis model based on a corresponding set of demand prompts and the candidate demand information set, including: The first analysis model is sorted according to a corresponding set of demand prompts to obtain the sorting results; Following the order of the sorted results, the corresponding requirement prompts are traversed from front to back. The traversed requirement prompts and the first reference information set are then input into the first analysis model to obtain the second reference information set output by the first analysis model. The second reference information set satisfies the requirements corresponding to the respective requirement prompts. When the traversed demand prompt word is the first demand prompt word in the sorting result, the first reference information set is the candidate demand information set. When the traversed demand prompt word is not the first demand prompt word in the sorting result, the first reference information set is the second reference information set previously output by the first analysis model. When the traversed demand prompt word is the last demand prompt word in the sorting result, the output second reference information set is the first information set.
6. The method as described in claim 1 or 4, characterized in that, After generating the target requirement document using the multiple requirement analysis models based on the multiple sets of requirement prompts and the candidate requirement information set, the method further includes: Determine the verification rules corresponding to the target requirement document, and verify the target requirement document according to the verification rules; If the target requirement document fails verification, the target requirement document is modified according to the verification rules for failure to obtain the modified target requirement document.
7. The method as described in claim 6, characterized in that, The step of determining the verification rules corresponding to the target requirement document includes: Identify the sub-requirement types included in the target requirements document; The verification rule is obtained based on the sub-requirement type.
8. The method as described in claim 7, characterized in that, Obtaining the verification rule according to the sub-requirement type includes: The sub-requirement type and the corresponding sub-requirement information are input into the pre-trained verification rules to generate the model; Obtain the verification rules output by the verification rule generation model.
9. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method for generating a requirements document as described in any one of claims 1-8.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program for performing the method for generating a requirements document as described in any one of claims 1-8.