Resource generation method, system, device, computing device and storage medium

Abstract

The embodiments of this specification provide a resource generation method, system, device, computing device and storage medium, wherein the method includes: determining the extended information corresponding to the initial resource; calling the business operation link of the resource generation business, analyzing the extended information, and generating a prompt text of the initial resource, wherein the link node in the business operation link has a corresponding relationship with the business process of the resource generation business; inputting the prompt text and the initial resource into a resource generation model based on image processing to obtain the target resource output by the resource generation model; obtaining the configuration information corresponding to the target resource position, adjusting the target resource according to the configuration information, and obtaining the resource to be displayed corresponding to the target resource position, wherein the resource to be displayed is used to be displayed at the target resource position. By performing resource generation based on the resource generation model based on image processing, labor costs can be reduced and production efficiency can be improved while ensuring the quality of resource generation.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of image processing technology, and in particular to a resource generation method, system, apparatus, computing device and storage medium. Background Art

[0002] In application scenarios such as activity display and product recommendation, resources are often displayed in the display area of ​​the application page. The display area may include multiple resource positions, and each resource position can be used to display pictures, titles and other information corresponding to a product, activity, etc. In order to generate materials for display in resource positions, the production method in the prior art is that the operator manually collects images of the object, manually adjusts the collected image according to the format of the resource position, generates a background image, and combines related elements with the background image to generate materials for display. The image generation efficiency of this method is very low, and the number of combined materials is small, which makes it difficult to meet the needs of refined traffic delivery. Therefore, how to more efficiently batch generate display materials is a problem that needs to be solved urgently. Summary of the invention

[0003] In view of this, an embodiment of this specification provides a resource generation method. One or more embodiments of this specification also relate to a resource generation system, a resource generation device, a computing device, a computer-readable storage medium and a computer program product to solve the technical defects existing in the prior art.

[0004] According to a first aspect of an embodiment of this specification, a resource generation method is provided, including:

[0005] Determine the extended information corresponding to the initial resource;

[0006] Calling a service operation link of a resource generation service, analyzing the extended information, and generating a prompt text of the initial resource, wherein the link nodes in the service operation link have a corresponding relationship with the service process of the resource generation service;

[0007] Inputting the prompt text and the initial resource into a resource generation model based on image processing to obtain a target resource output by the resource generation model;

[0008] Configuration information corresponding to the target resource position is acquired, and the target resource is adjusted according to the configuration information to obtain a resource to be displayed corresponding to the target resource position, wherein the resource to be displayed is used to be displayed at the target resource position.

[0009] According to a second aspect of the embodiments of this specification, a resource generation system is provided, the system comprising a client and a server, wherein:

[0010] The client is used to receive the initial resource and forward the initial resource to the server;

[0011] The server is used to determine the extended information corresponding to the initial resource; call the service operation link of the resource generation service, analyze the extended information, and generate a prompt text for the initial resource, wherein the link node in the service operation link has a corresponding relationship with the business process of the resource generation service; input the prompt text and the initial resource into the resource generation model based on image processing, and obtain the target resource output by the resource generation model; obtain the configuration information corresponding to the target resource position, adjust the target resource according to the configuration information, obtain the resource to be displayed corresponding to the target resource position and forward it to the client, wherein the resource to be displayed is used to be displayed at the target resource position;

[0012] The client is used to display a resource display page, wherein the resource display page includes the resource to be displayed.

[0013] According to a third aspect of an embodiment of this specification, there is provided a resource generation device, including:

[0014] A determination module, configured to determine the extended information corresponding to the initial resource;

[0015] A generating module is configured to call a service operation link of a resource generating service, analyze the extended information, and generate a prompt text of the initial resource, wherein the link nodes in the service operation link have a corresponding relationship with the service process of the resource generating service;

[0016] An input module, configured to input the prompt text and the initial resource into a resource generation model based on image processing, and obtain a target resource output by the resource generation model;

[0017] The adjustment module is configured to obtain configuration information corresponding to the target resource position, adjust the target resource according to the configuration information, and obtain the to-be-displayed resource corresponding to the target resource position, wherein the to-be-displayed resource is used to be displayed at the target resource position.

[0018] According to a fourth aspect of an embodiment of this specification, a computing device is provided, including:

[0019] Memory and processor;

[0020] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above resource generation method are implemented.

[0021] According to a fifth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned resource generation method are implemented.

[0022] According to a sixth aspect of the embodiments of this specification, a computer program product is provided, including a computer program or instructions, which implement the steps of the above-mentioned resource generation method when executed by a processor.

[0023] An embodiment of this specification implements determining the extended information corresponding to the initial resource, calling the business operation link of the resource generation business to analyze the extended information, and generating a prompt text for the initial resource. Resource generation is performed by using a business operation link that is deeply integrated with the resource generation business, thereby improving the efficiency of resource generation. In addition, the extended information of the initial resource provided for reference is analyzed to generate a prompt text, which facilitates the subsequent use of the resource generation model to generate the target resource. Resource generation is performed by using a resource generation model based on image processing, thereby reducing labor costs while ensuring the quality of resource generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flow chart of a resource generation method provided by an embodiment of this specification is shown;

[0025] Figure 2A A schematic diagram of initial resources in a resource generation method provided in an embodiment of this specification is shown;

[0026] Figure 2B A schematic diagram of target resources in a resource generation method provided in an embodiment of this specification is shown;

[0027] Figure 3A A schematic diagram of a resource bit page in a resource generation method provided in an embodiment of this specification is shown;

[0028] Figure 3B A schematic diagram of a display page in a resource generation method provided in an embodiment of this specification is shown;

[0029] Figure 4 A flowchart of a processing process of a resource generation method provided by an embodiment of this specification is shown;

[0030] Figure 5 A schematic diagram of the structure of a resource generation device provided by an embodiment of this specification is shown;

[0031] Figure 6 A schematic diagram of a process of a resource generation system provided by an embodiment of this specification is shown;

[0032] Figure 7It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0033] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0034] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0035] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0036] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0037] First, the terms involved in one or more embodiments of this specification are explained.

[0038] AIGC: Artificial Intelligence Generated Content, AIGC uses artificial intelligence technology to autonomously generate new content based on a large amount of training data and generation algorithm models. This technology is not limited to traditional text and image generation, but also includes music, video, 3D interactive content, strategy generation, code generation and other forms.

[0039] ComfyUI: ComfyUI is a Stable Diffusion operation interface based on node process. It splits the stable diffusion process into individual nodes. Users can customize the workflow accurately and reproduce reliably by customizing nodes and dragging connections to complete more complex image generation tasks with higher degrees of freedom.

[0040] At present, in many image generation fields such as artistic creation, advertising design, and visual content generation, SD (Stable-Diffusion) technology is often used for content generation. This model generates images by gradually denoising from noise and can generate images with high resolution and complex content. However, there are still some limitations and defects in practical applications, including: insufficient accuracy of generated content, instability of generation quality, problems with generation speed and efficiency, high computing power cost, lack of detailed control of the generation process, and difficulty in process and application integration. In response to these problems, the resource generation method provided in this manual optimizes the generation process by introducing AIGC automated intelligent tools, reduces cost and time investment, and improves overall efficiency and quality.

[0041] In this specification, a resource generation method is provided. This specification also involves a resource generation system, a resource generation device, a computing device, a computer-readable storage medium and a computer program product, which are described in detail one by one in the following embodiments.

[0042] See also Figure 1 , Figure 1 A flow chart of a resource generation method provided by an embodiment of this specification is shown, which specifically includes the following steps.

[0043] Step 102: Determine the extended information corresponding to the initial resource.

[0044] The initial resource can be understood as a reference resource provided by the designer, such as a reference image provided by the designer that meets specific requirements. The extended information corresponding to the initial resource can be understood as the specific design requirements proposed by the designer during the resource generation process based on the initial resource, such as style, filter, etc. The initial resource can be adjusted according to the extended information to generate resources.

[0045] In actual applications, when designers use resource generation services, they need to first provide initial resources as templates, and then call the workflow of the resource generation service to process them to achieve automated resource generation.

[0046] In a specific embodiment of this specification, if the operator wants to add relevant recommended resources for holiday activities on the homepage of the application, the resource generation service can be used to generate materials corresponding to the resource position. Designers need to upload the corresponding initial resources through the function portal. The initial resources can be images corresponding to holiday elements, such as Christmas tree element images corresponding to Christmas. Other material resources will be generated based on the Christmas tree element images later.

[0047] Furthermore, before determining the extended information corresponding to the initial resource, the method further includes: determining layer information corresponding to the resource file; parsing the resource file according to the layer information to obtain the initial resource corresponding to the resource file.

[0048] Among them, the resource file can be understood as a file containing the initial resources. In actual business such as image creation and editing, designers or artists often use PS (Photoshop, image processing software) software to process images. Therefore, when uploading the initial resources, the PSD file format will be used to upload the resources. PSD is the native file format of PS software, so in order to obtain the initial resources, the resource file needs to be parsed.

[0049] In actual applications, PSD files include complex structures such as layers, masks, texts, shapes, blending modes, etc. In order to be able to parse the PSD file normally, the file parsing process needs to be performed in the resource generation business. In one embodiment, ag-psd can be used to parse the PSD file. ag-psd is a JavaScript library specifically used to read and write PSD files. It provides an API interface to access layer properties, such as position, size, transparency, style, etc. In a resource file in PSD format, different layers may correspond to different resource materials, such as resource bit layers, background layers, etc. Therefore, in order to extract the initial resources from the PSD resource file, it is necessary to parse according to the corresponding layer information to determine the layer corresponding to the initial resource, so as to obtain the corresponding initial resource.

[0050] In a specific embodiment of this specification, the designer uploads a resource file in PSD format, and the resource file includes an image that the user expects to use as a template. In order to accurately extract the image resource from the resource file, it is necessary to first determine the layer information corresponding to the resource file. The layer information can be read from the resource file through the corresponding API interface to obtain the layer information in the PSD file, and then the resource file is parsed using the layer information to obtain the image resource corresponding to the required layer.

[0051] Furthermore, in order to accurately extract the required initial resources from the resource file according to the layer information, it is also necessary to determine the annotation information corresponding to the layer information, and specifically parse the resource file according to the layer information to obtain the initial resources corresponding to the resource file, including: parsing the resource file according to the layer information to obtain a layer resource set and layer annotation information corresponding to the layer resource set; extracting the target layer resources from the layer resource set according to the layer annotation information, and using the target layer resources as the initial resources corresponding to the resource file.

[0052] Among them, the layer resource set can be understood as a resource set formed by the resources corresponding to each layer. Since a resource file includes multiple layers, and each layer has its own corresponding material or image, in order to extract the required initial resources, it is also necessary to determine the layer annotation information corresponding to the layer resource set. The layer annotation information corresponding to the layer resource set can be understood as the annotation information corresponding to each layer in the layer resource set. The layer annotation information is used to indicate the resource attribute information corresponding to the current layer. The layer annotation information can be annotated with layer name, layer transparency, layer filter and other related information. The layer annotation information can be adjusted and determined by the designer when editing the image, or it can be set by the software according to the image editing operation. Therefore, when extracting the initial resources according to the layer annotation information, in order to ensure the extraction accuracy, it is necessary to standardize the layer annotation information.

[0053] In actual applications, common layer annotation information may be arranged according to digital numbers, such as "Layer 1", "Layer 2", etc. However, in order to facilitate the extraction of initial resources through layer annotation information, the corresponding names of the resources that need to be extracted later can be written in the layer annotation information. For example, if the background image resource needs to be extracted later, the corresponding layer annotation information may be "Layer 1-Background Image Resource". In this way, resources can be accurately extracted based on the layer annotation information later.

[0054] In a specific embodiment of the present specification, the ag-psd open source project is used to parse the PSD file to obtain a layer resource set composed of each layer resource in the PSD file and its corresponding layer annotation information. The layer resources corresponding to each layer are determined according to the layer annotation information, and the layer resources required by the user are extracted, including the layer resources corresponding to the background layer and the element layer, and the extracted layer resources are used as the initial resources this time.

[0055] Step 104: calling the service operation link of the resource generation service, analyzing the extended information, and generating a prompt text of the initial resource, wherein the link nodes in the service operation link have a corresponding relationship with the service process of the resource generation service.

[0056] Among them, the resource generation business can be understood as a business used to generate display resources for resource positions, and the business operation link of the resource generation business can be understood as a workflow link generated by using ComfyUI to customize the business process of the resource generation business. Therefore, the link nodes in the business operation link have a corresponding relationship with the business process of the resource generation business. For example, if the resource generation business includes an image cropping process, then the business operation link corresponds to a corresponding image cropping link node. By using ComfyUI to customize the workflow, a set of standardized processes suitable for the resource generation business is formed. The business operation link can adapt to the needs of different promotion channels and automatically complete operations such as data input, content generation, and result output.

[0057] In actual applications, through scripts and automated scheduling systems, it is possible to batch generate resource placement materials for various scenarios, integrate intelligent image generation technology into business processes, and achieve the transformation from traditional manual content generation to AI-driven production methods. AI can replace high-frequency and repetitive image generation work, reduce labor costs and improve generation efficiency. And through standardized workflows, it ensures the consistency of generated materials and avoids quality fluctuations caused by manual operations.

[0058] In specific implementation, after the user uploads the resource file, the corresponding material parsing module can be used to call the file parsing service to parse the resource file. After determining the initial resource and its corresponding extended information, the business operation link is automatically run to process it, including analyzing the extended information and generating prompt text for the initial resource. The prompt text can be a text generated based on the extended information, and the prompt text is used for subsequent input into the model for resource generation. The prompt text can be a text generated by extension and association based on the user's request, that is, the extended information. Accordingly, since there may be some information that can be extracted from the initial resource, the initial resource can also be analyzed in some scenarios to generate corresponding prompt text. For example, if the initial resource is a user image, after analyzing the initial resource, parameters such as the position of facial features and face shape can be analyzed as prompt text.

[0059] In a specific embodiment of the present specification, a resource generation service is used to generate display resources corresponding to a resource position, call a service operation link corresponding to the resource generation service, and analyze extended information. The extended information is the user's specific requirements for this resource generation, such as style information, resource type, similarity, etc. After analysis, a prompt text for the initial resource can be generated, and the prompt text is used for subsequent input into the model for resource generation.

[0060] Furthermore, in order to realize the automated execution of the business process of the resource generation service, it is necessary to call the link node corresponding to the business process in the business operation link, specifically call the business operation link of the resource generation service, and analyze the extended information, including: determining the business operation link of the resource generation service, and the link node in the business operation link; analyzing the extended information through the link node.

[0061] Among them, the link nodes in the business operation link can be link nodes that perform corresponding operations, and the link nodes correspond to the business processes in the resource generation business. For example, if the business processes in the resource generation business include data input, content generation and result output, the corresponding link nodes include data input nodes, content generation nodes and result output nodes.

[0062] In actual applications, each link node corresponds to a business process in the resource generation business, so the link node needs to be configured with a corresponding API interface to call the corresponding service to implement the processing operation corresponding to the business process. For example, if the business process is to determine the configuration information of the resource position, the corresponding link node can be integrated with the ag-psd function interface, and the uploaded PSD file can be parsed by integrating the ag-psd library to extract the element size and position of the resource position.

[0063] In a specific embodiment of the present specification, the service operation link of the resource generation service and the link node to be executed in the service operation link are determined, and the corresponding link node is called according to the service logic of the resource generation service to analyze the extended information and generate the corresponding prompt text. Other link nodes can be called later for further processing based on the prompt text.

[0064] Furthermore, when generating prompt text, text generation can be performed using either a natural language model or a knowledge graph. Specifically, the extended information is analyzed to generate a prompt text for the initial resource, including: performing text analysis on the extended information to determine extended keywords corresponding to the extended information; inputting the extended keywords into a text generation model based on language processing to obtain the prompt text for the initial resource output by the text generation model; and / or determining a preset knowledge graph, searching the preset knowledge graph according to the extended keywords, and determining the prompt text for the initial resource based on the search results.

[0065] Among them, the extended keywords can be understood as the key words extracted from the extended information. For example, the extended information can be "make a poster about the Winter Olympics", and the extracted key words can be "Winter Olympics" and "poster picture". Subsequently, prompt texts can be generated based on the extracted key words, such as "athlete style", "skiing event", "winning picture", etc. The generated prompt texts help the model better understand user expectations and output resources that better meet user needs.

[0066] In practical applications, prompt text can be generated through semantic analysis, such as using natural language processing NLP (Natural Language Processing) tools or services (BERT, GPT series) to understand text content and generate richer and more specific descriptive text prompts. Prompt text can also be generated through knowledge graph applications, such as by querying pre-built knowledge graphs to find concepts and attributes associated with keywords, and further refine and expand prompt text. For example, the knowledge graph node of "retro style" may be associated with elements such as "vintage camera" and "film texture".

[0067] In a specific embodiment of the present specification, a text generation model is used to generate prompt text. The text generation model may be a model obtained by training with a large amount of corpus in advance. By inputting the extended keywords in the extended information into the text generation model, the prompt text output by the text generation model can be obtained.

[0068] In another specific embodiment of the present specification, a knowledge graph is used to generate prompt text. The knowledge graph is constructed in advance, and nodes and edges associated with the extended keywords are searched in the knowledge graph by query, and the corresponding prompt text is obtained according to the search results.

[0069] Step 106: Input the prompt text and the initial resource into a resource generation model based on image processing to obtain a target resource output by the resource generation model.

[0070] The resource generation model can be a model that has been trained in advance for resource generation. In specific business scenarios, such as the medal resource generation business, the resource generation model can analyze a large number of medal design materials and extract common elements and other feature intervals. By adding these features to the data in the small sample model training, the model is more likely to generate images with these features when generating images.

[0071] In practical applications, according to the different style requirements of specific business actions, the parameters of each link node combination in the business execution link can also be optimized to ensure that the generated image can accurately convey the corresponding style information.

[0072] In the specific implementation, taking the launch of an activity as an example, the materials currently required to participate in the activity are generated. Figure 2A , Figure 2A The schematic diagram of initial resources in a resource generation method provided in an embodiment of the present specification is shown. These initial resources may be material elements or background images provided by designers. Subsequently, corresponding target resources may be generated according to the user's prompt text, such as Figure 2A The initial resource A is the medal material provided by the designer, the initial resource B is the background image, and the initial resource C is the artistic text.

[0073] See also Figure 2B , Figure 2B A schematic diagram of target resources in a resource generation method provided in an embodiment of the present specification is shown. It can be seen that the target resources may include initial resources and may also include AI-generated elements. The element layout or element size between the generated multiple target resources may be different, such as Figure 2B The contents of target resource A and target resource B are different. After obtaining the target resource, the resource position can be matched based on the target resource, and the attributes of the corresponding resource can be adjusted according to the resource position, such as size adjustment, color adjustment, etc., so as to generate a resource to be displayed that can be displayed in the resource position.

[0074] In a specific embodiment of the present specification, prompt texts such as "gold medal", "retro style", "athlete smile", and initial resources are input into the resource generation model, and the resource generation model performs AI creation to output target resources that meet user needs.

[0075] Furthermore, in some cases, the user can manually input model adjustment parameters to adjust the model to facilitate the generation of a more accurate image. Before inputting the prompt text and the initial resource into the resource generation model based on image processing, the method also includes: determining the model adjustment parameters of the resource generation model, and updating the resource generation model based on the model adjustment parameters to obtain an updated resource generation model; inputting the prompt text and the initial resource into the resource generation model based on image processing, including: inputting the prompt text and the initial resource into the updated resource generation model.

[0076] Among them, the model adjustment parameters can be understood as the parameters used to adjust the resource generation model. In practical applications, users can independently set appropriate hyperparameters for the resource generation model, such as the number of iterations, guidance weights, seed values, etc., to control the quality and diversity of the generated images.

[0077] In specific implementation, users can adjust model parameters before generating resources, or after generating resources, if they find that the generated model does not meet their needs, they can control the quality of the generated image by adjusting model parameters.

[0078] In a specific embodiment of the present specification, the user inputs a model adjustment parameter, and the model adjustment parameter is to adjust the model iteration rounds to 10 times. After the resource generation model is updated based on the model adjustment parameter, the prompt text and initial resources can continue to be input into the resource generation model based on image processing.

[0079] Furthermore, after the prompt text and the initial resource are input into a resource generation model based on image processing and the target resource output by the resource generation model is obtained, the method also includes: determining the image processing node in the business operation link; performing image editing on the target resource through the image processing node to obtain the edited target resource; and adjusting the target resource according to the configuration information, including: adjusting the edited target resource according to the configuration information.

[0080] Among them, the image processing node can be understood as corresponding to the image processing flow in the resource generation business, that is, after the output target resource is generated by the resource generation model, the appropriate node can be determined for image post-processing according to business needs. For example, the image processing node can be a filter effect node, a light and shadow adjustment node, a color correction node, etc. The filter effect node can add specific art filters to the target resource, such as oil painting effects, black and white toning, etc.; the light and shadow adjustment node can increase or modify the light and shadow effects in the image to make it more in line with the brand's visual language; the color correction node can ensure that the generated image color is consistent with the brand standard. It should be noted that the image processing node can be selected according to business needs, or it can be previewed to the user after the target resource is generated. After the preview, if the user thinks that simple adjustments are needed, he can choose to use the image processing node for further image processing.

[0081] In actual applications, the purpose of the resource generation service is to generate resources that meet the resource position display. Therefore, after the target resource is generated, it is necessary to adjust the target resource according to the configuration information. Therefore, after the image is edited by the image processing node, the edited target resource can be obtained. At this time, the target resource is adjusted based on the configuration information of the resource position to generate resources that meet user needs.

[0082] Step 108: Acquire configuration information corresponding to the target resource position, adjust the target resource according to the configuration information, and obtain the to-be-displayed resource corresponding to the target resource position, wherein the to-be-displayed resource is used to be displayed at the target resource position.

[0083] Among them, the configuration information corresponding to the target resource position can be understood as the number, location, size and other information of the materials that need to be displayed. The configuration information can be used to know the specifications required for the material resources corresponding to the resource position. Therefore, after generating the target resource, in order to enable the target resource to be displayed in the resource position, it is also necessary to adjust it according to the configuration information of the resource position.

[0084] In actual applications, there may be a situation where one target resource corresponds to multiple resource positions. In the past, this situation was solved by manually photographing the material and manually processing the image in sequence according to the resource position, thereby generating the display material corresponding to each resource position. In order to improve production efficiency, the target resource is currently created through the AI ​​model, and the target resource is matched with the corresponding resource position. After matching one or more resource positions, the configuration information corresponding to each resource position can be determined respectively, and then the target resource can be adjusted using the configuration information, thereby obtaining the resources to be displayed corresponding to each resource position, and realizing batch generation of resources.

[0085] For example, see Figure 3A , Figure 3AA schematic diagram of a resource position page in a resource generation method provided in an embodiment of the present specification is shown, wherein the display page may include multiple resource positions, such as resource position A, resource position B, etc., and the size, position and other information of the resource position, as well as the display form of the resource position, such as pop-up window display, home page display, etc., may be different according to the layout of the display page. In order to enable the generated target resource to adapt to these different resource positions, the target resource can be adjusted according to the configuration information corresponding to each resource position, so as to obtain the resources to be displayed adapted to each resource position.

[0086] It should be noted that the resource generation method provided in the embodiments of this specification can be applied to a media content sharing platform, which can be an application platform that integrates multiple contents. The media content sharing platform can provide users with rich and diverse multimedia content, including but not limited to live broadcast, on-demand video, audio, graphic information, social interaction, commodity trading, etc. The media content sharing platform can include one or more application interfaces, allowing users to access and consume various types of multimedia content. In actual implementation, the media content sharing platform can provide commodity trading functions and comment functions for media content, etc.

[0087] In a specific embodiment of the present specification, a target resource bit is determined from a plurality of resource bits, and configuration information corresponding to the target resource bit is determined, the configuration information including the display form, position, size, etc. of the target resource bit. The target resource is adjusted through the configuration information to obtain a resource to be displayed that can be displayed at the target resource bit.

[0088] Furthermore, obtaining configuration information corresponding to the target resource position includes: determining a resource position data set, and matching relationship information between the target resource and the resource position data set; and determining the target resource position corresponding to the target resource and the configuration information corresponding to the target resource position in the resource position data set based on the matching relationship information.

[0089] Among them, the resource position data set can be understood as a data set containing multiple resource positions. Since the resource positions are also provided by designers, the resource position data set is uploaded by a PSD format file. It is also necessary to parse the PSD format file first to determine the resource position data set. The resource position data set includes multiple resource positions of different styles.

[0090] In actual applications, in order to ensure that the target resource can be displayed in the corresponding resource position, it is also necessary to determine the matching relationship information between the target resource and the corresponding resource position. The matching relationship information can be determined by the designer in advance by identifying the resource position, such as target resource A corresponds to all pop-up resource positions, and target resource B corresponds to all homepage resource positions. Correspondingly, the matching relationship information can also be manually determined by the designer after generating the target resource, such as placing target resource A in resource position A and resource position B, and placing target resource B in resource C, so as to determine the matching relationship information corresponding to each target resource. After obtaining the matching relationship information, the configuration information of the resource position corresponding to the target resource can be determined from the resource position data set, so that the configuration information can be used to further adjust the target resource later.

[0091] Further, adjusting the target resource according to the configuration information to obtain the resource to be displayed corresponding to the target resource position includes: determining style information of the area to be filled in the target resource position according to the configuration information; adjusting the target resource based on the style information to obtain the resource to be displayed corresponding to the target resource position.

[0092] Among them, the area to be filled can be understood as the display area in the target resource position where resources need to be displayed. Since the positions and sizes of various resource positions are different, considering the aesthetics and display effects of the page layout, the styles of the areas to be filled in various resource positions may also be different. In order to adapt the target resource to the target resource position, it is necessary to first adjust the target resource according to the style information of the area to be filled in the target resource position.

[0093] In a specific embodiment of the present specification, it is determined that the style information of the area to be filled in the target resource position is a rectangle, and then the shape, size and other parameters of the target resource are adjusted according to the style information to obtain the corresponding resource to be displayed.

[0094] Furthermore, after obtaining the resource to be displayed corresponding to the target resource position, the method further includes: determining the position information of the area to be filled according to the configuration information; adding the resource to be displayed to the target resource position according to the position information, and obtaining a target resource data packet, wherein the target resource data packet is used to display the resource to be displayed at the target resource position.

[0095] Among them, the location information of the area to be filled can be understood as the location of the resources to be displayed in the target resource position. The resources to be displayed are added according to the location information, so as to ensure the aesthetic effect of the subsequent layout and avoid the situation where the resources to be displayed are blocked. After adding the resources to be displayed to the target resource position based on the location information, the target resource data packet can be obtained. The target resource package can be understood as a data packet that can be used directly later.

[0096] In actual applications, after obtaining the target resource data package, the target resource data package can be directly used when rendering the page, so as to display the corresponding resource in the resource position. For an example, see Figure 3B , Figure 3B A schematic diagram of a display page in a resource generation method provided in an embodiment of this specification is shown, wherein the corresponding material resources are displayed in the resource position at the top of the page, and the relevant introduction and description of the material displayed in the resource position is included at the bottom of the page. It should be noted that the page layout is only an exemplary description, and in actual situations, the number of resource positions in the page and the display requirements can be determined according to specific circumstances.

[0097] An embodiment of this specification implements determining the extended information corresponding to the initial resource, calling the business operation link of the resource generation business to analyze the extended information, and generating a prompt text for the initial resource. Resource generation is performed by using a business operation link that is deeply integrated with the resource generation business, thereby improving the efficiency of resource generation. In addition, the extended information of the initial resource provided for reference is analyzed to generate a prompt text, which facilitates the subsequent use of the resource generation model to generate the target resource. Resource generation is performed by using a resource generation model based on image processing, thereby reducing labor costs while ensuring the quality of resource generation.

[0098] The following combination Figure 4 Taking the application of the resource generation method provided in this specification in medal resource generation as an example, the resource generation method is further described. Figure 4 A process flow chart of a resource generation method provided by an embodiment of the present specification is shown, which specifically includes the following steps.

[0099] Step 402: Determine the layer information corresponding to the resource file, parse the resource file according to the layer information, and obtain the initial resource corresponding to the resource file.

[0100] In a specific embodiment, a designer generates medal material resources for a medal generation business, uploads a reference medal material, determines the layer information corresponding to the resource file, parses the resource file according to the layer information, obtains a layer resource set and layer annotation information corresponding to the layer resource set, extracts target layer resources from the layer resource set according to the layer annotation information, and obtains the medal image uploaded by the designer.

[0101] Step 404: Determine the extended information corresponding to the initial resource.

[0102] In a specific embodiment, the extended information includes style information of the medal image and user specific demand information.

[0103] Step 406: Call the service operation link of the resource generation service, analyze the extended information, and generate the prompt text of the initial resource.

[0104] In a specific embodiment, the extended information is analyzed through the link nodes in the business operation link to determine the corresponding extended keywords, and the corresponding prompt text is generated using the text generation model and / or the knowledge graph.

[0105] Step 408: Input the prompt text and the initial resource into the resource generation model based on image processing to obtain the target resource output by the resource generation model.

[0106] In a specific embodiment, the prompt texts "gold medal", "Olympic Games" and reference medal material resources are input into the resource generation model to obtain the target resource output by the model.

[0107] Step 410: determine an image processing node in the business operation link, and perform image editing on the target resource through the image processing node to obtain the edited target resource.

[0108] In a specific embodiment, the generated medal material resource is edited through the image processing node in the business operation link to obtain the edited medal material resource.

[0109] Step 412: Acquire configuration information corresponding to the target resource, and adjust the edited target resource according to the configuration information.

[0110] In a specific embodiment, a resource bit data set and matching relationship information between a target resource and a resource bit data set are determined, and based on the matching relationship information, a target resource bit corresponding to the target resource and configuration information corresponding to the target resource bit are determined in the resource bit data set. The edited medal material resource is adjusted according to the configuration information.

[0111] Step 414: Determine the location information of the area to be filled according to the configuration information.

[0112] Step 416: Add the resource to be displayed to the target resource position according to the position information to obtain a target resource data packet, wherein the target resource data packet is used to display the resource to be displayed at the target resource position.

[0113] An embodiment of this specification implements determining the extended information corresponding to the initial resource, calling the business operation link of the resource generation business to analyze the extended information, and generating a prompt text for the initial resource. Resource generation is performed by using a business operation link that is deeply integrated with the resource generation business, thereby improving the efficiency of resource generation. In addition, the extended information of the initial resource provided for reference is analyzed to generate a prompt text, which facilitates the subsequent use of the resource generation model to generate the target resource. Resource generation is performed by using a resource generation model based on image processing, thereby reducing labor costs while ensuring the quality of resource generation.

[0114] Corresponding to the above method embodiment, this specification also provides a resource generation device embodiment, Figure 5 FIG. 1 shows a schematic diagram of a resource generation device provided by an embodiment of the present specification. Figure 5 As shown, the device comprises:

[0115] The determination module 502 is configured to determine the extended information corresponding to the initial resource.

[0116] The generation module 504 is configured to call the service operation link of the resource generation service, analyze the extended information, and generate a prompt text of the initial resource, wherein the link nodes in the service operation link have a corresponding relationship with the service process of the resource generation service.

[0117] The input module 506 is configured to input the prompt text and the initial resource into the resource generation model based on image processing to obtain the target resource output by the resource generation model.

[0118] The adjustment module 508 is configured to obtain configuration information corresponding to the target resource position, adjust the target resource according to the configuration information, and obtain the to-be-displayed resource corresponding to the target resource position, wherein the to-be-displayed resource is used to be displayed at the target resource position.

[0119] Furthermore, the generation module 504 is further configured to perform text analysis on the extended information to determine the extended keywords corresponding to the extended information; input the extended keywords into a text generation model based on language processing to obtain the prompt text of the initial resource output by the text generation model; and / or determine a preset knowledge graph, search the preset knowledge graph according to the extended keywords, and determine the prompt text of the initial resource based on the search results.

[0120] Furthermore, the device also includes an updating module, which is configured to determine model adjustment parameters of the resource generation model, and update the resource generation model based on the model adjustment parameters to obtain an updated resource generation model; inputting the prompt text and the initial resource into the resource generation model based on image processing, including: inputting the prompt text and the initial resource into the updated resource generation model.

[0121] Furthermore, the device also includes an editing module, which is configured to determine an image processing node in the business operation link; perform image editing on the target resource through the image processing node to obtain an edited target resource; and adjust the target resource according to the configuration information, including: adjusting the edited target resource according to the configuration information.

[0122] Furthermore, the adjustment module 508 is further configured to determine a resource position data set and matching relationship information of the target resource associated with the resource position data set; based on the matching relationship information, determine the target resource position corresponding to the target resource and the configuration information corresponding to the target resource position in the resource position data set.

[0123] Furthermore, the adjustment module 508 is further configured to determine style information of the area to be filled in the target resource position according to the configuration information; and adjust the target resource based on the style information to obtain the resource to be displayed corresponding to the target resource position.

[0124] Furthermore, the device also includes an adding module, which is configured to determine the location information of the area to be filled according to the configuration information; add the resource to be displayed to the target resource position according to the location information, and obtain a target resource data packet, wherein the target resource data packet is used to display the resource to be displayed at the target resource position.

[0125] Furthermore, the device also includes a parsing module configured to determine layer information corresponding to a resource file; parse the resource file according to the layer information to obtain an initial resource corresponding to the resource file.

[0126] Furthermore, the parsing module is further configured to parse the resource file according to the layer information to obtain a layer resource set and layer annotation information corresponding to the layer resource set; extract target layer resources from the layer resource set according to the layer annotation information, and use the target layer resources as the initial resources corresponding to the resource file.

[0127] Furthermore, the generating module 504 is further configured to determine a service operation link of the resource generating service and a link node in the service operation link; and analyze the extended information through the link node.

[0128] The above is a schematic scheme of a resource generation device of this embodiment. It should be noted that the technical scheme of the resource generation device and the technical scheme of the resource generation method described above are of the same concept, and the details not described in detail in the technical scheme of the resource generation device can be found in the description of the technical scheme of the resource generation method described above.

[0129] Corresponding to the above method embodiment, this specification also provides a resource generation system embodiment. Figure 6 FIG. 1 shows a schematic diagram of a resource generation system provided by an embodiment of the present specification. Figure 6 As shown, the system includes a client 602 and a server 604, wherein:

[0130] The client is used to receive the initial resource and forward the initial resource to the server.

[0131] In one possible implementation, the client may be a terminal used by a user of a resource generation service, and the user may be an activity operator or a page manager. The user uploads the initial resource for reference to the client, and the client forwards the initial resource to the server, so that the server can generate resources. The server may be a service provider of the resource generation service.

[0132] The server is used to determine the extended information corresponding to the initial resource; call the service operation link of the resource generation service, analyze the extended information, and generate a prompt text for the initial resource, wherein the link node in the service operation link has a corresponding relationship with the business process of the resource generation service; input the prompt text and the initial resource into the resource generation model based on image processing, and obtain the target resource output by the resource generation model; obtain the configuration information corresponding to the target resource position, adjust the target resource according to the configuration information, obtain the resource to be displayed corresponding to the target resource position and forward it to the client, wherein the resource to be displayed is used to be displayed at the target resource position;

[0133] The client is used to display a resource display page, wherein the resource display page includes the resource to be displayed.

[0134] In one achievable manner, the client receives the resources to be displayed returned by the server, and can render and generate a resource display page based on the resources to be displayed and other resource elements, so that the user can preview the page or put the page online.

[0135] The above is a schematic scheme of a resource generation system of this embodiment. It should be noted that the technical scheme of the resource generation system and the technical scheme of the resource generation method described above are of the same concept, and the details not described in detail in the technical scheme of the resource generation system can be found in the description of the technical scheme of the resource generation method described above.

[0136] Figure 7 The block diagram of a computing device 700 according to an embodiment of the present specification is shown. The components of the computing device 700 include but are not limited to a memory 710 and a processor 720. The processor 720 is connected to the memory 710 via a bus 730, and the database 750 is used to store data.

[0137] The computing device 700 also includes an access device 740, which enables the computing device 700 to communicate via one or more networks 760. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 740 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0138] In one embodiment of the present specification, the above components of the computing device 700 and Figure 7 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 7 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0139] The computing device 700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 700 may also be a mobile or stationary server.

[0140] The processor 720 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned resource generation method.

[0141] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the resource generation method described above are of the same concept, and the details not described in detail in the technical scheme of the computing device can be found in the description of the technical scheme of the resource generation method described above.

[0142] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which can implement the steps of the above-mentioned resource generation method when executed by a processor.

[0143] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the resource generation method described above are of the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the resource generation method described above.

[0144] An embodiment of the present specification also provides a computer program product, including a computer program or instructions, which implement the steps of the above-mentioned resource generation method when executed by a processor.

[0145] The above is a schematic scheme of a computer program product of this embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the resource generation method described above are of the same concept, and the details not described in detail in the technical scheme of the computer program product can be found in the description of the technical scheme of the resource generation method described above.

[0146] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0147] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0148] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0149] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0150] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can understand and use this specification well.

Claims

1. A resource generation method, characterized in that: include: Determine the extended information corresponding to the initial resource; Calling a service operation link of a resource generation service, analyzing the extended information, and generating a prompt text of the initial resource, wherein the link nodes in the service operation link have a corresponding relationship with the service process of the resource generation service; Inputting the prompt text and the initial resource into a resource generation model based on image processing to obtain a target resource output by the resource generation model; Configuration information corresponding to the target resource position is acquired, and the target resource is adjusted according to the configuration information to obtain a resource to be displayed corresponding to the target resource position, wherein the resource to be displayed is used to be displayed at the target resource position.

2. The method according to claim 1, characterized in that Analyze the extended information to generate a prompt text of the initial resource, including: Performing text analysis on the extended information to determine extended keywords corresponding to the extended information; Inputting the extended keyword into a text generation model based on language processing to obtain a prompt text of the initial resource output by the text generation model; and / or, A preset knowledge graph is determined, and a search is performed in the preset knowledge graph according to the extended keyword, and a prompt text of the initial resource is determined according to the search result.

3. The method according to claim 1, characterized in that Before inputting the prompt text and the initial resource into the resource generation model based on image processing, the method further includes: Determining a model adjustment parameter of the resource generation model, and updating the resource generation model based on the model adjustment parameter to obtain an updated resource generation model; Inputting the prompt text and the initial resource into a resource generation model based on image processing, comprising: The prompt text and the initial resource are input into the updated resource generation model.

4. The method according to claim 1, characterized in that: After inputting the prompt text and the initial resource into a resource generation model based on image processing and obtaining a target resource output by the resource generation model, the method further includes: Determining an image processing node in the service operation link; Performing image editing on the target resource by using the image processing node to obtain the edited target resource; Adjusting the target resource according to the configuration information includes: The edited target resource is adjusted according to the configuration information.

5. The method according to claim 1, characterized in that Get the configuration information corresponding to the target resource location, including: Determine a resource location data set, and matching relationship information between the target resource and the resource location data set; Based on the matching relationship information, a target resource bit corresponding to the target resource and configuration information corresponding to the target resource bit are determined in the resource bit data set.

6. The method according to claim 1, characterized in that The target resource is adjusted according to the configuration information to obtain a resource to be displayed corresponding to the target resource, including: Determine style information of the area to be filled in the target resource position according to the configuration information; The target resource is adjusted based on the style information to obtain a resource to be displayed corresponding to the target resource.

7. The method according to claim 6, characterized in that After obtaining the resource to be displayed corresponding to the target resource position, the method further includes: Determine the position information of the area to be filled according to the configuration information; The resource to be displayed is added to the target resource position according to the position information to obtain a target resource data packet, wherein the target resource data packet is used to display the resource to be displayed at the target resource position.

8. The method according to claim 1, characterized in that Before determining the extended information corresponding to the initial resource, the method further includes: Determine the layer information corresponding to the resource file; The resource file is parsed according to the layer information to obtain initial resources corresponding to the resource file.

9. The method according to claim 8, characterized in that Parsing the resource file according to the layer information to obtain the initial resource corresponding to the resource file includes: Parsing the resource file according to the layer information to obtain a layer resource set and layer annotation information corresponding to the layer resource set; The target layer resource is extracted from the layer resource set according to the layer annotation information, and the target layer resource is used as the initial resource corresponding to the resource file.

10. The method according to any one of claims 1 to 9, characterized in that: Calling the service operation link of the resource generation service to analyze the extended information includes: Determine a service operation link of a resource generation service and link nodes in the service operation link; The extended information is analyzed by the link node.

11. A resource generation system, characterized in that: The system includes a client and a server, wherein: The client is used to receive the initial resource and forward the initial resource to the server; The server is used to determine the extended information corresponding to the initial resource; call the service operation link of the resource generation service, analyze the extended information, and generate a prompt text for the initial resource, wherein the link node in the service operation link has a corresponding relationship with the business process of the resource generation service; input the prompt text and the initial resource into the resource generation model based on image processing, and obtain the target resource output by the resource generation model; obtain the configuration information corresponding to the target resource position, adjust the target resource according to the configuration information, obtain the resource to be displayed corresponding to the target resource position and forward it to the client, wherein the resource to be displayed is used to be displayed at the target resource position; The client is used to display a resource display page, wherein the resource display page includes the resource to be displayed.

12. A resource generation device, characterized in that: include: A determination module, configured to determine the extended information corresponding to the initial resource; A generating module is configured to call a service operation link of a resource generating service, analyze the extended information, and generate a prompt text of the initial resource, wherein the link nodes in the service operation link have a corresponding relationship with the service process of the resource generating service; An input module, configured to input the prompt text and the initial resource into a resource generation model based on image processing, and obtain a target resource output by the resource generation model; The adjustment module is configured to obtain configuration information corresponding to the target resource position, adjust the target resource according to the configuration information, and obtain the to-be-displayed resource corresponding to the target resource position, wherein the to-be-displayed resource is used to be displayed at the target resource position.

13. A computing device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the resource generation method according to any one of claims 1 to 10 are implemented.

14. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, implement the steps of the resource generation method described in any one of claims 1 to 10.

15. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processor, implements the steps of the resource generation method according to any one of claims 1 to 10.

Images