CN112749364A

CN112749364A - Webpage generation method, device, equipment and storage medium based on artificial intelligence

Info

Publication number: CN112749364A
Application number: CN202010129527.XA
Authority: CN
Inventors: 梁宇轩
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-02-28
Filing date: 2020-02-28
Publication date: 2021-05-04
Anticipated expiration: 2040-02-28
Also published as: CN112749364B

Abstract

The embodiment of the application discloses a webpage generation method, a device, equipment and a storage medium based on artificial intelligence, wherein the method comprises the following steps: acquiring a target design drawing, wherein the target design drawing is designed aiming at a target webpage to be generated; generating a target webpage according to the target design drawing through a pre-trained webpage generation model; the webpage generation model is used for determining a control blocking area in a target design drawing, extracting image features of the control blocking area, determining an HTML element corresponding to an interactive control in a target webpage by combining the image features of the control blocking area, and generating the target webpage according to the HTML element corresponding to the interactive control. The method can improve the development efficiency of the webpage and ensure that the generated webpage has a good appearance interface design effect.

Description

Webpage generation method, device, equipment and storage medium based on artificial intelligence

Technical Field

The present application relates to the technical field of Artificial Intelligence (AI), and in particular, to a method, an apparatus, a device, and a storage medium for generating a web page.

Background

With the rapid development of the internet and information technology, activities and applications in various web page forms are endless. Different webpage activities and webpage applications have a lot of commonalities in function development, and great differences exist in webpage interface design, so that the development design of the webpage interface becomes one of the most important concerns in the webpage development process at present.

In the related technology, the development and design of the web page are mainly realized manually at present, namely, related workers write programs to configure and design various interactive controls in a web page interface based on a web page interface design drawing; the implementation mode completely depends on manual operation, the development efficiency is low, and the current large-scale webpage development requirement is difficult to meet. In addition, at present, some schemes develop webpages by automatically combining and assembling functional modules with solidified styles, and although the method can improve webpage development efficiency, the interfaces of the webpages generated based on the schemes are monotonous, which is not beneficial to popularization and use of the webpages in the market.

In summary, how to ensure the development efficiency of the web page and the design effect of the appearance interface of the web page are considered at the same time has become a problem to be solved urgently at present.

Disclosure of Invention

The embodiment of the application provides a webpage generating method, a webpage generating device, equipment and a storage medium based on artificial intelligence, which can improve the development efficiency of a webpage and ensure that the generated webpage has a good appearance interface design effect.

In view of the above, a first aspect of the present application provides a method for generating a web page based on artificial intelligence, where the method includes:

acquiring a target design drawing, wherein the target design drawing is designed aiming at a target webpage to be generated;

generating the target webpage according to the target design drawing through a pre-trained webpage generation model; the webpage generation model is used for determining a control block area in the target design drawing, extracting image features of the control block area, determining an HTML element corresponding to an interactive control in the target webpage by combining the image features, and generating the target webpage according to the HTML element corresponding to the interactive control.

A second aspect of the present application provides an artificial intelligence-based web page generation apparatus, including:

the design drawing acquisition module is used for acquiring a target design drawing, and the target design drawing is designed aiming at a target webpage to be generated;

the webpage generating module is used for generating the target webpage according to the target design drawing through a pre-trained webpage generating model; the webpage generation model is used for determining a control block area designed for the interactive control in the target webpage in the target design drawing, extracting image features of the control block area, determining an HTML element corresponding to the interactive control by combining the image features, and generating the target webpage according to the HTML element corresponding to the interactive control.

A third aspect of the application provides an electronic device comprising a processor and a memory:

the memory is used for storing a computer program;

the processor is configured to perform the steps of the artificial intelligence based web page generation method according to the first aspect as described above, according to the computer program.

A fourth aspect of the present application provides a computer-readable storage medium for storing a computer program for executing the steps of the artificial intelligence based web page generation method according to the first aspect.

A fifth aspect of the present application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the steps of the artificial intelligence based web page generation method of the first aspect described above.

According to the technical scheme, the embodiment of the application has the following advantages:

the embodiment of the application provides a webpage generation method based on artificial intelligence, and the method develops a new path, utilizes a webpage generation model trained in advance, and automatically generates a target webpage according to a target design drawing designed aiming at the target webpage, so that the development process of the webpage becomes more intelligent. Specifically, in the webpage generating method provided in the embodiment of the present application, after a target design drawing designed for a target webpage to be generated is acquired, the target design drawing is input into a webpage generating model trained in advance, the webpage generating model determines a control block region in the target design drawing, extracts image features of the control block region, determines HyperText Markup Language (HTML) elements corresponding to an interactive control in the target webpage in combination with the image features, and finally generates the target webpage according to the HTML elements corresponding to the interactive control and outputs the target webpage. Compared with the implementation mode of manually developing the webpage, the method provided by the embodiment of the application realizes the automation of webpage development by depending on the webpage generation model, and does not directly call the functional module with the solidified style in the process of generating the target webpage, and develops and designs each interactive control in the target webpage on the basis of the target design drawing designed for the target webpage, so that the interface of the finally generated target webpage has stronger design feeling, namely the appearance design effect of the interface is better, and the method is favorable for popularization and use of the target webpage.

Drawings

Fig. 1 is a schematic view of an application scenario of a web page generation method provided in an embodiment of the present application;

fig. 2 is a schematic flowchart of a webpage generating method according to an embodiment of the present application;

fig. 3 is a schematic diagram illustrating a target design drawing converted into pixel points according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of an implementation manner of verifying words and sentences according to an embodiment of the present application;

fig. 5 is a schematic diagram of an implementation manner of predicting contents in words and sentences according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a convolutional neural network layer provided in an embodiment of the present application;

fig. 7 is a schematic diagram of an implementation manner of a verification target web page provided in an embodiment of the present application;

fig. 8 is a schematic diagram of an implementation manner of an interactive control in a binary tree traversal verification target webpage according to an embodiment of the present application;

fig. 9 is a schematic diagram of an implementation architecture of a web page generation method according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a web page generation apparatus according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of another web page generation apparatus according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of a server according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of a terminal device according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Artificial intelligence is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

With the research and progress of artificial intelligence technology, the artificial intelligence technology is developed and applied in a plurality of fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, unmanned aerial vehicles, robots, smart medical care, smart customer service, and the like.

Machine Learning (ML) is a multi-domain cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and formal education learning.

The scheme provided by the embodiment of the application relates to an artificial intelligence webpage automatic generation technology, and is specifically explained by the following embodiment:

in the related art, the implementation mode of manually developing the web page has low development efficiency, and is difficult to meet the large-scale web page development requirement. The implementation mode of automatically combining and assembling the functional modules with the solidified styles to generate the webpage can improve the development efficiency of the webpage, but the appearance interface of the finally generated webpage is generally monotonous, and the popularization and the use of the webpage are not facilitated.

In view of the problems in the related art, the embodiments of the present application provide a method for generating a web page based on artificial intelligence, which can greatly improve the efficiency of developing a web page and ensure that the finally generated web page has an appearance interface with a better display effect.

Specifically, the webpage generating method provided by the embodiment of the present application includes: acquiring a target design drawing designed aiming at a target webpage to be generated, and generating the target webpage according to the target design drawing through a pre-trained webpage generation model; the webpage generation model is specifically used for determining a control blocking area in a target design drawing, extracting image features of the control blocking area, determining an HTML element corresponding to an interactive control in a target webpage by combining the image features of the control blocking area, and finally generating the target webpage according to the HTML element corresponding to the interactive control.

Compared with the implementation mode of manually developing the webpage in the related technology, the method provided by the embodiment of the application realizes the automation of webpage development through the webpage generation model, and greatly improves the efficiency of webpage development. In addition, compared with the implementation mode of developing the webpage by combining and assembling the functional modules with the solidified styles in the related technology, the method provided by the embodiment of the application always develops and designs each interactive control in the target webpage on the basis of the target design drawing in the process of developing the webpage, so that the finally generated target webpage can have strong design feeling, namely the interface display effect of the finally generated target webpage is ensured to be good, and the popularization and the use of the target webpage are facilitated.

It should be understood that the method for generating a web page based on artificial intelligence provided by the embodiment of the present application may be specifically executed by a device capable of supporting the operation of a neural network model, such as a terminal device or a server. The terminal device may specifically be a computer, a Personal Digital Assistant (PDA), a tablet computer, a smart phone, or the like. The server may specifically be a Web server or an application server, and in actual deployment, the server may be an independent server or a cluster server.

In order to facilitate understanding of the technical solution provided by the embodiment of the present application, an application scenario to which the method for generating a web page based on artificial intelligence provided by the embodiment of the present application is applied is exemplarily described below.

Referring to fig. 1, fig. 1 is a schematic view of an application scenario of a web page generation method based on artificial intelligence according to an embodiment of the present application. As shown in fig. 1, the application scenario includes a terminal device 110 and a server 120, where the terminal device 110 is configured to provide a target design drawing for a target web page design to be generated to the server 120, a web page generation model trained in advance is run in the server 120, and the server 120 is configured to execute the web page generation method provided in the embodiment of the present application based on the web page generation model.

Specifically, a target web page designer may design a target design drawing suitable for a target web page through the terminal device 110, and after the target design drawing is designed, transmit the target design drawing to the server 120 through the network, so as to generate a target web page matching the target design drawing through the server 120.

After receiving the target design drawing transmitted by the terminal device 110, the server 120 inputs the target design drawing into a webpage generation model 121 running by itself, the webpage generation model 121 determines a control block area in the target design drawing, extracts image features of the determined control block area, determines an HTML element corresponding to an interactive control in the target webpage in combination with the image features, finally generates a target webpage according to the HTML element corresponding to the interactive control, and outputs the target webpage. After acquiring the target web page output by the web page generation model 121, the server 120 may send the target web page to the terminal device 110 through the network, so that the target web page designer verifies whether the target web page meets the design standard expected by the target web page designer.

It should be noted that the target web page in the embodiment of the present application may include any content presented in a web page form, for example, the target web page may specifically be a web page application, and may also be a web page activity, and the present application is not specifically limited to the target web page.

It should be understood that the application scenario shown in fig. 1 is only an example, and in an actual application, the terminal device 110 or the server 120 may also independently execute the web page generation method provided in the embodiment of the present application, and generate the target web page according to the target design drawing designed for the target web page, and no limitation is made to the application scenario to which the web page generation method provided in the embodiment of the present application is applied.

The following describes the webpage generation method based on artificial intelligence in detail by embodiments.

Referring to fig. 2, fig. 2 is a schematic flowchart of a web page generation method based on artificial intelligence according to an embodiment of the present application. For convenience of description, the following embodiments are described taking a server as an execution subject. As shown in fig. 2, the web page generation method includes the steps of:

step 201: and acquiring a target design drawing, wherein the target design drawing is designed aiming at a target webpage to be generated.

When developing a target webpage, the server needs to acquire a target design drawing designed for the target webpage so as to subsequently call a pre-trained webpage generation model to develop the target webpage based on the target design drawing.

It should be noted that the target design drawing acquired by the server is a design drawing created for a display interface of a target web page, and the target design drawing may include a display style of each interactive control in the target web page interface, a background pattern of the target web page interface, a text element and an illustration element in the target web page interface, and the like, and the target design drawing in the embodiment of the present application is not specifically limited herein.

In one possible implementation, the server may obtain the target design drawing from the terminal device. Specifically, a user can design a display interface of a target webpage through the terminal device to complete drawing of the target design drawing, and then control the terminal device to transmit the target design drawing to the server through the network, so that the server can obtain the target design drawing as a manufacturing basis of the target webpage.

In another possible implementation, the server may retrieve the target design drawing from a relational database. Specifically, because the appearance interfaces of the webpages belonging to the same category have certain similarity, in practical application, design drawings created for various webpages can be stored in a database in advance, so that matched design drawings can be directly called from the database when certain webpages are developed; after the server receives the development request of the target webpage, the server can determine the category of the target webpage, and then correspondingly calls the design drawing matched with the category from the database as the target design drawing according to the category of the target webpage, and the target webpage is manufactured based on the target design drawing.

It should be understood that, in practical applications, the server may obtain the target design drawing in other ways besides the two possible implementations described above, and the present application does not limit any implementation manner for the server to obtain the target design drawing.

It should be noted that, when the execution subject of the embodiment of the present application is a terminal device, the terminal device may directly obtain a target design drawing created by a user through a related program executed by the terminal device, or may receive a target design drawing transmitted from another terminal device.

Step 202: generating the target webpage according to the target design drawing through a pre-trained webpage generation model; the webpage generation model is used for determining a control block area in the target design drawing, extracting image features of the control block area, determining an HTML element corresponding to an interactive control in the target webpage by combining the image features, and generating the target webpage according to the HTML element corresponding to the interactive control.

After the server acquires the target design drawing, the target design drawing can be input into a pre-trained webpage generation model, the webpage generation model is utilized to correspondingly process the target design drawing, and then a webpage which is output after the webpage generation model completes the processing of the target design drawing is acquired and used as a target webpage.

Specifically, after the target design drawing is input to a pre-trained webpage generation model by the server, the webpage generation model firstly determines each control block area in the target design drawing, namely determines the block areas which may be used as interactive controls in the target webpage one by one in the target design drawing, then extracts the image features of each control block area, correspondingly determines the HTML elements of the interactive controls corresponding to each control block area by combining the image features of each control block area, and finally generates the target webpage according to the HTML elements of each interactive control.

The web page generation model is a pre-trained neural network model, and is obtained by training based on a supervised training algorithm. Specifically, a large number of developed webpages and original design drawings corresponding to the developed webpages need to be obtained as training samples, then the original design drawings are input into a pre-built neural network model, the input original design drawings are correspondingly processed by the neural network model, a prediction webpage corresponding to the original design drawings is output, the prediction webpage output by the neural network model and a webpage corresponding to the original design drawings in the training samples are compared, model parameters of the neural network model are adjusted based on the comparison result, and thus, by the above mode, iterative training is performed on the neural network model based on a large number of training samples, and the model parameters are continuously adjusted until the neural network model meets the training end condition.

In order to facilitate understanding of the specific working principle of the web page generation model, the working principle of the web page generation model is described in detail below.

After the target design drawing is input into the web page generation model, the web page generation model converts the target design drawing into a preset number of pixel points, as shown in fig. 3, the web page generation model converts the input target design drawing into a preset number of pixel points, a pixel value corresponding to each pixel point can be represented by values of three color channels, namely r (red), g (green) and b (blue), and a value range of each color channel is between 0 and 255.

It should be understood that the preset number may be determined according to the actual processing capability of the web page generation model, and if the operation processing capability of the web page generation model is strong, the preset number may be set to be correspondingly large; if the operation processing capability of the webpage generation model is weak, the preset number can be set to be smaller correspondingly; the predetermined number is not specifically limited herein.

Furthermore, the webpage generation model can determine control blocking areas corresponding to the controls in the target webpage in the target design drawing according to the pixel values corresponding to the preset number of pixel points. Specifically, the webpage generation model can select one pixel point from a target design drawing as a target pixel point, search each pixel point adjacent to the target pixel point from the target pixel point, and then judge whether the pixel difference value between each adjacent pixel point and the target pixel point is within a preset range one by one, if yes, the adjacent pixel point and the target pixel point are determined to belong to the same control block area, and if not, the adjacent pixel point and the target pixel point are determined not to belong to the same control block area; and then, determining adjacent pixel points belonging to the same control blocking area as new target pixel points, and executing the operation based on the new target pixel points until the pixel points belonging to the control blocking area can not be found in the target design drawing any more, so that a control blocking area is determined.

It should be understood that, in practical applications, the control blocking area determined in the above manner may not be an area corresponding to the interaction control in the target webpage, which may correspond to a background area in the target webpage; in order to prevent the background area from being mistakenly determined as the area corresponding to the interactive control, after the webpage generation model determines the control blocking area, whether the shape of the determined control blocking area accords with the preset shape of the interactive control can be further judged, if yes, the control blocking area is determined to be valid and is the blocking area corresponding to the interactive control in the target webpage, and if not, the control blocking area is determined to be invalid and is the area corresponding to the background area in the target webpage.

Therefore, through the mode, all the pixel points in the target design drawing are processed in a traversing mode, and therefore the control blocking areas corresponding to all the interactive controls in the target webpage in the target design drawing are determined.

Optionally, when the target design drawing includes a word or a sentence, the webpage generation model may further identify whether the word or the sentence in the target design drawing conforms to a preset grammar rule in the following manner, and perform corresponding correction processing on the word or the sentence when it is determined that the word or the sentence in the target design drawing does not conform to the preset grammar rule.

Specifically, the webpage generation model can encode each character in the words and sentences through one-hot encoding, so as to obtain binary characteristic vectors corresponding to each character; then, judging whether the words and sentences accord with preset grammar rules or not according to the arrangement positions of the characters in the words and sentences and binary characteristic vectors corresponding to the characters respectively; if the word is determined to be in accordance with the sentence, the word is reserved; and if the characters do not accord with the preset grammar rules, the arrangement positions of the characters in the words and the sentences are exchanged according to the preset rules until the words and the sentences obtained after the exchange processing accord with the preset grammar rules according to the arrangement positions of the characters after the exchange processing and the binary characteristic vectors corresponding to the characters.

It should be noted that the words and phrases may be composed of a plurality of language units, where a language unit may specifically refer to each word in a word or each word in a sentence. The webpage generation model verifies words and sentences, and substantially verifies whether the deployment positions of all words in the words meet grammar rules or not and whether the deployment positions of all words in the sentences meet the grammar rules or not.

It should be understood that the above words and phrases may be words and phrases deployed in a background region of the target design drawing, or may be words and phrases deployed in a control block region of the target design drawing, and the application does not make any limitation on the deployment position of the verified words and phrases.

The verification method described above is exemplarily described below with reference to fig. 4, taking the expression "I can code" included in the target design drawing as an example. As shown in fig. 4, the web page generation model may perform one-hot encoding processing from a start character before a sentence to obtain a code corresponding to a start as shown in 401, then combine the start and the I to perform the one-hot encoding processing to obtain a code corresponding to the start I as shown in 402, then combine the start, the I and the can to perform the one-hot encoding processing to obtain a code corresponding to the start I can as shown in 403, then combine the start, the I, the can and the code to perform the one-hot encoding processing to obtain a code corresponding to the start I can code as shown in 404, and finally combine the start, the I, the can, the code and an end character after the sentence to perform the one-hot encoding processing to obtain a code corresponding to the start I can code end as shown in 405. Judging whether the code shown by 405 meets a preset grammar rule, if so, reserving the I can code for use when a target webpage is generated subsequently, if not, replacing the I, can and the code, such as converting into an I code can, a can I code, a can code I, a code I can I and a code I can I, and the like, further performing the judgment processing on the words and sentences obtained after the replacement processing until the words and sentences meeting the preset rule are determined, and reserving the words and sentences for calling when the target webpage is generated subsequently.

Optionally, in some cases, the webpage generation model may also implement prediction on the remaining content in the words and sentences according to the partial content in the words and sentences and the background pixel values corresponding to the partial content. As shown in fig. 5, the left half of the prediction function f () is a pixel value represented based on three color channels of RGB, the pixel value corresponds to the content of the word on the right half of the prediction function f (), and in the case where only a start character and the corresponding pixel value at the start character are known to exist, the prediction function f () can predict that the next character is I; in the case where it is known that there is a start character and a character I, and the pixel value at the start character and the character I are known, the prediction function f () can predict the next character of its character I as can; in the case where it is known that there is a start character, a character I, and a character can, and the pixel values at the start character, the character I, and the character can are known, the prediction function f () can predict the next character of the character can as a code; in the case where it is known that there is a start character, a character I, a character can, and a character code, and pixel values at the start character, the character I, the character can, and the character code are known, the prediction function f () can predict the next character of the character code as a character end.

In this way, the webpage generation model can supplement complete incomplete words and sentences correspondingly under the condition that the words and sentences included in the target design drawing are detected to be incomplete based on the manner.

After the webpage generation model determines the control blocking areas corresponding to the interactive controls in the target design drawing, image feature extraction processing can be respectively carried out on the control blocking areas by using a Convolutional Neural Network (CNN) of the webpage generation model, so that the image features of the control blocking areas are obtained.

The CNN may be obtained by training using data on ImageNet. In addition, the last layer of the CNN is a classification layer in general, and the webpage generation model in the embodiment of the present application only needs to extract image features, so the deployed CNN does not include the last classification layer, and the webpage generation model only needs to extract image features by using the previous layer of the classification layer in the CNN; fig. 6 is a schematic diagram of an exemplary CNN.

After the webpage generation model extracts the image features for each control block area, the HTML elements of the interactive controls corresponding to the control block areas can be correspondingly determined by combining the image features of each control block area in the following modes: the webpage generation model can determine the control type of the interactive control corresponding to the control blocking area according to the image characteristics of the control blocking area, then call the HTML element corresponding to the control type, and further write the related information in the control blocking area in the target design drawing into the HTML element, so that the HTML element corresponding to the interactive control is generated.

Specifically, the webpage generation model can determine which type of control the interactive control corresponding to the control blocking area belongs to according to the image characteristics of the control blocking area, e.g., determining that the interaction control belongs to a button control, a selection control, a text input control, etc., after determining the control type to which the interactive control belongs, the webpage generation model can call up the HTML element corresponding to the control type and pre-stored in the webpage generation model, the content in the control tile area in the target design drawing and the associated attributes of the control tile area are then written into the HTML element, e.g., the control blocking area can be written to the HTML element accordingly at the distribution location in the target design drawing, the text content in the control tile area may be written into an HTML element, the RGB color channel values of the control tile area may be written into an HTML element, and so on.

Optionally, in the process of generating the HTML element of the interactive control, the webpage generating model may also retrieve the animation effect applicable to the interactive control from the animation effect repository, and write the animation effect into the HTML element of the interactive control, so as to add a matching animation effect to the interactive control.

Therefore, through the above manner, the HTML elements of the interactive controls corresponding to the control blocking areas in the target design drawing are respectively determined.

Optionally, before generating the target webpage according to the respective HTML elements of the interactive controls, the webpage generation model may further perform corresponding processing on the background area of the target webpage, that is, the webpage generation model may further determine whether the background area of the target design drawing is a blank area, and when it is determined that the background area of the target design drawing is the blank area, the webpage generation model may discard the background area in the target design drawing, and deploy the respective HTML elements of the interactive controls directly based on the blank webpage, thereby generating the target webpage.

Specifically, the webpage generation model may determine whether the background area of the target design drawing is a blank area according to the pixel value of the background area part in the target design drawing, and if it is determined that the background area in the target design drawing is the blank area, the webpage generation model may directly discard the background area in the target design drawing, and deploy the HTML elements of the interactive controls in the blank webpage according to the logical association relationship between the interactive controls, so as to avoid the blank area in the target design drawing being additionally loaded in the target webpage and wasting unnecessary resources. If the background area in the target design drawing is determined not to be the blank area, the webpage generation model can correspondingly deploy the background area in the target design drawing in the target webpage, and then correspondingly deploy the HTML elements of the interaction controls in the target webpage with the background picture according to the logical association relationship among the interaction controls.

The webpage generation model correspondingly processes the target design drawing to obtain a target webpage through the process, and then outputs the generated target webpage; in order to further ensure the quality of the target webpage, the server may utilize the browser to virtually run the target webpage to verify whether the target webpage meets a preset standard.

Specifically, the server may call a browser to simulate running of the target webpage, determine a reduction degree of an interface of the target webpage relative to a target design drawing, and verify whether a function of an interactive control in the target webpage meets a preset requirement; and under the condition that the reduction degree is higher than the preset threshold value and the functions of the interactive controls in the target webpage meet the preset requirements, the server determines that the target webpage meets the preset standard and can put the target webpage into practical use.

As shown in fig. 7, the server may call the browser puppeteer to run the target webpage, intercept the display interface of the target webpage in the running process of the target webpage, then determine the similarity between the display style of each interactive control in the display interface and the display style of each control block region in the target design drawing one by one, and determine the reduction degree of the display interface of the target webpage relative to the target design drawing based on the similarity between each interactive control and the control block region corresponding thereto.

It should be noted that, for the text content in the display interface of the target web page, the server may determine whether it is consistent with the text content in the target design drawing based on an Optical Character Recognition technology (OCR), and when determining the reduction degree of the display interface of the target web page relative to the target design drawing, consider the consistency of the text content therein.

When the server calls puppeteer to operate the target webpage, the puppeteer can simulate each interactive control in the touch target webpage, obtain the response effect of the target webpage for each touch operation, and verify whether the function of each interactive control in the target webpage meets the preset requirement by judging whether the response effect actually made by the target webpage is consistent with the expected response effect.

In order to ensure that the functions of the interactive controls in the target webpage are comprehensively verified, the server can adopt a binary tree form and traverse and simulate the interactive controls in the touch target webpage according to the logical association relationship among the interactive controls. Taking 3 interactive controls included in the target webpage as an example, the implementation manner of puppeteer traversing and simulating each interactive control is described with reference to fig. 8. As shown in fig. 8, puppeteer can simulate the touch control No. 1 interactive control alone firstly, simulate the touch control No. 2 interactive control alone secondly, simulate the touch control No. 3 interactive control alone thirdly, simulate the continuous touch control No. 1 interactive control twice fourthly, simulate the continuous touch control No. 1 interactive control and No. 2 interactive control successively fifth, simulate the continuous touch control No. 3 interactive control and No. 1 interactive control successively sixth, simulate the continuous touch control No. 3 interactive control successively and No. 2 interactive control successively seventh, simulate the continuous touch control No. 1 interactive control three times continuously, simulate the continuous touch control No. 1 interactive control twice firstly, touch the continuous touch control No. 2 interactive control once again ninth, simulate the continuous touch control No. 1 interactive control successively, No. 2 interactive control successively and No. 1 interactive control successively tenth, and simulate the continuous touch control No. 3 interactive control successively eleventh, And a No. 2 interactive control and a No. 1 interactive control, and in the twelfth step, firstly, simulating to touch the No. 3 interactive control, and then, continuously touching the No. 2 interactive control twice.

Compared with the implementation mode of manually developing the webpage in the related technology, the webpage generation method provided by the embodiment of the application realizes the automation of webpage development through the webpage generation model, and greatly improves the efficiency of webpage development. In addition, compared with the implementation mode that the webpage is developed by combining and assembling the functional modules with the solidified styles in the related art, the webpage generating method provided by the embodiment of the application always develops and designs each interactive control in the target webpage on the basis of the target design drawing in the process of developing the webpage, so that the finally generated target webpage can have strong design feeling, namely the interface display effect of the finally generated target webpage is ensured to be good, and the popularization and the use of the target webpage are facilitated.

In order to further understand the web page generation method based on artificial intelligence provided in the embodiment of the present application, the following describes an example of the web page generation method in its entirety with reference to the implementation framework shown in fig. 9.

As shown in fig. 9, after acquiring the target design drawing, the server inputs the target design drawing into a pre-trained web page generation model. The webpage generation model firstly calls an area division module to determine a background area in the target design drawing and a control block area corresponding to an interactive control in the target webpage; then calling a convolutional neural network layer to correspondingly extract image features for each control block area, thereby obtaining the respective image features of each control block area; then, calling an HTML element generation module, correspondingly determining the control type of the corresponding interactive control according to the image characteristics of each control blocking area according to the image characteristics of the control blocking area, acquiring the HTML element corresponding to the control type, and writing the related information of the control blocking area into the HTML element so as to generate the interactive control corresponding to the control blocking area; and finally, calling a target webpage construction module, correspondingly deploying each interactive control in the blank webpage based on the HTML element corresponding to each interactive control according to the logic association relation among the interactive controls, and configuring the function of each interactive control, thereby generating the target webpage.

The method comprises the steps that after a server obtains a target webpage output by a webpage generation model, a browser puppeteer is called to simulate and run the target webpage, and whether the target webpage meets a preset standard or not is verified according to the reduction degree between a display interface of the target webpage and a target design drawing and the response effect of each interactive control in the target webpage aiming at simulated touch operation.

Aiming at the artificial intelligence webpage generation method, the application also provides a corresponding artificial intelligence webpage generation device, so that the artificial intelligence webpage generation method is applied and realized in practice.

Referring to fig. 10, fig. 10 is a schematic structural diagram of an artificial intelligence web page generation apparatus 1000 corresponding to the artificial intelligence web page generation method shown in fig. 2, the apparatus comprising:

a design drawing obtaining module 1001 configured to obtain a target design drawing, where the target design drawing is designed for a target web page to be generated;

a web page generating module 1002, configured to generate the target web page according to the target design drawing through a pre-trained web page generating model; the webpage generation model is used for determining a control block area designed for the interactive control in the target webpage in the target design drawing, extracting image features of the control block area, determining an HTML element corresponding to the interactive control by combining the image features, and generating the target webpage according to the HTML element corresponding to the interactive control.

Optionally, on the basis of the web page generation apparatus shown in fig. 10, when the target design drawing includes a word or a sentence, the web page generation model is further configured to:

coding each character in the words and sentences through one-hot coding to obtain a characteristic vector corresponding to each character;

judging whether the words and sentences accord with preset grammar rules or not according to the arrangement positions of the characters in the words and sentences and the characteristic vectors corresponding to the characters respectively;

if yes, the words and sentences are reserved; if not, the arrangement positions of the characters in the sentence are exchanged according to a preset rule until the sentence obtained after the exchange process is determined to accord with the grammar rule according to the arrangement positions of the characters after the exchange process and the feature vectors corresponding to the characters.

Optionally, on the basis of the web page generation apparatus shown in fig. 10, the web page generation model determines a control blocking area in the target design drawing, which corresponds to the interaction control in the target web page, by:

converting the target design drawing into a preset number of pixel points;

and determining the control blocking area according to the pixel values corresponding to the preset number of pixel points.

Optionally, on the basis of the web page generation apparatus shown in fig. 10, the web page generation model determines the HTML element corresponding to the interaction control by combining the image feature in the following manner:

determining the control type of the interactive control according to the image characteristics;

calling an HTML element corresponding to the control type;

and writing the relevant information of the control block area designed for the interactive control in the target design drawing into the HTML element to generate the HTML element corresponding to the interactive control.

Optionally, on the basis of the web page generation apparatus shown in fig. 10, the web page generation model is further configured to:

judging whether the background area of the target design drawing is a blank area;

under the condition that the background area of the target design drawing is determined to be a blank area, the webpage generation model generates the target webpage according to the HTML element corresponding to the interaction control in the following mode:

discarding a background region in the target design drawing;

and generating the target webpage according to the HTML element corresponding to the interactive control.

Optionally, on the basis of the web page generating apparatus shown in fig. 10, referring to fig. 11, fig. 11 is a schematic structural diagram of another network generating apparatus 1100 provided in the embodiment of the present application. As shown in fig. 11, the apparatus further includes:

a simulation operation module 1101, configured to invoke a browser to simulate and operate the target webpage, determine a reduction degree of an interface of the target webpage relative to the target design drawing, and verify whether a function of an interactive control in the target webpage meets a preset requirement;

the web page verification module 1102 is configured to determine that the target web page meets a preset standard when it is determined that the reduction degree is higher than a preset threshold and the function of the interactive control in the target web page meets a preset requirement.

Optionally, on the basis of the web page generating apparatus shown in fig. 11, the simulation running module 1101 is specifically configured to:

intercepting an interface of the target webpage in the running process of the target webpage;

determining the reduction degree according to the similarity between the display style of the interactive control in the interface and the display style of the control blocking area in the target design drawing;

simulating and touching an interactive control in the target webpage to acquire a response effect of the target webpage for the touch operation;

and judging whether the response effect is consistent with the expected response effect.

Compared with the implementation mode of manually developing the webpage in the related technology, the webpage generation device provided by the embodiment of the application realizes the automation of webpage development through the webpage generation model, and greatly improves the efficiency of webpage development. In addition, compared with the implementation mode that the webpage is developed by combining and assembling the functional modules with the solidified styles in the related art, the webpage generating device provided by the embodiment of the application always develops and designs each interactive control in the target webpage on the basis of the target design drawing in the process of developing the webpage, so that the finally generated target webpage can have a strong design feeling, namely the interface display effect of the finally generated target webpage is guaranteed to be good, and the popularization and the use of the target webpage are facilitated.

The embodiment of the present application further provides an electronic device for generating a web page based on an artificial intelligence technology, where the electronic device may specifically be a server or a terminal device, and the server or the terminal device provided in the embodiment of the present application will be introduced from the perspective of hardware materialization.

Referring to fig. 12, fig. 12 is a schematic diagram of a server structure provided by an embodiment of the present application, where the server 1200 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 1222 (e.g., one or more processors) and a memory 1232, and one or more storage media 1230 (e.g., one or more mass storage devices) storing an application program 1242 or data 1244. Memory 1232 and storage media 1230 can be, among other things, transient storage or persistent storage. The program stored in the storage medium 1230 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 1222 may be configured to communicate with the storage medium 1230, to execute a series of instruction operations in the storage medium 1230 on the server 1200.

The server 1200 may also include one or more power supplies 1226, one or more wired or wireless network interfaces 1250, one or more input-output interfaces 1258, and/or one or more operating systems 1241, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

The steps performed by the server in the above embodiment may be based on the server structure shown in fig. 12.

The CPU 1222 is configured to perform the following steps:

Optionally, the CPU 1222 may also be used to execute the steps of any implementation manner of the artificial intelligence based web page generation method in the embodiment of the present application.

Referring to fig. 13, fig. 13 is a schematic structural diagram of a terminal device according to an embodiment of the present application. For convenience of explanation, only the parts related to the embodiments of the present application are shown, and details of the specific technology are not disclosed. The terminal may be any terminal device including a computer, a tablet computer, a Personal Digital Assistant (PDA), and the like, taking the terminal as the computer as an example:

fig. 13 is a block diagram showing a partial structure of a computer related to a terminal provided in an embodiment of the present application. Referring to fig. 13, the computer includes: radio Frequency (RF) circuit 1310, memory 1320, input unit 1330, display unit 1340, sensor 1350, audio circuit 1360, wireless fidelity (WiFi) module 1370, processor 1380, and power supply 1390. Those skilled in the art will appreciate that the computer architecture shown in FIG. 13 is not intended to be limiting of computers, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.

The memory 1320 may be used to store software programs and modules, and the processor 1380 executes various functional applications and data processing of the computer by operating the software programs and modules stored in the memory 1320. The memory 1320 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the computer, etc. Further, the memory 1320 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The processor 1380 is a control center of the computer, connects various parts of the entire computer using various interfaces and lines, performs various functions of the computer and processes data by operating or executing software programs and/or modules stored in the memory 1320 and calling data stored in the memory 1320, thereby monitoring the entire computer. Optionally, processor 1380 may include one or more processing units; preferably, the processor 1380 may integrate an application processor, which handles primarily operating systems, user interfaces, application programs, etc., and a modem processor, which handles primarily wireless communications. It will be appreciated that the modem processor described above may not be integrated within processor 1380.

In the embodiment of the present application, the processor 1380 included in the terminal further has the following functions:

Optionally, the processor 1380 is further configured to execute the steps of any implementation manner of the artificial intelligence based webpage generating method provided in the embodiment of the present application.

The embodiment of the present application further provides a computer-readable storage medium for storing a computer program, where the computer program is configured to execute any one implementation manner of the artificial intelligence based web page generation method described in the foregoing embodiments.

The present application further provides a computer program product including instructions, which when run on a computer, causes the computer to execute any one of the implementation manners of the artificial intelligence based web page generation method described in the foregoing embodiments.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing computer programs.

It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A webpage generation method based on artificial intelligence is characterized by comprising the following steps:

2. The method of claim 1, wherein when the target design drawing includes a word or sentence, the webpage generation model is further configured to:

3. The method of claim 1, wherein the web page generation model determines the control blocking area in the target design drawing corresponding to the interaction control in the target web page by:

converting the target design drawing into a preset number of pixel points;

4. The method of claim 1, wherein the web page generation model determines the HTML element corresponding to the interaction control in combination with the image feature by:

calling an HTML element corresponding to the control type;

5. The method of claim 1, wherein the web page generation model is further configured to:

discarding a background region in the target design drawing;

6. The method of claim 1, wherein after the generating the target web page from the target design drawing through the pre-trained web page generation model, the method further comprises:

calling a browser to simulate and run the target webpage, determining the reduction degree of the interface of the target webpage relative to the target design drawing, and verifying whether the function of the interactive control in the target webpage meets the preset requirement;

and under the condition that the reduction degree is higher than a preset threshold value and the function of the interactive control in the target webpage meets a preset requirement, determining that the target webpage meets a preset standard.

7. The method of claim 6, wherein the determining the degree of reduction of the interface of the target web page relative to the target design drawing comprises:

the verifying whether the function of the interactive control in the target webpage meets the preset requirement includes:

simulating and touching an interactive control in the target webpage to obtain a response effect of the target webpage aiming at the touch operation;

8. An artificial intelligence based web page generation apparatus, the apparatus comprising:

9. An electronic device, comprising: a memory and a processor;

the memory is used for storing a computer program;

the processor is configured to execute the artificial intelligence based web page generation method of any one of claims 1 to 7 according to the computer program.

10. A computer-readable storage medium for storing a computer program for executing the artificial intelligence based web page generation method of any one of claims 1 to 7.