Creation prompting method and device, electronic equipment, storage medium and program product

Abstract

The invention provides a creation prompting method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of data processing, the method comprises the following steps: receiving a client type input by a first user; determining a style type corresponding to the customer type based on a preset style model, wherein the preset style model is used for analyzing the style type preferred by the customer type; determining cue words corresponding to the style types, and generating guidance suggestions based on the cue words; style parameters corresponding to the style type are obtained, an image sketch is generated based on the cue word and the style parameters, and the image sketch is used for representing the image condition preferred by the customer type; and outputting the guidance opinions and the image sketch, wherein the guidance opinions and the image sketch are used for performing creation prompt on the first user. The creation effect can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a creation prompt method, device, electronic device, storage medium and program product. Background Art

[0002] Digital collectibles are a form of non-fungible tokens (NFTs) that can protect digital artworks. In related technologies, after creating a digital artwork, creators upload it to a management platform, which then displays and trades the digital artwork. However, in these technologies, the creation of digital artworks primarily relies on the creator's own ideas. Different creators create digital artworks in different styles, and sometimes the style of the created digital artwork is less popular, resulting in poor creative results.

[0003] It can be seen that there is a problem in the related art that the style of the works is less popular, resulting in poor creative effects of the works. Summary of the Invention

[0004] The embodiments of the present invention provide a creation prompt method, device, electronic device and readable storage medium to solve the problem in related technologies that the style of works is less popular, resulting in poor creation effect of the works.

[0005] To solve the above problems, the present invention is achieved as follows:

[0006] In a first aspect, an embodiment of the present invention provides a creation prompt method, comprising:

[0007] receiving a customer type input by a first user;

[0008] Determining the style type corresponding to the customer type based on a preset style model, wherein the preset style model is used to analyze the style type preferred by the customer type;

[0009] Determining prompt words corresponding to the style type, and generating guidance based on the prompt words;

[0010] Obtaining style parameters corresponding to the style type, and generating an image sketch based on the prompt word and the style parameters, wherein the image sketch is used to represent the image situation preferred by the customer type;

[0011] The guiding opinions and the image sketch are output, and the guiding opinions and the image sketch are used to provide creation prompts to the first user.

[0012] In a second aspect, an embodiment of the present invention further provides a creation prompting device, comprising:

[0013] A receiving module, configured to receive a customer type input by a first user;

[0014] A first determining module, configured to determine a style type corresponding to the customer type based on a preset style model, wherein the preset style model is configured to analyze the style type preferred by the customer type;

[0015] A second determining module is used to determine the prompt word corresponding to the style type and generate guidance based on the prompt word;

[0016] an acquisition module, configured to acquire style parameters corresponding to the style type, and generate an image sketch based on the prompt word and the style parameters, wherein the image sketch is used to represent the image situation preferred by the customer type;

[0017] An output module is used to output the guiding opinions and the image sketch, wherein the guiding opinions and the image sketch are used to provide creation prompts to the first user.

[0018] In a third aspect, an embodiment of the present invention further provides an electronic device, including a transceiver and a processor.

[0019] The transceiver is configured to receive a customer type input by a first user;

[0020] The processor is configured to determine a style type corresponding to the customer type based on a preset style model, wherein the preset style model is configured to analyze the style type preferred by the customer type;

[0021] The processor is further configured to determine a prompt word corresponding to the style type and generate guidance based on the prompt word;

[0022] The processor is further configured to obtain style parameters corresponding to the style type, and generate an image sketch based on the prompt word and the style parameters, wherein the image sketch is used to represent the image situation preferred by the customer type;

[0023] The transceiver is further configured to output the guiding opinions and the image sketch, wherein the guiding opinions and the image sketch are used to provide creation prompts to the first user.

[0024] In a fourth aspect, an embodiment of the present invention provides an electronic device comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the creation prompt method described in the first aspect above.

[0025] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the creation prompt method described in the first aspect are implemented.

[0026] In a sixth aspect, the present invention further provides a computer program product comprising computer instructions, which, when executed by a processor, implement the steps of the creation prompt method as described in the first aspect above.

[0027] In an embodiment of the present invention, a customer type input by a first user is received; a style type corresponding to the customer type is determined based on a preset style model, the preset style model being used to analyze the style type preferred by the customer type; a prompt word corresponding to the style type is determined, and guidance opinions are generated based on the prompt word; style parameters corresponding to the style type are obtained, and an image sketch is generated based on the prompt word and the style parameters, the image sketch being used to represent the image situation preferred by the customer type; and the guidance opinions and the image sketch are output, the guidance opinions and the image sketch being used to provide creative prompts to the first user. In this way, by determining the style type by determining the customer type, generating prompt words based on the style type, and then generating guidance opinions based on the prompt words, and then generating an image sketch based on the style parameters corresponding to the style type and the prompt word, the image sketch and guidance opinions are style type-related opinions, and the style type is the style type preferred by the customer type. The image sketch and guidance opinions are used to provide creative prompts to the first user, so that the digital collection created by the first user is the work preferred by the customer type, thereby improving the creative effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0029] Figure 1 This is a flow chart of a creation prompt method provided by an embodiment of the present invention;

[0030] Figure 2 is a schematic structural diagram of a processing system provided by an embodiment of the present invention;

[0031] Figure 3 is a schematic diagram of expected information provided by an embodiment of the present invention;

[0032] Figure 4 is a schematic diagram of a creation prompt provided by an embodiment of the present invention;

[0033] Figure 5 This is a flowchart of creating a preset style model provided by an embodiment of the present invention;

[0034] Figure 6 This is a structural diagram of a creation prompting device provided by an embodiment of the present invention;

[0035] Figure 7 This is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0037] The embodiments of the present invention provide a creation prompt method, device, electronic device, storage medium and program product to solve the problem in related technologies that the style of works is less popular, resulting in poor creation effect of the works.

[0038] See Figure 1 , Figure 1 This is a flow chart of a creation prompt method provided by an embodiment of the present invention. Figure 1 As shown, the following steps are included:

[0039] Step 101: Receive a customer type input by a first user.

[0040] The first user is a user who wishes to create a digital collection, and the customer type is the type of customer expected to be the digital collection created by the first user. It should be noted that before the first user creates a digital collection, if creation prompts are desired using the method described in the embodiments of the present invention, the processing system must input the expected information, including the customer type, so that the processing system can analyze the customer type and determine the style preferred by the customer.

[0041] The processing system is a system for outputting creation prompts. In some embodiments, the processing system can also be used to display digital collections. The processing system can be used to display digital collections and provide creation prompts for digital collections.

[0042] Specifically, such as Figure 2As shown, the processing system consists of a presentation layer, an application layer, a computing layer, and a foundation layer. The presentation layer provides interactive services with users, including but not limited to user interfaces (UIs) such as desktop programs, web pages, H5 pages, applications (apps), and mini-programs. These allow users to upload digital collections, conduct transactions and operations, query operation records, and request design guidance. It coordinates applications to perform specific operations according to business logic and completes various business logic processing. The computing layer, which includes a central processing unit (CPU) and an AI-accelerated data processing card, calculates actual application data and submits it to other devices for processing. The foundation layer, including communication and storage modules, is responsible for internal and external data transmission and communication, data storage, database establishment, and basic data support services. The processing system communicates with an external blockchain cluster, which is used to implement internet-wide digital collection blockchains, copyright declarations, and authorization management.

[0043] The display layer deploys the upload module, design guidance module, and display and transaction module; the application layer and operation layer deploy the image analysis module, operation analysis module, and image generation module; and the basic layer deploys the storage module.

[0044] in,

[0045] The upload module is used to receive image files uploaded by the creative user, and submit the image files to the external blockchain cluster for chain authentication through this module; after successful authentication, a digital collection is created based on the image file.

[0046] The display and transaction module provides a public interface, showcasing registered digital collections to browsing users and offering various digital collection transaction services. Transaction types include, but are not limited to, sales and transfers, leases, authorized citations, and free exhibitions. After a user completes a transaction through this module, the module submits the transaction data to an internal storage module for recording. The relevant record fields include, but are not limited to, transaction time, amount, digital collection number, trader registration information, transaction type, and number of transactions.

[0047] The design guidance module provides a creative interface for users. Users enter a request for creative guidance, which the module then calls upon the operations analysis module to generate specific prompts and sends to the image generation module, which then creates a rough sketch. Finally, the prompts are converted into user-interpretable creative guidance, and a presentation containing both the guidance and the rough sketch is displayed to the user. This presentation helps users create digital artifacts more effectively and create more desirable digital artifacts.

[0048] The image analysis module uses image analysis technology to analyze and summarize digital collections registered on the blockchain, obtaining style parameters that characterize the digital collection's artistic style, including composition, color tone, painting subject, skeleton diagram, accessory information, background image, etc. The style parameters are then summarized and saved, with the skeleton diagram and background image saved in non-text form.

[0049] The operational analysis module analyzes the performance of all digital collections, such as the popularity of different styles, compositions, tones, subjects, accessories, and backgrounds among different target customers. This popularity includes information such as pageviews, citations, authorized rentals, comments, likes, and transactions. This popularity analysis generates style models tailored to different target customers, which in turn generate creative ideas.

[0050] The image generation module is used to process information such as prompt words, painting subjects, skeleton images, background images, etc. through a diffusion algorithm to generate an image sketch. The image sketch serves as a design prototype of the digital collection and can be provided to the creative user as a creation prompt.

[0051] The storage module stores background data, including but not limited to data information submitted and generated by the aforementioned modules, system operation logs, and other information.

[0052] Step 102: Determine the style type corresponding to the customer type based on a preset style model, where the preset style model is used to analyze the style type preferred by the customer type.

[0053] The above-mentioned style types refer to the types of works. Works of the same style type have similar style parameters, while works of different style types have significantly different style parameters. Customers within the same customer type tend to have similar preferences for works of the same style type, but differ significantly in preferences for works of different style types. By determining the style types that correspond to customer types, we can create works that are more preferred by the customers.

[0054] The preset style model and the pre-trained model are used to analyze the style types preferred by different customer types. The preset style model can analyze the correlation between different customer types and different style types, and then determine the style type preferred by each customer type.

[0055] In some optional embodiments, in addition to receiving the customer type input by the first user and then determining the style type corresponding to the customer type based on a preset style model, it is also possible to directly receive the style type input by the first user and then generate creation prompts including guidance and image sketches based on the input style type.

[0056] Further, if Figure 3As shown, the expected information input by the first user into the processing system may also include at least one of the basic information of the creating user, the style he is good at, the type of client, the style type, the expected theme of the work and the design purpose, so as to determine the style type through the expected information and then generate a creation prompt.

[0057] Step 103: Determine prompt words corresponding to the style type, and generate guidance based on the prompt words.

[0058] The above-mentioned prompt words are used to describe the parameters of the style type, such as the composition, color tone, and painting subject corresponding to the style type. The above-mentioned guidance opinions are opinions generated based on the prompt words, and can be obtained by processing the prompt words through a natural language generation (NLG) engine to achieve the conversion of the prompt words into text data that is easy for the first user to understand.

[0059] Step 104: Obtain style parameters corresponding to the style type, and generate an image sketch based on the prompt word and the style parameters. The image sketch is used to represent the image situation preferred by the customer type.

[0060] The above-mentioned style parameters are used to characterize the image conditions of the works corresponding to the style type, such as composition, color tone, painting subject, etc. An image sketch is generated by using the style parameters and prompt words, so that the image sketch can stylistically belong to the works corresponding to the style type, and thus can characterize the image conditions preferred by the customer.

[0061] Step 105: Output the guidance and the image sketch, where the guidance and the image sketch are used to provide creation prompts to the first user.

[0062] In some embodiments, prompt information including guidance and image sketches may be output, such as Figure 4 As shown, the first user can create a digital collection according to the guidance and image sketch.

[0063] In an embodiment of the present invention, a customer type input by a first user is received; a style type corresponding to the customer type is determined based on a preset style model, the preset style model being used to analyze the style type preferred by the customer type; a prompt word corresponding to the style type is determined, and guidance opinions are generated based on the prompt word; style parameters corresponding to the style type are obtained, and an image sketch is generated based on the prompt word and the style parameters, the image sketch being used to represent the image situation preferred by the customer type; and the guidance opinions and the image sketch are output, the guidance opinions and the image sketch being used to provide creative prompts to the first user. In this way, by determining the style type by determining the customer type, generating prompt words based on the style type, and then generating guidance opinions based on the prompt words, and then generating an image sketch based on the style parameters corresponding to the style type and the prompt word, the image sketch and guidance opinions are style type-related opinions, and the style type is the style type preferred by the customer type. The image sketch and guidance opinions are used to provide creative prompts to the first user, so that the digital collection created by the first user is the work preferred by the customer type, thereby improving the creative effect.

[0064] In one embodiment, the preset style model is obtained by:

[0065] Acquiring operation data, the operation data including popularity information of each first work among a plurality of first works, style parameters corresponding to each first work, and customer information corresponding to each first work;

[0066] Clustering the style parameters corresponding to the plurality of first works to obtain a plurality of style types, each style type corresponding to at least one first work;

[0067] Clustering the customer information corresponding to the plurality of first works to obtain a plurality of customer types, each customer type corresponding to at least one first work;

[0068] Associating the plurality of customer types with the plurality of style types based on the popularity information to obtain an association relationship between each customer type and each style type;

[0069] The preset style model is constructed based on the association relationship between each customer type and each style type.

[0070] The aforementioned operational data is user-related data collected during the display of multiple first works, such as popularity information and transaction information. In this embodiment, the operational data includes popularity information for each of the multiple first works, style parameters corresponding to each first work, and customer information corresponding to each first work. The popularity information, style parameters, and customer information can be used to determine the association between each customer type and each style type.

[0071] The popularity information may include at least one of browsing traffic, citations, authorized rentals, comments, likes, and transactions. Higher browsing traffic, citations, authorized rentals, comments, likes, and transactions indicate a higher popularity of the work. In this embodiment of the present invention, popularity information is used as the independent variable, and client type and genre type are used as dependent variables, thereby enabling correlation between different client types and different genre types.

[0072] In some embodiments, a customer type can be associated with multiple style types, and the associated multiple style types are sorted by popularity information, so that when the style type corresponding to the customer type is subsequently output through a preset style model, multiple style types can be output based on the sorting order, and then creation prompts can be generated based on each style; or, a style type is selected from multiple style types, and then a creation prompt for the style type is generated.

[0073] The customer information includes at least one of the customer's age, gender, and registration information. Customers can be categorized based on the customer information. Specifically, the customer information corresponding to the multiple first works is clustered to obtain multiple customer types. The customer information within each customer type is similar, while the customer information of different customer types varies significantly. In this way, different customers can be divided through clustering.

[0074] The style parameters include information such as style, composition, color tone, subject, accessories, and background image. The style parameters can be used to categorize the first works into different style types. Specifically, the style parameters corresponding to the multiple first works are clustered to obtain multiple style types, such that the style parameters of the first works within each style type are similar, while the style parameters of the first works within different style types vary significantly. In this way, the different first works can be categorized by clustering.

[0075] In an embodiment of the present invention, operational data is obtained, the operational data including popularity information of each first work among a plurality of first works, style parameters corresponding to each first work, and customer information corresponding to each first work; the style parameters corresponding to the plurality of first works are clustered to obtain a plurality of style types, each style type corresponding to at least one first work; the customer information corresponding to the plurality of first works is clustered to obtain a plurality of customer types, each customer type corresponding to at least one first work; the plurality of customer types are associated with the plurality of style types based on the popularity information to obtain an association relationship between each customer type and each style type; and the preset style model is constructed based on the association relationship between each customer type and each style type. In this way, a plurality of style types and a plurality of customer types are obtained by clustering, and then the plurality of style types and the plurality of customer types are associated based on the popularity length information to obtain an association relationship, so that a preset style model can be constructed through the association relationship, and the preset style model can subsequently determine the style type preferred by the customer type through the association relationship.

[0076] In one embodiment, obtaining the operational data includes:

[0077] receiving the plurality of first works;

[0078] Performing visual analysis on each of the first works to obtain style parameters corresponding to each of the first works;

[0079] displaying the plurality of first works;

[0080] Obtain popularity information of each first work and customer information corresponding to each first work, wherein the popularity information is information obtained by evaluating the multiple first works by a first customer group after displaying the multiple first works, and the customer information is information of each customer in the first customer group.

[0081] The first work is uploaded by the user to the processing system. After the user uploads the first work, a visual analysis can be performed on the first work to obtain the first work's style parameters. At the same time, the processing system displays the first work to collect the corresponding popularity information and customer information.

[0082] Specifically, such as Figure 5 As shown, after the creative user uploads the digital collection (i.e., the first work), the digital collection is registered on the chain and the style parameters of the digital collection are analyzed; after obtaining the style parameters, the digital collection is displayed, and customer information and popularity information are collected, thereby creating a preset style model.

[0083] In one embodiment, determining the prompt word corresponding to the style type includes:

[0084] Determining a prompt word corresponding to the style type based on a prompt word mapping table, wherein the prompt word mapping table includes a plurality of style types and a prompt word corresponding to each style type;

[0085] The prompt word mapping table is obtained in the following manner:

[0086] Obtaining a first prompt word corresponding to each first work among the plurality of first works, where the first prompt word is used to describe a style parameter of each first work;

[0087] The multiple first works are clustered based on the first prompt word to obtain the multiple style types and the second prompt word corresponding to each style type in the multiple style types, the second prompt word is used to describe the style parameters of each style type, and the prompt word corresponding to the style type is the second prompt word corresponding to the style type.

[0088] The first prompt word is a prompt word that describes the style parameters of the first work. The first prompt word is a prompt word for a single work. It should be noted that the multiple style types are obtained by clustering the style parameters, and the first prompt word is used to describe the style parameters. Clustering the multiple first works based on the first prompt word can also yield the multiple style types.

[0089] The second prompt words are obtained after clustering the first prompt words of the plurality of first works, so that the second prompt words can describe the style parameters of each style type.

[0090] In some embodiments, the first prompt word is generated after visually analyzing each first work to obtain style parameters corresponding to each first work. Specifically, after obtaining the style parameters, a prompt word corresponding to the style parameters is output using a preset rule or a preset model. The preset model is a model trained to extract features of the style parameters, and the prompt word may be obtained by converting the features.

[0091] In one embodiment, the style parameters corresponding to the style type include at least one of composition information, color tone information, painting subject information, skeleton diagram information, accessory information, and background diagram information;

[0092] The generating of the image sketch based on the prompt word and the style parameter includes:

[0093] The initial image is corrected based on at least one of the composition information, the color tone information, the painting subject information, the skeleton diagram information, the accessories information, and the background image information through a diffusion algorithm to obtain the image sketch, where the initial image is a pre-created image based on the prompt word.

[0094] The initial image is pre-created based on the prompt word and is used to represent the image condition associated with the prompt word. In this embodiment of the present invention, after determining the style type, style parameters corresponding to the style type are determined, including at least one of composition information, color tone information, subject information, skeleton information, accessory information, and background image information. A diffusion algorithm is then used to modify the initial image based on the style parameters to generate an image sketch that represents the image condition preferred by the customer.

[0095] The initial image is corrected based on at least one of the composition information, the color tone information, the painting subject information, the skeleton diagram information, the accessories information, and the background image information through a diffusion algorithm. Specifically, Gaussian noise is gradually added to the initial image based on style parameters during the diffusion process through a diffusion algorithm model, and then the noise added in the forward process is predicted and removed through the trained model in the reverse diffusion process, thereby finally generating a new image sketch.

[0096] In one embodiment, at least one of the composition information, the color tone information, the painting subject information, the skeleton image information, the accessory information, and the background image information is obtained by:

[0097] Obtaining at least one of initial composition information, initial color tone information, initial painting subject information, initial skeleton image information, initial accessory information, and initial background image information for each of a plurality of second works, wherein the plurality of second works are works corresponding to the style type;

[0098] Clustering the initial composition information of each second work to obtain the composition information; and / or clustering the initial color tone information of each second work to obtain the composition information; and / or clustering the initial painting subject information of each second work to obtain the painting subject information; and / or clustering the initial skeleton image information of each second work to obtain the skeleton image information; and / or clustering the initial accessory information of each second work to obtain the accessory information; and / or clustering the initial background image information of each second work to obtain the background image information.

[0099] In an embodiment of the present invention, by obtaining the initial composition information, initial color tone information, initial painting subject information, initial skeleton diagram information, initial accessories information, and initial background image information of each second work in a plurality of second works, and then clustering to obtain the composition information, the color tone information, the painting subject information, the skeleton diagram information, the accessories information, and the background image information, it is possible to obtain the style parameters of the style type by clustering the style parameters of each second work.

[0100] In one embodiment, obtaining at least one of initial composition information, initial color tone information, initial painting subject information, initial skeleton image information, initial accessory information, and initial background image information of each second work in the plurality of second works includes:

[0101] performing object extraction on the second work based on a preset neural network model to obtain object information corresponding to the object and the initial background image information, wherein the second work is one of the plurality of second works, and the preset neural network model is a neural network model trained to extract objects from images;

[0102] determining the initial painting subject information and the initial composition information based on the position and size ratio of the object in the second work;

[0103] The object is identified to obtain the initial accessory information, the initial skeleton image information and the initial color tone information.

[0104] The above-mentioned object extraction of the second work based on the preset neural network model to obtain the object information corresponding to the object and the initial background image information can be specifically performed through the Faster R-CNN algorithm model or the Mask R-CNN algorithm model. In some embodiments, the second work is pre-fetched with the learnable region selection (Region Proposal Network, RPN) network in the Faster R-CNN algorithm model or the Mask R-CNN algorithm model to select the candidate region (Region Proposal), and then the Region Proposal coordinates are used to perform the region of interest (Region of Interest) on the last feature map of the convolutional layer of the Convolutional Neural Networks (CNN). The feature map of the region of interest (RoI) is extracted to obtain RoI features; finally, all RoI features are input into the classification and regression modules to identify the objects in the image and obtain object information and initial background image information.

[0105] Furthermore, after obtaining the object information, the extracted objects and background images are segmented and numbered.

[0106] The above-mentioned determination of the initial painting subject information and the initial composition information based on the position and size ratio of the objects in the second work is specifically to confirm the initial composition information of the position and size of each object in the picture, so as to determine which objects are the painting subjects.

[0107] Furthermore, by performing image analysis on the object to extract sub-objects, initial skeleton image information is obtained; by confirming the clothing and accessories sub-objects in the sub-objects, initial accessories information is obtained; and then using computer vision library functions, the color histogram information of the object is calculated, and the color of the relevant objects is confirmed to obtain initial hue information.

[0108] See Figure 6 , Figure 6 This is a structural diagram of a creation prompt device provided by an embodiment of the present invention. Figure 6 As shown, the creation prompting device 600 includes:

[0109] Receiving module 601, configured to receive a customer type input by a first user;

[0110] A first determining module 602 is configured to determine a style type corresponding to the customer type based on a preset style model, wherein the preset style model is configured to analyze the style type preferred by the customer type;

[0111] The second determining module 603 is used to determine the prompt word corresponding to the style type and generate guidance based on the prompt word;

[0112] An acquisition module 604 is configured to acquire style parameters corresponding to the style type, and generate an image sketch based on the prompt word and the style parameters, wherein the image sketch is used to represent the image situation preferred by the customer type;

[0113] The output module 605 is used to output the guiding opinions and the image sketch, where the guiding opinions and the image sketch are used to provide creation prompts to the first user.

[0114] In one embodiment, the preset style model is obtained by:

[0115] Acquiring operation data, the operation data including popularity information of each first work among a plurality of first works, style parameters corresponding to each first work, and customer information corresponding to each first work;

[0116] Clustering the style parameters corresponding to the plurality of first works to obtain a plurality of style types, each style type corresponding to at least one first work;

[0117] Clustering the customer information corresponding to the plurality of first works to obtain a plurality of customer types, each customer type corresponding to at least one first work;

[0118] Associating the plurality of customer types with the plurality of style types based on the popularity information to obtain an association relationship between each customer type and each style type;

[0119] The preset style model is constructed based on the association relationship between each customer type and each style type.

[0120] In one embodiment, obtaining the operational data includes:

[0121] receiving the plurality of first works;

[0122] Performing visual analysis on each of the first works to obtain style parameters corresponding to each of the first works;

[0123] displaying the plurality of first works;

[0124] Obtain popularity information of each first work and customer information corresponding to each first work, wherein the popularity information is information obtained by evaluating the multiple first works by a first customer group after displaying the multiple first works, and the customer information is information of each customer in the first customer group.

[0125] In one embodiment, the second determining module 603 includes:

[0126] a first determining unit, configured to determine a prompt word corresponding to the style type based on a prompt word mapping table, wherein the prompt word mapping table includes a plurality of style types and a prompt word corresponding to each style type;

[0127] The prompt word mapping table is obtained in the following manner:

[0128] Obtaining a first prompt word corresponding to each first work among the plurality of first works, where the first prompt word is used to describe a style parameter of each first work;

[0129] The multiple first works are clustered based on the first prompt word to obtain the multiple style types and the second prompt word corresponding to each style type in the multiple style types, the second prompt word is used to describe the style parameters of each style type, and the prompt word corresponding to the style type is the second prompt word corresponding to the style type.

[0130] In one embodiment, the style parameters corresponding to the style type include at least one of composition information, color tone information, painting subject information, skeleton diagram information, accessory information, and background diagram information;

[0131] The acquisition module 604 includes:

[0132] A generating unit is configured to correct an initial image based on at least one of the composition information, the hue information, the painting subject information, the skeleton diagram information, the accessory information, and the background image information using a diffusion algorithm to obtain the image sketch, wherein the initial image is a pre-created image based on the prompt word.

[0133] In one embodiment, at least one of the composition information, the color tone information, the painting subject information, the skeleton image information, the accessory information, and the background image information is obtained by:

[0134] Obtaining at least one of initial composition information, initial color tone information, initial painting subject information, initial skeleton image information, initial accessory information, and initial background image information for each of a plurality of second works, wherein the plurality of second works are works corresponding to the style type;

[0135] Clustering the initial composition information of each second work to obtain the composition information; and / or clustering the initial color tone information of each second work to obtain the composition information; and / or clustering the initial painting subject information of each second work to obtain the painting subject information; and / or clustering the initial skeleton image information of each second work to obtain the skeleton image information; and / or clustering the initial accessory information of each second work to obtain the accessory information; and / or clustering the initial background image information of each second work to obtain the background image information.

[0136] In one embodiment, obtaining at least one of initial composition information, initial color tone information, initial painting subject information, initial skeleton image information, initial accessory information, and initial background image information of each second work in the plurality of second works includes:

[0137] performing object extraction on the second work based on a preset neural network model to obtain object information corresponding to the object and the initial background image information, wherein the second work is one of the plurality of second works, and the preset neural network model is a neural network model trained to extract objects from images;

[0138] determining the initial painting subject information and the initial composition information based on the position and size ratio of the object in the second work;

[0139] The object is identified to obtain the initial accessory information, the initial skeleton image information and the initial color tone information.

[0140] The creation prompt device provided by the embodiment of the present invention is capable of implementing each process of each embodiment of the above-mentioned creation prompt method. The technical features correspond one to one and can achieve the same technical effect. To avoid repetition, they will not be described here.

[0141] It should be noted that the creation prompt device in the embodiment of the present invention can be a device, or a component, integrated circuit, or chip in an electronic device.

[0142] An embodiment of the present invention also provides an electronic device, comprising: a processor, a memory, and a program stored in the memory and runnable on the processor. When the program is executed by the processor, the various processes of the above-mentioned creation prompt method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0143] For details, see Figure 7 As shown, an embodiment of the present invention further provides an electronic device, including a bus 701 , a transceiver 702 , an antenna 703 , a bus interface 704 , a processor 705 and a memory 706 .

[0144] The transceiver 702 is configured to receive a customer type input by a first user;

[0145] The processor 705 is configured to determine a style type corresponding to the customer type based on a preset style model, wherein the preset style model is configured to analyze the style type preferred by the customer type;

[0146] The processor 705 is further configured to determine a prompt word corresponding to the style type and generate guidance based on the prompt word;

[0147] The processor 705 is further configured to obtain style parameters corresponding to the style type, and generate an image sketch based on the prompt word and the style parameters, wherein the image sketch is used to represent the image situation of the customer type preference;

[0148] The transceiver 702 is further configured to output the guiding opinions and the image sketch, where the guiding opinions and the image sketch are used to provide creation prompts to the first user.

[0149] In one embodiment, the preset style model is obtained by:

[0150] Acquiring operation data, the operation data including popularity information of each first work among a plurality of first works, style parameters corresponding to each first work, and customer information corresponding to each first work;

[0151] Clustering the style parameters corresponding to the plurality of first works to obtain a plurality of style types, each style type corresponding to at least one first work;

[0152] Clustering the customer information corresponding to the plurality of first works to obtain a plurality of customer types, each customer type corresponding to at least one first work;

[0153] Associating the plurality of customer types with the plurality of style types based on the popularity information to obtain an association relationship between each customer type and each style type;

[0154] The preset style model is constructed based on the association relationship between each customer type and each style type.

[0155] In one embodiment, obtaining the operational data includes:

[0156] receiving the plurality of first works;

[0157] Performing visual analysis on each of the first works to obtain style parameters corresponding to each of the first works;

[0158] displaying the plurality of first works;

[0159] Obtain popularity information of each first work and customer information corresponding to each first work, wherein the popularity information is information obtained by evaluating the multiple first works by a first customer group after displaying the multiple first works, and the customer information is information of each customer in the first customer group.

[0160] In one embodiment, determining the prompt word corresponding to the style type includes:

[0161] Determining a prompt word corresponding to the style type based on a prompt word mapping table, wherein the prompt word mapping table includes a plurality of style types and a prompt word corresponding to each style type;

[0162] The prompt word mapping table is obtained in the following manner:

[0163] Obtaining a first prompt word corresponding to each first work among the plurality of first works, where the first prompt word is used to describe a style parameter of each first work;

[0164] The multiple first works are clustered based on the first prompt word to obtain the multiple style types and the second prompt word corresponding to each style type in the multiple style types, the second prompt word is used to describe the style parameters of each style type, and the prompt word corresponding to the style type is the second prompt word corresponding to the style type.

[0165] In one embodiment, the style parameters corresponding to the style type include at least one of composition information, color tone information, painting subject information, skeleton diagram information, accessory information, and background diagram information;

[0166] The generating of the image sketch based on the prompt word and the style parameter includes:

[0167] The initial image is corrected based on at least one of the composition information, the color tone information, the painting subject information, the skeleton diagram information, the accessories information, and the background image information through a diffusion algorithm to obtain the image sketch, where the initial image is a pre-created image based on the prompt word.

[0168] In one embodiment, at least one of the composition information, the color tone information, the painting subject information, the skeleton image information, the accessory information, and the background image information is obtained by:

[0169] Obtaining at least one of initial composition information, initial color tone information, initial painting subject information, initial skeleton image information, initial accessory information, and initial background image information for each of a plurality of second works, wherein the plurality of second works are works corresponding to the style type;

[0170] Clustering the initial composition information of each second work to obtain the composition information; and / or clustering the initial color tone information of each second work to obtain the composition information; and / or clustering the initial painting subject information of each second work to obtain the painting subject information; and / or clustering the initial skeleton image information of each second work to obtain the skeleton image information; and / or clustering the initial accessory information of each second work to obtain the accessory information; and / or clustering the initial background image information of each second work to obtain the background image information.

[0171] In one embodiment, obtaining at least one of initial composition information, initial color tone information, initial painting subject information, initial skeleton image information, initial accessory information, and initial background image information of each second work in the plurality of second works includes:

[0172] performing object extraction on the second work based on a preset neural network model to obtain object information corresponding to the object and the initial background image information, wherein the second work is one of the plurality of second works, and the preset neural network model is a neural network model trained to extract objects from images;

[0173] determining the initial painting subject information and the initial composition information based on the position and size ratio of the object in the second work;

[0174] The object is identified to obtain the initial accessory information, the initial skeleton image information and the initial color tone information.

[0175] exist Figure 7 In the embodiment, the bus architecture (represented by bus 701) is shown. Bus 701 may include any number of interconnected buses and bridges. Bus 701 links together various circuits including one or more processors represented by processor 705 and memory represented by memory 706. Bus 701 may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not described further herein. Bus interface 704 provides an interface between bus 701 and transceiver 702. Transceiver 702 may be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. Data processed by processor 705 is transmitted on a wireless medium via antenna 703. Furthermore, antenna 703 receives data and transmits the data to processor 705.

[0176] The processor 705 is responsible for managing the bus 701 and general processing, and may also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. The memory 706 may be used to store data used by the processor 705 when performing operations.

[0177] Optionally, the processor 705 may be a CPU, an ASIC, an FPGA, or a CPLD.

[0178] The embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the various processes of the above-mentioned creation prompt method embodiment are implemented and can achieve the same technical effect. To avoid repetition, the details are not described here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0179] The present invention also provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the corresponding creation prompt method implementation examples can achieve the same technical effects, so they will not be described here to avoid repetition.

[0180] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0181] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0182] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are protected by the present invention.

Claims

1. A creation prompt method, characterized in that: include: receiving a customer type input by a first user; Determining the style type corresponding to the customer type based on a preset style model, wherein the preset style model is used to analyze the style type preferred by the customer type; Determining prompt words corresponding to the style type, and generating guidance based on the prompt words; Obtaining style parameters corresponding to the style type, and generating an image sketch based on the prompt word and the style parameters, wherein the image sketch is used to represent the image situation preferred by the customer type; The guiding opinions and the image sketch are output, and the guiding opinions and the image sketch are used to provide creation prompts to the first user.

2. The method according to claim 1, wherein The preset style model is obtained in the following way: Acquiring operation data, the operation data including popularity information of each first work among a plurality of first works, style parameters corresponding to each first work, and customer information corresponding to each first work; Clustering the style parameters corresponding to the plurality of first works to obtain a plurality of style types, each style type corresponding to at least one first work; Clustering the customer information corresponding to the plurality of first works to obtain a plurality of customer types, each customer type corresponding to at least one first work; Associating the plurality of customer types with the plurality of style types based on the popularity information to obtain an association relationship between each customer type and each style type; The preset style model is constructed based on the association relationship between each customer type and each style type.

3. The method according to claim 2, wherein The obtaining of operational data includes: receiving the plurality of first works; Performing visual analysis on each of the first works to obtain style parameters corresponding to each of the first works; displaying the plurality of first works; Obtain popularity information of each first work and customer information corresponding to each first work, wherein the popularity information is information obtained by evaluating the multiple first works by a first customer group after displaying the multiple first works, and the customer information is information of each customer in the first customer group.

4. The method according to claim 1, wherein The step of determining the prompt word corresponding to the style type includes: Determining a prompt word corresponding to the style type based on a prompt word mapping table, wherein the prompt word mapping table includes a plurality of style types and a prompt word corresponding to each style type; The prompt word mapping table is obtained in the following manner: Obtaining a first prompt word corresponding to each first work among the plurality of first works, where the first prompt word is used to describe a style parameter of each first work; The multiple first works are clustered based on the first prompt word to obtain the multiple style types and the second prompt word corresponding to each style type in the multiple style types, the second prompt word is used to describe the style parameters of each style type, and the prompt word corresponding to the style type is the second prompt word corresponding to the style type.

5. The method according to any one of claims 1 to 4, characterized in that The style parameters corresponding to the style type include at least one of composition information, color tone information, painting subject information, skeleton diagram information, accessories information, and background diagram information; The generating of the image sketch based on the prompt word and the style parameter includes: The initial image is corrected based on at least one of the composition information, the color tone information, the painting subject information, the skeleton diagram information, the accessories information, and the background image information through a diffusion algorithm to obtain the image sketch, where the initial image is a pre-created image based on the prompt word.

6. The method according to claim 5, wherein At least one of the composition information, the color tone information, the painting subject information, the skeleton image information, the accessories information, and the background image information is obtained in the following manner: Obtaining at least one of initial composition information, initial color tone information, initial painting subject information, initial skeleton image information, initial accessory information, and initial background image information for each of a plurality of second works, wherein the plurality of second works are works corresponding to the style type; Clustering the initial composition information of each second work to obtain the composition information; and / or, clustering the initial color tone information of each second work to obtain the composition information; and / or, clustering the initial painting subject information of each second work to obtain the painting subject information; and / or, clustering the initial skeleton graph information of each second work to obtain the skeleton graph information; And / or, clustering the initial accessory information of each second work to obtain the accessory information; and / or, clustering the initial background image information of each second work to obtain the background image information.

7. The method according to claim 6, wherein The obtaining of at least one of initial composition information, initial color tone information, initial painting subject information, initial skeleton image information, initial accessory information, and initial background image information of each second work in the plurality of second works includes: performing object extraction on the second work based on a preset neural network model to obtain object information corresponding to the object and the initial background image information, wherein the second work is one of the plurality of second works, and the preset neural network model is a neural network model trained to extract objects from images; determining the initial painting subject information and the initial composition information based on the position and size ratio of the object in the second work; The object is identified to obtain the initial accessory information, the initial skeleton image information and the initial color tone information.

8. A creation prompting device, characterized in that: include: A receiving module, configured to receive a customer type input by a first user; A first determining module is configured to determine a style type corresponding to the customer type based on a preset style model, wherein the preset style model is configured to analyze the style type preferred by the customer type; A second determining module is used to determine the prompt word corresponding to the style type and generate guidance based on the prompt word; an acquisition module, configured to acquire style parameters corresponding to the style type, and generate an image sketch based on the prompt word and the style parameters, wherein the image sketch is used to represent the image situation preferred by the customer type; An output module is used to output the guiding opinions and the image sketch, wherein the guiding opinions and the image sketch are used to provide creation prompts to the first user.

9. An electronic device, characterized in that: Including transceiver and processor, The transceiver is configured to receive a customer type input by a first user; The processor is configured to determine a style type corresponding to the customer type based on a preset style model, wherein the preset style model is configured to analyze the style type preferred by the customer type; The processor is further configured to determine a prompt word corresponding to the style type and generate guidance based on the prompt word; The processor is further configured to obtain style parameters corresponding to the style type, and generate an image sketch based on the prompt word and the style parameters, wherein the image sketch is used to represent the image situation preferred by the customer type; The transceiver is further configured to output the guiding opinions and the image sketch, wherein the guiding opinions and the image sketch are used to provide creation prompts to the first user.

10. An electronic device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the creation prompt method according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the creation prompt method according to any one of claims 1 to 7.

12. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the creation prompt method according to any one of claims 1 to 7.

Images