CN116954605A - Page generation method and device and electronic equipment - Google Patents
Page generation method and device and electronic equipment Download PDFInfo
- Publication number
- CN116954605A CN116954605A CN202310847496.5A CN202310847496A CN116954605A CN 116954605 A CN116954605 A CN 116954605A CN 202310847496 A CN202310847496 A CN 202310847496A CN 116954605 A CN116954605 A CN 116954605A
- Authority
- CN
- China
- Prior art keywords
- page
- target
- base map
- layout
- generating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 107
- 239000000463 material Substances 0.000 claims abstract description 115
- 238000009877 rendering Methods 0.000 claims abstract description 18
- 238000010586 diagram Methods 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 21
- 238000003860 storage Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 14
- 230000003044 adaptive effect Effects 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 8
- 238000005034 decoration Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 36
- 238000004590 computer program Methods 0.000 description 15
- 238000011161 development Methods 0.000 description 12
- 230000018109 developmental process Effects 0.000 description 12
- 230000000694 effects Effects 0.000 description 12
- 238000013461 design Methods 0.000 description 9
- 238000011049 filling Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 3
- 238000013256 Gubra-Amylin NASH model Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 239000002537 cosmetic Substances 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000011068 loading method Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000008485 antagonism Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000009417 prefabrication Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000010421 standard material Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/38—Creation or generation of source code for implementing user interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0475—Generative networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/094—Adversarial learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Human Computer Interaction (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the specification discloses a page generation method, a page generation device and electronic equipment, and relates to the technical field of computers, wherein the method comprises the following steps: generating a target base map according to the page base map in the historical target page; automatically combining materials in a material library according to a predefined material combination rule based on a layout pattern in a historical target page, and generating a picture layout on a target base map; generating a page document on the target base map according to text information, the target base map and the picture layout in the historical target page; rendering the element attributes on the target base map, the picture layout and the page document to generate a target page. By utilizing the technical scheme provided by the specification, the automatic and intelligent generation of the page is realized, and the flexibility of page generation is improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a page generating method, a device, and an electronic device.
Background
With the development of computer Internet technology, pages (such as web pages or H5 pages) are widely applied to various marketing scenes, traditional page development is excessively dependent on development and participation of designers, and generation of a set of pages is dependent on the development personnel to have higher programming skills, and the development period is longer, so that the requirement of rapid online activities cannot be met.
In the prior art, there are many schemes for generating pages, and the schemes can be mainly divided into two main categories: the method is based on component library arrangement generation and theme plug-in generation, and the thinking is to construct own components or plug-in libraries, but the learning curve is steeper due to the difference of development frameworks, and a certain front-end development experience is needed for skilled use. Basically, the idea of generating the page in the prior art is not to bypass a template filling scheme, and is a combined idea, the principle is that materials are filled into a specified template page or a prefabricated page frame, the problems of template splicing and prefabrication of the template exist, and the page generating mode has the problems of poor overall layout, poor image and collocation degree, poor fusion degree and the like, so that the flexibility of page generation is poor.
How to improve the flexibility of page generation is a technical problem that needs to be solved in the art.
Disclosure of Invention
The embodiment of the specification provides a page generation method, device, equipment, storage medium and computer program product, which can realize automatic and intelligent generation of pages and promote flexibility of page generation.
In one aspect, an embodiment of the present disclosure provides a page generating method, where the method includes:
Generating a target base map according to the page base map in the historical target page;
automatically combining materials in a material library according to a predefined material combination rule based on the layout style in the historical target page, and generating a picture layout on the target base map;
generating a page document on the target base map according to the text information in the historical target page, the target base map and the picture layout;
rendering the target base map, the picture layout and the element attribute on the page document to generate a target page.
Another aspect provides a page generating apparatus, the apparatus comprising:
the base map generation module is used for generating a target base map according to the page base map in the historical target page;
the layout generation module is used for automatically combining the materials in the material library according to a predefined material combination rule based on the layout patterns in the historical target page, and generating a picture layout on the target base map;
the document generation module is used for generating a page document on the target base map according to the text information in the historical target page, the target base map and the picture layout;
And the page generation module is used for rendering the target base map, the picture layout and the element attribute on the page document to generate a target page.
Another aspect provides an electronic device, comprising: a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the page generation method of any of the above.
Another aspect provides a computer readable storage medium which, when executed by a processor of an electronic device, causes the electronic device to perform any of the page generation methods described above.
Another aspect provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the page generation method provided in the various alternative implementations described above.
The page generation method, device, equipment, storage medium and computer program product provided by the embodiments of the present specification have the following technical effects:
According to the page generation method provided by the embodiment of the specification, a template filling-based scheme is bypassed, a process of simulating a designer to make creatives is selected, a page base map, a layout and a document of a historical target page designed by an excellent designer are learned, a target base map, a picture layout and a page document required by the target page are generated, and then element rendering is carried out to generate the target page. Compared with the template filling scheme, the method realizes the automatic and intelligent generation of the target page, can more flexibly determine the page attributes such as layout, style, font size and the like, and improves the flexibility of page generation. In addition, when the picture layout of the target page is generated, the materials of the material library are freely combined according to the layout style of the historical target page based on the predefined material combination rule, so that the picture layout of different styles can be obtained, the requirements of different users are met, rich and various page effects are generated, flexible combination and efficient utilization of the materials are realized, and the flexibility of page generation is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present description, and other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic diagram of an application environment of a page generating method according to an embodiment of the present disclosure;
FIG. 2 is a flow diagram of a page generation method provided by one embodiment of the present disclosure;
FIG. 3 is a schematic diagram of page document generation in one embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a page generating apparatus according to an embodiment of the present disclosure;
FIG. 5 is a block diagram of an electronic device for page generation provided by an embodiment of the present description;
fig. 6 is a block diagram of another electronic device for page generation provided by an embodiment of the present description.
Detailed Description
The technical solutions of the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is apparent that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and the claims of the embodiments of the present specification and the above-described drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the present description described herein may be 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 server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, fig. 1 is a schematic diagram of an application environment of a page generating method according to an embodiment of the present disclosure, where the application environment may include at least a server 100 and a terminal 200.
In an alternative embodiment, the server 100 may be used to perform the page generation process, where the server 100 may be an independent physical server, or may be a server cluster or a distributed system formed by multiple physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms.
In an alternative embodiment, the terminal 200 may be a client that sends a page generation request to the server 100, and in particular, the terminal 200 may include, but is not limited to, a smart phone, a desktop computer, a tablet computer, a notebook computer, a smart speaker, a digital assistant, an augmented reality (augmented reality, AR)/Virtual Reality (VR) device, a smart wearable device, a vehicle-mounted terminal, a smart television, and other types of electronic devices; or software running on the electronic device, such as an application, applet, etc. Operating systems running on the electronic device in embodiments of the present description may include, but are not limited to, android systems, IOS systems, linux, windows, and the like.
In addition, it should be noted that, the application environment shown in fig. 1 is only an application environment of the page generating method, and the embodiment of the present disclosure is not limited to the above.
In the embodiment of the present specification, the server 100 and the terminal 200 may be directly or indirectly connected through a wired or wireless communication manner, and the embodiment of the present specification is not limited herein.
The page in the embodiment of the present disclosure may be understood as a Web page or an H5 page, where the H5 page may be understood as HTML5, which is a language description manner for building Web content, and the H5 page may also be understood as a Web page, which is just like a large container, in which a file in a basic streaming media format such as text, pictures, audio and video may be placed. With the development of internet technology, pages are increasingly applied, and many pieces of information are carried in the pages, such as: the advertising page may be used to advertise a particular product. Therefore, how to quickly generate high quality pages is a key technology.
In the page generation process, DSL (domain-specific language) language is generally used, where DSL language is defined as follows: grammar, semantics and grammar tree definition, and generating pages including page structure, style, layout, etc. according to DSL language and data model. However, in general, when generating a target page based on DSL, a mode of template filling and component library or plug-in library development is adopted, and the page generation mode is relatively dead and has low flexibility.
In the following, a page generating method according to an embodiment of the present disclosure is described, and fig. 2 is a schematic flow chart of a page generating method according to an embodiment of the present disclosure, where method operation steps according to an embodiment or a flowchart are provided, but more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented in a real system or server product, the methods illustrated in the embodiments or figures may be performed sequentially or in parallel (e.g., in a parallel processor or multithreaded environment). The method can be applied to terminal equipment such as computers, tablet computers, smart phones and the like, and can also be applied to servers. As shown in fig. 2, the method may include:
s202: and generating a target base map according to the page base map in the historical target page.
In a specific implementation, a history target page may be understood as a page that has been created such as: h5 pages or web pages can be selected to be excellent pages with higher quality and better display effect as historical target pages, or pages designed by a designated designer (such as excellent designer) are selected to be historical target pages, and the number of the historical target pages can be selected according to actual needs, so that the embodiment of the specification is not particularly limited. In addition, when selecting the historical target page, the historical target page with the same type can be selected according to the type of the target page to be created, such as: if a propaganda webpage template of the cosmetic product needs to be created, a page of the cosmetic product can be selected from the created excellent pages to serve as a historical target page. And then the information mining is carried out on the historical target page to obtain a page base diagram in the historical target page, wherein the page base diagram can be understood as an image placed at the bottommost part of a plurality of layers in the drawing process, can be understood as a basic frame or background of the page, and other materials or elements can be added on the basis of the page base diagram to generate a specific page. After obtaining the page base map from the historical target page, a new page base map can be generated based on the page base map of the historical target page to serve as the target base map of the target page, for example: the page base map of the historical target page can be used as a target base map, main information such as color, text and the like of the page base map of the historical target page can be extracted, and a new base map is constructed to be used as the target base map based on the extracted information.
Some embodiments of the present description generate a new base map based on the page base map in the historical target page by learning design ideas from the historical target page designed by the you show designer. Wherein, the number of target base graphs generated based on the page base graphs of the historical target pages can be one or more, such as: one or more target base graphs may be generated based on the page base graphs of one excellent historical target page, or one or more target base graphs may be generated based on the page base graphs of a plurality of excellent historical target pages. Specifically, a machine learning algorithm or model may be used to learn the design idea of the page base map in the historical target page, and the target base map of the target page is generated, and the embodiment of the description of the specific process is not limited specifically.
In some embodiments of the present disclosure, generating a target base graph from page base graphs in a historical target page includes:
acquiring a page base map from a historical target page, and cutting the page base map into a plurality of base map images with different sizes;
analyzing the page base map to obtain base map features of the page base map;
and generating a target base map by using the conditional antagonism network model according to the base map image and the base map characteristics. In a specific implementation process, the main purpose of the process of generating the target base map based on the page base map of the historical target page is to acquire materials on the base map and mine information of the materials, acquire more sizes to generate the target base map with more sizes, and the specific process can be divided into base map acquisition and filtration, base map element analysis, image content restoration and base map regeneration. Specifically, the page base map may be obtained from the historical target page, for example: the function GetSourceImage (inmageObj) may be used to obtain information about the page base map from the historical target page, and then filter the obtained page base map, for example: and filtering out the base drawings which are not suitable for creating the target page, such as unattractive, pure text, typesetting dislocation and the like. And cutting the acquired page base map into a plurality of base map images with different sizes so as to generate a plurality of target base maps with different sizes based on the base map images with different sizes.
In some embodiments of the present description, cutting a page base into a plurality of differently sized base images includes:
dividing the page base map into a plurality of page sub-base maps with different sizes;
carrying out cavity convolution processing on a plurality of page sub-base graphs with different sizes, and fusing the multi-size features of each page sub-base graph to obtain a plurality of page fusion sub-base graphs with different sizes;
and repairing the page fusion sub-base images respectively to obtain a plurality of base image images with different sizes.
In a specific implementation process, after obtaining the page base map of the historical target page, the page base map can be divided into page sub-base maps with different sizes by adopting an encoder-decoder (encoding-decoding) structure based on a full convolution network, for example: the original image can be processed into page sub-base images of 1/2, 1/4, 1/8 and 1/16. And fusing the multi-size features of the plurality of page sub-base graphs with different sizes through hole convolution processing to construct a Segment-matching two-stage fine tuning network, so as to obtain the plurality of page fusion sub-base graphs with different sizes. However, the images cut by the fine-tuning network based on the Segment-matching two-stage may not be smooth enough and have a burr, and in the embodiment of the present disclosure, a GAN (Generative Adversarial Nets) model or an AE (auto encoder) model may be used to repair the fused sub-base map of each page, so as to ensure that the area where the pixels are generated and maintain semantic continuity with the known area.
The initial proposal of the hole convolution is to solve the problem of image segmentation, and common image segmentation algorithms generally use a pooling layer and a convolution layer to increase Receptive field (Receptive filled), reduce the size of a feature map (resolution), and then restore the image size by up-sampling, so that the precision is lost in the process of reducing and re-amplifying the feature map. The hole convolution can increase the receptive field while keeping the feature map size unchanged, thereby replacing the downsampling and upsampling operations. Segment can be understood as a hard Segment, i.e., a Segment of pixels in a picture into multiple categories. The matching can be understood as soft segmentation, which is a type of foreground-background segmentation problem, and the goal of the matching is to find out the color of the foreground and the background and the fusion degree between them so as to combine the foreground onto the new background, and the matching belongs to a regression task.
It can be seen that, in the embodiment of the specification, on the basis of the convolution network, the page base map pages of the historical target pages are subjected to multi-size segmentation, fusion and repair, so that the original page base map can be segmented into base map images with different sizes, and the quality of the original base map is kept as much as possible, thereby being convenient for generating high-quality target base maps with different sizes based on the segmented base map images, and improving the generation quality of the target pages.
In addition, after the page base map of the historical target page is obtained, the filtered page base map of the historical target page can be analyzed, and base map features of the page base map are obtained, for example: main title, subtitle, style, material characteristics, etc. Based on the multi-size base map image obtained by segmentation and the base map features obtained by analysis, a new target base map is generated by using a Conditional-GAN model, which is a network model, and the number of generated target base maps can be determined according to actual needs, and the embodiment of the present disclosure is not limited specifically. Specifically, in the embodiment of the present disclosure, based on the information such as the base image, the main title, the subtitle, the style, etc., how to generate the new base image may be learned from the historical target page, and the generation process of the new base image may be decomposed into four flows: the system comprises a material library module, a planner module, an optimizer module and a generator module. The material library module is responsible for material management and labeling; the planner module is used for learning design habits and rules of a designer in different styles; the optimizer is used for fine adjustment of the result output by the planner; the generator module acts to generate material and ultimately renders the base map. Specific procedures can be referred to as follows:
(1) And a material library module: extracting low-level semantic features by adopting a traditional classifier, and acquiring complex semantic features in a base map by adopting a deep learning method based on CNN (Convolutional Neural Network ) and the like, such as: the function materialfeaturevec=can be employed
The features of the semantic features on the base image are acquired by the features matching (traditionalAlgo (meterials), deepLearningAlgo (meterials)), and the features of the material can be roughly divided into: the method has the advantages that the materials in the base map image can be better understood through labeling the material characteristics, and a data foundation is laid for the generation of a subsequent target base map.
(2) And a planning module: the module mainly learns the material design process in the existing excellent designs in the material library, and can select similar materials from the material library to generate a target base map. The end-to-end training image generation model may be implemented using a Conditional-GAN. In addition, in some embodiments of the present disclosure, the problem of multi-layer overlapping of material layers is considered, which is actually complex for the GAN model, and in the embodiments of the present disclosure, the process of continuously overlapping materials on a base map is analogous to words and sentences in NLP (Natural Language Processing ), and the whole generating process is implemented by using a sequence generating model. The specific process can be as follows: initial input (material base map (i.e. base map image), material characteristics (i.e. material characteristics extracted in step (1)), title (e.g. main title, sub-title), style), embedding processing, multi-layer LSTM (Long Short-Term Memory network), material characteristic sequence. In this process, the result output by a single path may not be optimal enough, and a plurality of supervised sequence generation may be introduced, and the generated loss is comprehensively evaluated, so as to generate a final target base graph. The material feature sequence may be understood as attribute information on the target base map, such as: brightness, font, color, etc., and the embodiment of the present specification is not particularly limited. The user can also customize the theme color or style when generating the target base map, and specifically can adjust according to actual needs, and the embodiment of the specification is not particularly limited.
(3) And an optimization module: the module is mainly used for carrying out optimization processing on the generated target base map, including base map brightness, small icon movement, base map scaling, font correction, rendering enhancement and the like, wherein an evaluation function is a template evaluation function of a template evaluation item, and the target base map with better quality is selected by continuously converging with a score difference as loss.
(4) The generation module is used for: rendering the material characteristic sequence generated in the step (3) through a generator to generate a final target base map, and a general scheme is not described herein.
According to the embodiment of the specification, the page base map of the historical target page designed by the excellent designer is intelligently learned, the base map of the excellent target page is general in universality, the target base map of the target page is automatically generated based on the historical target page by using a machine learning algorithm, automatic generation of the base map is realized, the page base map of the excellent target page is learned, the quality of the target base map can be ensured, and further the quality of the target page is ensured.
S204: and automatically combining the materials in the material library according to a predefined material combination rule based on the layout patterns in the historical target page, and generating a picture layout on the target base map.
In a specific implementation process, in a target page development process, materials are taken as important components of a target page, and the materials can comprise pictures, characters, icons, backgrounds, videos, audios, animations and the like, so that the problems of diversity and usability of page generation are related to how to arrange and combine various materials to generate target pages of different styles. In the embodiment of the present disclosure, after the target base map is generated, the layout patterns in the history target page may be learned as follows: and automatically combining the materials based on the layout patterns in the historical target pages according to the material combination rules by utilizing a material library and a predefined material combination rule to generate the picture layout of the target pages. The material library can be collected and constructed according to the service requirement or scene of the target page which is required to be created, for example: if a target page of the product A needs to be generated, pictures, characters, icons, backgrounds, videos, audios, animations and the like related to the product A can be collected to construct a material library. The specific content and the construction method of the material library are not specifically limited in the embodiment of the present specification, and in addition, the materials in the material library may be understood as objects of entities, such as: pictures, words, icons, etc., the material on the base map of the page described in the above embodiments may be understood as the features of the material on the base map, and are mainly used to represent the visual effect on the base map, for example: color, brightness, etc., which differ somewhat.
In some embodiments of the present disclosure, a method for obtaining a layout style in a history target page includes:
acquiring the image embedded information of a page base map in a historical target page;
acquiring distribution information of hidden space vectors in the image embedded information by using an encoding module in a deformer model;
and decoding the distribution information of the hidden space vector by using a decoding module in the deformer model to obtain the layout style of the historical target page.
In a specific implementation, the nature of the layout may be understood as an abstract set of material+locations, and in some embodiments of the present disclosure, a deep learning-based algorithm may be employed to learn the layout style in the historical target page. Firstly, the embedding information of an image (such as a page base diagram) in a historical target page can be obtained, and then the distribution information of the hidden space vector X of the image can be obtained through a transformer, namely an encoding module in a deformer model, such as: and sampling the mean value and the variance of X, and finally obtaining the position and the category of each material in the graph through a decoder, namely a decoding module to obtain and generate the layout style in the historical target page.
According to the embodiment of the specification, the layout patterns of the excellent historical target pages are learned by using a machine learning algorithm, on the basis, materials in a material library are freely combined by combining defined material combination rules, rich and various page effects are generated, meanwhile, the layout patterns of the excellent historical target pages are learned, and under the constraint of the layout patterns of the excellent target pages, the materials are freely combined according to the material combination rules, so that the generated new picture layout is close to the design thought of an excellent designer, the quality of the picture layout of the target pages is improved, and flexible combination and efficient utilization of the materials are realized.
In addition, in some embodiments of the present disclosure, specific content of a material combination rule is further provided, where the material combination rule may include at least one of the following: color matching rules; the same color brightness changes and matches the rule; a rule of matching adjacent color changes; button elements are matched with color change matching rules; decorative textures and texture collocation rules; frame background collocation rules; font collocation rules; decorative patterns, textures, outline frames and light and shadow collocation rules; the matching rules of decorations (such as small decorations, small props, mascot, etc.); layout and size collocation; the definition of the picture is regular. It can be seen that the material combination rule defines collocation combination rules of colors, same-color brightness, adjacent color change, decoration, fonts, props and the like, and based on the material combination rule, the free combination of different materials can be realized, for example: based on the color matching rules, different materials in the material library are freely combined according to the set color matching rules, so that picture layouts of different styles are obtained, the requirements of different users are met, and the richness of pages is improved.
In some embodiments of the present specification, the process of freely combining materials may refer to the following:
1) And (3) collecting and reading materials: and constructing a standard material library from different types of materials including pictures, characters, icons, backgrounds, videos, audios, animations and the like.
2) Defining abstract template classes: the step defines the basic structure and style of the target page, including layout, background, color, texture, font and the like, and can learn the excellent layout style of the historical target page, and the layout style of the historical target page is taken as the basic structure and style of the target page.
3) Defining a material combination rule: based on the material type and the characteristics, a material combination rule is defined, and the material combination rule in some embodiments of the present specification may refer to the following:
(1) Color matching rules: the color phase of the whole color is not more than three, and each color phase can be changed by two brightness at most;
(2) Module & background rules: matching the same color brightness change and adjacent color change;
(3) Button, main element & background rules: element contrast color change matching and secondary button adjacent color change matching;
(4) Decorative pattern & texture rules: the brightness of the same color is changed and matched;
(5) Frame & background rules: element contrast color change matching;
(6) Font collocation rules: no more than three fonts, the font types are limited to a head map font, a title font and a text font;
(7) Decorative pattern, texture, outline border, light and shadow collocation rule: selecting one or more kinds of collocations;
(8) Small decorations & small props & mascot collocation rules: adding small decorations, small props or mascot, and enhancing visual atmosphere;
(9) Layout & size collocation rules: the layout comprises a head diagram, a login, an active area, a text area, a shading and the like, and the size proportion is selectable: 1:2:2:1, 1:3:3:1, 2:5:4:3:1, etc.;
(10) Picture definition rule: the selectable types are classified into normal definition, good definition and fine definition, and can be measured by using the value range of 0 to 100.
3) And a material automatic combination module: based on the set material combination rule, automatically combining materials on the basis of the layout style of the historical target page, and generating picture layouts of different styles.
Of course, the material combination rules described in the above embodiments may be modified, adjusted or supplemented according to actual needs, and the embodiments of the present disclosure are not limited specifically.
S206: and generating a page document on the target base map according to the text information, the target base map and the picture layout in the historical target page.
In a specific implementation process, after the base map and the layout are determined, a corresponding page document can be generated on the target base map based on text information in the historical target page and the generated target base map and picture layout. The page document may include: text information, and fonts, sizes, positions, specific text contents, and the like of the text. For example: the layout can contain text position information, and the text information in the historical target page can be added into the target base map according to the text position information in the picture layout. In general, the page document of the excellent page also has universality, and the page document of the target page can be generated based on the page document of the excellent page. Of course, according to actual use needs, appropriate text information may also be selected from the material library and added to the target base chart, or the user may edit and modify the generated page text according to needs, which is not specifically limited in the embodiment of the present disclosure.
In some embodiments of the present disclosure, generating a page document at a target base map according to text information, the target base map, and a picture layout in a history target page includes:
acquiring basic attributes of objects on a target base map and text information on a history target page;
Respectively extracting the basic attribute, text information, picture layout and embedded information corresponding to the multi-layer frame nested logic dependency relationship of the preset target page;
inputting the extracted embedded information into a multi-layer deformer model to generate an element logic sequence of a page document;
and adding the element logic sequence to the target base diagram to obtain the page document.
In a specific implementation process, the conventional general graph upper file generation scheme is based on rule file replacement and predefined template matching, so that the scheme is not flexible enough and needs a large amount of manual participation. Fig. 3 is a schematic diagram of page document generation in an embodiment of the present disclosure, as shown in fig. 3, in the embodiment of the present disclosure, a mode of generating page documents based on deep learning is adopted, and in the embodiment of the present disclosure, correspondence between documents, base map commodities and text boxes is considered, so as to satisfy suitability of documents and positions and coordination of commodities and document styles, and provide a scheme of an N-layer transducer model with multi-modal input. As shown in fig. 3, in the embodiment of the present disclosure, a machine learning model is proposed, where the model may include a plurality of embedding modules, each of the embedding modules may be used to extract embedding information of corresponding data, where Image embedding may represent a picture embedding module, object location embedding may represent an object position (i.e., a multi-layer frame nested logical dependency) embedding module, color embedding may represent a Color embedding module, category embedding may represent a category embedding module, title & text embedding may represent a Title text embedding module, and layout embedding module. Text information on the page base of the historical target page and basic attributes of the object on the target base can be acquired firstly, such as: the type, location, or ground color of merchandise or props, etc. Data such as basic attributes (types, positions and ground colors) of objects (commodities/props and the like) on a target base map, text information on the map, layout information, multi-layer frame nesting logic dependency relations and the like are used as input of a model, and after the corresponding EMBedding module processes the information, embedded information of corresponding data is extracted and then is uniformly input into an N-layer transformer model. The multi-layer box nested logical dependency relationship can be understood as a nested logical relationship between each layer or material or document in the page.
As shown in fig. 3, the embodiment of the present disclosure includes a multi-layer transformer, and the information extracted by the embedding module is input into the multi-layer transformer, and the output of the multi-layer transformer can generate the element sequence depending on the front and back, i.e., the element logic sequence of the page document, i.e., the prediction result of the result layer in fig. 3 through prediction (prediction model). Wherein, the prediction may select an autoregressive model, and the element logic sequence may include: text and logical relationships between text and other material, the font of the words in the text, the word size, the layer of text on the base map, which area the text is placed in, whether there is a lace, etc. And adding the element logic sequence of the page document to the target base graph according to the logic relationship, thus generating the page document.
According to the embodiment of the description, the text in the excellent template is learned by using the deep learning algorithm, and the page text in the new page to be generated is automatically generated, so that the automatic generation of the text is realized, the matching based on the preset template is not needed, the replacement of the text on the existing template is not needed, the manual participation is reduced, and the flexibility and the efficiency of the text generation are improved.
And S208, rendering the object base map, the picture layout and the element attribute on the page document to generate the object page.
In a specific implementation process, after the target base map, the picture layout and the page document are generated, rendering of element attributes can be performed to generate a target page. The element attribute may be understood as visual attributes in the target base map, the picture layout and the page document, such as: visual effects of color, sharpness, fonts, borders, and the like. Rendering of the element attribute can be understood as enhancement processing of the visual attribute of the target base map, the picture layout and the page document, and the display effect of the target page is improved. The whole distribution of the target base map, the picture layout and the page document can be cut, and the generated whole distribution effect of the target page can be better through rendering of the element attributes. Element attribute rendering may include: whether the text in the page document needs gradual change, font creative adjustment, tracing and the like can be specifically determined according to actual use scenes, and the embodiment of the specification is not limited specifically.
According to the page generation method provided by the embodiment of the specification, a template filling-based scheme is bypassed, a process of simulating a designer to make creatives is selected, a page base map, a layout and a document of a historical target page designed by an excellent designer are learned, a target base map, a picture layout and a page document required by the target page are generated, and then element rendering is carried out to generate the target page. Compared with the template filling scheme, the method realizes the automatic and intelligent generation of the target page, can more flexibly determine the page attributes such as layout, style, font size and the like, and improves the flexibility of page generation. In addition, when the picture layout of the target page is generated, the materials of the material library are freely combined according to the layout style of the historical target page based on the predefined material combination rule, so that the picture layout of different styles can be obtained, the requirements of different users are met, rich and various page effects are generated, flexible combination and efficient utilization of the materials are realized, and the flexibility of page generation is further improved.
In some embodiments of the present disclosure, the generated image layout includes image layouts of different styles, rendering element attributes on a target base map, the image layout, and a page document, and generating a target page includes:
rendering the target base map, the picture layout of different styles and the element attribute on the page document to generate target pages of different styles;
scoring the target pages in different styles, and determining screening target pages based on the scores of the target pages in different styles.
In a specific implementation process, referring to the description of the embodiment, when materials in the material library are freely combined, different types of picture layouts can be obtained, and different types of target pages can be generated based on the different types of picture layouts. After obtaining the target pages with different styles, scoring the target pages with different styles, for example: machine learning algorithms (such as deep learning algorithms, random depths Lin Suanfa and the like) can be used for scoring the target pages in different styles, and the target pages with good quality are selected to be used as screening target pages based on the scores of the target pages. The number of the screening target pages can be determined according to actual needs, the target pages with scores larger than a preset threshold value can be used as the screening target pages, and the target pages with scores ranked in the appointed ranking can be used as the screening target pages.
According to the embodiment of the specification, based on different material combination rules, the materials are freely combined to generate pages with different styles, and the pages are subjected to manual screening or intelligent screening, for example: the score of the generated target page is obtained through automatic scoring of the target page, so that a large number of high-quality target pages can be obtained rapidly, the generation quality of the pages is improved, and the usability of the generated pages is guaranteed.
In some embodiments of the present description, the method further comprises:
when the target page is applied to target equipment, acquiring page parameters of the target page and equipment information of the target equipment;
generating a basic layout of the target page based on the page parameters and the equipment information;
and generating an adaptive target page of the target equipment according to the preset responsive rule and basic layout, and displaying the adaptive target page in a screen of the target equipment.
In a specific implementation process, parameters such as size, resolution ratio and the like of different devices are likely to be different, and in the embodiment of the present disclosure, when the generated target page is applied to the target device, an algorithm of a page self-adaptive device is provided, and according to user requirements and scene characteristics, a page suitable for the target device is automatically generated. Specific procedures can be referred to as follows:
1) Initializing page parameters: the page parameters of the target page may be obtained first, where the page parameters may include layout, style, pixels, initial base map size, elements, and the like of the page, and the embodiment of the present disclosure is not limited specifically.
2) Reading in input data: acquiring device information of the target device, the device information may include: screen size, resolution, pixel density, etc.
3) Data preprocessing: based on the device information and the page parameters, a base layout is designed, which may include: page width, height, border, region segmentation, region location, region size, font size, theme color, background color, adjacent color, decorative pattern, texture, etc. In addition, a generalized vector processing tool may be further used to vector device information and/or page parameters, each class is converted into 128-bit vectors, and the converted vectors may be used for calculating page similarity, such as: and calculating the similarity between the generated target page and the excellent historical target page, scoring the target page, and screening the excellent target page.
4) Defining a response rule: the adoption of the responsive design can enable the page to adapt to screens with different sizes, and the responsive rule comprises information such as layout, style, element display and hiding under different screen sizes; the responsive rules may be a rule such as an elastic box layout mode, a streaming layout mode, a percentage layout mode, a dynamic picture, and a media query, and one of the responsive rules may be selected according to an actual usage scenario. The specific implementation process of each responsive rule can be referred to as follows:
Elastic box layout mode: placing the elements in the page in an elastic box layout, automatically adjusting the size and the position according to the available space, and specifically implementing that the elastic box layout can be implemented by using the Flexbox layout technology in the CSS (of course, there are many other implementations, which are not described here again);
stream layout mode: placing the elements in the page in a streaming layout, so that the elements in the page can be automatically adjusted in size and position according to the under-band and position of the browser window, and the streaming layout in CSS can be adopted;
percentage layout mode: the width and height of the element can be set by using the percentage in the CSS, for example, the width of the page body is set to be not 80%, so that the page body is kept in a certain proportion under different screen sizes;
moving picture and media query modes: the method has the advantages that a dynamic loading mode is adopted, the size of a screen is detected through pictures or each query, and different CSS styles are applied according to requirements, so that the method is suitable for loading on different equipment faster and has better adaptability;
5) And (3) page generation: based on the basic layout and the response type rule, a template function is called, the generated target page is automatically subjected to operations such as stretching, translation and replacement, the self-adaptive adjustment of the material is realized through the intelligent adjustment of the size, the position and the style of the material, and the self-adaptive target page comprising code information such as HTML, CSS, JS is generated, and can adapt to the screen size and the resolution of target equipment.
6) Template application: and displaying the adaptive target page generated in the step 5) in a screen of the target device.
In the page generation process, the self-adaptive algorithm can be utilized to stretch, translate and replace the materials according to the characteristics of the materials and the requirements of users, and the self-adaptive adjustment of the materials is realized by intelligently adjusting the sizes, the positions and the styles of the materials, so that the generated page can be automatically adapted to the screen sizes and the resolutions of different target devices, and the display effect of page application is improved. And the whole process does not need excessive code editing, so that page generation of a low-code design is realized, the workload of developers can be reduced, the development efficiency is improved, the conditions of stretching distortion or compression can not occur, and the page display effect and the user experience are improved.
In some embodiments of the present disclosure, after generating the adaptive target page for the target device, the method further includes:
and calculating the self-adaption degree of the self-adaption target page by adopting a self-adaption algorithm, and carrying out optimization adjustment on the self-adaption target page based on the self-adaption degree.
In a specific implementation process, after the generated target page is applied to the target device and the target page is adaptively displayed on the target device by adopting the method provided by the embodiment, the self-adaption degree of the page can be calculated by adopting a self-adaption algorithm, the self-adaption target page is continuously adjusted and optimized, the adaption degree between the page and the target device is improved, and further the display effect of the page in the target device is improved. The self-adaption can be understood as automatically adjusting a processing method, a processing sequence, processing parameters, boundary conditions or constraint conditions according to the data characteristics of the processed data in the processing and analyzing processes, so that the processing parameters, the boundary conditions or the constraint conditions are adapted to the statistical distribution characteristics and the structural characteristics of the processed data to obtain the optimal processing effect. An adaptive process is a process that continuously approximates a target, and the path followed by the adaptive process is represented by a mathematical model, which is called an adaptive algorithm. The specific algorithm of the adaptive algorithm can be selected according to actual needs, for example: gradient-based algorithms, genetic algorithms, or the like may be selected, and the embodiments of the present specification are not particularly limited. The self-adaptation degree of the self-adaptive target page can be understood as the matching degree of the self-adaptive target page and the target device, the calculation method can be set according to actual needs, and the embodiment of the specification is not particularly limited.
The embodiment of the specification provides a page generation method of low-code design, and a user only needs to input a few simple configuration items such as: color theme, historical target pages, material libraries and the like can be self-adaptive page generation, material stretching, translation and replacement and free material combination, and a large number of pages are automatically generated based on the existing material libraries; and then the score of the generated target page is obtained through an automatic scoring module, so that a large number of high-quality pages can be quickly obtained. According to the page generation method provided by the embodiment of the specification, a set of automation scheme for page generation is designed, each step can be completed by a machine learning model, page design ideas of excellent designers are learned, new target pages are generated based on historical target pages, materials in a material library and the like, so that the problem of page generation and filling of the socket is solved, the adaptability and usability of the page are improved well, the page development efficiency, the adaptability of the page under different devices or screens and the usability of free combination of page materials are improved, and further flexible generation of the page is realized, and template filling is not relied on.
Based on the page generation method, one or more embodiments of the present disclosure further provide a client and a server for page generation processing. The client, server, etc. may include devices (including distributed systems), software (applications), modules, components, servers, clients, etc. that use the methods described in the embodiments of the present disclosure, in combination with the necessary devices to implement the hardware. Based on the same innovative concepts, the embodiments of the present description provide means in one or more embodiments as described in the following embodiments. Because the implementation schemes and methods of the device for solving the problems are similar, the implementation of the device in the embodiments of the present disclosure may refer to the implementation of the foregoing method, and the repetition is omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
As can be seen from the technical solutions provided by the embodiments of the present disclosure, the embodiments of the present disclosure further provide a page generating device, and fig. 4 is a schematic structural diagram of the page generating device provided by the embodiments of the present disclosure, as shown in fig. 4, where the device includes:
the base map generating module 410 is configured to generate a target base map according to page base maps in the historical target pages;
the layout generation module 420 is configured to automatically combine materials in a material library according to a predefined material combination rule based on a layout style in the historical target page, and generate a picture layout on the target base map;
a document generation module 430, configured to generate a page document on the target base map according to text information in the historical target page, the target base map, and the picture layout;
and the page generation module 440 is configured to render the target base map, the picture layout, and the element attribute on the page document, and generate a target page.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein. The description of the apparatus in the foregoing embodiments according to the method embodiments may further include other implementations, and specific implementation may refer to the description of the related method embodiments, which are not described herein in detail.
Fig. 5 is a block diagram of an electronic device for page generation, which may be a terminal, and an internal structure diagram thereof may be as shown in fig. 5, provided in an embodiment of the present disclosure. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the electronic device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a page generation method. The display screen of the electronic equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the electronic equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
Fig. 6 is a block diagram of another electronic device for page generation, which may be a server, and an internal structure diagram thereof may be as shown in fig. 6, provided in the embodiment of the present specification. The electronic device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic device includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the electronic device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a page generation method.
It will be appreciated by those skilled in the art that the structures shown in fig. 5 or 6 are merely block diagrams of partial structures related to embodiments of the present specification and do not constitute limitations of the electronic devices to which the embodiments of the present specification apply, and that a particular electronic device may include more or fewer components than shown, or may combine certain components, or have different arrangements of components.
In an exemplary embodiment, there is also provided an electronic device including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the page generation method as in the embodiments of the present specification.
In an exemplary embodiment, a computer-readable storage medium is also provided, which when executed by a processor of an electronic device, enables the electronic device to perform the page generation method in the embodiments of the present specification.
In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the page generation method provided in the various alternative implementations described above.
It will be appreciated that in the detailed description of the present invention, data relating to users is referred to, and when the above embodiments of the present invention are applied to particular products or technologies, user approval or consent is required, and the collection, use and processing of the relevant data is required to comply with relevant laws and regulations and standards of the relevant countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
Other implementations of the examples herein will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This description is intended to cover any variations, uses, or adaptations of the embodiments following, in general, the principles of the embodiments and including such departures from the present disclosure as come within known or customary practice within the art to which the embodiments are not disclosed. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the embodiments being indicated by the following claims.
It is to be understood that the embodiments of the present specification are not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be made without departing from the scope thereof. The scope of the embodiments of the present specification is limited only by the appended claims.
Claims (12)
1. A method of generating a page, the method comprising:
generating a target base map according to the page base map in the historical target page;
automatically combining materials in a material library according to a predefined material combination rule based on the layout style in the historical target page, and generating a picture layout on the target base map;
Generating a page document on the target base map according to the text information in the historical target page, the target base map and the picture layout;
rendering the target base map, the picture layout and the element attribute on the page document to generate a target page.
2. The method of claim 1, wherein the generating the target base map from the page base maps in the historical target pages comprises:
acquiring a page base map from the historical target page, and cutting the page base map into a plurality of base map images with different sizes;
analyzing the page base map to obtain base map features of the page base map;
and generating the target base map by using a conditional countermeasure network model according to the base map image and the base map features.
3. The method of claim 2, wherein the cutting the page base into a plurality of differently sized base images comprises:
dividing the page base map into a plurality of page sub-base maps with different sizes;
carrying out cavity convolution processing on the plurality of page sub-base graphs with different sizes, and fusing the multi-size features of each page sub-base graph to obtain a plurality of page fusion sub-base graphs with different sizes;
And repairing the page fusion sub-base map respectively to obtain a plurality of base map images with different sizes.
4. The method according to claim 1, wherein the method for acquiring the layout style in the history target page comprises:
acquiring the image embedded information of the page base map in the historical target page;
acquiring distribution information of hidden space vectors in the image embedded information by using an encoding module in a deformer model;
and decoding the distribution information of the hidden space vector by using a decoding module in the deformer model to obtain the layout style of the historical target page.
5. The method of claim 1, wherein the material combining rule comprises at least one of: color matching rules; the same color brightness changes and matches the rule; a rule of matching adjacent color changes; button elements are matched with color change matching rules; decorative textures and texture collocation rules; frame background collocation rules; font collocation rules; decorative patterns, textures, outline frames and light and shadow collocation rules; decoration matching rules; layout and size collocation; the definition of the picture is regular.
6. The method of claim 1, wherein the generated picture layout includes picture layouts of different styles, the rendering the target base map, the picture layout, the element attributes on the page document, and generating the target page comprises:
Rendering the target base map, the picture layout of different styles and the element attribute on the page document to generate target pages of different styles;
and scoring the target pages in different styles, and determining screening target pages based on the scores of the target pages in different styles.
7. The method of claim 1, wherein the generating a page document at the target base from the text information in the historical target page, the target base, the picture layout, comprises:
acquiring basic attributes of the objects on the target base map and text information on the historical target page;
respectively extracting the basic attribute, the text information, the picture layout and embedded information corresponding to a multi-layer frame nesting logic dependency relationship of a preset target page;
inputting the extracted embedded information into a multi-layer deformer model to generate an element logic sequence of a page document;
and adding the element logic sequence to the target base diagram to obtain the page document.
8. The method according to claim 1, wherein the method further comprises:
when the target page is applied to target equipment, acquiring page parameters of the target page and equipment information of the target equipment;
Generating a basic layout of the target page based on the page parameters and the equipment information;
and generating an adaptive target page of the target equipment according to a preset responsive rule and the basic layout, and displaying the adaptive target page in a screen of the target equipment.
9. The method of claim 8, wherein after generating the adaptive target page for the target device, the method further comprises:
and calculating the self-adaption degree of the self-adaption target page by adopting a self-adaption algorithm, and carrying out optimization adjustment on the self-adaption target page based on the self-adaption degree.
10. A page generating apparatus, the apparatus comprising:
the base map generation module is used for generating a target base map according to the page base map in the historical target page;
the layout generation module is used for automatically combining the materials in the material library according to a predefined material combination rule based on the layout patterns in the historical target page, and generating a picture layout on the target base map;
the document generation module is used for generating a page document on the target base map according to the text information in the historical target page, the target base map and the picture layout;
And the page generation module is used for rendering the target base map, the picture layout and the element attribute on the page document to generate a target page.
11. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the page generation method of any of claims 1 to 9.
12. A computer readable storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the page generation method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310847496.5A CN116954605A (en) | 2023-07-11 | 2023-07-11 | Page generation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310847496.5A CN116954605A (en) | 2023-07-11 | 2023-07-11 | Page generation method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116954605A true CN116954605A (en) | 2023-10-27 |
Family
ID=88443706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310847496.5A Pending CN116954605A (en) | 2023-07-11 | 2023-07-11 | Page generation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116954605A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117576247A (en) * | 2024-01-17 | 2024-02-20 | 江西拓世智能科技股份有限公司 | Picture generation method and system based on artificial intelligence |
-
2023
- 2023-07-11 CN CN202310847496.5A patent/CN116954605A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117576247A (en) * | 2024-01-17 | 2024-02-20 | 江西拓世智能科技股份有限公司 | Picture generation method and system based on artificial intelligence |
| CN117576247B (en) * | 2024-01-17 | 2024-03-29 | 江西拓世智能科技股份有限公司 | Picture generation method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10984177B2 (en) | System and method providing responsive editing and viewing, integrating hierarchical fluid components and dynamic layout | |
| US10657652B2 (en) | Image matting using deep learning | |
| AU2020284731B2 (en) | System and method for integrating user feedback into website building system services | |
| US8456467B1 (en) | Embeddable three-dimensional (3D) image viewer | |
| CN115511969B (en) | Image processing and data rendering method, apparatus and medium | |
| CN114514560A (en) | Image replacement repair | |
| CN117058271A (en) | Method and computing device for generating commodity main graph background | |
| CN112257406A (en) | Content cover generator and method based on web front end | |
| CN116954605A (en) | Page generation method and device and electronic equipment | |
| US20200279355A1 (en) | Previewing a content-aware fill | |
| CN117372570A (en) | Advertisement image generation method and device | |
| Ji et al. | Design and development of a maintenance and virtual training system for ancient Chinese architecture | |
| US20240144623A1 (en) | Modifying poses of two-dimensional humans in two-dimensional images by reposing three-dimensional human models representing the two-dimensional humans | |
| US20240144520A1 (en) | Generating three-dimensional human models representing two-dimensional humans in two-dimensional images | |
| US20240144586A1 (en) | Generating shadows for objects in two-dimensional images utilizing a plurality of shadow maps | |
| GB2623623A (en) | Stylized glyphs using generative AI | |
| US20240256218A1 (en) | Modifying digital images using combinations of direct interactions with the digital images and context-informing speech input | |
| US20240169628A1 (en) | Moving objects casting a shadow and generating porxy shadows within a digital image | |
| Setlur et al. | Retargeting vector animation for small displays | |
| US20230123658A1 (en) | Generating shadows for digital objects within digital images utilizing a height map | |
| US20240135612A1 (en) | Generating shadows for placed objects in depth estimated scenes of two-dimensional images | |
| US20240127509A1 (en) | Generating scale fields indicating pixel-to-metric distances relationships in digital images via neural networks | |
| US20240257421A1 (en) | Generating and using behavioral policy graphs that assign behaviors to objects for digital image editing | |
| CN117437135A (en) | Image background switching method, device and medium | |
| CN117853612A (en) | Generating a modified digital image using a human repair model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |