Advertisement creativity generation method and device, storage medium and electronic equipment

Abstract

The invention relates to an advertisement creativity generation method and device, a storage medium and electronic equipment. The method comprises the following steps: generating an advertisement structure matched with advertisement information according to the advertisement information input by a user and a preset advertisement template; calling a text generation model, a picture generation model and a video generation model according to the advertisement structure and an advertisement original material uploaded by a user, and respectively generating a plurality of text creative materials, image creative materials and video creative materials to obtain multiple types of creative materials; performing cross multiplication combination on the multiple types of creative materials to generate multiple groups of advertisement creative schemes, and performing similarity detection and duplicate removal processing to obtain a duplicate-removed advertisement creative scheme set; and storing the advertisement creative scheme set in an advertisement material database, and displaying the advertisement creative scheme set on a user interface of the user. The technical problem that automatic generation and diversification of creative contents are difficult to realize in the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of multimedia intelligent processing technology, and in particular to a method, apparatus, storage medium, and electronic device for generating advertising ideas. Background Technology

[0002] With the rapid development of digital advertising platforms, the generation and optimization of ad creatives have become crucial factors affecting ad performance and conversion rates. Existing advertising platforms generally rely on advertisers manually creating ad structures, requiring them to repeatedly fill in numerous fields across multiple levels, including campaigns, ads, and creatives, and manually upload and configure creative materials. This method is not only cumbersome and inefficient but also heavily reliant on advertisers' expertise and experience, leading to significant variations in creative quality and campaign performance. Furthermore, the system lacks intelligent optimization and expansion capabilities for uploaded creative materials, making it difficult to achieve automatic generation and diversification of creative content. In addition, inefficient or poorly performing creatives cannot be identified and removed in a timely manner, continuously consuming system computing and indexing resources, resulting in resource waste and impacting the exposure opportunities of high-quality creatives. Summary of the Invention

[0003] This application provides a method, apparatus, storage medium, and electronic device for generating advertising creative ideas, in order to solve the technical problem that existing technologies struggle to achieve automatic generation and diversification of creative content.

[0004] Firstly, this application provides a method for generating advertising creatives, comprising: generating an advertising structure matching the advertising information input by the user and a preset advertising template; generating multiple text creative materials, image creative materials, and video creative materials respectively by calling a text generation model, an image generation model, and a video generation model based on the advertising structure and the original advertising materials uploaded by the user, thereby obtaining multiple types of creative materials; performing cross-product combination on the multiple types of creative materials to generate multiple sets of advertising creative schemes, and performing similarity detection and deduplication processing to obtain a set of deduplicated advertising creative schemes; storing the set of advertising creative schemes in an advertising material database and displaying it on the user's user interface.

[0005] Secondly, this application provides an advertising creative generation device, comprising: a first generation module, used to generate an advertising structure matching the advertising information input by the user and a preset advertising template; a second generation module, used to generate multiple text creative materials, image creative materials, and video creative materials respectively by calling a text generation model, an image generation model, and a video generation model based on the advertising structure and the original advertising materials uploaded by the user, thereby obtaining multiple types of creative materials; a combination module, used to perform cross-product combination of the above-mentioned multiple types of creative materials to generate multiple sets of advertising creative schemes, and perform similarity detection and deduplication processing to obtain a set of deduplicated advertising creative schemes; and a storage module, used to store the above-mentioned set of advertising creative schemes in an advertising material database and display it on the user's user interface.

[0006] As an optional example, the above-mentioned device further includes: a construction module, used to abstract and define the structural elements of the advertisement based on historical advertising data, industry category and advertisement type before generating an advertisement structure that matches the advertisement information input by the user and a preset advertisement template, and to construct an advertisement template that includes an advertisement title, copy area, image area, video area and interactive area; and a configuration module, used to parameterize the layout, content hierarchy and creative display logic of the advertisement template according to different industry characteristics and advertising objectives.

[0007] As an optional example, the second generation module includes: a first extraction unit, used to extract the corresponding advertising theme based on the text placeholder area in the above advertising structure; and a first generation unit, used to input the title, description and selling point information in the above original advertising material into the above text generation model, so that the above text generation model generates multiple text creative materials that conform to the above advertising theme.

[0008] As an optional example, the second generation module includes: a second extraction unit, used to extract the main elements, brand logo, and background information from the original advertising materials based on the layout requirements and visual theme of the image placement area in the advertising structure; a second generation unit, used to input the visual theme, the main elements, the brand logo, and the background information into the image generation model, so that the image generation model has multiple image creative materials; and a filtering unit, used to perform clarity, composition ratio, and visual consistency checks on all image creative materials to filter out image creative materials that meet the layout requirements.

[0009] As an optional example, the second generation module includes: an analysis unit, used to perform frame-level analysis and segmentation of the original advertising material based on the video duration, aspect ratio, and rhythm parameters in the advertising structure, to obtain keyframes; a third generation unit, used to input the keyframes into the video generation model, so that the video generation model generates multiple dynamic video contents that conform to the advertising theme in the advertising structure; and a detection unit, used to detect the continuity of the images, the smoothness of the transitions, and the synchronization of audio and video for all dynamic video contents, and output multiple video creative materials that conform to the advertising placement specifications.

[0010] As an optional example, the above combination module includes: a processing unit, configured to determine the unprocessed advertising creative scheme among the multiple sets of advertising creative schemes generated by cross-product combination as the current advertising creative scheme, and perform the following processing on the current advertising creative scheme: calculate the cosine similarity of the feature vectors of the current advertising creative scheme and the first advertising creative scheme, wherein the first advertising creative scheme is any advertising creative scheme other than the current advertising creative scheme among the multiple sets of advertising creative schemes; if the cosine similarity of the feature vectors is greater than the similarity threshold, remove the current advertising creative scheme or the first advertising creative scheme.

[0011] As an optional example, the above apparatus further includes: a detection module, used to monitor the delivery data of each advertising creative scheme in the advertising creative scheme set during the delivery process after storing the above advertising creative scheme set in the advertising material database and displaying it on the user's user interface; a marking module, used to compare the delivery data with a preset performance threshold, and mark the second advertising creative scheme as an inefficient advertising creative scheme if it is detected that the delivery data of the second advertising creative scheme is lower than the preset performance threshold for a continuous preset period, wherein the second advertising creative scheme is any one of the advertising creative schemes in the advertising creative scheme set; and an execution module, used to perform pause, archive, or replacement operations on the second advertising creative scheme through a rule engine.

[0012] Thirdly, this application provides a storage medium storing a computer program, wherein the computer program is executed by a processor to perform the above-described method for generating advertising creatives.

[0013] Fourthly, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-described method for generating advertising creatives through the computer program.

[0014] The technical solutions provided in this application have the following advantages compared with the prior art: This application employs a method that generates an advertising structure matching the user-input advertising information and a preset advertising template; based on the advertising structure and the user-uploaded original advertising materials, it calls text generation models, image generation models, and video generation models to generate multiple text creative materials, image creative materials, and video creative materials, respectively, resulting in multiple types of creative materials; it performs cross-product combination on the above-mentioned multiple types of creative materials to generate multiple sets of advertising creative schemes, and performs similarity detection and deduplication processing to obtain a set of deduplicated advertising creative schemes; it stores the above set of advertising creative schemes in an advertising material database and displays it on the user's user interface. In this method, the advertising structure is automatically generated based on the user-input advertising information and a preset template, and multiple types of creative materials are generated by calling text, image, and video generation models respectively; then, the multiple types of materials are cross-product combined and similarity deduplication processed to obtain a high-quality set of advertising creative schemes, which is then stored and displayed on the user interface. This automates and automates the advertising creation process, significantly improving advertising generation efficiency and creative diversity, reducing manual configuration costs, and enhancing advertising effectiveness and system resource utilization. It also solves the technical problem that existing technologies struggle to achieve automatic generation and diversification of creative content. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0018] Figure 1 This is a flowchart of an optional method for generating advertising creatives according to an embodiment of this application; Figure 2 This is a flowchart illustrating the specific implementation of an optional method for generating advertising creatives according to an embodiment of this application. Figure 3 This is a schematic diagram of an optional advertising creative generation device according to an embodiment of this application; Figure 4This is a schematic diagram of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0021] According to a first aspect of the embodiments of this application, a method for generating advertising creative is provided, optionally, as follows: Figure 1 As shown, the above method includes: S102, Generate an advertising structure that matches the advertising information based on the advertising information input by the user and the preset advertising template; S104: Based on the ad structure and the original ad materials uploaded by the user, call the text generation model, image generation model and video generation model to generate multiple text creative materials, image creative materials and video creative materials respectively, to obtain multiple types of creative materials; S106: Perform cross-product combination on multiple types of creative materials to generate multiple sets of advertising creative schemes, and perform similarity detection and deduplication to obtain a set of deduplicated advertising creative schemes. S108 stores the collection of advertising creative solutions in the advertising material database and displays them on the user's user interface.

[0022] Optionally, in this embodiment, an advertising creative generation method combining artificial intelligence and automated processes is provided to address the problems of low efficiency, unstable creative quality, and low resource utilization in existing advertising creation processes. The specific implementation process is as follows: Figure 2 As shown, it includes the following steps: First, based on the user-input advertising information and preset advertising templates, an advertising structure matching the advertising information is automatically generated. By abstracting the common configurations of advertising campaigns and advertising levels into JSON templates and combining them with a dynamic parameterized population mechanism, an advertising structure conforming to platform specifications can be quickly generated when users only need to fill in a few core fields, thereby significantly reducing operational complexity.

[0023] Secondly, based on the ad structure and the original ad creatives uploaded by users, the system automatically invokes text generation, image generation, and video generation models to generate multiple text-based, image-based, and video creative creatives, respectively. Specifically, the text generation model generates diverse ad copy based on ad keywords, product characteristics, and target audience information; the image generation model utilizes generative adversarial networks or diffusion models to perform style transfer, background expansion, and visual enhancement on uploaded images; and the video generation model generates dynamic video creative content based on image sequences or existing video footage through techniques such as video re-editing and motion enhancement. Through these steps, a collection of high-quality creative creatives of various types and styles can be obtained.

[0024] Then, a cross-product combination operation is performed on the generated creative materials of various types. Based on different combinations of text, images, and video materials, multiple sets of advertising creative schemes are generated in batches. To avoid creative redundancy and content duplication, hash verification and feature vector comparison algorithms are further used to perform similarity detection and deduplication on the generated results, resulting in a set of advertising creative schemes with high uniqueness.

[0025] Finally, the deduplicated set of advertising creative solutions is stored in the advertising material database and displayed to users in real time through the front-end interface, allowing advertisers to preview, filter, and deploy the ads.

[0026] Optionally, this embodiment introduces a template-based creation and AI-powered intelligent generation mechanism to achieve automatic construction of ad structures and efficient production of creative content, significantly reducing the manual workload for advertisers. Multimodal AI-generated text, image, and video materials can automatically undergo style optimization and content expansion, enhancing the creative richness and visual appeal of ads. Through cross-product combination and deduplication algorithms, the efficiency of creative generation and content diversity are greatly improved, providing more high-quality candidate solutions for ad placement. Furthermore, the system can continuously optimize creative content and improve resource utilization, thereby automating, streamlining, and intelligentizing the ad creation process, improving overall placement effectiveness and the operational revenue of the advertising platform.

[0027] As an optional example, before generating an ad structure that matches the user-input ad information and a preset ad template, the above method further includes: Based on historical advertising data, industry categories, and advertising types, the structural elements of advertising are abstracted and defined to construct an advertising template that includes an advertising title, text area, image area, video area, and interactive area. Based on the characteristics of different industries and the goals of advertising campaigns, the layout, content hierarchy, and creative display logic of the advertising templates are configured parametrically.

[0028] Optionally, in this embodiment, before generating an ad structure matching the user-input ad information and a preset ad template, the general configuration of ad campaigns and ad levels is abstracted into a predefined JSON template. This template is then dynamically instantiated using Java reflection. Specifically, firstly, based on historical ad delivery data, industry categories, and ad types, the structural elements of the ad are abstracted and defined, constructing a standardized ad template that includes an ad title, text area, image area, video area, and interactive area. Subsequently, according to different industry characteristics and ad delivery goals, the template's layout, content hierarchy, and creative display logic are parameterized to achieve flexible adaptation and structural reuse of the ad template. Through these steps, the ad construction logic can be unified and standardized at the template level, reducing repetitive configuration operations for advertisers when creating ads.

[0029] Optionally, this embodiment significantly reduces the complexity of ad structure generation through the abstraction and parameterization of template structure, and improves the system's adaptability in multiple industries and multi-target scenarios; it realizes the standardization, modularization and efficiency of the ad creation process, and provides a unified structural foundation for subsequent AI creative generation, thereby improving ad creation efficiency and overall delivery quality.

[0030] As an optional example, based on the ad structure and the original ad creatives uploaded by the user, the text generation model, image generation model, and video generation model are invoked to generate multiple text creative creatives, image creative creatives, and video creative creatives, resulting in various types of creative creatives, including: Extract the corresponding ad theme based on the text placeholder area in the ad structure; Input the title, description, and selling points from the original advertising materials into the text generation model so that the text generation model can generate multiple text creative materials that match the advertising theme.

[0031] Optionally, in this embodiment, an asynchronous message-driven AI processing pipeline is constructed. After the user uploads the original materials, the text generation model, image generation model, and video generation model are automatically invoked for parallel processing. Based on the ad structure and the user-uploaded original ad materials, multiple text creative materials, image creative materials, and video creative materials are generated to obtain various types of creative materials. Specifically, in the process of generating text creative materials, the corresponding ad theme and semantic context information are first extracted based on the text placeholder area in the ad structure. Then, the title, product description, and selling point information in the original ad materials are input into the text generation model, enabling the model to generate ad copy that conforms to semantic logic and has diverse styles based on the ad theme. The generated text creative materials can be optimized in tone and content according to different placement scenarios, audience characteristics, and marketing goals, thereby improving the targeting and attractiveness of the ad expression.

[0032] Optionally, this embodiment achieves automated creation and diversified output of advertising copy through intelligent reasoning based on thematic extraction from the advertising structure and text generation models, reducing manual writing costs. The generated copy content can achieve a balance between semantic consistency and creative expression, significantly improving the quality of advertising creativity and the effectiveness of ad placement, and providing efficient and intelligent text creative support for automated advertising generation systems.

[0033] As an optional example, based on the ad structure and the original ad creatives uploaded by the user, the text generation model, image generation model, and video generation model are invoked to generate multiple text creative creatives, image creative creatives, and video creative creatives, resulting in various types of creative creatives, including: Based on the layout requirements and visual theme of the image placement area in the advertising structure, the main elements, brand logos and background information in the original advertising materials are extracted; Input the visual theme, main elements, brand logo, and background information into the image generation model to generate multiple creative image materials for the image generation model; All image creative materials are tested for clarity, composition ratio, and visual consistency in order to select those that meet the layout requirements.

[0034] Optionally, in this embodiment, an asynchronous message-driven AI processing pipeline is constructed. After the user uploads the original materials, the text generation model, image generation model, and video generation model are automatically invoked for parallel processing. Based on the ad structure and the user-uploaded original ad materials, multiple text creative materials, image creative materials, and video creative materials are generated to obtain multiple types of creative materials. Specifically, in the process of generating image creative materials, firstly, based on the layout requirements and visual theme of the image placement area in the ad structure, the main elements, brand logo, and background information in the original ad materials are extracted; then, the extracted visual theme, main elements, brand logo, and background information are input into the image generation model. Through generative techniques such as image enhancement, style transfer, and background expansion, multiple image creative materials that conform to the visual style and brand tone of the ad are generated; finally, all generated image creative materials are tested for clarity, composition ratio, and visual consistency, and target image materials that meet the template layout and display standards are selected.

[0035] Optionally, this embodiment combines advertising structure and visual theme features to achieve intelligent generation and quality screening of image creative materials, which can enrich the visual expression of advertising while ensuring brand consistency.

[0036] As an optional example, based on the ad structure and the original ad creatives uploaded by the user, the text generation model, image generation model, and video generation model are invoked to generate multiple text creative creatives, image creative creatives, and video creative creatives, resulting in various types of creative creatives, including: Based on the video duration, aspect ratio, and rhythm parameters in the advertising structure, frame-level analysis and segmentation are performed on the original advertising materials to obtain keyframes; Keyframes are input into the video generation model so that the video generation model can generate multiple dynamic video contents that conform to the advertising theme in the advertising structure; The system performs tests on the continuity of the video footage, the smoothness of transitions, and the synchronization of audio and video for all dynamic video content, and outputs multiple creative video materials that meet advertising standards.

[0037] Optionally, in this embodiment, an asynchronous message-driven AI processing pipeline is constructed. After the user uploads the original materials, the text generation model, image generation model, and video generation model are automatically invoked for parallel processing. Based on the ad structure and the user-uploaded original ad materials, multiple text creative materials, image creative materials, and video creative materials are generated to obtain multiple types of creative materials. Specifically, in the process of generating video creative materials, firstly, based on the video duration, aspect ratio, and rhythm parameters set in the ad structure, frame-level analysis and segmentation of the original ad materials are performed to extract representative keyframes. Subsequently, the keyframes are input into the video generation model, and multiple dynamic video contents that match the ad theme and have a coordinated visual rhythm are generated through technologies such as image-generated video, video re-editing, or motion enhancement. Finally, all generated video contents are tested for visual coherence, smoothness of transitions, and audio-visual synchronization to select high-quality video creative materials that meet the ad placement specifications.

[0038] Optionally, this embodiment achieves automated generation and quality control of advertising video content by performing frame-level analysis and AI-powered optimization of video footage, significantly reducing manual editing and production costs. The generated video footage has advantages in visual smoothness and content consistency, enhancing the immersiveness and communicative power of advertising displays, thereby improving the overall advertising effectiveness and user conversion rate.

[0039] As an optional example, similarity detection and deduplication are performed to obtain a set of deduplicated advertising creative solutions, including: The unprocessed ad creative scheme among the multiple ad creative schemes generated by cross-product combination is identified as the current ad creative scheme, and the following processing is performed on the current ad creative scheme: Calculate the cosine similarity of the feature vectors of the current ad creative and the first ad creative, where the first ad creative is any ad creative other than the current ad creative among multiple ad creatives; If the cosine similarity of the feature vectors is greater than the similarity threshold, the current ad creative or the first ad creative will be removed.

[0040] Optionally, in this embodiment, the unprocessed advertising creative schemes are first identified as the current advertising creative scheme, and similarity detection and deduplication are performed. Specifically, feature vectors are extracted from the current advertising creative scheme and other advertising creative schemes (i.e., the first advertising creative scheme), and the cosine similarity of their feature vectors is calculated to measure the similarity between the two in terms of creative content, element combination, and design features. When the calculated cosine similarity of the feature vectors exceeds a preset similarity threshold, it is determined that the current advertising creative scheme and the first advertising creative scheme have high similarity, and one of them is removed according to the set strategy. In this way, redundant schemes are traversed and screened one by one, and finally a set of deduplicated and optimized advertising creative schemes is obtained.

[0041] Optionally, this embodiment introduces a feature vector similarity detection and deduplication mechanism during the ad creative generation process. This effectively avoids the occurrence of duplicate or highly similar ad creatives, reduces the workload of manual screening, and improves the diversity and quality of generated schemes. Simultaneously, using cosine similarity as a criterion allows for accurate measurement of the similarity between creatives while maintaining computational efficiency. This ensures that the output set of ad creative schemes is more differentiated and innovative, providing more valuable reference schemes for subsequent ad placement and optimization.

[0042] As an alternative example, after storing the collection of advertising creative options in an advertising creative database and displaying it on the user's user interface, the above method also includes: Monitor the delivery data of each ad creative in the ad creative scheme collection during the delivery process; The delivery data is compared with the preset performance threshold. If the delivery data of the second advertising creative scheme is lower than the preset performance threshold in a continuous preset period, the second advertising creative scheme is marked as an inefficient advertising creative scheme. The second advertising creative scheme is any one of the advertising creative schemes in the set of advertising creative schemes. The rules engine allows you to pause, archive, or replace the second ad creative.

[0043] Optionally, in this embodiment, after the set of advertising creative schemes is generated and stored in the advertising material database, the set of advertising creative schemes is displayed on the user interface for users to view, filter, and manage the placement. During the advertising placement process, the placement data of each advertising creative scheme in the set is continuously monitored, including but not limited to key indicators such as impressions, click-through rate, and conversion rate, and the monitored placement data is compared with preset performance thresholds in real time. When it is detected that the placement data of a certain advertising creative scheme (i.e., the second advertising creative scheme) is consistently lower than the preset performance threshold within a consecutive preset period, the advertising creative scheme is automatically marked as an inefficient advertising creative scheme. Subsequently, the rule engine performs corresponding processing operations on the inefficient advertising creative scheme, including pausing placement, archiving and saving, or replacing with a new advertising creative scheme, so as to achieve dynamic optimization of advertising content and reasonable allocation of resources.

[0044] Optionally, this embodiment introduces performance monitoring and intelligent decision-making mechanisms during the ad creative delivery stage, enabling automated quality assessment and dynamic adjustment of ad creative solutions. It can identify inefficient creatives in real time based on delivery performance and automatically execute optimization operations, thereby effectively improving the overall conversion efficiency and budget utilization of ad delivery.

[0045] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0046] According to another aspect of the embodiments of this application, an apparatus for generating advertising creative ideas is also provided, such as... Figure 3 As shown, it includes: The first generation module 302 is used to generate an advertising structure that matches the advertising information based on the advertising information input by the user and the preset advertising template. The second generation module 304 is used to call the text generation model, image generation model and video generation model according to the advertising structure and the original advertising materials uploaded by the user, to generate multiple text creative materials, image creative materials and video creative materials respectively, so as to obtain multiple types of creative materials; The combination module 306 is used to perform cross-product combination on multiple types of creative materials to generate multiple sets of advertising creative schemes, and to perform similarity detection and deduplication to obtain a set of deduplicated advertising creative schemes. Storage module 308 is used to store the collection of advertising creative schemes into the advertising material database and display them on the user's user interface.

[0047] It should be noted that the first generation module 302 in this embodiment can be used to execute step S102 in this application embodiment, the second generation module 304 in this embodiment can be used to execute step S104 in this application embodiment, the combination module 306 in this embodiment can be used to execute step S106 in this application embodiment, and the storage module 308 in this embodiment can be used to execute step S108 in this application embodiment.

[0048] As an optional example, the above-described apparatus further includes: The building module is used to abstract and define the structural elements of the advertisement based on historical advertising data, industry category and advertisement type before generating an advertisement structure that matches the advertisement information based on the advertisement information input by the user and the preset advertisement template. It builds an advertisement template that includes an advertisement title, copy area, image area, video area and interactive area. The configuration module is used to parametrically configure the layout, content hierarchy, and creative display logic of the ad templates according to different industry characteristics and campaign objectives.

[0049] As an optional example, the second generation module includes: The first extraction unit is used to extract the corresponding advertising theme based on the text placeholder area in the advertising structure. The first generation unit is used to input the title, description, and selling point information from the original advertising materials into the text generation model, so that the text generation model can generate multiple text creative materials that conform to the advertising theme.

[0050] As an optional example, the second generation module includes: The second extraction unit is used to extract the main elements, brand logos and background information from the original advertising materials based on the layout requirements and visual themes of the image placement area in the advertising structure. The second generation unit is used to input visual themes, main elements, brand logos, and background information into the image generation model, so that the image generation model can generate multiple image creative materials. The filtering unit is used to check the clarity, composition ratio and visual consistency of all image creative materials in order to filter out image creative materials that meet the layout requirements.

[0051] As an optional example, the second generation module includes: The analysis unit is used to perform frame-level analysis and segmentation of the original advertising material based on the video duration, aspect ratio and rhythm parameters in the advertising structure, and to obtain keyframes. The third generation unit is used to input keyframes into the video generation model so that the video generation model can generate multiple dynamic video contents that conform to the advertising theme in the advertising structure. The detection unit is used to detect the continuity of the video, the smoothness of the transitions, and the synchronization of audio and video in all dynamic video content, and output multiple video creative materials that meet the advertising placement specifications.

[0052] As an optional example, the composite module includes: The processing unit is used to identify the unprocessed advertising creative scheme from the multiple sets of advertising creative schemes generated by cross-product combination as the current advertising creative scheme, and to perform the following processing on the current advertising creative scheme: Calculate the cosine similarity of the feature vectors of the current ad creative and the first ad creative, where the first ad creative is any ad creative other than the current ad creative among multiple ad creatives; If the cosine similarity of the feature vectors is greater than the similarity threshold, the current ad creative or the first ad creative will be removed.

[0053] As an optional example, the above-described apparatus further includes: The detection module is used to monitor the delivery data of each ad creative in the ad creative set during the delivery process after the ad creative set is stored in the ad creative database and displayed on the user's user interface; The marking module is used to compare the delivery data with the preset performance threshold, and when it is detected that the delivery data of the second advertising creative scheme is lower than the preset performance threshold in a continuous preset period, the second advertising creative scheme is marked as an inefficient advertising creative scheme. The second advertising creative scheme is any one of the advertising creative schemes in the set of advertising creative schemes. The execution module is used to perform pause, archive, or replacement operations on the second ad creative scheme through the rules engine.

[0054] For other examples of this embodiment, please refer to the examples above, which will not be repeated here.

[0055] Figure 4 This is a schematic diagram of an optional electronic device according to an embodiment of this application, such as... Figure 4 As shown, it includes a processor 402, a communication interface 404, a memory 406, and a communication bus 408. The processor 402, communication interface 404, and memory 406 communicate with each other via the communication bus 408. Memory 406 is used to store computer programs; When processor 402 executes a computer program stored in memory 406, it performs the following steps: Based on the advertising information input by the user and the preset advertising template, generate an advertising structure that matches the advertising information; Based on the ad structure and the original ad materials uploaded by users, the text generation model, image generation model, and video generation model are invoked to generate multiple text creative materials, image creative materials, and video creative materials, resulting in multiple types of creative materials; Multiple types of creative materials are cross-multiplied and combined to generate multiple sets of advertising creative schemes. Similarity detection and deduplication are then performed to obtain a set of deduplicated advertising creative schemes. The collection of advertising creative solutions is stored in the advertising creative database and displayed on the user's user interface.

[0056] Optionally, in this embodiment, the communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single thick line, but this does not indicate that there is only one bus or one type of bus. The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0057] The memory may include RAM, or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0058] As an example, the memory 406 described above may include, but is not limited to, the first generation module 302, the second generation module 304, the combination module 306, and the storage module 308 in the aforementioned advertising creative generation device. Furthermore, it may include, but is not limited to, other module units in the aforementioned advertising creative generation device, which will not be elaborated upon in this example.

[0059] The processor mentioned above can be a general-purpose processor, including but not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0060] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0061] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. The device used to implement the above-described method for generating advertising creatives can be a terminal device, such as a smartphone (e.g., an Android phone, an iOS phone), a tablet computer, a PDA, a mobile internet device (MID), a PAD, or other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic devices. For example, the electronic device may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.

[0062] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, ROM, RAM, disk or optical disk, etc.

[0063] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, which, when executed by a processor, performs the steps in the above-described method for generating advertising creatives.

[0064] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0065] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0066] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0067] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0068] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0069] 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0070] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0071] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for generating advertising creative ideas, characterized in that, include: Based on the advertising information input by the user and the preset advertising template, an advertising structure matching the advertising information is generated; Based on the advertising structure and the original advertising materials uploaded by the user, the text generation model, image generation model, and video generation model are invoked to generate multiple text creative materials, image creative materials, and video creative materials, respectively, resulting in multiple types of creative materials; The various types of creative materials are cross-multiplied and combined to generate multiple sets of advertising creative schemes. Similarity detection and deduplication are then performed to obtain a set of deduplicated advertising creative schemes. The collection of advertising creative solutions is stored in the advertising material database and displayed on the user's user interface.

2. The method according to claim 1, characterized in that, Before generating an ad structure matching the user-input ad information and a preset ad template, the method further includes: Based on historical advertising data, industry categories, and advertising types, the structural elements of advertising are abstracted and defined to construct an advertising template that includes an advertising title, text area, image area, video area, and interactive area. Based on the characteristics of different industries and the goals of advertising campaigns, the layout, content hierarchy, and creative display logic of the advertising templates are configured parametrically.

3. The method according to claim 1, characterized in that, Based on the advertised structure and the user-uploaded original advertising materials, text generation models, image generation models, and video generation models are invoked to generate multiple text creative materials, image creative materials, and video creative materials, resulting in various types of creative materials, including: Based on the text placeholder area in the advertisement structure, extract the corresponding advertisement theme; The title, description, and selling points of the original advertising materials are input into the text generation model so that the text generation model generates multiple text creative materials that conform to the advertising theme.

4. The method according to claim 1, characterized in that, Based on the advertised structure and the user-uploaded original advertising materials, text generation models, image generation models, and video generation models are invoked to generate multiple text creative materials, image creative materials, and video creative materials, resulting in various types of creative materials, including: Based on the layout requirements and visual theme of the image placement area in the advertisement structure, the main elements, brand logo and background information in the original advertisement material are extracted; The visual theme, the main element, the brand logo, and the background information are input into the image generation model to generate multiple creative image materials for the image generation model. All image creative materials are tested for clarity, composition ratio, and visual consistency in order to select those that meet the layout requirements.

5. The method according to claim 1, characterized in that, Based on the advertised structure and the user-uploaded original advertising materials, text generation models, image generation models, and video generation models are invoked to generate multiple text creative materials, image creative materials, and video creative materials, resulting in various types of creative materials, including: Based on the video duration, aspect ratio, and rhythm parameters in the advertising structure, frame-level analysis and segmentation are performed on the original advertising material to obtain keyframes. The keyframes are input into the video generation model so that the video generation model generates multiple dynamic video contents that conform to the advertising theme in the advertising structure; The system performs tests on the continuity of the video footage, the smoothness of transitions, and the synchronization of audio and video for all dynamic video content, and outputs multiple creative video materials that meet advertising standards.

6. The method according to claim 1, characterized in that, After performing similarity detection and deduplication, the resulting set of deduplicated advertising creative solutions includes: The unprocessed ad creative scheme among the multiple ad creative schemes generated by cross-product combination is identified as the current ad creative scheme, and the following processing is performed on the current ad creative scheme: Calculate the cosine similarity of the feature vectors of the current advertising creative scheme and the first advertising creative scheme, wherein the first advertising creative scheme is any one of the multiple advertising creative schemes except the current advertising creative scheme; If the cosine similarity of the feature vectors is greater than the similarity threshold, the current advertising creative scheme or the first advertising creative scheme is discarded.

7. The method according to claim 1, characterized in that, After storing the collection of advertising creative solutions in the advertising creative database and displaying it on the user's user interface, the method further includes: Monitor the delivery data of each advertising creative in the aforementioned set of advertising creative schemes during the delivery process; The delivery data is compared with a preset performance threshold. If the delivery data of the second advertising creative scheme is lower than the preset performance threshold for a continuous preset period, the second advertising creative scheme is marked as an inefficient advertising creative scheme. The second advertising creative scheme is any one of the advertising creative schemes in the set of advertising creative schemes. The rules engine performs pause, archive, or replacement operations on the second ad creative.

8. An advertising creative generation device, characterized in that, include: The first generation module is used to generate an advertising structure that matches the advertising information input by the user and a preset advertising template. The second generation module is used to call the text generation model, image generation model and video generation model according to the advertising structure and the original advertising materials uploaded by the user, to generate multiple text creative materials, image creative materials and video creative materials respectively, so as to obtain multiple types of creative materials; The combination module is used to perform cross-product combination on the multiple types of creative materials to generate multiple sets of advertising creative schemes, and to perform similarity detection and deduplication to obtain a set of deduplicated advertising creative schemes. The storage module is used to store the collection of advertising creative schemes into the advertising material database and display them on the user's user interface.

9. A computer-readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to perform the method described in any one of claims 1 to 7.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method described in any one of claims 1 to 7 through the computer program.

Images