Page design auxiliary processing method and device, and electronic equipment

Abstract

Embodiments of the present application disclose a page design auxiliary processing method and device and electronic equipment. The method comprises: obtaining target information of a page design; determining a target design material and a target layout mode that match the target information of the page design from a pre-obtained design material set and a layout mode set; and determining a recommended design scheme according to the target design material and the target layout mode. Through the embodiments of the present application, the design efficiency of a front-end interface can be improved.

Description

Technical Field

[0001] This application relates to the field of interface-aided design technology, and in particular to page design aid processing methods, devices and electronic devices. Background Technology

[0002] For applications (Apps) or websites, the visual effect of the front-end interface (UI) provides users with a direct psychological experience. When designing front-end pages, the selection of the main color scheme and the layout of related visual elements directly affect the overall style of the page design. Furthermore, the visual effect of the front-end interface is also an important means of conveying ideas to the outside world; therefore, front-end page design is extremely important.

[0003] The traditional front-end interface development chain is as follows: product engineers propose specific requirements and corresponding goals; designers, based on these requirements and goals, derive design intent, conduct corresponding design work, including material selection and layout, and produce design drafts; finally, code engineers recreate the design drafts using code. However, to address the issue of different user groups having different visual preferences, some applications or websites have introduced a "personalized" visual solution. That is, the same interface or module can display different visual effects when targeting different user groups. For example, when targeting elderly users, the visual style can be more minimalist with larger fonts, while when targeting younger users, a more lively and fashionable style can be adopted, and so on.

[0004] However, the workload for designers is quite heavy in the process of recommending different visual effects to different groups of people. Previously, designers only needed to design one visual draft for each requirement. Now, because of the need for "personalized experiences," designers need to design multiple styles and designs for a single interface or module, producing multiple design drafts, and then generating visual code for each. This is especially true in systems such as product information services, which involve a large number of interfaces and frequently launch various marketing campaigns. Each marketing campaign requires the design of interface visual effects. Combined with the aforementioned requirement to design multiple different visual effects for different groups, the workload for designers becomes even heavier, and efficiency is very low.

[0005] Therefore, how to improve the design efficiency of front-end interfaces has become a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0006] This application provides recommended methods, devices, and electronic equipment for page design, which can improve the efficiency of front-end interface design.

[0007] This application provides the following solution:

[0008] A page design auxiliary processing method, comprising:

[0009] Obtain the target information for the page design;

[0010] From the pre-acquired set of design materials and layout methods, determine the target design materials and target layout methods that match the target information of the page design;

[0011] Based on the target design materials and target layout, a recommended design scheme is determined.

[0012] A page design auxiliary processing method, comprising:

[0013] Obtain the target information for the page design;

[0014] Feature extraction is performed on the target information of the page design;

[0015] By comparing the extracted features with the features corresponding to multiple historical design targets, historical design targets that meet the similarity criteria with the target information of the page design are identified.

[0016] Based on the historical design schemes corresponding to the historical design objectives that meet the conditions, a recommended design scheme is determined.

[0017] A page design auxiliary processing method, comprising:

[0018] Provide an interface for page design, the interface including operation options for obtaining recommended design schemes;

[0019] After receiving an operation request through the operation options, the target information of the input page design is received;

[0020] Based on the target information of the page design, a recommended design scheme is provided. The recommended design scheme is generated based on the target design materials and target layout methods that match the target information of the page design.

[0021] A method for processing a page design algorithm model, comprising:

[0022] Obtain historical design records, which include multiple historical design goals and corresponding historical design schemes, and the historical design schemes include design materials and layout information;

[0023] Obtain a collection of design materials and layout options;

[0024] Feature extraction is performed on the historical design objectives;

[0025] The target algorithm model is trained by using the extracted features, the set of design materials, the set of layout methods, and the information of the corresponding historical design schemes.

[0026] A page design auxiliary processing device, comprising:

[0027] The design target acquisition unit is used to acquire target information for page design.

[0028] The determining unit is used to determine the target design material and target layout method that match the target information of the page design from the pre-acquired set of design materials and set of layout methods;

[0029] The recommended design scheme determination unit is used to determine the recommended design scheme based on the target design materials and target layout method.

[0030] A page design auxiliary processing device, comprising:

[0031] The design target acquisition unit is used to acquire target information for page design.

[0032] The feature extraction unit is used to extract features from the target information of the page design;

[0033] The similarity comparison unit is used to determine the historical design target that meets the similarity condition with the target information of the page design by comparing the extracted features with the features corresponding to multiple historical design targets.

[0034] The recommended design scheme determination unit is used to determine the recommended design scheme based on the historical design schemes corresponding to the historical design objectives that meet the conditions.

[0035] A page design auxiliary processing device, comprising:

[0036] An interface providing unit is used to provide an interface for page design, the interface including operation options for obtaining recommended design schemes;

[0037] The target receiving unit is used to receive the target information of the input page design after receiving the operation request through the operation options;

[0038] The recommended design scheme providing unit is used to provide recommended design schemes based on the target information of the page design. The recommended design schemes are generated based on target design materials and target layout methods that match the target information of the page design.

[0039] A processing device for a page design algorithm model, comprising:

[0040] The historical design record acquisition unit is used to acquire historical design records, which include multiple historical design targets and corresponding historical design schemes. The historical design schemes include design materials and layout information.

[0041] The collection retrieval unit is used to retrieve the collection of design materials and the collection of layout methods;

[0042] A feature extraction unit is used to extract features from the historical design objectives;

[0043] The model training unit is used to train the target algorithm model by utilizing the extracted features, the set of design materials, the set of layout methods, and the information of the corresponding historical design schemes.

[0044] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0045] In this embodiment, a set of optional design materials and a set of layout methods can be obtained in advance. After determining the design target information, target design materials and target layout methods that match the target information of the page design can be determined from the set of design materials and the set of layout methods. This allows for the generation of a complete design scheme for recommendation to users. This scheme automatically determines the layout and design material combination that meets the page design target, thereby generating a complete design scheme. This ensures that the recommended result is a complete design scheme, which designers can modify or fine-tune before delivery, or even deliver directly. Therefore, it improves the efficiency of page design.

[0046] In an optional implementation, an algorithm model for automatically generating design schemes can be developed based on experience from a large number of previous design drafts. Then, based on this algorithm model, matching target design materials and layout methods are determined for the specific page design's target information. Because the learning process utilizes the correspondence between historical design schemes, historical design goals, design materials, and layout methods, and can even consider factors such as the designer's personal style and habits for recommendations, the recommended design schemes are more likely to meet the needs of the actual design process.

[0047] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a schematic diagram of the system architecture provided in the embodiments of this application;

[0050] Figure 2 This is a flowchart of the first method provided in the embodiments of this application;

[0051] Figure 3 This is a schematic diagram of the interface provided in an embodiment of this application;

[0052] Figure 4 This is a schematic diagram of the design flow system provided in the embodiments of this application;

[0053] Figure 5 This is a flowchart of the second method provided in the embodiments of this application;

[0054] Figure 6 This is a flowchart of the third method provided in the embodiments of this application;

[0055] Figure 7 This is a flowchart of the third method provided in the embodiments of this application;

[0056] Figure 8 This is a schematic diagram of the first device provided in the embodiments of this application;

[0057] Figure 9 This is a schematic diagram of the second device provided in the embodiments of this application;

[0058] Figure 10 This is a schematic diagram of the third device provided in the embodiments of this application;

[0059] Figure 11 This is a schematic diagram of the fourth device provided in the embodiments of this application.

[0060] Figure 12 This is a schematic diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0061] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0062] In this embodiment, a corresponding auxiliary design scheme is provided to improve the design efficiency of the front-end interface. This scheme allows for the pre-saving of a set of selectable design materials and a set of layout methods. During the auxiliary design process, the user can input specific design target information, including requirements documents, design intent, etc. The system can then determine target design materials and target layout methods that match the target information from the specific set of design materials and layout methods, and determine a recommended design scheme based on these target materials and layout methods. The user can then further design based on the recommended design scheme or directly deliver the design, thereby improving efficiency.

[0063] Specifically, design materials refer to the basic elements of page design, which can be categorized by granularity into components, basic components, modules, etc. Layout methods can specifically include layers, the distribution and arrangement of design materials within layers, and display styles. By arranging specific design materials according to a certain layout method, a specific design scheme can be formed. The auxiliary design scheme provided in this application embodiment automatically selects target design materials and target layout methods based on the user-input page design target information, and generates a corresponding design scheme for recommendation to the user.

[0064] Specifically, there are several ways to determine the target design materials and layout methods that match the target information of the page design. One approach is to use historical design records as training samples to train an algorithm model. In this way, the design target information can be input into the algorithm model, automatically matching suitable design materials and layout methods for the specific design target, thereby generating the corresponding design scheme.

[0065] Specifically, when using the algorithm model for training and prediction, the typical page design process usually begins by determining the design goals (which may include requirements documents, design intent, design materials to be included or excluded, etc.). Then, the designer selects design materials and determines the layout based on these goals. Therefore, historical design records can save not only the specific design schemes but also the corresponding design goals, allowing us to establish a correspondence between historical design schemes and design goals. Furthermore, specific design schemes are usually stored in a file format, from which information such as included design materials and layout methods can be extracted. This allows us to establish a correspondence between design schemes and their corresponding design materials and layout methods. Thus, through these two correspondences, we can establish a relationship between historical design goals, historical design schemes, design materials, and layout methods. This correspondence can then be used to train the algorithm model. During training, a suitable algorithm model can be selected, and the relevant parameter set can be initialized.

[0066] Additionally, corresponding feature vectors can be generated based on specific historical design goals. This step can be implemented using specific feature extraction models. These feature vectors can then be used as input to the algorithm model, with the corresponding historical design scheme as the target. Through constructing a loss function and adjusting parameters in multiple iterations, the value of the loss function is gradually reduced until a certain target is reached. The iteration then ends, thus determining the parameter values ​​of each parameter in the parameter set and completing the training of the algorithm model.

[0067] After training the algorithm model, it can be used to automatically generate design schemes corresponding to specific page design goals. Specifically, the required page design goals can first be determined (for example, providing designers with an interface to input design goals, etc.), and corresponding feature vectors can be generated. Then, the feature vectors can be input into the algorithm model to obtain recommended design materials and layout information. Based on the specific design materials and layout information, a specific design scheme can be generated. Compared to designers manually selecting design materials, layers, setting fonts, and adjusting positions to generate design schemes, this method can effectively improve the efficiency of design scheme delivery.

[0068] From a system architecture perspective, embodiments of this application can provide designers with an interface-aided design tool. This tool can run on the terminal device associated with the designer. In one implementation, the tool can also be associated with a pre-trained algorithm model. This algorithm model can be directly built into the tool. Or, as... Figure 1 As shown, this automated design tool can also exist in a server-client model. Specifically, the server can train the algorithm model and then distribute it to the client. This way, when the algorithm model is updated, the server can redistribute it to the client, achieving synchronous updates to the client-side algorithm model. Alternatively, the algorithm model can be stored solely on the server. In this case, designers can input specific design target information through the client, including requirement documents, design intent, and design materials to be included or excluded. The client can then submit this information to the server, which uses the algorithm model to predict design materials and layout methods, generating a specific design scheme. This design scheme can then be returned to the client for display, and so on. The client can exist as a standalone application or as a web page; the specific form is not limited here.

[0069] The specific implementation schemes provided in the embodiments of this application will be described in detail below.

[0070] Example 1

[0071] This first embodiment provides a page design assistance method from the perspective of the server-side, see [link to example]. Figure 2 The method may specifically include:

[0072] S201: Obtain target information for page design;

[0073] As mentioned earlier, specific design goals can be expressed through various dimensions of information. For example, this could include design requirement documents expressed in text form, design intent information described using tags (e.g., "complex," "simple," "mediocre," etc.), or design materials to be included or excluded as input or selected images, and so on. In practical implementation, a client-side interface can be provided for designers to input the aforementioned design goal information. This interface could include text input controls for uploading specific requirement documents, image input controls for uploading design material images, and various optional tags to allow designers to select the specific design intent they require, and so on.

[0074] The specific requirements document primarily describes the page design requirements in text form. For example, a requirements document might include multiple headings such as "Requirement Background," "Requirement Content," and "Requirement Details," each describing a specific design requirement. The "Requirement Background" section describes the design context of the current interface. For instance, in a product object information service system, if an interface is the homepage of a "Points Year-End Rewards" activity provided to users, the "Requirement Background" section could describe the activity's name, the types and quantities of redeemable user benefits. The "Requirement Content" section can include the text and images to be displayed on the interface. The "Requirement Details" section can include specific components that need to be displayed or optimized. For example, in the above example, it might be necessary to optimize the "Timer" component, the "Benefits Redemption" component, and so on. Since functions like "Timer" and "Benefits Redemption" can be used in multiple interfaces, and these functions require multiple specific elements, these elements can be combined to generate components. These components can then be reused in subsequent designs, improving design efficiency. Of course, when reusing the above components in each specific page design, the specific components can be optimized according to different scenario requirements. The above requirement details can describe the components that need to be used or optimized. In this embodiment of the application, specific design goals can be obtained through this requirement document information.

[0075] It should be noted that, in practical implementation, specific design goals can include one or more of the following: requirements described in text form, design intent described using tags, and design materials to be included or excluded as described in image form. That is, if only a requirements document is provided, without specific design intent or information on included or excluded design materials, the design goals can be determined directly from that document. Alternatively, if only design intent is provided, without a requirements document, the specific design goals can be determined solely based on the design intent information, and so on. Of course, in practical implementation, the richer the information contained in the design goals, the closer the final design solution will be to the specific requirements. If the design goals information is insufficient, a rough design solution can still be generated, and designers or users can add other design elements to it.

[0076] Additionally, it's worth noting that in practice, design goals can be recommended based on the characteristics of the specific interface to be designed. For example, design material information, including or excluding elements, can be recommended based on factors such as the type of associated store object and historical design records. The specific store object type information and historical design records can be pre-input into the system, typically in the form of text content. The system can then analyze this text content using natural language processing (NLP) to determine the potential design goals.

[0077] Furthermore, when obtaining design goals, it's also possible to interact with specific user stakeholders. For example, in a product information system, the user stakeholder might be a seller who needs to design the homepage and other interfaces of their associated store. In this case, the system can provide an entry point for interaction with the user stakeholder. By interacting with them, specific design requirements and other information can be obtained, thus helping to determine the specific design goals.

[0078] S202: Determine the target design material and target layout method that match the target information of the page design from the pre-acquired set of design materials and set of layout methods;

[0079] The design resource set can be simply referred to as the resource pool, and the layout method set can be simply referred to as the layout pool. As the names suggest, each pool can store multiple selectable design resources and multiple selectable layout methods. In practice, the specific resource pool and layout pool can be determined based on the predefined selectable resources and layout methods in the system. For example, if the system defines 100 resources and 50 layout methods, then the resource pool can include all 100 resources, and the layout method set can include all 50 layout methods, and so on. Subsequently, design resources and layout methods that meet the specific page design goals can be determined from the specific resource pool and layout pool, thereby generating a specific design scheme. Of course, in practical applications, the content in these resource pools and / or layout pools can also be updated or reordered. For example, when new design resources are collected, they can be added to the resource pool, and so on.

[0080] After determining the design target information, target design materials and target layout methods that match the target information of the page design can be selected from the set of design materials and the set of layout methods. As mentioned earlier, this step can be implemented in various ways. For example, in one approach, tags can be pre-added to various design materials and layout methods. These tags can indicate the scenarios in which a particular material or layout method is applicable. In this way, based on the matching results between the specific design target information and the tags of the specific material or layout method, matching target materials and target layout methods can be determined for the specific design target information.

[0081] Alternatively, in a more preferred approach, a pre-trained model can be used to determine the target design materials and target layout that match the target information of the page design. In this approach, since specific design target information can typically be expressed in text, image, or tag form, feature extraction can be performed based on the received design target information to facilitate processing by the algorithm model. The extracted features can then be used as input to the algorithm model to obtain design materials and layout information that conform to the specific design target.

[0082] The extracted features can be expressed in various ways. In one approach, to facilitate computation by the algorithm model, the features can exist in the form of feature vectors. That is, after feature extraction based on various design objectives, specific feature vectors can be generated, and then these feature vectors are input into the algorithm model for computation.

[0083] In generating feature vectors based on design target information, different processing methods can be used depending on the content or format of the specific design target information. For example, if the specific design target information includes textual information, text feature extraction algorithms can be used to extract textual features from the textual information to generate the feature vector. Specifically, since textual information is usually composed of documents, which can represent words, sentences, or even paragraphs of text, the inherent unstructured (no well-formatted data columns) and noisy nature of text data makes it more difficult for machine learning methods to directly process raw text data. Therefore, meaningful features can be extracted from the text data first to form feature vectors, which can be easily used to build machine learning or deep learning models. Specifically, there are some popular and effective strategies in the existing technology for processing text data and extracting meaningful features from it, which can be used in downstream machine learning systems. For example, the bag-of-words model represents unstructured text (or any other data) as numerical vectors, where each dimension of the vector is a specific feature / attribute; that is, documents are converted into numerical vectors, and each document is represented by a vector (row) in the feature matrix. In addition, models such as TF-IDF (Termfrequency–inverse document frequency) can also be used to extract features from text data, but they will not be introduced one by one here.

[0084] Furthermore, if the design target information includes design material information that needs to be included or excluded, since this information is usually specified through input or selected image information, image feature extraction algorithms can be used to extract the image features of the target image to generate the feature vector. There are various specific image feature extraction algorithms. For example, the Histogram of Oriented Gradient (HOG) feature is a feature descriptor used for object detection in computer vision and image processing. It constructs features by calculating and statistically analyzing the gradient orientation histograms of local image regions. Specifically, this algorithm first divides the image into small connected regions, which can be called "cell units." Then, it collects the gradient or edge orientation histograms of each pixel in the cell unit. Finally, these histograms are combined to form the feature descriptor. Additionally, LBP (Local Binary Pattern) is an operator used to describe the local texture features of an image; it has significant advantages such as rotation invariance and grayscale invariance. In applications of LBP, such as texture classification and face analysis, LBP maps are generally not used as feature vectors for classification and recognition. Instead, statistical histograms of LBP feature spectra are used as feature vectors for classification and recognition, and so on.

[0085] Furthermore, if the target information of the page design includes design intent information expressed through tags, the feature vector can be directly generated based on the tags and a pre-determined vector structure. For example, specifically, the vector length can be determined based on the total number of possible tags (the specific vector length can be determined by the number of vector dimensions; for example, for an n-dimensional vector, its length is n, etc.), and each dimension of the vector can correspond to a specific tag. For a specific design target, if its design intent includes a certain tag, the value in the vector corresponding to that tag's dimension can be set to 1; otherwise, it is 0. In this way, for various different design targets, feature vectors of equal length but with different values ​​in each dimension can be obtained, and so on.

[0086] After obtaining the feature vectors corresponding to the specific design goals through the above steps, these vectors can be used as input to the algorithm model. The algorithm model then determines multiple design materials and layout information that conform to the design goals. Specifically, if the same design goal includes multiple categories of information such as text data, image data, and tags, the aforementioned text feature extraction, image feature extraction, and tag vector generation can be performed separately to obtain multiple different feature vectors. These feature vectors can then be used as input to the algorithm model for calculation.

[0087] In particular, since historical design records can be used as training samples when training the algorithm model, and the correspondence between historical design goals and historical design schemes, as well as the correspondence between historical design schemes and the design materials and layout information used, can be extracted from the historical design records, the specifically trained algorithm model can predict the design materials and corresponding layout information that meet the specific design goals, and then generate specific design schemes based on the specific design materials and layouts.

[0088] It's important to note that in practical applications, the specific interface design may be related not only to the design goals but also to the designer's personal style and habits. In other words, for the same design goals, different designers may generate different design solutions. Therefore, in implementation, it's necessary to identify the specific designer's information and extract behavioral data based on their historical design records, including their preferred design materials and layout characteristics. This data is then used to generate a feature vector for the designer. This feature vector is then input into the algorithm model for calculation.

[0089] It should also be noted that, in specific implementation, the algorithm model provided in this application embodiment can be general. This generality can be reflected within a single system, or even across multiple systems, depending on the range of training samples collected during model training. However, for some large-scale information systems, the concept of functional domains may exist. That is, the system can be divided into multiple functional domains, each corresponding to different functions. For example, a product object information system may include a large number of functional domains, such as those providing group-buying services, those providing curated product object information services, and so on. Different functional domains, due to their different functions, target different user groups, and may differ in the concepts they convey to users and the atmosphere they create. Meanwhile, multiple interfaces or modules within the same functional domain often have high similarity in these aspects. Therefore, the design materials and layout methods used in page design are also highly similar. In other words, each functional domain may have a unique mindset, and designers may have corresponding design styles and design languages. Therefore, in the process of generating new design solutions based on the experience of historical design records, historical design records within the same or similar functional domains have high reference or reference value for new design goals within that functional domain; otherwise, they may not be very useful for reference or may even introduce noise.

[0090] Therefore, in optional implementations, the first algorithm model can be trained within specific functional domains, allowing the trained first algorithm model to be associated with functional domain information. Thus, in the future, when a designer user is in an existing functional domain or a new functional domain that can be related to an existing one in some way, relevant design materials and layout information can be automatically recommended. Specifically, when using the first algorithm model for prediction, the first algorithm model can be selected based on the functional domain information associated with the page design goal, for recommending the design materials and layout information. The functional domain information associated with the specific design goal can be specified by the designer user, or it can be automatically determined based on information in the specific requirements document, etc.

[0091] If no first algorithm model exists for the functional domain associated with the page design goal, the feature vector of the functional domain associated with the page design goal can be obtained. Then, by calculating the similarity of the feature vectors, functional domains similar to or close to the functional domain associated with the page design goal can be determined, so that the first algorithm model corresponding to the similar or close functional domains can be used to recommend the design materials and layout information.

[0092] S203: Based on the target design materials and target layout method, determine the recommended design scheme.

[0093] After determining the target design materials and layout information, a specific design scheme can be generated based on this information for recommendation to the user. In other words, in this embodiment, the system can determine the corresponding combination of layout information and design materials according to the user's desired design goals, thereby generating a complete design scheme and providing specific prediction results on a per-scheme basis. From the designer's perspective, after inputting specific design goal information, the system can automatically generate a design scheme. The designer then only needs to make some modifications or fine-tuning to the design scheme before it can be delivered, and in some cases, it may even be ready for immediate delivery, thus improving the efficiency of page design.

[0094] Specifically, when generating a design scheme, the design scheme can exist as a design draft in a document format corresponding to a certain design tool. These design tools typically provide layer functionality. In the traditional design process, designers can create multiple layers, add specific design materials to different layers, and combine the design results of multiple layers to generate the final design draft. This decoupling between different layers ensures that modifications to one layer do not affect other layers. In this case, based on the recommended design materials and layout information, at least one layer, the design materials associated with that layer, and the display attributes of the design materials within the corresponding layer can be determined to generate the recommended design scheme.

[0095] Furthermore, when displaying specific recommended design schemes to users, the recommended design schemes can also be displayed in the associated design tools according to the at least one layer included in the design scheme, the design materials associated with the layers, and the display attribute information of the design materials in the corresponding layers. That is, the specific design results displayed can also include multiple layers, and each layer can contain one or more specific design materials. For example, after providing a design scheme for a "page 1", the following can be displayed: Figure 3 The interface shown is used for display. Furthermore, a layer list can be provided on the left side of the interface, based on the layers included in the specific design scheme and the hierarchical relationships between layers. Selecting a layer will display only the content related to that layer. Moreover, to facilitate modification or adjustment of the recommended design scheme, editing options can be provided to allow for editing based on the recommended design scheme.

[0096] The aforementioned methods enable the automatic generation of design schemes. However, in the actual page design process, besides determining specific design goals during the design preparation phase and completing the design scheme during the design phase (automatic design can be achieved using a specific algorithm model in this embodiment), the delivery quality of the generated design scheme typically needs to be evaluated. This evaluation can include assessing the overall appearance of the interface, whether it meets design goals, and whether it adheres to design principles. In traditional implementations, this evaluation process is usually performed manually, resulting in inefficiency. Therefore, in this embodiment, after the system automatically generates the specific design scheme, it can also automatically evaluate the delivery quality of the design scheme and provide the evaluation results, thereby reducing the workload of manual evaluation and improving efficiency in the delivery quality evaluation stage.

[0097] In other words, such as Figure 4 As shown, a specific interface-aided design tool can include not only a design scheme recommendation module, but also a design scheme editing module and a delivery quality assessment module. In the specific design process, after determining suitable design schemes based on the received design target information, these schemes are presented to the design scheme editing module for display. Designers can then perform further editing operations, such as fine-tuning, based on the recommended schemes. Afterward, a specific design draft is generated. Before delivery, the delivery quality assessment module can evaluate the draft. Delivery is only made after the draft meets the delivery criteria, thus improving the quality of the delivered design draft.

[0098] Specifically, when evaluating delivery quality, assessments can be made from multiple aspects, including overall appearance, whether it meets design goals, and whether it adheres to design principles. Specifically, when evaluating overall appearance, the design scheme can be input into a second algorithm model to obtain its overall appearance quality. This second algorithm model can be trained based on historical design schemes and corresponding overall appearance annotation information. In other words, during training, a large number of historical design schemes and their corresponding overall appearance annotation information can be used as training samples. The annotation information can include labels such as "good" and "bad," which can be obtained through manual annotation or other methods. After training the second algorithm model, by inputting the generated design scheme into it, a predicted result such as "good" or "bad" can be obtained.

[0099] Similarly, when evaluating whether a design meets design goals, the design scheme and its corresponding design goals can be input into a third algorithm model to obtain the delivery quality of the design scheme in terms of whether it meets the design goals. This third algorithm model can be trained based on historical design schemes and annotation information regarding whether they meet the corresponding design goals. The specific annotation information in the training data can include labels such as "compliant" and "non-compliant," which can also be added manually. Thus, after training the third algorithm model, by inputting the generated design scheme and its corresponding design goal information into this third algorithm model, a prediction result such as "compliant" or "non-compliant" can be obtained.

[0100] In addition, when evaluating design principles, since specific delivery principles are usually relatively fixed, including whether the division of layers is reasonable, specific design principle evaluation rules can be set in advance. Then, the delivery quality of the design scheme in terms of whether it conforms to the design principles can be evaluated according to these evaluation rules.

[0101] The above methods not only automatically generate design schemes but also evaluate the quality of their delivery, thereby further improving the efficiency of the entire design process. Of course, the evaluation of design scheme delivery quality is not limited to automatically generated schemes in this embodiment; it can also include evaluating the delivery quality of schemes generated manually, and so on.

[0102] In summary, in this embodiment, a set of optional design materials and a set of layout methods can be obtained in advance. After determining the design target information, target design materials and target layout methods that match the target information of the page design can be determined from the set of design materials and the set of layout methods. This allows for the generation of a complete design scheme for recommendation to users. This scheme automatically determines the layout and design material combination that meets the page design target, thereby generating a complete design scheme. This ensures that the recommended result is a complete design scheme, which designers can modify or fine-tune before delivery, or even deliver directly. Therefore, it improves the efficiency of page design.

[0103] In an optional implementation, an algorithm model for automatically generating design schemes can be developed based on experience from a large number of previous design drafts. Then, based on this algorithm model, matching target design materials and layout methods are determined for the specific page design's target information. Because the learning process utilizes the correspondence between historical design schemes, historical design goals, design materials, and layout methods, and can even consider factors such as the designer's personal style and habits for recommendations, the recommended design schemes are more likely to meet the needs of the actual design process.

[0104] Example 2

[0105] In the aforementioned Example 1, design materials and layout information that meet the design goals are predicted, and specific design schemes are generated for recommendation based on this. In Example 2, historical design schemes corresponding to historical design goals similar to the current design goals can also be recommended based on the similarity of design goals. That is, in Example 2, a historical design scheme can be recommended to the designer, allowing the designer to modify or adjust it to obtain a design scheme that better meets the current design goals. For details, see... Figure 5 This third embodiment provides a page design auxiliary processing method, specifically, the method may include:

[0106] S501: Obtain target information for page design;

[0107] S502: Extract features from the target information of the page design;

[0108] S503: By comparing the extracted features with the features corresponding to multiple historical design targets, a historical design target whose similarity to the target information of the page design meets the conditions is determined;

[0109] S504: Determine the recommended design scheme based on the historical design schemes corresponding to the historical design objectives that meet the conditions.

[0110] Example 3

[0111] This third embodiment mainly provides a page design assistance method from the perspective of specific auxiliary design tools. See [link to relevant documentation]. Figure 6 The method may specifically include:

[0112] S601: Provides an interface for page design, the interface including operation options for obtaining recommended design schemes;

[0113] S602: After receiving the operation request through the operation options, receive the target information of the input page design;

[0114] S603: Based on the target information of the page design, provide a recommended design scheme, which is generated based on the target design materials and target layout method that match the target information of the page design.

[0115] Example 4

[0116] In this fourth embodiment, a method for processing a page design algorithm model is provided, primarily focusing on the training process of the first specific algorithm model. (See [link to previous document]). Figure 7 The method may specifically include:

[0117] S701: Obtain historical design records, which include multiple historical design targets and corresponding historical design schemes, and the historical design schemes include design materials and layout information;

[0118] S702: Obtain the set of design materials and the set of layout methods;

[0119] S703: Extract features from the historical design objectives;

[0120] S704: Using the extracted features, the set of design materials, the set of layout methods, and the information of the corresponding historical design schemes, complete the training of the target algorithm model.

[0121] For the parts not described in detail in Embodiments 2 to 4 above, please refer to the description in Embodiment 1, which will not be repeated here.

[0122] It should be noted that the embodiments of this application may involve the use of user data. In practical applications, user-specific personal data may be used in the scheme described herein within the scope permitted by applicable laws and regulations, provided that it complies with the applicable laws and regulations of the country (e.g., with the user's explicit consent, with the user being properly notified, etc.).

[0123] Corresponding to Embodiment 1, this application also provides a page design auxiliary processing device, see [link to embodiment]. Figure 8 The device may include:

[0124] Design target acquisition unit 801 is used to acquire target information for page design;

[0125] The determining unit 802 is used to determine the target design material and target layout method that match the target information of the page design from the pre-acquired set of design materials and set of layout methods;

[0126] The recommended design scheme determination unit 803 is used to cut off the recommended design scheme based on the target design material and the target layout method.

[0127] The target information of the page design includes one or more of the following: requirement information described in text form, design intent information described in tags, and design material information, including or excluding, described in image form.

[0128] Specifically, the determining unit may include:

[0129] The feature extraction subunit is used to extract features from the target information of the page design;

[0130] The model operation subunit is used to determine the target design material and target layout method that match the target information of the page design by inputting the extracted features into the first algorithm model.

[0131] The first algorithm model is trained using historical design records as training samples. The historical design records include multiple historical design target information and corresponding historical design schemes. The historical design schemes include the design materials used and the layout methods.

[0132] In a specific implementation, the determining unit may further include:

[0133] The feature vector generation subunit is used to extract features from the target information of the page design and generate feature vectors so that the feature vectors can be input into the first algorithm model for calculation.

[0134] Wherein, if the target information of the page design includes textual information, the feature extraction subunit can specifically be used for:

[0135] Text feature extraction algorithms are used to extract text features from the information in the text form in order to generate the feature vector.

[0136] If the target information of the page design includes information in the form of images, then the feature extraction subunit can specifically be used for:

[0137] Image feature extraction algorithms are used to extract image features from the information in the image form to generate the feature vector.

[0138] If the target information of the page design includes information in the form of tags, then the feature extraction subunit can specifically be used for:

[0139] The feature vector is generated based on the tag words and the pre-determined vector structure information.

[0140] In addition, the model operation subunit can be specifically used for:

[0141] If the target information of the page design includes multiple types of information such as text, images, and tags, then the feature vectors corresponding to each type of information are obtained and input into the algorithm model for calculation.

[0142] Additionally, it may include:

[0143] The designer user information determination unit is used to determine the information of associated designer users;

[0144] The designer user feature extraction unit is used to obtain feature information of the designer user dimension based on the historical design records associated with the designer user; so that the feature extraction results corresponding to the designer user are input into the algorithm model to determine the target design materials and target layout methods that match the target information of the page design.

[0145] In addition, the first algorithm model is associated with functional domain information;

[0146] The device may further include:

[0147] The model selection unit is used to select a first algorithm model based on the functional domain information associated with the page design target, so as to determine the target design material and target layout method that match the target information of the page design.

[0148] Additionally, the device may also include:

[0149] The design target feature extraction unit is used to obtain feature information of the functional domain associated with the page design target if there is no first algorithm model corresponding to the functional domain associated with the page design target.

[0150] The target similarity calculation unit is used to determine, through feature similarity calculation, functional domains that are similar or close to the functional domains associated with the page design target, so as to use the first algorithm model corresponding to the similar or close functional domains to determine the target design materials and target layout methods that match the target information of the page design.

[0151] Specifically, the recommended design scheme determination unit can be used for:

[0152] Based on the target design materials and target layout information, at least one layer, the design materials associated with the layer, and the display attribute information of the design materials in the corresponding layer are determined to generate the recommended design scheme.

[0153] Additionally, the device may also include:

[0154] The display unit is used to display the recommended design scheme according to the at least one layer included in the design scheme, the design materials associated with the layer, and the display attribute information of the design materials in the corresponding layer.

[0155] Furthermore, the device may also include:

[0156] The editing option providing unit is used to provide operation options for editing the recommended design scheme, so as to perform editing operations based on the recommended design scheme.

[0157] To facilitate the assessment of delivery quality, the device may further include:

[0158] The delivery quality assessment unit is used to assess the delivery quality of the design scheme after it has been generated.

[0159] The evaluation result providing unit is used to provide evaluation results on the delivery quality of the design scheme.

[0160] Specifically, the delivery quality assessment unit can be used for:

[0161] By inputting the design scheme into the second algorithm model, the delivery quality of the design scheme in terms of overall appearance is obtained; the second algorithm model is trained based on historical design schemes and corresponding overall appearance annotation information.

[0162] Alternatively, the delivery quality assessment unit may be specifically used for:

[0163] By inputting the design scheme into the third algorithm model, the delivery quality of the design scheme in terms of whether it meets the design goal is obtained; the third algorithm model is trained based on historical design schemes and annotation information on whether they meet the corresponding design goals.

[0164] Alternatively, the delivery quality assessment unit may be specifically used for:

[0165] Based on pre-defined design principle evaluation rules, the delivery quality of the design scheme is evaluated to determine whether it conforms to the design principles.

[0166] Corresponding to Embodiment 2, this application also provides a page design scheme recommendation device, see [link to embodiment]. Figure 9 The device may include:

[0167] Design target acquisition unit 901 is used to acquire target information for page design;

[0168] Feature extraction unit 902 is used to extract features from the target information of the page design;

[0169] The similarity comparison unit 903 is used to determine the historical design target whose similarity to the target information of the page design meets the conditions by comparing the extracted features with the features corresponding to multiple historical design targets.

[0170] The recommended design scheme determination unit 904 is used to determine the recommended design scheme based on the historical design schemes corresponding to the historical design objectives that meet the conditions.

[0171] Corresponding to Embodiment 3, this application also provides a page design auxiliary processing device, see [link to embodiment]. Figure 10 The device may include:

[0172] The interface providing unit 1001 is used to provide an interface for page design, the interface including operation options for obtaining recommended design schemes;

[0173] The target receiving unit 1002 is used to receive the target information of the input page design after receiving the operation request through the operation options;

[0174] The recommended design scheme providing unit 1003 is used to provide a recommended design scheme based on the target information of the page design. The recommended design scheme is generated based on the target design materials and target layout methods that match the target information of the page design.

[0175] Corresponding to Embodiment 4, this application also provides a processing device for a page design algorithm model, see [link to embodiment]. Figure 11 The device may include:

[0176] The historical design record acquisition unit 1101 is used to acquire historical design records, which include multiple historical design targets and corresponding historical design schemes. The historical design schemes include design materials and layout information.

[0177] Optional set acquisition unit 1102 is used to acquire the design material set and the layout method set;

[0178] Feature extraction unit 1103 is used to extract features from the historical design target;

[0179] The model training unit 1104 is used to train the target algorithm model by utilizing the extracted features, the set of design materials, the set of layout methods, and the information of the corresponding historical design schemes.

[0180] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0181] And an electronic device, comprising:

[0182] One or more processors; and

[0183] A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.

[0184] in, Figure 12 An exemplary architecture of an electronic device is shown, which may include a processor 1210, a video display adapter 1211, a disk drive 1212, an input / output interface 1213, a network interface 1214, and a memory 1220. The processor 1210, video display adapter 1211, disk drive 1212, input / output interface 1213, network interface 1214, and memory 1220 can communicate with each other via a communication bus 1230.

[0185] The processor 1210 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided in this application.

[0186] The memory 1220 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1220 can store the operating system 1221 for controlling the operation of the electronic device 1200, and the basic input / output system (BIOS) for controlling the low-level operations of the electronic device 1200. Additionally, it can store a web browser 1223, a data storage management system 1224, and a page design scheme processing system 1225, etc. The aforementioned page design scheme processing system 1225 can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when implementing the technical solution provided in this application through software or firmware, the relevant program code is stored in the memory 1220 and is called and executed by the processor 1210.

[0187] Input / output interface 1213 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0188] Network interface 1214 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0189] Bus 1230 includes a pathway for transmitting information between various components of the device, such as processor 1210, video display adapter 1211, disk drive 1212, input / output interface 1213, network interface 1214, and memory 1220.

[0190] It should be noted that although the above-described device only shows the processor 1210, video display adapter 1211, disk drive 1212, input / output interface 1213, network interface 1214, memory 1220, bus 1230, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.

[0191] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0192] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0193] The page design auxiliary processing method, apparatus, and electronic device provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and its core ideas. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A page design auxiliary processing method, characterized in that, include: Obtain the design goal information of the page design input by the designer user through the client; Feature extraction is performed on the design target information, and after determining the designer user information, feature information on the designer user dimension is obtained based on the historical design records associated with the designer user. The features extracted from the design target information and the feature information on the designer user dimension are input into the first algorithm model to determine the target design materials and target layout methods that match the design target information from the pre-acquired set of design materials and set of layout methods. The first algorithm model is trained using historical design records as training samples. The historical design records include multiple historical design target information and corresponding historical design schemes. The historical design schemes include the design materials and layout methods used. The target design materials are arranged according to the target layout to generate a corresponding design scheme, which is then recommended to the designer user.

2. The method according to claim 1, characterized in that, The design target information includes one or more of the following: requirement information described in text form, design intent information described in tags, and design material information, including or excluding materials, described in image form.

3. The method according to claim 1, characterized in that, Also includes: After extracting features from the design target information, a feature vector is generated so that the feature vector can be input into the first algorithm model for calculation.

4. The method according to claim 3, characterized in that, If the design target information includes textual information, then feature extraction is performed on the design target information, including: Text feature extraction algorithms are used to extract text features from the information in the text form in order to generate the feature vector.

5. The method according to claim 3, characterized in that, If the design target information includes information in image form, then feature extraction is performed on the design target information, including: Image feature extraction algorithms are used to extract image features from the information in the image form to generate the feature vector.

6. The method according to claim 3, characterized in that, If the design target information includes information in the form of tag words, then the generation of feature vectors includes: The feature vector is generated based on the tag words and the pre-determined vector structure information.

7. The method according to claim 3, characterized in that, If the design target information includes multiple types of information such as text, images, and tags, then the feature vectors corresponding to each type of information are obtained and input into the algorithm model for calculation.

8. The method according to any one of claims 1 to 7, characterized in that, The first algorithm model is associated with functional domain information; The method further includes: The first algorithm model is selected based on the functional domain information associated with the design target information, in order to determine the target design material and target layout method that match the design target information.

9. The method according to claim 8, characterized in that, Also includes: If there is no first algorithm model corresponding to the functional domain associated with the design target information, then obtain the feature information of the functional domain associated with the design target information; By calculating feature similarity, functional domains that are similar or close to the functional domains associated with the design target information are determined, so as to use the first algorithm model corresponding to the similar or close functional domains to determine the target design materials and target layout methods that match the design target information.

10. The method according to any one of claims 1 to 7, characterized in that, The step of arranging the target design materials according to the target layout method to generate the corresponding design scheme includes: Based on the target design materials and target layout information, at least one layer, the design materials associated with the layer, and the display attribute information of the design materials in the corresponding layer are determined to generate the corresponding design scheme.

11. The method according to claim 10, characterized in that, Also includes: The design scheme is presented to the designer user according to at least one layer included in the design scheme, the design materials associated with the layer, and the display attribute information of the design materials in the corresponding layer.

12. The method according to claim 11, characterized in that, Also includes: The system provides operation options for editing the design schemes recommended to the designer user, so that the designer user can perform editing operations based on the design schemes.

13. The method according to any one of claims 1 to 7, characterized in that, Also includes: After the corresponding design scheme is generated, the delivery quality of the design scheme is evaluated. Provide evaluation results on the quality of the delivered design proposal.

14. The method according to claim 13, characterized in that, The evaluation of the delivery quality of the design scheme includes: By inputting the design scheme into the second algorithm model, the delivery quality of the design scheme in terms of overall appearance is obtained; the second algorithm model is trained based on historical design schemes and corresponding overall appearance annotation information.

15. The method according to claim 13, characterized in that, The evaluation of the delivery quality of the design scheme includes: By inputting the design scheme into the third algorithm model, the delivery quality of the design scheme in terms of whether it meets the design goals is obtained; the third algorithm model is trained based on historical design schemes and annotation information on whether they meet the corresponding design goals.

16. The method according to claim 13, characterized in that, The evaluation of the delivery quality of the design scheme includes: Based on pre-defined design principle evaluation rules, the delivery quality of the design scheme is evaluated to determine whether it conforms to the design principles.

17. A page design auxiliary processing method, characterized in that, include: Obtain the design goal information of the page design input by the designer user through the client; Feature extraction is performed on the design target information, and after determining the designer user information, feature information in the designer user dimension is obtained based on the historical design records associated with the designer user. The features extracted from the design target information and the feature information from the designer user dimension are input into the first algorithm model. By comparing the extracted features and the feature information from the designer user dimension with the features corresponding to multiple historical design target information, the target historical design target information that meets the similarity condition with the design target information of the page design is determined. The first algorithm model is trained using historical design records as training samples. The historical design records include multiple historical design target information and corresponding historical design schemes. The historical design schemes include the design materials used and the layout methods. Based on the target historical design schemes corresponding to the target historical design information, a recommended design scheme is determined.

18. A page design auxiliary processing method, characterized in that, include: Provide an interface for page design, the interface including operation options for obtaining recommended design schemes; After receiving an operation request through the operation options, the design target information of the input page design is received; Based on the design target information, a recommended design scheme is provided. The recommended design scheme is generated by arranging target design materials that match the design target information according to the target layout method. The target design materials and target layout method are determined by extracting features from the design target information and, after determining the designer user's information, obtaining feature information on the designer user dimension based on the historical design records associated with the designer user. The features extracted from the design target information and the feature information on the designer user dimension are input into a first algorithm model to be determined from a pre-acquired set of design materials and a set of layout methods. The first algorithm model is trained using historical design records as training samples. The historical design records include multiple historical design target information and corresponding historical design schemes. The historical design schemes include the design materials and layout methods used.

19. A method for processing a page design algorithm model, characterized in that, include: Obtain historical design records, which include information on multiple historical design targets and corresponding historical design schemes. The historical design schemes include information on the design materials used and the layout methods. Obtain a collection of design materials and layout options; Feature extraction is performed on the historical design goals, and feature information on the designer user dimension is obtained based on the historical design records associated with the designer user. The target algorithm model is trained by utilizing the extracted features, the feature information of the designer user dimension, the set of design materials, the set of layout methods, and the information of the corresponding historical design schemes.

20. A page design auxiliary processing device, characterized in that, include: The design goal acquisition unit is used to acquire the design goal information of the page design input by the designer user through the client. A determining unit is used to extract features from the design target information, and after determining the designer user's information, to obtain feature information in the designer user dimension based on the historical design records associated with the designer user. The features extracted from the design target information and the feature information in the designer user dimension are input into a first algorithm model to determine the target design materials and target layout methods that match the design target information from a pre-acquired set of design materials and a set of layout methods. The first algorithm model is trained using historical design records as training samples. The historical design records include multiple historical design target information and corresponding historical design schemes. The historical design schemes include the design materials and layout methods used. The recommended design scheme determination unit is used to arrange the target design materials according to the target layout method to generate a corresponding design scheme, and recommend it to the designer user.

21. A page design auxiliary processing device, characterized in that, include: The design goal acquisition unit is used to acquire the design goal information of the page design input by the designer user through the client. The feature extraction unit is used to extract features from the design target information, and after determining the information of the designer user, to obtain feature information in the dimension of the designer user based on the historical design records associated with the designer user. A similarity comparison unit is used to input the features extracted from the design target information and the feature information from the designer user dimension into the first algorithm model, so as to compare the extracted features and the feature information from the designer user dimension with the features corresponding to multiple historical design target information to determine the target historical design target information that meets the similarity conditions with the design target information of the page design; wherein, the first algorithm model is trained using historical design records as training samples, the historical design records include multiple historical design target information and corresponding historical design schemes, and the historical design schemes include the design materials used and the layout methods; The recommended design scheme determination unit is used to determine the recommended design scheme based on the target historical design scheme corresponding to the target historical design target information.

22. A page design auxiliary processing device, characterized in that, include: An interface providing unit is used to provide an interface for page design, the interface including operation options for obtaining recommended design schemes; The target receiving unit is used to receive the design target information of the input page design after receiving the operation request through the operation options; A recommended design scheme providing unit is used to provide recommended design schemes based on the design target information. The recommended design scheme is generated by arranging target design materials that match the design target information according to the target layout method. The target design materials and target layout method are determined by extracting features from the design target information and, after determining the designer user's information, obtaining feature information on the designer user dimension based on the historical design records associated with the designer user. The features extracted from the design target information and the feature information on the designer user dimension are input into a first algorithm model to be determined from a pre-acquired set of design materials and a set of layout methods. The first algorithm model is obtained by training historical design records as training samples. The historical design records include multiple historical design target information and corresponding historical design schemes. The historical design schemes include the design materials and layout methods used.

23. A processing device for a page design algorithm model, characterized in that, include: The historical design record acquisition unit is used to acquire historical design records, which include multiple historical design target information and corresponding historical design schemes. The historical design schemes include information on the design materials used and the layout methods. The collection retrieval unit is used to retrieve the collection of design materials and the collection of layout methods; The feature extraction unit is used to extract features from the historical design target and obtain feature information in the designer user dimension based on the historical design records associated with the designer user. The model training unit is used to train the target algorithm model by utilizing the extracted features, feature information from the designer user dimension, the set of design materials, the set of layout methods, and information from the corresponding historical design schemes.

24. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program performs the steps of the method described in any one of claims 1 to 19.

25. An electronic device, characterized in that, include: One or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method according to any one of claims 1 to 19.

Images