Page development method and device based on artificial intelligence, equipment and storage medium

Abstract

The invention belongs to the field of artificial intelligence, and relates to an artificial intelligence-based page development method, which comprises the following steps of: receiving a page demand document, and analyzing the page demand document to obtain a business logic demand and an interface design demand of the page demand document; matching a service component corresponding to the service logic demand from a preset component library, and configuring by using the service component according to the service logic demand to obtain an initial component configuration scheme; obtaining a target interface design draft corresponding to the interface design demand from a preset interface library, and analyzing the target interface design draft to obtain interface design information; integrating the interface design information and the initial component configuration scheme to obtain a target component configuration scheme, and generating a target visual interface on a preset low-code platform according to the target component configuration scheme to obtain a target page. In addition, the invention also relates to a block chain technology, and the target page and the like can be stored in a block chain. According to the method, the page development efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a page development method based on artificial intelligence. Background Art

[0002] With the continuous advancement of artificial intelligence technology, its application in multiple fields is becoming more and more extensive, especially in the field of automated processing. In the field of software page development, the traditional software page development model requires developers to manually understand product requirements, manually drag in nested components, bind variables and write a lot of business logic code according to product requirements to obtain the final software page. It can be seen that the traditional software page development model requires a lot of manual operations, resulting in low efficiency and accuracy of page development.

[0003] At present, in order to avoid the problem of low efficiency and accuracy of page development caused by the traditional page development model, low-code is used to develop pages. As an important tool for rapid application development, low-code platforms are showing a diversified trend in the market. Among them, low-code is a visual software development method that aims to enable users to deliver applications with less code and faster speed by minimizing the amount of manual coding and introducing visual development tools.

[0004] Although low-code page development can improve efficiency and accuracy compared to traditional page development methods, manual intervention is still required, and there are technical problems such as low page development efficiency and accuracy. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a page development method, device, equipment and storage medium based on artificial intelligence, the main purpose of which is to improve the efficiency and accuracy of page development.

[0006] In order to solve the above technical problems, the embodiment of the present application provides a page development method based on artificial intelligence, which adopts the following technical solutions:

[0007] Receiving a page requirement document, parsing the page requirement document, and obtaining business logic requirements and interface design requirements of the page requirement document;

[0008] According to the business logic requirements, matching business components corresponding to the business logic requirements from a preset component library, using the business components to perform configuration according to the business logic requirements, and obtaining an initial component configuration solution;

[0009] Acquire a target interface design draft corresponding to the interface design requirement from the preset interface library, and parse the target interface design draft to obtain interface design information;

[0010] The interface design information and the initial component configuration plan are integrated to obtain a target component configuration plan. According to the target component configuration plan, a target visualization interface is generated on a preset low-code platform to obtain a target page.

[0011] Furthermore, the page requirement document is parsed to obtain the business logic requirements and interface design requirements of the page requirement document, including:

[0012] Performing word segmentation and part-of-speech tagging processing on the page requirement document to obtain a word segmentation set with part-of-speech tags;

[0013] Convert all the word segments in the word segmentation set into vector representations to obtain a word segmentation vector set;

[0014] Using a pre-trained page demand extraction model to process the word segmentation vector set, to obtain a target demand set with classification labels;

[0015] The target requirement set is classified according to the classification labels to obtain the business logic requirements and the interface design requirements.

[0016] Furthermore, matching the business components corresponding to the business logic requirements from the preset component library includes:

[0017] Extracting keywords and function requirement parameters of each of the business logic requirements, and obtaining keywords and component specifications of each of the business components in the preset component library;

[0018] Based on each of the business logic requirements, initially matching the keywords of all business components according to the keywords of each of the business logic requirements to obtain an initial business component set;

[0019] A secondary match is performed on the component specifications in the initial business component set according to the functional requirement parameters of each business logic requirement to obtain a business component corresponding to each business logic requirement.

[0020] Furthermore, after initially matching the keywords of all business components based on the keywords of each business logic requirement to obtain an initial business component set, the method further includes:

[0021] Identifying the number of the initial set of business components;

[0022] When it is identified that the number of the initial business component set is zero, writing a design document for a newly added business component according to the functional requirement parameters of the business logic requirement;

[0023] According to the design document, a preset development language is used to develop components to obtain the newly added business components;

[0024] The newly added business component is used as the business component corresponding to the business logic requirement.

[0025] Further, the using the business component to configure according to the business logic requirements to obtain an initial component configuration scheme includes:

[0026] Based on each of the business logic requirements, function configuration is performed through the corresponding business components to obtain a specific function set;

[0027] The specific function set is integrated to obtain the initial component configuration solution.

[0028] Furthermore, the step of acquiring a target interface design draft corresponding to the interface design requirement from the preset interface library includes:

[0029] Obtaining basic interface information of each interface design draft in the preset interface library, wherein the basic interface information includes interface design field, interface design style, and number of interface components;

[0030] Obtaining basic information of the interface design requirements, wherein the basic information includes the required design field, required design style, and required component quantity;

[0031] The basic information of the interface design requirement is matched with the basic interface information of each interface design draft in the preset interface library. When the basic information of the requirement is completely consistent with the basic interface information, the target interface design draft corresponding to the interface design requirement is obtained.

[0032] Furthermore, the target interface design draft is parsed to obtain interface design information, including:

[0033] Detect the target interface design draft through a target detection model, identify an element set in the target interface design draft, and extract position information of each element from the element set;

[0034] Extracting features from the element set and position information of each element using a pre-trained hierarchical extraction model to obtain hierarchical relationship features, and calculating the hierarchical relationship between the element sets based on the hierarchical relationship features;

[0035] Extracting visual features of the target interface design draft through a pre-trained design style recognition model, calculating the visual features through a preset classification algorithm, and obtaining the design style of the target interface design draft;

[0036] The element set and position information of each element, the hierarchical relationship between the element sets, and the design style of the target interface design draft are collected to obtain the interface design information.

[0037] In order to solve the above technical problems, the embodiment of the present application further provides a page development device based on artificial intelligence, which adopts the following technical solution:

[0038] A receiving module, used to receive a page requirement document, parse the page requirement document, and obtain business logic requirements and interface design requirements of the page requirement document;

[0039] A configuration module, used to match business components corresponding to the business logic requirements from a preset component library according to the business logic requirements, and use the business components to perform configuration according to the business logic requirements to obtain an initial component configuration solution;

[0040] A parsing module, used to obtain a target interface design draft corresponding to the interface design requirement from the preset interface library, and parse the target interface design draft to obtain interface design information;

[0041] An integration module is used to integrate the interface design information and the initial component configuration plan to obtain a target component configuration plan, and generate a target visualization interface on a preset low-code platform according to the target component configuration plan to obtain a target page.

[0042] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the artificial intelligence-based page development method as described above.

[0043] In order to solve the above technical problems, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned artificial intelligence-based page development method.

[0044] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0045] By parsing the page requirement document, the business logic requirements and interface design requirements of the page requirement document are obtained, thereby avoiding the problems of low efficiency and accuracy caused by manual intervention, and improving the efficiency and accuracy of subsequent page development;

[0046] By matching components corresponding to business logic requirements from the preset component library, errors caused by manual component selection are avoided, improving the accuracy and efficiency of subsequent page development;

[0047] Obtaining a target interface design draft corresponding to the interface design requirement from the preset interface library, parsing the target interface design draft to obtain interface design information, thereby avoiding the need for manual dragging when subsequently generating a page, thereby improving the efficiency of page generation and ensuring the consistency and accuracy of the design;

[0048] By mapping the initial component configuration scheme to the interface design information, there is no need to manually adjust the position, size, and design style of each component, which improves the efficiency of page development. By parsing information from the existing target design draft, the original design information is retained, thereby retaining the fluidity and beauty of the original scheme, improving the user experience. In addition, the integrated target component configuration scheme has a clear structure and rigorous logic, which facilitates subsequent development and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0051] Figure 2 A flowchart of an embodiment of the method for developing a page based on artificial intelligence according to the present application;

[0052] Figure 3 is a structural schematic diagram of an embodiment of an artificial intelligence-based page development device according to the present application;

[0053] Figure 4 It is a structural schematic diagram of an embodiment of a device according to the present application. DETAILED DESCRIPTION

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0055] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0056] 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 accompanying drawings.

[0057] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0058] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0059] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0060] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0061] It should be noted that the artificial intelligence-based page development method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based page development device is generally set in the server / terminal device.

[0062] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0063] Continue to refer Figure 2 , showing a flow chart of an embodiment of an artificial intelligence-based page development method according to the present application. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted. The artificial intelligence-based page development method provided in the embodiment of the present application can be applied to any scenario that requires artificial intelligence-based page development, and the artificial intelligence-based page development method can be applied to products in these scenarios. The artificial intelligence-based page development method includes the following steps:

[0064] Step S201: receiving a page requirement document, parsing the page requirement document, and obtaining business logic requirements and interface design requirements of the page requirement document;

[0065] In this embodiment, the electronic device (e.g. Figure 1The server / terminal device shown in the figure) can receive the page requirement document uploaded by the user through a wired connection or a wireless connection. It should be pointed out that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future. The executor of the present application may be a page requirement extraction model, or simply referred to as a model. The above-mentioned page requirement document usually has the same format as the page document training data used in the training of the page requirement extraction model, but the training data contains other noise, depending on the specific situation. Among them, in the business scenario of extracting page requirement documents, the page requirement document data may include page requirement documents automatically generated by artificial intelligence (AI) or manually written page requirement documents.

[0066] In this embodiment, the above-mentioned page requirement document (Requirement Document) refers to a document of detailed page design requirements and functional requirements proposed by the user for the target page finally developed; by parsing the page requirement document, some functional key points of the page requirement document are understood, and then the business logic requirements and interface design requirements of the page requirement document are parsed according to the above functional key points.

[0067] In this embodiment, when a page design document uploaded by a user is received, a text preprocessing operation is performed on the page design document. Specifically, the above-mentioned text preprocessing operation includes but is not limited to a text cleaning operation, removing irrelevant characters, punctuation marks, special symbols, etc., so as to reduce the noise of the page requirement document and improve the quality of the page requirement document; a character standardization operation, converting the format of the text in the page requirement document according to a pre-set format, wherein the text is not limited to Chinese characters, but also includes English characters, such as uppercase and lowercase format conversion; a word segmentation operation, performing a word segmentation operation on the page requirement document to obtain a word segmentation set corresponding to the page requirement document, and obtaining a preprocessed page requirement document.

[0068] In one embodiment, the parsing of the page requirement document to obtain the business logic requirements and interface design requirements of the page requirement document includes:

[0069] Performing word segmentation and part-of-speech tagging processing on the page requirement document to obtain a word segmentation set with part-of-speech tags;

[0070] Convert all the word segments in the word segmentation set into vector representations to obtain a word segmentation vector set;

[0071] Using a pre-trained page demand extraction model to process the word segmentation vector set, to obtain a target demand set with classification labels;

[0072] The target requirement set is classified according to the classification labels to obtain the business logic requirements and the interface design requirements.

[0073] In this embodiment, the pre-trained page demand extraction model refers to a transformer model, which includes an input layer, an encoding layer, a classification head and an output layer; a preset word segmentation tool (such as Jieba word segmentation tool, etc.) is used to perform word segmentation on the pre-processed page demand document to obtain a word segmentation set, and a part-of-speech tagging tool is used to perform part-of-speech tagging on each word in the word segmentation set to obtain a word segmentation set with part-of-speech tags, and each word in the word segmentation set is converted into a vector representation through a vector conversion technology (such as Word2Vec, BERT, etc.) to obtain a word segmentation vector. The set can also be transformed into a vector representation by adding an embedding layer to a pre-trained page demand model; the word segmentation vector set is processed by a pre-trained page demand extraction model, and the features of the word segmentation vector set are extracted by a self-attention mechanism through an encoding layer, and the features of the word segmentation vector set are predicted through a classification head to obtain a target demand set with classification labels, and the target demand set is classified according to the classification labels, and finally the business logic requirements and interface design requirements are output through an output layer; it is worth mentioning that the above-mentioned document demand extraction model can also be extracted through architectures such as a recurrent neural network (RNN).

[0074] In this embodiment, the page requirement document is parsed through a pre-trained page requirement model to obtain business logic requirements and interface design requirements, and the requirements of the page requirement document can be automatically parsed, thereby improving the recognition efficiency of the page requirement document; and avoiding errors caused by manual understanding of the requirement document, thereby improving the parsing accuracy of the page requirement document.

[0075] In another embodiment, before using the pre-trained page requirement extraction model to process the word segmentation vector set to obtain a target requirement set with classification labels, the method further includes:

[0076] Obtaining a labeled requirement document dataset, and dividing the labeled document dataset into a training set and a test set according to a preset ratio;

[0077] Constructing an initial page demand extraction model, and using the training set to train the initial page demand extraction model to obtain an intermediate page demand extraction model;

[0078] Testing the intermediate page demand extraction model through a test set to obtain a loss value;

[0079] When the loss value is less than or equal to a preset loss threshold, obtaining the pre-trained page demand extraction model;

[0080] When the loss value is greater than the preset loss threshold, the initial page demand extraction model is continuously trained using the training set until the loss value is less than or equal to the preset loss threshold, and the training is completed to obtain the pre-trained page demand extraction model.

[0081] In this embodiment, a large number of annotated demand document data sets are obtained, for example, business logic requirements and interface design requirements are annotated. A large number of annotated demand document data sets are split into training sets and test sets according to a preset ratio; the initial page demand extraction model is trained with the training set to obtain an intermediate page demand extraction model; the intermediate page demand extraction model is tested with the test set to obtain a loss value, and it is determined whether the loss value is less than or equal to a preset loss threshold. When the loss value is less than or equal to the preset loss threshold, the training is completed to obtain a pre-trained page demand extraction model. When the loss value is greater than the preset loss threshold, the initial page demand extraction model is continuously trained with the training set until the loss value is less than or equal to the preset loss threshold, the training is terminated to obtain a pre-trained page demand extraction model. The above-mentioned loss value may refer to the probability of accurate prediction.

[0082] In this embodiment, by parsing the page requirement document, the business logic requirements and interface design requirements of the page requirement document are obtained, thereby avoiding the problems of low efficiency and accuracy caused by manual intervention and improving the efficiency and accuracy of subsequent page development.

[0083] S202: According to the business logic requirement, match the business components corresponding to the business logic requirement from the preset component library, use the business components to configure according to the business logic requirement, and obtain an initial component configuration solution.

[0084] In this embodiment, the logic requirements include but are not limited to CRUD, search, export, and positive correlation between the two parties (for example, if the user selects a higher insurance compensation amount, the premium amount will also increase accordingly), etc.; the pre-set component library includes business components corresponding to various business logics, such as CRUD components, search components, export components, correlation calculation components, etc.;

[0085] After parsing the business logic requirements, match the business components corresponding to each business logic requirement from the preset component library according to the business logic requirements, configure the components corresponding to each business logic requirement, and configure the corresponding functions of each component, such as configuring data sources, data tables, field mappings, etc. through CRUD components, configuring search conditions, index fields, search result display methods, etc. through search components, configuring export formats, data fields, export trigger conditions, etc. through export components, configuring input variables (such as compensation amount), output variables (such as premium amount), and calculation rules (linear relationship, nonlinear relationship, etc.) through positive correlation configuration components, integrating the configured components and the functions of component configurations to obtain an initial component configuration plan.

[0086] In one embodiment, matching the business components corresponding to the business logic requirements from the preset component library includes:

[0087] Extracting keywords and function requirement parameters of each of the business logic requirements, and obtaining keywords and component specifications of each of the business components in the preset component library;

[0088] Based on each of the business logic requirements, initially matching the keywords of all business components according to the keywords of each of the business logic requirements to obtain an initial business component set;

[0089] A secondary match is performed on the component specifications in the initial business component set according to the functional requirement parameters of each business logic requirement to obtain a business component corresponding to each business logic requirement.

[0090] In this embodiment, keywords and function requirement parameters corresponding to each business logic requirement are extracted, such as the keywords of the export function are: "export", "data export"; the function requirement parameters include but are not limited to the export format, data range, trigger conditions, etc.; and the keywords and component specifications of each business component in the preset component library are obtained, such as the keyword of the export component is "export", wherein the component specification is pre-defined, recording a detailed description of the business component, and the description of the component is formalized to obtain the component specification; first, for each business logic requirement, the keywords are first matched with the keywords of all components in the preset component library to screen out an initial business component set, wherein the initial business component set includes zero, and the keyword matching algorithm includes but is not limited to Limited to exact matching algorithm, fuzzy matching algorithm, semantic matching algorithm, maximum matching algorithm, etc.; secondly, when the number of the initial business component set is not zero, a secondary matching is performed through the functional parameters of the business logic requirements and the component specifications of the initial business component set, and according to the results of the functional matching, a matching score of each candidate business component is obtained, indicating the degree to which it meets the requirements; according to the matching score of each candidate component, the business component with the highest matching score is determined as the business component corresponding to the business logic requirement. The implementation method of the secondary matching can use the functional requirement parameters of the business logic requirements to calculate the similarity with each functional parameter of the component specification, and all scores in the functional requirement parameters are calculated by weighted average to obtain the matching score of each candidate business component.

[0091] In this embodiment, two screenings are performed by keyword screening and function requirement parameter screening, which can quickly match components corresponding to business logic requirements from the preset component library, avoid matching all components one by one, and improve the efficiency of component matching; secondary matching is performed on the basis of the initial matching, which can further locate the business components corresponding to the business logic requirements, reduce the possibility of mismatching and missed matching, and improve the accuracy of business component matching.

[0092] In another embodiment, after initially matching the keywords of all business components based on the keywords of each business logic requirement to obtain an initial business component set, the method further includes:

[0093] Identifying the number of the initial set of business components;

[0094] When it is identified that the number of the initial business component set is zero, writing a design document for a newly added business component according to the functional requirement parameters of the business logic requirement;

[0095] According to the design document, a preset development language is used to develop components to obtain the newly added business components;

[0096] The newly added business component is used as the business component corresponding to the business logic requirement.

[0097] In this embodiment, when it is identified that the number of the business component set is zero, it indicates that there is no component corresponding to the business logic requirement in the preset component library, and a new component needs to be created to complete the function of the business logic requirement. According to the functional requirement parameters of the business logic requirement, the architecture and logic of the newly added component are designed by artificial intelligence (AI) and other methods, including data flow, business logic processing, exception handling, etc., and the interface and data structure of the component are determined, and the contents of each part are gradually written according to the above architecture and logic to obtain the design document of the newly added business component. According to the design document, a preset development language (such as JAVA, etc.) is used, or the corresponding component code is written according to the design document, and the new business component is developed through the component code, and the new business component is tested through the test case corresponding to the new business component until the new business component meets the functional requirements of the business logic requirement, the test is stopped, and the new business component is used as the business component corresponding to the business logic requirement, and the new business component is stored in the preset component library.

[0098] In this embodiment, the number of initial business component sets is identified to determine whether there is a business component corresponding to the business logic requirements in the preset component library. If not, a corresponding business component is added according to the functional requirement parameters of the business logic and stored in the preset component library to meet customization requirements, improve the efficiency of subsequent page generation, and enrich the content of the preset component library.

[0099] In one embodiment, the using the business component to configure according to the business logic requirements to obtain an initial component configuration solution includes:

[0100] Based on each of the business logic requirements, function configuration is performed through the corresponding business components to obtain a specific function set;

[0101] The specific function set is integrated to obtain the initial component configuration solution.

[0102] In this embodiment, based on each business logic requirement, function configuration is performed through the components corresponding to the business logic requirement to obtain specific functions corresponding to each business component, such as configuring data sources, data tables, field mappings, etc. through CRUD components, configuring search conditions, index fields, search result display methods, etc. through search components, configuring export formats, data fields, export trigger conditions, etc. through export components, and configuring input variables (such as compensation amount), output variables (such as premium amount), and calculation rules (linear relationship, nonlinear relationship, etc.) through positive correlation configuration components; the specific functions of all component configurations are collected to obtain a specific function set, and then the configured business components and specific function sets are integrated to obtain an initial component configuration plan, the initial component configuration plan is tested through preset samples or testing tools, and the initial component configuration plan is adjusted and optimized according to the test results.

[0103] In this embodiment, by integrating all components and corresponding specific functions to form an initial component configuration plan, not only the efficiency of subsequent page development is improved, but also the consistency and maintainability of the components are ensured, and the initial component configuration plan is tested to prevent the initial component configuration plan from failing to achieve the preset effect due to component damage.

[0104] In this embodiment, by matching components corresponding to business logic requirements from a preset component library, errors caused by manual selection of components are avoided, thereby improving the accuracy and efficiency of subsequent page development.

[0105] S203: Acquire a target interface design draft corresponding to the interface design requirement from a preset interface library, and parse the target interface design draft to obtain interface design information.

[0106] In this embodiment, the interface design requirements include but are not limited to component quantity requirements, design style requirements, etc. According to the interface design requirements, an interface design draft corresponding to the interface design requirements is matched from a preset interface library. The preset interface design draft can exist in the form of a picture or in the form of a file. The interface design information is obtained by parsing the preset interface design draft.

[0107] In one embodiment, the step of acquiring a target interface design draft corresponding to the interface design requirement from a preset interface library includes:

[0108] Obtaining basic interface information of each interface design draft in the preset interface library, wherein the basic interface information includes interface design field, interface design style, and number of interface components;

[0109] Obtaining basic information of the interface design requirements, wherein the basic information includes the required design field, required design style, and required component quantity;

[0110] The basic information of the interface design requirement is matched with the basic interface information of each interface design draft in the preset interface library. When the basic information of the requirement is completely consistent with the basic interface information, the target interface design draft corresponding to the interface design requirement is obtained.

[0111] In this embodiment, the preset interface library includes interface design drafts of multiple different fields (such as insurance field, shopping field, etc.), different design styles (such as theme color and interface layout, etc.), and different numbers of interface components (such as 5 components, etc.); the basic interface information of each interface design draft in the preset interface library is obtained, and the basic interface information includes the interface design field, interface design style, and the number of interface components, and then the basic information of the interface design requirements is obtained, and the basic information of the requirements includes the required design field, the required design style, and the number of required components. When each specific requirement of the interface design requirement is consistent with the basic information of the interface design draft, the interface is determined. The interface design draft is the target interface design draft corresponding to the interface design requirements. For example, the basic information of the requirements is the insurance field, the cascading design style and the number of components is 5. According to the above basic information of the requirements, the interface design drafts with the number of components being 5 are screened out from the preset interface library to obtain the first interface design draft set, and then the interface design drafts with the cascading design style are screened out from the first design draft set according to the cascading design style to obtain the second interface design draft set, and then the final target interface design draft is determined from the second interface design draft set according to the insurance field. It is worth mentioning that the above order is not specified, and the first design draft set can also be determined first according to the insurance field.

[0112] In this embodiment, by matching the corresponding target interface design draft from the preset interface library, manual creation of interface templates is prevented, thereby improving the efficiency of subsequent page development.

[0113] Since the interface design drafts in the preset interface library exist in the form of files or pictures, in order to prevent the interface design drafts from being unable to be parsed, the interface design drafts need to be converted into specific image formats (such as PNG, JPG, etc.) or design files (such as Sketch source files, etc.). When the interface design draft is in image format, the interface design draft also needs to be pre-processed with image enhancement, denoising, and other steps to improve the accuracy of subsequent interface design information extraction.

[0114] In one embodiment, parsing the target interface design draft to obtain interface design information includes:

[0115] Detect the target interface design draft through a target detection model, identify an element set in the target interface design draft, and extract position information of each element from the element set;

[0116] Extracting features from the element set and position information of each element using a pre-trained hierarchical extraction model to obtain hierarchical relationship features, and calculating the hierarchical relationship between the element sets based on the hierarchical relationship features;

[0117] Extracting visual features of the target interface design draft through a pre-trained design style recognition model, calculating the visual features through a preset classification algorithm, and obtaining the design style of the target interface design draft;

[0118] The element set and position information of each element, the hierarchical relationship between the element sets, and the design style of the target interface design draft are collected to obtain the interface design information.

[0119] In this embodiment, the target interface design draft is parsed by an interface design information extraction model to extract the interface design information of the target interface design draft, wherein the interface design information includes element set (such as buttons, etc.) information, position information corresponding to each element, hierarchical information between elements, and design style information; the preset interface design information extraction model includes a target detection model, a hierarchical extraction model, and a design style recognition model, the target detection model and the hierarchical extraction model refer to a convolutional neural network (CNN), and the design style recognition model refers to a recurrent neural network (RNN); the target detection model and the hierarchical extraction model are end-to-end connected, with the purpose of outputting the position information corresponding to the element information of the element information set output by the target detection model to the hierarchical extraction model.

[0120] In this embodiment, the target interface design draft is first detected by the target detection model, and the target interface design draft is input into the target detection model. The feature information is gradually extracted through the convolution layer and pooling layer of the target detection model. The feature information includes edge features, etc., and then the various elements in the target interface design draft are detected through the region proposal network (RPN), region of interest pooling (POIPooling) and other technologies. An element mapping table can also be constructed, which records the edge frame of each element. When the extracted features are consistent with the element mapping table, they are determined to be the elements corresponding to the mapping table; and the position information of each element is marked from the pre-constructed two-dimensional coordinate system.

[0121] Secondly, the element set and the position information corresponding to the elements are input into the hierarchical extraction model, and each element information is detected by the hierarchical extraction model. The hierarchical extraction model is used to detect the hierarchical relationship features of each element respectively, and the hierarchical relationship features include but are not limited to shadow features; if the hierarchical relationship features have shadow features, it is determined that the element has a hierarchical relationship, and the elements with a hierarchical relationship with the element are found through the position information. The specific method is: find the specific nearest element according to the position information of the element, and make a difference in the position information of the two elements. If the difference is within a preset difference threshold, it is determined that there is a hierarchical relationship between the two elements. If not, it is determined that there is no hierarchical relationship between the two elements. All elements are traversed to obtain the hierarchical relationship between the element sets.

[0122] Finally, the target interface design draft is feature extracted through the pre-trained design style recognition model, specifically: extracting the visual feature information (such as color distribution, texture features, etc.) of the target interface design draft, identifying the design style of the target interface design draft through a classification algorithm (such as support vector machine, etc.), and outputting the design style label corresponding to the design style; collecting the element set and the position information of each element, the hierarchical connection between the element sets, and the design style of the target interface design draft to obtain the interface design information.

[0123] In this embodiment, the target interface design draft is parsed through multiple models, which avoids manual identification and improves the accuracy and efficiency of page parsing; and the extracted page design information includes the comprehensiveness of the page design, providing a basis for subsequent target page generation, thereby improving the efficiency of subsequent page generation.

[0124] In this embodiment, a target interface design draft corresponding to the interface design requirements is obtained from the preset interface library, and the target interface design draft is parsed to obtain interface design information, thereby avoiding the need for manual dragging when generating pages later, thereby improving the efficiency of page generation and ensuring the consistency and accuracy of the design.

[0125] S204. Integrate the interface design information and the initial component configuration plan to obtain a target component configuration plan, and generate a target visualization interface on a preset low-code platform according to the target component configuration plan to obtain a target page.

[0126] In this embodiment, each component of the initial component configuration scheme is mapped according to the elements of the interface design information and the position information of the elements, and the original hierarchical relationship and design style are retained to obtain a target component configuration scheme. During the integration process, the interaction logic and time processing mechanism in the initial component configuration scheme are kept unchanged, and the size of each element is adjusted according to the layout requirements of the interface design information. The adjustment method can be scaled proportionally or manually fine-tuned to obtain the final target component configuration scheme. The target component configuration scheme is imported into a preset low-code platform, and a target visualization interface is generated on the preset low-code platform to obtain a target page.

[0127] In this embodiment, the above-mentioned interface design information can be first mapped to the low-code platform, and then the initial component configuration plan can be integrated with the interface design information on the low-code platform to finally generate a target component configuration plan, and then generate a target visualization interface on the preset low-code platform according to the target component configuration plan to obtain the target page.

[0128] In this embodiment, by mapping the initial component configuration scheme to the interface design information, there is no need to manually adjust the position, size, and design style of each component, thereby improving the efficiency of page development; by parsing information from an existing target design draft, the original design information is retained, thereby retaining the fluidity and beauty of the original scheme, improving the user experience, and the integrated target component configuration scheme has a clear structure and rigorous logic, which facilitates subsequent development and maintenance work.

[0129] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned artificial intelligence-based page development results, etc., the above-mentioned artificial intelligence-based page development results, etc. can also be stored in a blockchain node.

[0130] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0131] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0132] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0133] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0134] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0135] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a page development device based on artificial intelligence, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the apparatus can be specifically applied to various computer devices.

[0136] like Figure 3 As shown, the artificial intelligence-based page development device 300 described in this embodiment includes: a receiving module 301, a configuration module 302, a parsing module 303, and an integration module 304.

[0137] in:

[0138] The receiving module 301 is used to receive a page requirement document, parse the page requirement document, and obtain the business logic requirements and interface design requirements of the page requirement document.

[0139] In one embodiment, the receiving module 301 includes:

[0140] A word segmentation submodule, used to perform word segmentation and part-of-speech tagging on the page requirement document to obtain a word segmentation set with part-of-speech tags;

[0141] A conversion submodule, used for converting all the segmented words in the segmented word set into vector representations to obtain a segmented word vector set;

[0142] A processing submodule, used to process the word segmentation vector set using a pre-trained page demand extraction model to obtain a target demand set with classification labels;

[0143] The classification submodule is used to classify the target requirement set according to the classification label to obtain the business logic requirement and the interface design requirement.

[0144] The configuration module 302 is used to match the business components corresponding to the business logic requirements from the preset component library according to the business logic requirements, and use the business components to perform configuration according to the business logic requirements to obtain an initial component configuration solution.

[0145] In one embodiment, the configuration module 302 includes:

[0146] An extraction submodule, used to extract keywords and functional requirement parameters of each of the business logic requirements, and to obtain keywords and component specifications of each of the business components in the preset component library;

[0147] A first matching submodule is used to perform an initial matching of keywords of all business components based on each of the business logic requirements according to the keywords of each of the business logic requirements to obtain an initial business component set;

[0148] The second matching submodule is used to perform secondary matching on the component specifications in the initial business component set according to the functional requirement parameters of each business logic requirement to obtain the business component corresponding to each business logic requirement.

[0149] In one embodiment, the configuration module 302, the method further includes:

[0150] An identification submodule, used to identify the number of the initial service component set;

[0151] A newly added submodule is used to write a design document for a newly added business component according to the functional requirement parameters of the business logic requirements when it is identified that the number of the initial business component set is zero;

[0152] A development submodule, used to develop components according to the design document using a preset development language to obtain the newly added business components;

[0153] The confirmation submodule is used to use the newly added business component as the business component corresponding to the business logic requirement.

[0154] In one embodiment, the configuration module 302 includes:

[0155] A configuration submodule, used to perform function configuration through the corresponding business components based on each of the business logic requirements to obtain a specific function set;

[0156] The integration submodule is used to integrate the specific function set to obtain the initial component configuration solution.

[0157] The parsing module 303 is used to obtain a target interface design draft corresponding to the interface design requirement from a preset interface library, and parse the target interface design draft to obtain interface design information.

[0158] In one embodiment, the parsing module 303 includes:

[0159] The first acquisition submodule is used to acquire basic interface information of each interface design draft in the preset interface library, wherein the basic interface information includes interface design field, interface design style, and number of interface components;

[0160] The second acquisition submodule is used to acquire basic information of the interface design requirements, wherein the basic information includes the required design field, required design style, and required component quantity;

[0161] The third matching submodule is used to match the basic information of the interface design requirement with the basic interface information of each interface design draft in the preset interface library, and when the basic information of the requirement is completely consistent with the basic interface information, the target interface design draft corresponding to the interface design requirement is obtained.

[0162] In one embodiment, the parsing module 303 includes:

[0163] A detection submodule, used to detect the target interface design draft through a target detection model, identify an element set in the target interface design draft, and extract position information of each element from the element set;

[0164] A first calculation submodule is used to extract features of the element set and position information of each element through a pre-trained hierarchical extraction model to obtain hierarchical relationship features, and calculate the hierarchical relationship between the element sets according to the hierarchical relationship features;

[0165] The second calculation submodule is used to extract the visual features of the target interface design draft through a pre-trained design style recognition model, calculate the visual features through a preset classification algorithm, and obtain the design style of the target interface design draft;

[0166] The collection submodule is used to collect the element set and the position information of each element, the hierarchical connection between the element sets, and the design style of the target interface design draft to obtain the interface design information.

[0167] The integration module 304 is used to integrate the interface design information and the initial component configuration plan to obtain a target component configuration plan, and generate a target visualization interface on a preset low-code platform according to the target component configuration plan to obtain a target page.

[0168] In this embodiment, by parsing the page requirement document, the business logic requirements and interface design requirements of the page requirement document are obtained, thereby avoiding the problems of low efficiency and accuracy caused by manual intervention, and improving the efficiency and accuracy of subsequent page development;

[0169] By matching components corresponding to business logic requirements from the preset component library, errors caused by manual component selection are avoided, improving the accuracy and efficiency of subsequent page development;

[0170] Obtaining a target interface design draft corresponding to the interface design requirement from the preset interface library, parsing the target interface design draft to obtain interface design information, thereby avoiding the need for manual dragging when subsequently generating a page, thereby improving the efficiency of page generation and ensuring the consistency and accuracy of the design;

[0171] By mapping the initial component configuration scheme to the interface design information, there is no need to manually adjust the position, size, and design style of each component, which improves the efficiency of page development. By parsing information from the existing target design draft, the original design information is retained, thereby retaining the fluidity and beauty of the original scheme, improving the user experience. In addition, the integrated target component configuration scheme has a clear structure and rigorous logic, which facilitates subsequent development and maintenance.

[0172] In order to solve the above technical problems, the present application embodiment also provides a device (computer device). Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0173] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0174] The computer device may be a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with the user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0175] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the page development method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0176] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the artificial intelligence-based page development method.

[0177] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0178] During the implementation of the electronic device of the present application, the business logic requirements and interface design requirements of the page requirement document are obtained by parsing the page requirement document, thereby avoiding the problems of low efficiency and accuracy caused by manual intervention, and improving the efficiency and accuracy of subsequent page development;

[0179] By matching components corresponding to business logic requirements from the preset component library, errors caused by manual component selection are avoided, improving the accuracy and efficiency of subsequent page development;

[0180] Obtaining a target interface design draft corresponding to the interface design requirement from the preset interface library, parsing the target interface design draft to obtain interface design information, thereby avoiding the need for manual dragging when subsequently generating a page, thereby improving the efficiency of page generation and ensuring the consistency and accuracy of the design;

[0181] By mapping the initial component configuration scheme to the interface design information, there is no need to manually adjust the position, size, and design style of each component, which improves the efficiency of page development. By parsing information from the existing target design draft, the original design information is retained, thereby retaining the fluidity and beauty of the original scheme, improving the user experience. In addition, the integrated target component configuration scheme has a clear structure and rigorous logic, which facilitates subsequent development and maintenance.

[0182] The present application also provides another implementation, namely, providing a storage medium (computer-readable storage medium), wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the artificial intelligence-based page development method as described above.

[0183] During the implementation process, the computer-readable storage medium of the present application parses the page requirement document to obtain the business logic requirements and interface design requirements of the page requirement document, thereby avoiding the problems of low efficiency and accuracy caused by manual intervention, and improving the efficiency and accuracy of subsequent page development;

[0184] By matching components corresponding to business logic requirements from the preset component library, errors caused by manual component selection are avoided, improving the accuracy and efficiency of subsequent page development;

[0185] Obtaining a target interface design draft corresponding to the interface design requirement from the preset interface library, parsing the target interface design draft to obtain interface design information, thereby avoiding the need for manual dragging when subsequently generating a page, thereby improving the efficiency of page generation and ensuring the consistency and accuracy of the design;

[0186] By mapping the initial component configuration scheme to the interface design information, there is no need to manually adjust the position, size, and design style of each component, which improves the efficiency of page development. By parsing information from the existing target design draft, the original design information is retained, thereby retaining the fluidity and beauty of the original scheme, improving the user experience. In addition, the integrated target component configuration scheme has a clear structure and rigorous logic, which facilitates subsequent development and maintenance.

[0187] The non-Company software tools or components appearing in the embodiments of this application are merely examples and do not represent actual use.

[0188] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0189] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A page development method based on artificial intelligence, characterized in that: The steps include: Receiving a page requirement document, parsing the page requirement document, and obtaining business logic requirements and interface design requirements of the page requirement document; According to the business logic requirements, matching business components corresponding to the business logic requirements from a preset component library, using the business components to perform configuration according to the business logic requirements, and obtaining an initial component configuration solution; Acquire a target interface design draft corresponding to the interface design requirement from a preset interface library, and parse the target interface design draft to obtain interface design information; The interface design information and the initial component configuration plan are integrated to obtain a target component configuration plan. According to the target component configuration plan, a target visualization interface is generated on a preset low-code platform to obtain a target page.

2. The method for developing a page based on artificial intelligence as claimed in claim 1, characterized in that: The parsing of the page requirement document to obtain the business logic requirements and interface design requirements of the page requirement document includes: Performing word segmentation and part-of-speech tagging processing on the page requirement document to obtain a word segmentation set with part-of-speech tags; Convert all the word segments in the word segmentation set into vector representations to obtain a word segmentation vector set; Using a pre-trained page demand extraction model to process the word segmentation vector set, to obtain a target demand set with classification labels; The target requirement set is classified according to the classification labels to obtain the business logic requirements and the interface design requirements.

3. The page development method based on artificial intelligence as claimed in claim 1, characterized in that: The matching of the business components corresponding to the business logic requirements from the preset component library includes: Extracting keywords and function requirement parameters of each of the business logic requirements, and obtaining keywords and component specifications of each of the business components in the preset component library; Based on each of the business logic requirements, initially matching the keywords of all business components according to the keywords of each of the business logic requirements to obtain an initial business component set; A secondary match is performed on the component specifications in the initial business component set according to the functional requirement parameters of each business logic requirement to obtain a business component corresponding to each business logic requirement.

4. The page development method based on artificial intelligence as claimed in claim 3, characterized in that: After initially matching the keywords of all business components based on the keywords of each business logic requirement to obtain an initial business component set, the method further includes: Identifying the number of the initial set of business components; When it is identified that the number of the initial business component set is zero, writing a design document for a newly added business component according to the functional requirement parameters of the business logic requirement; According to the design document, a preset development language is used to develop components to obtain the newly added business components; The newly added business component is used as the business component corresponding to the business logic requirement.

5. The page development method based on artificial intelligence as claimed in claim 1, characterized in that: The using the business component to configure according to the business logic requirements to obtain an initial component configuration scheme includes: Based on each of the business logic requirements, function configuration is performed through the corresponding business components to obtain a specific function set; The specific function set is integrated to obtain the initial component configuration solution.

6. The page development method based on artificial intelligence as claimed in claim 1, characterized in that: The step of acquiring a target interface design draft corresponding to the interface design requirement from a preset interface library includes: Obtaining basic interface information of each interface design draft in the preset interface library, wherein the basic interface information includes interface design field, interface design style, and number of interface components; Obtaining basic information of the interface design requirements, wherein the basic information includes the required design field, required design style, and required component quantity; The basic information of the interface design requirement is matched with the basic interface information of each interface design draft in the preset interface library. When the basic information of the requirement is completely consistent with the basic interface information, the target interface design draft corresponding to the interface design requirement is obtained.

7. The method for developing a page based on artificial intelligence as claimed in claim 6, characterized in that: The step of parsing the target interface design draft to obtain interface design information includes: Detect the target interface design draft through a target detection model, identify an element set in the target interface design draft, and extract position information of each element from the element set; Extracting features from the element set and position information of each element using a pre-trained hierarchical extraction model to obtain hierarchical relationship features, and calculating the hierarchical relationship between the element sets based on the hierarchical relationship features; Extracting visual features of the target interface design draft through a pre-trained design style recognition model, calculating the visual features through a preset classification algorithm, and obtaining the design style of the target interface design draft; The element set and position information of each element, the hierarchical relationship between the element sets, and the design style of the target interface design draft are collected to obtain the interface design information.

8. A page development device based on artificial intelligence, characterized in that: The device comprises: A receiving module, used to receive a page requirement document, parse the page requirement document, and obtain business logic requirements and interface design requirements of the page requirement document; A configuration module, used to match business components corresponding to the business logic requirements from a preset component library according to the business logic requirements, and use the business components to perform configuration according to the business logic requirements to obtain an initial component configuration solution; A parsing module, used to obtain a target interface design draft corresponding to the interface design requirement from a preset interface library, and parse the target interface design draft to obtain interface design information; An integration module is used to integrate the interface design information and the initial component configuration plan to obtain a target component configuration plan, and generate a target visualization interface on a preset low-code platform according to the target component configuration plan to obtain a target page.

9. A computer device, characterized in that: The computer device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the artificial intelligence-based page development method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the artificial intelligence-based page development method as described in any one of claims 1 to 7 is implemented.

Images