Software product development method and device, electronic equipment and nonvolatile storage medium

By analyzing the user input text and using the underlying corpus to generate logical connection relationships, the problem of poor design corpus standardization in software product design is solved, and the usability and rapid generation of design content generated by artificial intelligence models is achieved.

CN118916451APending Publication Date: 2024-11-08SUPCON TECH CO LTD +1

Patent Information

Application Number
CN202410862582.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-28
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In the software product design process, due to the poor standardization and independence of each design link, the design content generated with the help of artificial intelligence models is poor.

Method used

By obtaining the natural language text input by users, analyzing and determining the business type and business scenarios, using the historical software product development process and process nodes in the underlying corpus, a logical connection relationship is generated, a standardized software product development process is formed, and a standardized software product development process is used to pass the artificial intelligence model. Quickly assemble and generate design content.

Benefits of technology

It improves the standardization and usability of software product design content, realizes the rapid generation and reuse of design content, and reduces the work burden and communication costs of product managers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118916451A_ABST
    Figure CN118916451A_ABST
Patent Text Reader

Abstract

The invention discloses a software product development method and device, electronic equipment and a nonvolatile storage medium. The method comprises the following steps: acquiring a text input by a user, and determining a business type and a business scene corresponding to a software product to be developed by analyzing the text input by the user; obtaining a process node corresponding to the service type and the service scene in a bottom corpus; and according to a historical software product development process containing process nodes corresponding to the service types and the service scenes in the underlying corpus, determining a logic connection relationship between the process nodes, and generating a software product development process corresponding to the to-be-developed software product. The technical problem that in the software product design process, due to the fact that design corpora of all design links are poor in normativity and independent and isolated from one another, the usability of design content generated by means of an artificial intelligence model is poor is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of software engineering product design, and in particular, to a software product development method, device, electronic device and non-volatile storage medium. Background Art

[0002] In the context of digital transformation, informatization within enterprises continues to improve, and the requirements for data online, standardized, and streamlined are becoming increasingly higher. However, in the process of software product design, a variety of design tools are used, and the capabilities of each tool vary, resulting in the inability to reuse the design well.

[0003] In addition, with the rapid development of artificial intelligence, general models have become relatively mature and can generate processes, pages, data modeling, etc. with one click. However, due to the poor standardization of design corpus in each design link in the software product design process, and their independence and isolation, the design content generated with the help of artificial intelligence models has poor usability.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a software product development method, device, electronic device and non-volatile storage medium to at least solve the technical problem of poor usability of design content generated with the help of artificial intelligence models due to the poor standardization of design corpus in each design link and their mutual independence and isolation in the software product design process.

[0006] According to one aspect of an embodiment of the present application, a software product development method is provided, comprising: obtaining user input text, and determining a business type and a business scenario corresponding to a software product to be developed by parsing the user input text, wherein the user input text is a natural language text describing the design requirements of the software product; obtaining process nodes corresponding to the business type and the business scenario in an underlying corpus, wherein the underlying corpus stores: historical software product development processes that have been generated and verified, and process nodes in the historical software product development processes; determining a logical connection relationship between each process node based on the historical software product development processes that contain process nodes corresponding to the business type and the business scenario in the underlying corpus, and generating a software product development process corresponding to the software product to be developed.

[0007] Optionally, parsing the user input text and determining the business type and business scenario corresponding to the software product to be developed includes: using a large language model to perform text cleaning on the user input text, and performing word segmentation on the cleaned user input text, wherein text cleaning is used to delete interference characters in the user input text, and the interference characters include at least one of the following: punctuation marks, special characters; determining the part of speech of each participle obtained after the word segmentation process, and deleting the part of speech of the part of speech being an adjective, wherein the part of speech includes at least one of the following: noun, verb, adjective; determining the demand information corresponding to the user input text based on the part of speech of the participle and the contextual position relationship between each participle in the user input text, wherein the demand information includes: business scenario, business type, functional requirements, user interface requirements, and performance indicators.

[0008] Optionally, obtaining the process nodes corresponding to the business types and business scenarios in the underlying corpus includes: accurately matching the keywords used to characterize the business types and business scenarios in the user input text with the labels corresponding to each process node in the underlying corpus, wherein the labels are used to characterize the business types and business scenarios corresponding to the process nodes; when the fields between the labels and the keywords are exactly the same, it is determined that the labels and keywords are accurately matched successfully, and the process nodes that are accurately matched successfully are determined as the process nodes corresponding to the business types and business scenarios.

[0009] Optionally, the method also includes: when the keyword and all the tags in the underlying corpus are not accurately matched, determining the extended word corresponding to the keyword based on a preset synonym library, wherein the preset synonym library contains multiple groups of preset synonyms or near synonyms; determining the text similarity between the extended word and the tag, wherein the text similarity includes: literal similarity and semantic similarity, literal similarity is used to characterize the similarity between the character forms of two texts, and semantic similarity is used to characterize the similarity between the semantic meanings of two texts; and determining the process node corresponding to the tag whose text similarity exceeds the preset similarity threshold as the process node corresponding to the business type and business scenario.

[0010] Optionally, determining the logical connection relationship between each process node based on the historical software product development process containing process nodes corresponding to the business type and business scenario in the underlying corpus includes: screening the process nodes corresponding to the functional requirements among the process nodes corresponding to the business type and business scenario, and determining the historical software product development process containing the screened process nodes in the underlying corpus; determining the execution order between the screened process nodes based on the requirement information corresponding to the user input text; obtaining the corresponding logical connection relationship between adjacent process nodes contained in the historical software product development process, and counting the frequency of occurrence of each logical connection relationship in the historical software product development process; determining the generation type of each logical connection relationship, wherein the generation type includes: automatically generated by the model, generated in response to the user's modification instructions; determining the score corresponding to each logical connection relationship based on the frequency of occurrence and the generation type, and determining the logical connection relationship with the highest score as the final logical connection relationship between adjacent process nodes, wherein the score is used to characterize the credibility of the logical connection relationship.

[0011] Optionally, after generating the software product development process corresponding to the software product to be developed, the method also includes: sending the software product development process to the front-end interactive interface for display; adjusting the software product development process when receiving a modification instruction input from the front-end interactive interface; or, when receiving a verification pass instruction input from the front-end interactive interface, storing the software product development process as a historical software product development process in the underlying corpus, and adding corresponding labels to each process node in the software product development process.

[0012] Optionally, the underlying corpus also includes: page component information, data field entities and node services corresponding to process nodes in each historical software product development process.

[0013] According to another aspect of an embodiment of the present application, a software product development device is also provided, including: a text acquisition module, used to acquire user input text, and determine the business type and business scenario corresponding to the software product to be developed by parsing the user input text, wherein the user input text is a natural language text that describes the design requirements of the software product; a node selection module, used to acquire process nodes corresponding to the business type and business scenario in the underlying corpus, wherein the underlying corpus stores: historical software product development processes that have been generated and verified, and process nodes in the historical software product development processes; a process generation module, used to determine the logical connection relationship between each process node based on the historical software product development process containing process nodes corresponding to the business type and business scenario in the underlying corpus, and generate a software product development process corresponding to the software product to be developed.

[0014] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the software product development method is executed when the program is run.

[0015] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, the non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the software product development method by running the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, which implements the steps of the software product development method when the computer program is executed by a processor.

[0017] In an embodiment of the present application, a method is adopted in which a user input text is obtained, and the business type and business scenario corresponding to the software product to be developed are determined by parsing the user input text, wherein the user input text is a natural language text that describes the design requirements of the software product; the process nodes corresponding to the business type and business scenario in the underlying corpus are obtained, wherein the underlying corpus stores: historical software product development processes that have been generated and verified, and process nodes in the historical software product development processes; based on the historical software product development processes in the underlying corpus containing process nodes corresponding to the business type and business scenario, the logical connection relationship between each process node is determined, and a software product development process corresponding to the software product to be developed is generated. By standardizing the product design content, precipitating it into the underlying corpus, and quickly assembling and generating it through an artificial intelligence model, the purpose of quickly generating corresponding standardized product design content is achieved, thereby solving the technical problem of poor usability of the design content generated with the help of an artificial intelligence model due to the poor standardization of the design corpus of each design link in the software product design process, and the mutual independence and isolation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 It is a hardware structure block diagram of a computer terminal (or electronic device) for implementing a method for developing a software product according to an embodiment of the present application;

[0020] Figure 2 It is a schematic diagram of a method flow for software product development provided according to an embodiment of the present application;

[0021] Figure 3It is a schematic diagram of an overall system architecture provided according to an embodiment of the present application;

[0022] Figure 4 It is a schematic diagram of a software product design principle provided according to an embodiment of the present application;

[0023] Figure 5 It is a timing diagram of a software product design technology interaction process provided according to an embodiment of the present application;

[0024] Figure 6 It is a structural diagram of a software product development device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] In order to facilitate those skilled in the art to better understand the embodiments of the present application, some technical terms or nouns involved in the embodiments of the present application are explained as follows:

[0028] 4A architecture: also known as enterprise architecture, it includes the integrated design of business architecture, information architecture, application architecture and technology architecture. It is a general method for the overall design of information systems for enterprise digital transformation projects.

[0029] Supplier relationship management (SRM) is a management philosophy and software technology solution used to improve relationships with upstream suppliers in the supply chain and is committed to establishing and maintaining long-term, close partnerships with suppliers.

[0030] In the context of digital transformation, informatization within enterprises is constantly improving, and the requirements for data online, standardized, and process-based are becoming higher and higher. Many Internet companies or enterprises are constantly improving their software capabilities; but they are still unable to manage and reuse the products of software design very well, and many software design products also depend on the abilities and habits of product designers, and cannot be changed and improved very well; there are various tools on the market that serve product designers, such as Axure, Mocha, Visio, Process On, etc. Due to the differences in the capabilities of different tools, the design content cannot be well precipitated and reused, resulting in a relatively loose field of software engineering product design, and there is a lot of room for cost reduction and efficiency improvement.

[0031] The above problems arise mainly because the prototypes, processes, modeling, and service designs in related technologies are not standardized enough, are independent and isolated from each other, and cannot be mutually verified on the design side.

[0032] In addition, with the increasing popularity of artificial intelligence, general models have developed relatively maturely. For example, artificial intelligence models such as chat GPT, PMAI, MidjourneyAI, etc. can generate processes, pages, data modeling, PRD (Product Requirement Document), etc. with one click. However, due to the non-standard underlying design corpus disclosed in each design link in the software product design process, the design content generated by the artificial intelligence model has poor usability. Most of the generated design content is very simple and does not conform to the flowcharts and pages of the business scenarios, and is basically unusable.

[0033] Specifically, when system designers design corresponding requirements, they need to structure the design content and express the corresponding logic clearly; based on structured data, it is conducive to AI (Artificial Intelligence) capabilities to quickly assemble corresponding product design outputs; in the past, when product managers designed processes, pages, and entities, they were isolated and illogical, resulting in poor constraints. In order to save effort, product managers sometimes only produced processes, entities, or pages, and described product logic through notes. This leads to uneven outputs from product managers, and the personal abilities of product managers vary greatly, and it is impossible to conduct a good assessment. The communication cost between the technical side and the product side is also getting higher and higher. Some product managers even design content that is not logically closed-loop, and there are multiple reviews and development rework scenarios. Based on the differences in product managers' outputs, many AIs generate processes, pages, and entities in a single way, and the generated content deviates greatly from what they actually want, which basically does not contribute to value.

[0034] In order to solve the above problems, relevant solutions are provided in the embodiments of the present application, which are beneficial to the theory of enterprise management architecture TOGAF. Based on the 4A concept within the architecture, the design form of the product is defined so as to better meet the requirements of software engineering and enterprise management. The following is a detailed description.

[0035] According to an embodiment of the present application, a method embodiment of software product development is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or electronic device) for implementing a software product development method. Figure 1 As shown, the computer terminal 10 (or electronic device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0037] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or electronic device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0038] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the software product development method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned software product development method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0039] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or electronic device).

[0041] In the above operating environment, the embodiment of the present application provides a software product development method. Figure 2is a schematic diagram of a method flow for developing a software product according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0042] Step S202, obtaining a user input text, and determining the business type and business scenario corresponding to the software product to be developed by parsing the user input text, wherein the user input text is a natural language text describing the design requirements of the software product;

[0043] Step S204, obtaining process nodes corresponding to business types and business scenarios in the underlying corpus, wherein the underlying corpus stores: historical software product development processes that have been generated and verified, and process nodes in the historical software product development processes;

[0044] Step S206, based on the historical software product development process containing process nodes corresponding to the business type and business scenario in the underlying corpus, determine the logical connection relationship between each process node, and generate a software product development process corresponding to the software product to be developed.

[0045] Through the above steps, by standardizing the product design content, precipitating it into the underlying corpus, and quickly assembling and generating it through the artificial intelligence model, the purpose of quickly generating the corresponding standardized product design content is achieved, thereby solving the technical problem of poor usability of the design content generated with the help of the artificial intelligence model due to the poor standardization of the design corpus of each design link in the software product design process, and the mutual independence and isolation.

[0046] The following is a further introduction to the software product development method in steps S202 to S206 of the embodiment of the present application.

[0047] In the embodiment of the present application, the above software product development method can be implemented by using the 4A+AI product design tool. Figure 3 is a schematic diagram of an overall system architecture provided according to an embodiment of the present application, such as Figure 3 As shown, by standardizing the product design content in 4A product design, precipitating it into the underlying corpus, and integrating it with the generation capability of AI, the corresponding product design content can be quickly generated.

[0048] Figure 5 is a timing diagram of a software product design technology interaction process provided according to an embodiment of the present application, Figure 5 The interaction flow shown can be applied to Figure 3 In the system architecture shown, the generation process of product design is further introduced below by taking the generation of software product development process as an example.

[0049] First, obtain the user input text entered by the system designer through natural language description, such as "Help me generate an SRM procurement flowchart"; by parsing the user input text, determine the business type and business scenario corresponding to the software product to be developed. For example, the natural language in the user input text can be parsed by the AI ​​big model, and it can be analyzed that the business type corresponding to the above user input text is SRM, and the business scenario is procurement.

[0050] As an optional implementation, parsing user input text and determining the business type and business scenario corresponding to the software product to be developed includes the following steps: using a large language model to perform text cleaning on the user input text, and performing word segmentation on the cleaned user input text, wherein text cleaning is used to delete interference characters in the user input text, and the interference characters include at least one of the following: punctuation marks, special characters; determining the part of speech of each participle obtained after the word segmentation process, and deleting the part of speech of the part of speech being an adjective, wherein the part of speech includes at least one of the following: noun, verb, adjective; determining the demand information corresponding to the user input text based on the part of speech of the participle and the contextual position relationship between each participle in the user input text, wherein the demand information includes: business scenario, business type, functional requirements, user interface requirements, and performance indicators.

[0051] After determining the business type, business scenario and other demand information corresponding to the user input text, the process nodes corresponding to the business type, business scenario and other demand information in the underlying corpus can be obtained. Specifically, the 4A underlying corpus (process) can be called through AI to match the business type (SRM), scenario type (procurement) and the labels of each process node in the underlying corpus.

[0052] In an embodiment of the present application, in the process of matching keywords used to characterize demand information such as business types and business scenarios with labels of each process node in the underlying corpus, accurate matching can be performed first, and the specific steps are as follows.

[0053] In some embodiments of the present application, obtaining process nodes corresponding to business types and business scenarios in the underlying corpus includes the following steps: accurately matching the keywords used to characterize business types and business scenarios in the user input text with the labels corresponding to each process node in the underlying corpus, wherein the labels are used to characterize the business types and business scenarios corresponding to the process nodes; when the fields between the labels and the keywords are exactly the same, determining that the labels and keywords have been accurately matched successfully, and determining the process nodes that have been accurately matched successfully as the process nodes corresponding to the business types and business scenarios.

[0054] If the precise match fails to successfully match the process node corresponding to the business type, business scenario and other demand information in the underlying corpus, fuzzy matching can be used for further matching. The specific steps are as follows.

[0055] In some embodiments of the present application, the method also includes the following steps: when the keyword and all the tags in the underlying corpus are not accurately matched, determining the extended word corresponding to the keyword based on a preset synonym library, wherein the preset synonym library contains multiple groups of preset synonyms or near synonyms; determining the text similarity between the extended word and the tag, wherein the text similarity includes: literal similarity and semantic similarity, literal similarity is used to characterize the similarity between the character forms of two texts, and semantic similarity is used to characterize the similarity between the semantic meanings of two texts; determining the process node corresponding to the tag whose text similarity exceeds the preset similarity threshold as the process node corresponding to the business type and business scenario.

[0056] After determining the process nodes in the underlying corpus that correspond to the current business type, business scenario and other demand information, the logical connection relationship between each process node can be determined based on the historical software product development process in the underlying corpus that contains process nodes corresponding to the business type and business scenario to construct the software product development process. The specific steps are as follows.

[0057] In some embodiments of the present application, determining the logical connection relationship between each process node based on the historical software product development process containing process nodes corresponding to the business type and business scenario in the underlying corpus includes the following steps: among the process nodes corresponding to the business type and business scenario, screening the process nodes corresponding to the functional requirements, and determining the historical software product development process containing the screened process nodes in the underlying corpus; determining the execution order between the screened process nodes based on the requirement information corresponding to the user input text; obtaining the corresponding logical connection relationship between adjacent process nodes contained in the historical software product development process, and counting the frequency of occurrence of each logical connection relationship in the historical software product development process; determining the generation type of each logical connection relationship, wherein the generation type includes: automatically generated by the model, generated in response to the user's modification instructions; determining the score corresponding to each logical connection relationship based on the frequency of occurrence and the generation type, and determining the logical connection relationship with the highest score as the final logical connection relationship between adjacent process nodes, wherein the score is used to characterize the credibility of the logical connection relationship.

[0058] Specifically, after matching the process nodes that meet the business type SRM and procurement scenarios, the AI ​​model can be used to score the node combination scores according to the learned SRM, procurement multi-scenario process or the adjusted component priority of the user-generated procurement process. According to the high and low scores, the business activity components (process nodes) required for the next node are generated in turn, thereby generating a complete flowchart. Among them, the activity component (process node) in the corpus corresponds to pages, modeling, and services, which can be generated for system designers at one time.

[0059] The page and modeling generation process is the same as the process generation process, so I will not go into details here.

[0060] In addition, after generating the software product development process corresponding to the software product to be developed, the method further includes the following steps: the software product development process can be sent to the front-end interactive interface for display, so as to be viewed and reviewed by designers; the designers can adjust the software product development process generated by AI, that is, the system adjusts the software product development process when receiving the modification instruction inputted from the front-end interactive interface;

[0061] Alternatively, when the designer confirms that the AI-generated software product development process has passed the review, that is, when the verification pass instruction input from the front-end interactive interface is received, the software product development process can be stored as a historical software product development process in the underlying corpus, and corresponding labels can be added to each process node in the software product development process. The underlying corpus also includes: page component information, data field entities and node services corresponding to the process nodes in each historical software product development process.

[0062] The following is an introduction to the update of the underlying corpus and the training process of the artificial intelligence model. Figure 4 As shown, first sort out the business scenario process (BA), the system pages and personnel involved in the process nodes. Based on the information that the personnel at the process nodes need to operate, sort out the field information required by the page (DA), then design the product page (AA) based on the process node, associate and sort out the existing field information, and write the PRD. Based on the page, field and other information, design the corresponding service (TA). Through the above design process, after the product manager's logic is self-consistent, the logic of the entire product design is synchronized with the development side, the efficiency is high, and the product design reuse line is also high.

[0063] Based on the above design content, it is precipitated into the 4A corpus (i.e. the underlying corpus), and the domain, industry, product, and scenario characteristics are labeled according to the product level (i.e. corresponding labels are added to each process node in the software product development process); the process is inherited to the corresponding node, the page is inherited to the corresponding component, and the modeling is inherited to the corresponding field entity table; and the design association relationship between the process, modeling, page, and service is retained.

[0064] Specifically, the design is associated and deposited into the underlying corpus database through 4A. In the underlying corpus, the process is deposited into the corresponding node package according to the process node. The node package contains: node name and node page, page data model and services within the node. The node package will be marked according to industry, field, and product type. At the same time, the node package will be combined into a new process according to the algorithm through natural language input. The new process contains pages, data, and services in different nodes.

[0065] The prototype design will be precipitated into the corresponding page structure and components. The corresponding components will be bound to data modeling fields and service design. The corresponding page structure will be labeled with industry, field, and product type. According to the different industries, fields, and product types, the page combination design and generation will be carried out through page structure and common components. At the same time, the corresponding data modeling of the page and the service design of the corresponding components will be generated.

[0066] The modeling design will be precipitated into the corresponding business object, which contains entity fields and attributes. According to the fields entered by the user in natural language, they are automatically classified into business objects or entities through fuzzy matching of the algorithm to generate a new modeling table.

[0067] The service design will be deposited into the corresponding page components and process nodes, and automatically inherit the corresponding marking content.

[0068] In addition, based on the 4A corpus, corresponding artificial intelligence models can also be trained (deep learning models, decision trees) to learn the relationship and logic between different processes, pages, and modeling features. Apply the trained AI model to new input data to generate a design product with multiple process features, multiple page features, and multiple modeling features. And have corresponding association relationships (such as process nodes contain pages and entities; page generation contains entities).

[0069] Specifically, you can deploy an AI model. Before deployment, you need to install the environment and dependencies required for the model to run, and then load the 4A corpus data in the underlying corpus into the model; adjust the corresponding parameters of the model, including but not limited to: maximum sequence length, learning rate, GPU device number, dataset path, model path, set the fine-tuned model and log output path, etc., and finally train the model with the data in the underlying corpus.

[0070] This application solution can standardize the output of product design and quickly improve the corresponding product design efficiency through AI capabilities. It adopts a route that combines the digital transformation of the enterprise, defines new product design standards, and transforms traditional product design requirements. It can intuitively display the perfection and logic of product design, which is convenient for assessment. Based on structured product design, AI capabilities can be used to quickly assemble and generate corresponding product designs.

[0071] According to an embodiment of the present application, an embodiment of a software product development device is also provided. Figure 6 Schematic diagram of a software product development device provided according to an embodiment of the present application. Figure 6 As shown, the device comprises:

[0072] The text acquisition module 60 is used to acquire the user input text and determine the business type and business scenario corresponding to the software product to be developed by parsing the user input text, wherein the user input text is a natural language text describing the design requirements of the software product;

[0073] The node selection module 62 is used to obtain the process nodes corresponding to the business type and business scenario in the underlying corpus, wherein the underlying corpus stores: the historical software product development process that has been generated and passed the verification, and the process nodes in the historical software product development process;

[0074] The process generation module 64 is used to determine the logical connection relationship between each process node based on the historical software product development process containing process nodes corresponding to the business type and business scenario in the underlying corpus, and generate a software product development process corresponding to the software product to be developed.

[0075] Optionally, parsing the user input text and determining the business type and business scenario corresponding to the software product to be developed includes: using a large language model to perform text cleaning on the user input text, and performing word segmentation on the cleaned user input text, wherein text cleaning is used to delete interference characters in the user input text, and the interference characters include at least one of the following: punctuation marks, special characters; determining the part of speech of each participle obtained after the word segmentation process, and deleting the part of speech of the part of speech being an adjective, wherein the part of speech includes at least one of the following: noun, verb, adjective; determining the demand information corresponding to the user input text based on the part of speech of the participle and the contextual position relationship between each participle in the user input text, wherein the demand information includes: business scenario, business type, functional requirements, user interface requirements, and performance indicators.

[0076] Optionally, obtaining the process nodes corresponding to the business types and business scenarios in the underlying corpus includes: accurately matching the keywords used to characterize the business types and business scenarios in the user input text with the labels corresponding to each process node in the underlying corpus, wherein the labels are used to characterize the business types and business scenarios corresponding to the process nodes; when the fields between the labels and the keywords are exactly the same, it is determined that the labels and keywords are accurately matched successfully, and the process nodes that are accurately matched successfully are determined as the process nodes corresponding to the business types and business scenarios.

[0077] Optionally, the node selection module 62 is also used for: when the keyword and all the labels in the underlying corpus are not accurately matched, determining the expansion word corresponding to the keyword based on a preset synonym library, wherein the preset synonym library contains multiple groups of preset synonyms or near synonyms; determining the text similarity between the expansion word and the label, wherein the text similarity includes: literal similarity and semantic similarity, literal similarity is used to characterize the similarity between the character forms of two texts, and semantic similarity is used to characterize the similarity between the semantic meanings of two texts; determining the process node corresponding to the label whose text similarity exceeds the preset similarity threshold as the process node corresponding to the business type and business scenario.

[0078] Optionally, determining the logical connection relationship between each process node based on the historical software product development process containing process nodes corresponding to the business type and business scenario in the underlying corpus includes: screening the process nodes corresponding to the functional requirements among the process nodes corresponding to the business type and business scenario, and determining the historical software product development process containing the screened process nodes in the underlying corpus; determining the execution order between the screened process nodes based on the requirement information corresponding to the user input text; obtaining the corresponding logical connection relationship between adjacent process nodes contained in the historical software product development process, and counting the frequency of occurrence of each logical connection relationship in the historical software product development process; determining the generation type of each logical connection relationship, wherein the generation type includes: automatically generated by the model, generated in response to the user's modification instructions; determining the score corresponding to each logical connection relationship based on the frequency of occurrence and the generation type, and determining the logical connection relationship with the highest score as the final logical connection relationship between adjacent process nodes, wherein the score is used to characterize the credibility of the logical connection relationship.

[0079] Optionally, after generating the software product development process corresponding to the software product to be developed, the software product development device is also used to: send the software product development process to the front-end interactive interface for display; adjust the software product development process when receiving a modification instruction input from the front-end interactive interface; or, when receiving a verification pass instruction input from the front-end interactive interface, store the software product development process as a historical software product development process in the underlying corpus, and add corresponding labels to each process node in the software product development process.

[0080] Optionally, the underlying corpus also includes: page component information, data field entities and node services corresponding to process nodes in each historical software product development process.

[0081] It should be noted that the various modules in the above-mentioned software product development device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0082] It should be noted that the software product development device provided in this embodiment can be used to execute Figure 2 The software product development method shown, therefore, the relevant explanations and instructions on the above-mentioned software product development method are also applicable to the embodiments of the present application and will not be repeated here.

[0083] The embodiment of the present application also provides a non-volatile storage medium, the non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following software product development method by running the computer program: obtaining user input text, and determining the business type and business scenario corresponding to the software product to be developed by parsing the user input text, wherein the user input text is a natural language text that describes the design requirements of the software product; obtaining process nodes corresponding to the business type and business scenario in the underlying corpus, wherein the underlying corpus stores: historical software product development processes that have been generated and verified, and process nodes in the historical software product development processes; determining the logical connection relationship between each process node based on the historical software product development process containing process nodes corresponding to the business type and business scenario in the underlying corpus, and generating a software product development process corresponding to the software product to be developed.

[0084] The embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the software product development method described in each embodiment of the present application: obtaining user input text, and determining the business type and business scenario corresponding to the software product to be developed by parsing the user input text, wherein the user input text is a natural language text that describes the design requirements of the software product; obtaining process nodes corresponding to the business type and business scenario in the underlying corpus, wherein the underlying corpus stores: historical software product development processes that have been generated and passed verification, and process nodes in the historical software product development processes; based on the historical software product development processes that contain process nodes corresponding to the business type and business scenario in the underlying corpus, determining the logical connection relationship between each process node, and generating a software product development process corresponding to the software product to be developed.

[0085] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0086] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0087] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0088] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0089] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0090] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0091] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A software product development method, characterized in that: include: Acquire a user input text, and determine the business type and business scenario corresponding to the software product to be developed by parsing the user input text, wherein the user input text is a natural language text describing the design requirements of the software product; Obtaining a process node corresponding to the business type and the business scenario in an underlying corpus, wherein the underlying corpus stores: a historical software product development process that has been generated and passed verification, and process nodes in the historical software product development process; Based on the historical software product development process containing the process nodes corresponding to the business type and the business scenario in the underlying corpus, the logical connection relationship between each of the process nodes is determined, and the software product development process corresponding to the software product to be developed is generated.

2. The software product development method according to claim 1, characterized in that: Parsing the user input text to determine the business type and business scenario corresponding to the software product to be developed includes: Using a large language model, the user input text is cleaned, and the cleaned user input text is segmented, wherein the text cleaning is used to delete interference characters in the user input text, and the interference characters include at least one of the following: punctuation marks, special characters; Determine the part of speech of each participle obtained after the word segmentation processing, and delete the participle whose part of speech is adjective, wherein the part of speech includes at least one of the following: noun, verb, adjective; Determine the demand information corresponding to the user input text based on the part of speech of the word segment and the contextual position relationship between each word segment in the user input text, wherein the demand information includes: business scenario, business type, functional requirements, user interface requirements, and performance indicators.

3. The software product development method according to claim 2, characterized in that: Acquiring a process node corresponding to the business type and the business scenario in the underlying corpus includes: Accurately matching the keywords used to characterize the business type and the business scenario in the user input text with the labels corresponding to each of the process nodes in the underlying corpus, wherein the labels are used to characterize the business type and the business scenario corresponding to the process nodes; In the case that the fields between the tag and the keyword are completely identical, it is determined that the tag and the keyword are accurately matched successfully, and the process node with the accurate match is determined as the process node corresponding to the business type and the business scenario.

4. The software product development method according to claim 3, characterized in that: The method further comprises: In the case that the keyword and all the tags in the underlying corpus are not accurately matched, the extended word corresponding to the keyword is determined according to a preset synonym library, wherein the preset synonym library contains multiple groups of preset synonyms or near synonyms; Determining the text similarity between the expanded word and the label, wherein the text similarity includes: literal similarity and semantic similarity, the literal similarity is used to represent the similarity between the character forms of the two texts, and the semantic similarity is used to represent the similarity between the semantic meanings of the two texts; The process node corresponding to the tag whose text similarity exceeds a preset similarity threshold is determined as a process node corresponding to the business type and the business scenario.

5. The software product development method according to claim 3, characterized in that: Determining the logical connection relationship between each of the process nodes according to the historical software product development process containing the process nodes corresponding to the business type and the business scenario in the underlying corpus includes: Filtering the process nodes corresponding to the functional requirements among the process nodes corresponding to the business type and the business scenario, and determining the historical software product development process that contains the filtered process nodes in the underlying corpus; Determining the execution order of each selected process node according to the requirement information corresponding to the user input text; Obtaining corresponding logical connection relationships between adjacent process nodes contained in the historical software product development process, and counting the occurrence frequency of each logical connection relationship in the historical software product development process; Determining a generation type of each of the logical connection relationships, wherein the generation type includes: automatically generated by a model, generated in response to a modification instruction of a user; Based on the occurrence frequency and the generation type, the score corresponding to each of the logical connection relationships is determined, and the logical connection relationship with the highest score is determined as the final logical connection relationship between the adjacent process nodes, wherein the score is used to characterize the credibility of the logical connection relationship.

6. The software product development method according to claim 3, characterized in that: After generating the software product development process corresponding to the software product to be developed, the method further includes: Sending the software product development process to the front-end interactive interface for display; Upon receiving a modification instruction inputted through the front-end interactive interface, adjusting the software product development process; or, When a verification pass instruction inputted from the front-end interactive interface is received, the software product development process is stored in the underlying corpus as the historical software product development process, and corresponding labels are added to each process node in the software product development process.

7. The software product development method according to claim 6, characterized in that: The underlying corpus also includes: page component information, data field entities and node services corresponding to the process nodes in each of the historical software product development processes.

8. A software product development device, characterized in that: include: A text acquisition module is used to acquire user input text and determine the business type and business scenario corresponding to the software product to be developed by parsing the user input text, wherein the user input text is a natural language text describing the design requirements of the software product; A node selection module, used for obtaining a process node corresponding to the business type and the business scenario in an underlying corpus, wherein the underlying corpus stores: a historical software product development process that has been generated and passed verification, and process nodes in the historical software product development process; A process generation module is used to determine the logical connection relationship between each process node based on the historical software product development process containing the process nodes corresponding to the business type and the business scenario in the underlying corpus, and generate a software product development process corresponding to the software product to be developed.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program executes the software product development method according to any one of claims 1 to 7 when running.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the software product development method according to any one of claims 1 to 7 by running the computer program.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the software product development method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Service process generation method and device, electronic equipment and medium

    CN113887941A

  • Business process modeling method and device, terminal equipment and storage medium

    CN117314139A

  • Business flow chart generation method, processing equipment and storage medium

    CN117608650A

Cited By

  • Artificial intelligence assistant injection method, device and equipment and computer readable medium

    CN119149060A

  • Method and device for generating software based on large model technology, medium and electronic equipment

    CN120085843A

  • Method, apparatus, medium and electronic device for generating software based on large model technology

    CN120085843B

  • MOM scene component identification method, system and device based on dynamic chain type process and medium

    CN120873871A

  • Intelligent connection method, system and equipment for task flow processing nodes

    CN121256385A