Picture generation method, content generation method, and computing device

Abstract

Provided in the embodiments of the present application are a picture generation method, a content generation method and a computing device. The picture generation method comprises: determining a target promotion object provided by a target user; providing on a user interface selection prompt information for at least one processing mode; in response to a mode selection operation of the target user, determining a selected first processing mode; providing on the user interface selection prompt information for at least one style; in response to a style selection operation of the target user, determining a selected first style; determining at least one promotion picture conforming to the first style and generated on the basis of object information of the target promotion object and according to the first processing mode; and providing on the user interface picture prompt information of the at least one promotion picture. The technical solution provided by the embodiment of the present application improves the content generation efficiency and reduces the content generation cost.

Description

Image generation method, content generation method and computing device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on September 21, 2023, with application number 202311227659.6 and application name “Image Generation Method, Content Generation Method and Computing Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of the present application relate to the field of electronic technology, and in particular to an image generation method, a content generation method, and a computing device. Background Art

[0003] In some online systems that provide objects for consumers to interact with, these objects are often provided by users, who are the object providers. To help increase object conversion rates, object promotion has become a solution.

[0004] In order to conduct targeted promotion, effective and accurate promotional content is needed to attract consumers. In traditional methods, promotional content is generated by users, which is inefficient and costly.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide an image generation method, a content generation method, and a computing device to solve the technical problems of low efficiency and high cost of promotional content generation in the prior art.

[0007] In a first aspect, an embodiment of the present application provides a method for generating an image, comprising:

[0008] Determine the target promotion objects provided by target users;

[0009] Providing a selection prompt for at least one processing method in the user interface;

[0010] In response to a method selection operation of the target user, determining a selected first processing method;

[0011] Providing at least one style of selection prompt information in the user interface;

[0012] In response to a style selection operation by the target user, determining a selected first style;

[0013] Determining at least one promotional image that conforms to the first style and is generated according to the first processing method based on the object information of the target promotion object;

[0014] Provide image prompt information of the at least one promotional image on the user interface.

[0015] Optionally, the object information includes a target picture, and the method further includes: screening at least one candidate picture that meets the picture requirements corresponding to the first processing method from at least one object picture corresponding to the target promotion object; displaying picture prompt information of the at least one candidate picture on the user interface; and in response to the target user's picture selection operation for any candidate picture, using the selected candidate picture as the target picture.

[0016] Optionally, determining the target promotion object provided by the target user includes:

[0017] The user interface provides object prompt information of at least one promotion object corresponding to the target user; and in response to the object selection operation of the target user, determines the selected target promotion object.

[0018] Optionally, it also includes:

[0019] In response to an adjustment operation on the at least one promotion object, an object list is displayed in the user interface; and according to at least one object selected by the target user from the object list, the at least one promotion object is updated.

[0020] Optionally, it also includes:

[0021] In response to the image selection operation triggered by the target user for any promotional image, the selected promotional image is saved in the delivery list of the target object; the delivery list corresponding to at least one promotional object is displayed on the user interface; in response to the image selection operation for the delivery list, at least one selected target promotional image is determined; in combination with at least one target promotional image corresponding to the at least one promotional object, a promotion request is generated; the promotion request is used to instruct the execution of an object promotion operation in combination with at least one target promotional image corresponding to the at least one promotional object.

[0022] Optionally, providing at least one style of selection prompt information in the user interface includes:

[0023] Providing selection prompt information of at least one style corresponding to the first processing method on the user interface.

[0024] Optionally, it also includes:

[0025] According to the image requirements corresponding to different processing methods, at least one processing method that matches at least one object image of the target promotion object is determined; wherein the at least one object image is provided by the target user.

[0026] Optionally, providing object prompt information of at least one promotion object corresponding to the target user on the user interface includes:

[0027] Providing promotion invitation information on a user interface; the promotion invitation information is sent to target users who meet promotion conditions; in response to a confirmation operation on the promotion invitation information, providing object prompt information of at least one promotion object corresponding to the target user on the user interface.

[0028] Optionally, it also includes:

[0029] At least one promotion object that meets the promotion requirements is determined from the multiple objects corresponding to the target user.

[0030] Optionally, determining at least one promotion object that meets promotion requirements from the multiple objects corresponding to the target user includes:

[0031] Based on the interactive data generated by the objects published by the online system, at least one hot object that meets the first hot condition is screened; the interactive data includes object exposure information, object click information, object sales information, and / or object conversion information; at least one hot object feature of the at least one hot object is counted; according to the degree of matching between multiple objects corresponding to the target user and the at least one hot object feature, at least one promotion object whose matching degree meets the matching requirements is selected.

[0032] Optionally, it also includes:

[0033] Displaying an invalid mark on the promotional images that are in an invalid state in the delivery list;

[0034] Alternatively, in response to the image selection operation for the delivery list, if the promotional item selected by the target user is in an invalid state, a selection failure prompt message is displayed.

[0035] Optionally, it also includes:

[0036] Displaying configuration prompt information corresponding to the at least one promotion object on a user interface; determining generated promotion configuration information in response to a configuration operation of the target user;

[0037] The generating of the promotion request by combining at least one target promotion image corresponding to the at least one promotion object includes:

[0038] A promotion request is generated by combining at least one target promotion picture corresponding to the at least one promotion object and the promotion configuration information.

[0039] Optionally, it also includes:

[0040] Select a first hot picture that meets a second hot condition from at least one object picture corresponding to a similar object of the target promotion object; determine a second processing method and a second style corresponding to the first hot picture; generate a promotional picture that conforms to the second style based on the object information of the target promotion object according to the second processing method; and save the promotional picture to a delivery list corresponding to the promotion object.

[0041] Optionally, the determining of at least one promotional image conforming to the first style generated according to the first processing method based on the object information of the target promotion object includes:

[0042] The image generation model corresponding to the first processing method is called to generate at least one promotional image that conforms to the first style based on the object information of the target object.

[0043] Optionally, it also includes:

[0044] Providing effect viewing prompt information in the user interface; in response to the target user's effect viewing operation for any promotion object or any promotion task, displaying corresponding promotion effect information in the user interface.

[0045] In a second aspect, an embodiment of the present application provides a content generation method, including:

[0046] Determine the target promotion objects provided by target users;

[0047] Providing a selection prompt for at least one processing method in the user interface;

[0048] In response to a method selection operation of the target user, determining a selected first processing method;

[0049] Providing at least one style of selection prompt information in the user interface;

[0050] In response to a style selection operation by the target user, determining a selected first style;

[0051] determining at least one promotional content that conforms to the first style and is generated according to the first processing method based on the object information of the target object;

[0052] Providing content prompt information of the at least one promotional content on the user interface.

[0053] In a third aspect, an embodiment of the present application provides a method for generating an image, including:

[0054] Determine the target audience provided by the target users;

[0055] Sending a selection prompt message of at least one processing method to the user terminal;

[0056] Determining a first processing method selected by the target user;

[0057] Sending at least one style selection prompt information to the user terminal;

[0058] determining a first style selected by the target user;

[0059] According to the first processing manner, at least one promotional image that conforms to the first style is generated based on the object information of the target object.

[0060] Optionally, it also includes:

[0061] Sending picture prompt information of the at least one promotional picture to the user terminal; saving the promotional picture to the delivery list corresponding to the target object according to the promotional picture selected by the target user; sending the delivery list corresponding to at least one promotional object corresponding to the target user to the user terminal; determining at least one target promotional picture selected by the target user for the at least one promotional object; and performing an object promotion operation in combination with the at least one target promotional picture corresponding to the at least one promotional object.

[0062] Optionally, it also includes:

[0063] Screening at least one popular object that meets a first popularity condition based on interactive data generated by objects published by an online system; the interactive data includes object exposure information, object click information, object sales information, and / or object conversion information; calculating at least one popular object feature of the at least one popular object; selecting at least one promotion object whose matching degree meets the matching requirement based on the matching degree between multiple objects corresponding to the target user and the at least one popular object feature; and sending object prompt information of the at least one promotion object to the user terminal;

[0064] Determining the target object provided by the target user includes:

[0065] The target object selected by the target user is determined.

[0066] Optionally, it also includes:

[0067] From the object images corresponding to similar objects of the target promotion object, select a first hot image that meets the second hotness condition; analyze and obtain a second processing method and a second style corresponding to the first hot image; according to the second processing method, generate a promotional image that conforms to the second style based on the object information of the target promotion object; save the promotional image to the delivery list corresponding to the promotion object.

[0068] Optionally, generating at least one promotional image conforming to the first style based on the object information of the target object according to the first processing manner includes:

[0069] Calling the image generation model corresponding to the first processing method to generate at least one promotional image that conforms to the first style based on the object information of the target object; the image generation model is trained using multiple training samples; the training samples include sample object information and sample images that conform to the sample style.

[0070] Optionally, it also includes:

[0071] Performing image review on the at least one promotional image respectively; if any promotional image fails the review, setting the promotional image to an invalid state;

[0072] Optionally, performing the object promotion operation in combination with at least one target promotion image corresponding to the at least one promotion object includes:

[0073] For any promotion object, select a second hot picture that meets the third hot condition from at least one object picture corresponding to a similar object of the promotion object; filter a picture to be promoted that matches the second hot picture from at least one target promotion picture corresponding to the promotion object; and perform an object promotion operation for the promotion object in combination with the picture to be promoted.

[0074] Optionally, it also includes:

[0075] Sending configuration prompt information to the user terminal so that the user terminal displays the configuration prompt information on the user interface, generating a configuration request in response to the configuration operation of the target user; receiving the configuration request sent by the user terminal, and determining the generated promotion configuration information;

[0076] The performing of the object promotion operation in combination with at least one target promotion picture corresponding to the at least one promotion object includes:

[0077] An object promotion operation is performed in combination with at least one target promotion picture corresponding to the at least one promotion object and the promotion configuration information.

[0078] Optionally, it also includes:

[0079] Sending object prompt information of at least one promotion object to the user terminal;

[0080] Determining the target object provided by the target user includes:

[0081] The target object selected by the target user is determined.

[0082] Optionally, the sending of object prompt information of at least one promotion object to the user terminal includes:

[0083] When the target user meets the promotion conditions, a promotion invitation message is sent to the user terminal; and according to a confirmation operation of the target user, object prompt information of at least one promotion object is sent to the user terminal.

[0084] Optionally, it also includes:

[0085] According to the adjustment request for the at least one promotion object, the object list corresponding to the target user is sent to the user terminal; according to the at least one object selected by the target user from the object list, the at least one promotion object is updated.

[0086] Optionally, it also includes:

[0087] At least one promotion object that meets the promotion requirements is determined from the multiple objects corresponding to the target user.

[0088] Optionally, the first processing method includes generating text, synthesizing pictures, switching backgrounds, or changing skins.

[0089] Optionally, it also includes:

[0090] Statistics are collected on the promotion effects corresponding to the promotion tasks consisting of the at least one promotion object, as well as the promotion effects of any promotion object; effect viewing prompt information is sent to the user terminal; upon receiving an effect viewing request from the user terminal for any promotion task or any promotion object, the promotion effect information of the promotion task or the promotion object is sent to the user terminal.

[0091] Optionally, it also includes:

[0092] Receive a promotion termination request for any promotion task or any promotion object sent by the user terminal, and suspend the object promotion operation corresponding to the promotion task or the promotion object.

[0093] Optionally, it also includes:

[0094] When an update operation is detected for the image generation model, the image generation model is used to regenerate at least one promotional image that conforms to the first style based on the object information of the target object; and the at least one regenerated promotional image is used to update at least one historically generated promotional image corresponding to the target object.

[0095] Optionally, the object information includes a target image, and the method further includes:

[0096] A target image that conforms to the first processing method and the first style is screened from at least one object image corresponding to the target promotion object; the at least one object image is provided by the target user.

[0097] Optionally, it also includes:

[0098] According to the image requirements corresponding to different processing methods, at least one processing method that matches at least one object image of the target promotion object is determined; wherein the at least one object image is provided by the target user.

[0099] In a fourth aspect, an embodiment of the present application provides a content generation method, including:

[0100] Determine the target audience provided by the target users;

[0101] Sending a selection prompt message of at least one processing method to the user terminal;

[0102] Determining a first processing method selected by the target user;

[0103] Sending at least one style selection prompt information to the user terminal;

[0104] determining a first style selected by the target user;

[0105] According to the first processing manner, at least one promotional content conforming to the first style is generated based on the object information of the target object.

[0106] In a fifth aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component;

[0107] The storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the image generation method as described in the first aspect above, or the content generation method as described in the second aspect above, or the image generation method as described in the third aspect above, or the content generation method as described in the fourth aspect above.

[0108] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a computer, it implements the image generation method described in the first aspect above, or the content generation method described in the second aspect above, or the image generation method described in the third aspect above, or the content generation method described in the fourth aspect above.

[0109] In an embodiment of the present application, a target promotion object provided by a user is determined, and a selection prompt for at least one processing method is provided in a user interface; in response to the method selection operation of the target user, a selected first processing method is determined, and a selection prompt for at least one style is provided in the user interface; in response to the style selection operation of the target user, a selected first style is determined; at least one promotional image that conforms to the first style and is generated according to the target first processing method based on the object information of the target promotion object is determined; and image prompt information for the at least one promotional image is displayed in the user interface. This embodiment of the present application achieves automatic generation of promotional images through human-computer interaction, thereby improving content generation efficiency and reducing content generation costs.

[0110] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0111] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0112] FIG1 shows a flow chart of an embodiment of a content generation method provided by the present application;

[0113] FIG2 shows a flow chart of an embodiment of a method for generating an image provided by the present application;

[0114] FIG3a to FIG3c are schematic diagrams of user interfaces in a practical application of an embodiment of the present application;

[0115] FIG4 shows a flow chart of another embodiment of a content generation method provided by the present application;

[0116] FIG5 shows a flowchart of another embodiment of a method for generating an image provided by the present application;

[0117] FIG6 a shows a schematic diagram of scene interaction in an actual application of an embodiment of the present application;

[0118] FIG6 b shows a system architecture diagram applicable to a practical application of the technical solution of an embodiment of the present application;

[0119] FIG7 shows a schematic structural diagram of an embodiment of a content generation device provided by an embodiment of the present application;

[0120] FIG8 shows a schematic structural diagram of another embodiment of a content generation device provided in an embodiment of the present application;

[0121] FIG9 shows a schematic structural diagram of an embodiment of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0122] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0123] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0124] The technical solution of the embodiment of the present application can be applied to the object promotion scenario to efficiently, cost-effectively and accurately generate promotional content for the promotion object. The promotional content may include information types such as pictures, text, audio and / or video.

[0125] The object in this article can refer to a virtual object provided online for consumers to interact with, and the user in this article can refer to the object provider. For example, the goods provided by online trading platforms can refer to tangible items or intangible services, and consumers can perform interactive behaviors such as browsing, collecting, and purchasing. The object provider is the merchant. To increase the click-through rate and conversion rate of goods, product promotion is currently a solution. In practical applications, product promotion can refer to product advertising. The quality of advertising content is a key factor affecting the click-through rate and conversion rate of goods. As described in the background technology, current advertising content is usually produced by merchants themselves, and the production process is complex. In particular, advertising images require merchants to use a lot of third-party software to operate them, and then upload them to the online trading platform for output through various advertising channels. It can be seen that the production cost is high, the efficiency is low, and the accuracy of self-made content cannot be guaranteed. The effect of improving the click-through rate and conversion rate of goods is not obvious.

[0126] Therefore, in order to reduce production costs and improve production efficiency, the inventor proposed the technical solution of this application after a series of studies. In the embodiment of this application, through human-computer interaction, the user only needs to select the target promotion object to realize the automatic generation of promotional pictures, thereby saving picture production efficiency and production costs.

[0127] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0128] It should be noted that the technical solution of the embodiment of the present application is applicable to a network virtual environment. The users described generally refer to "virtual users". Real users can register user accounts in the server through registration to obtain user identities in the network environment. In the embodiment of the present application, the same user account can be used to log in to the server through different types of clients, so that the server can identify the same user. Of course, different user accounts can also be used to log in to the server through different types of clients. The server stores binding relationships between different user accounts, so that different user accounts with binding relationships can be considered to be the same user.

[0129] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0130] Figure 1 is a flow chart of an embodiment of a content generation method provided by an embodiment of the present application. The technical solution of this embodiment can be executed by a user end. In practical applications, a system architecture in which the embodiment of the present application can be applied may include a user end and a server end. The user end is user-oriented, meaning it is the object provider. Users can request the server end to publish objects through the user end, and consumers can perform interactive behaviors such as searching, browsing, and purchasing objects through the consumer end.

[0131] The connection between the client and the server is established via a network. The network provides the medium for the communication link between the client and the server. The network can include various connection types, such as wired or wireless communication links or fiber optic cables.

[0132] The client can interact with the server 102 through the network to receive or send messages, etc.

[0133] The user end can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5) application, a light application (also known as a mini-program, a lightweight application), or a cloud application. The user end can be deployed in an electronic device and requires the device to run or certain apps in the device to run. For example, the electronic device can have a display and support information browsing, such as a personal mobile terminal such as a mobile phone, tablet computer, personal computer, desktop computer, smart speaker, smart watch, etc. For ease of understanding, Figure 1 mainly uses the device image to represent the user end. Various other types of applications can also be configured in the electronic device, such as human-computer interaction applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. The electronic device can refer to a device used by the user and has the required computing, Internet access, communication, etc., such as a mobile phone, tablet computer, personal computer, wearable device, etc. The electronic device generally includes at least one processing component and at least one storage component. The electronic device may also include basic configurations such as a network card chip, an IO bus, audio and video components, which are not limited in this application. Optionally, depending on the implementation form of the electronic device, it may also include some peripheral devices, such as a keyboard, a mouse, an input pen, a printer, etc., which are not limited in this application.

[0134] The server may include a server that provides various services, such as a server that processes interactive information sent by the user.

[0135] It should be noted that the server can be implemented as a distributed server cluster consisting of multiple servers or a single server. The server can also be a server in a distributed system or a server integrated with blockchain. The server can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0136] The content generation method shown in FIG1 may include the following steps:

[0137] 101: Determine the target promotion objects provided by target users.

[0138] The target user may refer to any user, or alternatively, any user who meets the promotion conditions. The promotion condition may refer to the existence of a historical promotion record, or, in an actual application, a user may participate in a promotion activity on an online system to promote an object on a specific object promotion page. In this case, the promotion condition may refer to participation in the promotion activity.

[0139] Optionally, the target object provided by the user may be determined according to an object selection operation of the target user.

[0140] As an optional method, determining the target promotion object provided by the target user may include: providing object prompt information of at least one promotion object in a user interface; and determining the selected target promotion object in response to an object selection operation by the target user. The object selection operation may be a trigger operation performed on any object prompt information, and the object prompt information may be in the form of a control for the user to click or otherwise select the corresponding target promotion object.

[0141] The at least one promotion object can be determined from multiple objects corresponding to the target user, and the multiple objects are requested by the target user to be published to the online system. In order to improve the flexibility of object selection, the method can optionally further include:

[0142] In response to an adjustment operation on at least one promotion object, an object list is displayed on the user interface; the object list may include multiple objects corresponding to the target user; and at least one promotion object is updated according to at least one object selected by the target user from the object list.

[0143] In the object list, the target user can select or deselect an object to update at least one promotion object.

[0144] As can be seen from the above description, the target user may refer to any user who meets the promotion conditions. Therefore, optionally, providing object prompt information of at least one promotion object corresponding to the target user in the user interface may include:

[0145] Providing promotion invitation information on the user interface; the promotion invitation information may be sent to target users who meet the promotion conditions, and is used to prompt the target users whether to create promotional content, etc.; in response to a confirmation operation on the promotion invitation information, object prompt information of at least one promotion object corresponding to the target user is provided on the user interface.

[0146] Optionally, the method may further include: determining at least one promotion object that meets the promotion requirements from a plurality of objects corresponding to the target user.

[0147] The promotion requirements may, for example, refer to the inclusion of specified object features, etc. The specified object features may be pre-configured, or may be obtained by statistically analyzing the object features contained in at least one hot object in the online system, etc. A hot object may refer to an object whose interactive data satisfies the hot conditions, and the interactive data may, for example, refer to object exposure information, object click information, object sales information, and / or object conversion information, etc. Object exposure information may, for example, refer to the object exposure volume of content within a specified time; object click information may, for example, refer to the object click volume within a specified time, object sales information may refer to the object sales volume within a specified time, and object conversion volume may refer to the object conversion rate within a specified time, and the object conversion rate may, for example, be calculated based on the ratio of the object sales volume to the object exposure volume, etc. The first hot condition may, for example, refer to the object exposure volume, object click volume, object sales volume, and / or object conversion rate being greater than certain values, etc.

[0148] Furthermore, as another optional manner, determining at least one promotion object that meets the promotion requirements from among multiple objects corresponding to the target user may include:

[0149] Based on the interactive data generated by the objects published by the online system, at least one hot object that meets the first hot condition is screened; the interactive data includes object exposure information, object click information, object sales information, and / or object conversion rate; at least one hot object feature of at least one hot object is counted; according to the degree of matching between multiple objects corresponding to the target user and at least one hot object feature, at least one promotion object whose matching degree meets the matching requirements is selected.

[0150] The at least one hot object feature may include, for example, basic information such as object category, object name, object origin, and image attribute features. The image attribute features may include, for example, processing method and / or style.

[0151] That is, for each object, the degree of matching of multiple objects can be calculated based on whether each object has at least one hot object feature, or the size of the deviation from the at least one hot object feature. The specific calculation method can be pre-set by the calculation party or implemented through a machine learning model, etc., which is not specifically limited in this application. In this way, at least one promotion object can be screened based on the degree of matching. The matching requirement can, for example, mean that the degree of matching is greater than a specified value. The greater the degree of matching, the more hot object features the object contains, or the closer it is to the hot object feature.

[0152] 102: Providing selection prompt information for at least one processing method on the user interface.

[0153] In the embodiment of the present application, the processing method may include, for example, generating text, synthesizing pictures, switching backgrounds, changing skins, etc.

[0154] Optionally, the online system may provide multiple processing methods, and the at least one processing method may be determined from the multiple processing methods. The at least one processing method may be determined to match at least one target image of the target promotion object based on the image requirements corresponding to the different processing methods. The at least one target image is provided by the target user.

[0155] The image requirements can be set based on actual needs. For example, in the copywriting processing method, the image requirement may refer to the target promotion object having an object image containing text information. In the processing method of synthesizing images, the image requirement may refer to the target promotion object having multiple object images. In the processing method of switching backgrounds, the image requirement may refer to the target promotion object having an object image with a solid color background. In the processing method of changing skins, the image requirement may refer to the target promotion object having an object image containing a human body. It should be noted that these are only examples and this application is not limited to them.

[0156] 103: In response to the target user's mode selection operation, determine the selected first processing mode.

[0157] 104: Providing at least one style selection prompt information in the user interface.

[0158] 105 : In response to the target user's style selection operation, determine the selected first style.

[0159] The mode selection operation can be a trigger operation for the selection prompt information of any processing mode, and the selection prompt information can be in the form of a control to perceive the user trigger operation, such as clicking, etc., so as to determine the processing mode selected by the target user based on the mode selection operation. For the convenience of description, the processing mode selected by the target user is named as the first processing mode in this article. In the embodiment of the present application, each processing mode can be configured with one or more styles. For example, at least one style corresponding to the processing mode for generating text can include text color such as red, text position such as the upper right corner of the picture, and text background shape such as rectangle, heart shape, etc.; at least one style corresponding to the processing mode for synthesizing pictures can include layout mode such as top and bottom layout, left and right layout, and arrangement number such as one row and three columns, etc.; at least one style corresponding to the processing mode for switching backgrounds can include beach, green land, sky, etc.; at least one style corresponding to the processing mode for changing skin can include skin color such as yellow, white, etc., skin type such as Asian, European and American, etc. It should be noted that this is only an example, and the present application is not limited to this.

[0160] As an optional method, the at least one style selection prompt information provided in the user interface may refer to all styles corresponding to the at least one processing method. The user can select a style that is suitable for the first processing method based on his understanding of each processing method. In addition, in order to avoid the problem of content generation errors caused by mismatch between processing method and style,

[0161] After all styles corresponding to at least one processing method are provided in the user interface, in response to the target user's style selection operation, it can be determined whether the currently selected style matches the first processing method. If it does not match, an error message can be displayed to prompt the target user that the style selection is incorrect, so that the target user can reselect. If it matches, the style can be used as the first style. In addition, as another implementation method, the selection prompt information of each style that does not match the first processing method can be switched to an unselectable state, so that the target user cannot perform the selection operation; or, the selection prompt information of each style that matches the first processing method can be set with a specific mark symbol to prompt the target user to perform the selection operation by displaying the style selection prompt information that matches the specific mark.

[0162] At this time, selection prompt information of at least one processing method and selection prompt information of at least one style may be displayed simultaneously in the user interface.

[0163] In addition, in order to improve selection efficiency, etc., as another optional manner, providing selection prompt information of at least one style in the user interface may be providing selection prompt information of at least one style corresponding to the first processing manner in the user interface.

[0164] After the first processing method is selected, a selection prompt for at least one style corresponding to the first processing method may be displayed in the user interface. Only the selection prompt for at least one style corresponding to the first processing method may be displayed in the user interface, and the selection prompts for styles corresponding to other processing methods may be stopped from being displayed or hidden.

[0165] In addition, in this optional method, selection prompt information of at least one processing method can be first displayed in the user interface. After the first processing method is determined, selection prompt information of at least one style corresponding to the first processing method can be displayed in the user interface.

[0166] The style selection operation may refer to a triggering operation for selection prompt information of any style. The selection prompt information may be in the form of a control, for example, to perceive a user triggering operation, such as a click, etc., so that the style selected by the target user can be determined based on the style selection operation. For the sake of convenience of description, the style selected by the target user is named the first style in this article.

[0167] In addition, optionally, after determining the selected first processing method, a selection mark symbol can be displayed at the corresponding display position of the selection prompt information of the first processing method to prompt that the first processing method is selected; after determining the selected first style, a selection mark symbol can be displayed at the corresponding display position of the selection prompt information of the first style to prompt that the first style is selected, etc.

[0168] 106 : Determine at least one promotional content that is generated based on the object information of the target object and conforms to the first style according to the first processing method.

[0169] The object information may include, for example, one or more of an object name, an object title, an object picture, and key information extracted from an object details page.

[0170] Promotional content may include one or more of promotional pictures, promotional copy, promotional audio, promotional videos, etc.

[0171] The user end can send the first processing method and the first style selected by the target user to the server end, and the server end generates at least one promotional content that conforms to the first style according to the first processing method based on the object information of the target object, and sends the at least one promotional content to the user end.

[0172] Of course, the user terminal may also generate at least one promotional content that conforms to the first style based on the object information of the target object in accordance with the first processing method.

[0173] In one implementation, a content generation model corresponding to the first processing method may be called to generate at least one promotional content conforming to the first style based on the object information of the target object.

[0174] In an embodiment of the present application, different processing methods can be implemented using different content generation models, wherein the content generation model can be trained using multiple training samples, and the training samples can include sample object information and sample images that conform to the sample style.

[0175] Optionally, the content generation model can be implemented using an AIGC (Artificial Intelligence Generated Content) model, such as stable diffusion (an open source AI drawing generation tool), etc., but of course the present application is not limited thereto.

[0176] 107: Providing content prompt information of at least one promotional content on the user interface.

[0177] In order to facilitate the target user to view the promotion content so as to perform subsequent operations, etc., content prompt information of at least one promotion content may be displayed on the user interface.

[0178] The content prompt information may include the promotional content or key information extracted from the promotional content. When the promotional content includes a promotional picture, the content prompt information may include a thumbnail of the promotional picture, etc.

[0179] Based on the content prompt information, the target user may request to view the corresponding promotion content, request to download the corresponding promotion content to local storage, or request to add the corresponding promotion content to the delivery list, so as to perform subsequent object promotion operations on the target promotion objects in the delivery list.

[0180] In this embodiment, through human-computer interaction, users only need to select the target promotion object to automatically generate promotional images, thereby reducing image production efficiency and costs. Furthermore, to improve the accuracy of promotional content, a content generation model can be used to generate promotional content, which not only helps improve content generation efficiency but also ensures content accuracy.

[0181] As can be seen from the above description, the promotional content may include one or more of promotional pictures, promotional copy, promotional audio, promotional videos, etc., and may have multiple information types. For ease of understanding and description, one or more embodiments below will mainly use the promotional content as promotional pictures as an example to introduce the technical solutions of the embodiments of this application.

[0182] FIG2 is a flowchart of an embodiment of a method for generating an image provided by an embodiment of the present application. The technical solution of this embodiment is executed by a user terminal. The method may include the following steps:

[0183] 201: Determine the target promotion objects provided by the target users.

[0184] 202: Providing selection prompt information for at least one processing method on the user interface.

[0185] For ease of understanding, FIG3 a shows a possible display diagram of a user interface in an actual application. In the user interface 300 , selection prompt information 301 of at least one processing method may be displayed.

[0186] 203: In response to the target user's mode selection operation, determine the selected first processing mode.

[0187] 204: Providing at least one style selection prompt information in the user interface.

[0188] 205 : In response to the target user's style selection operation, determine the selected first style.

[0189] As an optional method, the at least one style selection prompt information provided in the user interface may refer to all styles corresponding to the at least one processing method. The user can select a style that is suitable for the first processing method based on his understanding of each processing method. In addition, in order to avoid the problem of content generation errors caused by mismatch between processing method and style,

[0190] After all styles corresponding to at least one processing method are provided in the user interface, in response to the target user's style selection operation, it can be determined whether the currently selected style matches the first processing method. If it does not match, an error message can be displayed to prompt the target user that the style selection is incorrect, so that the target user can reselect. If it matches, the style can be used as the first style. In addition, as another implementation method, the selection prompt information of each style that does not match the first processing method can be switched to an unselectable state, so that the target user cannot perform the selection operation; or, the selection prompt information of each style that matches the first processing method can be set with a specific mark symbol to prompt the target user to perform the selection operation by displaying the style selection prompt information that matches the specific mark.

[0191] In addition, in order to improve selection efficiency, etc., as another optional manner, providing selection prompt information of at least one style in the user interface may be providing selection prompt information of at least one style corresponding to the first processing manner in the user interface.

[0192] As shown in FIG3 a , the target user can perform a method selection operation on any processing method selection prompt information to determine the corresponding first processing method, and can display at least one style of selection prompt information 302 corresponding to the first processing method in the user interface 300 .

[0193] 206: Determine at least one promotional image that conforms to the first style and is generated according to the first processing method based on the object information of the target promotion object.

[0194] 207: Displaying image prompt information of at least one promotional image on the user interface.

[0195] As shown in FIG. 3 a , the user interface 300 may display picture prompt information 303 of at least one promotional picture.

[0196] It should be noted that this embodiment differs from the embodiment shown in FIG1 in that the promotional content specifically refers to a promotional image. Specifically, the promotional image is generated in accordance with the first processing method based on the object information of the target promotion object, and is at least one promotional image conforming to the first style. Furthermore, the image prompt information displayed in the user interface is the at least one promotional image. Other identical or similar steps are described in detail in the embodiment shown in FIG1 and are not further detailed here.

[0197] In some embodiments, the method may further include: determining at least one processing method that matches at least one object image of the target promotion object according to image requirements corresponding to different processing methods; wherein the at least one object image is provided by the target user.

[0198] In some embodiments, the object information may specifically include a target picture; the method may further include: screening a target picture that meets the picture requirements corresponding to the first processing method from at least one object picture corresponding to the target promotion object; at least one object picture is provided by the target user.

[0199] That is, after selecting the first processing method and the first style, since the target promotion object may have multiple target images, the target images that meet the image requirements can be screened according to the image requirements corresponding to the first processing method.

[0200] In some embodiments, filtering target images that meet the first processing method and the first style from at least one object image corresponding to the target promotion object may include: filtering at least one candidate image that meets the image requirements corresponding to the first processing method from at least one object image corresponding to the target promotion object; displaying image prompt information of at least one candidate image on the user interface; and in response to the target user's image selection operation for any candidate image, using the selected candidate image as the target image.

[0201] The image prompt information of each candidate image may include, for example, a thumbnail of the candidate image, etc., and may be in the form of a control to facilitate perception of the image selection operation triggered by the target user.

[0202] As shown in FIG. 3 a , the user interface 300 may display selection prompt information 304 of at least one candidate image, for the target user to select a target image from among them.

[0203] In addition, as shown in Figure 3a, a generation prompt information 305 can also be displayed in the user interface 300, so that in response to the trigger operation for generating the prompt information 305, at least one promotional image that conforms to the first style can be generated according to the first processing method based on the object information of the target promotion object, or a request can be generated to the server so that the server can generate at least one promotional image that conforms to the first style according to the first processing method based on the object information of the target promotion object.

[0204] As can be seen from the above description, based on the image prompt information of any promotional image, the target user can perform an image download operation to download the selected promotional image for local storage, perform an image view operation to display the selected promotional image on the user interface, and perform an image selection operation to add the selected promotional image to the target user's corresponding delivery list. Therefore, in some embodiments, the method may further include: in response to the target user's image selection operation for any promotional image, saving the selected promotional image to the target object's delivery list.

[0205] The delivery list may store one or more promotional images corresponding to the target promotion objects.

[0206] In some embodiments, the method may further include: displaying a delivery list corresponding to at least one promotion object on a user interface; determining at least one selected target promotion image in response to an image selection operation on the delivery list; generating a promotion request in combination with at least one target promotion image corresponding to at least one promotion object; the promotion request is used to indicate the execution of an object promotion operation in combination with at least one target promotion image corresponding to at least one promotion object.

[0207] Optionally, as shown in FIG3a , a list view prompt 306 may be displayed in user interface 300. In response to a triggering operation based on list view prompt 306 , a placement list 307 corresponding to at least one promotional object may be displayed in user interface 300, as shown in FIG3b . Each placement list for a promotional object includes one or more promotional images. The target user may select at least one target promotional image 308 from the placement list corresponding to any promotional object.

[0208] Optionally, as shown in FIG3b , promotion prompt information 309 may also be displayed in the user interface 300 , so that in response to a triggering operation on the promotion prompt information 309 , a promotion request may be generated in combination with at least one target promotion picture corresponding to at least one promotion object.

[0209] In addition, in some embodiments, the method may further include: displaying configuration prompt information corresponding to at least one promotion object in the user interface, such as configuration prompt information 310 shown in FIG3b , so that in response to a configuration operation triggered by a target user for the configuration prompt information, the generated promotion configuration information may be determined, thereby generating a promotion request by combining at least one target promotion picture and promotion configuration information corresponding to at least one promotion object.

[0210] The promotion configuration information may include, for example, a promotion task name, a promotion budget cost, and a promotion strategy.

[0211] In some embodiments, determining the target promotion object provided by the target user may include: providing object prompt information of at least one promotion object corresponding to the target user on a user interface; and determining the selected target promotion object in response to an object selection operation of the target user.

[0212] In some embodiments, providing object prompt information of at least one promotion object corresponding to the target user in the user interface includes: providing promotion invitation information in the user interface; the promotion invitation information is sent to the target user who meets the promotion conditions; in response to a confirmation operation on the promotion invitation information, providing object prompt information of at least one promotion object corresponding to the target user in the user interface.

[0213] In some embodiments, the method may further include: displaying an object list on a user interface in response to an adjustment operation on at least one promotion object; and updating at least one promotion object according to at least one object selected by the target user from the object list.

[0214] Optionally, as shown in FIG3 a , the user interface 300 may display object prompt information 311 of at least one promotion object. In addition, adjustment prompt information 312 may also be displayed. The adjustment operation may be a trigger operation for the adjustment prompt information.

[0215] As shown in FIG3b , an object list may be displayed on the user interface 300 , which may include object prompt information 313 of multiple objects corresponding to the target user. The target user may perform an object selection operation in the object list, thereby updating at least one promotional object based on at least one reselected object.

[0216] A promotion task may be generated based on at least one promotion object.

[0217] In some embodiments, the method may further include: selecting a first hot picture that meets a second hot condition from at least one object picture corresponding to a similar object of the target promotion object; determining a second processing method and a second style corresponding to the first hot picture; generating a promotional picture that conforms to the second style based on the object information of the target promotion object according to the second processing method; and saving the promotional picture to a delivery list corresponding to the promotion object.

[0218] Optionally, the image generation model corresponding to the second processing method may be called to generate a promotional image conforming to the second style based on the object information of the target promotion object.

[0219] The image generation model can be implemented using an AIGC model, such as stable diffusion, etc. Of course, this application is not limited to this, and other model structures can also be used for implementation, such as GAN (Generative Adversarial Nets, generative adversarial network), etc.

[0220] The second popularity condition may, for example, refer to the number of clicks on the image and / or the number of exposures of the image being greater than a certain value.

[0221] Among them, the similar objects of the target promotion object can, for example, refer to objects that have at least some of the same object features as the target promotion object, or the similarity score between the target promotion object and any object can be calculated based on the object features, so that objects with a similarity score greater than a specified score can be screened as similar objects, etc.

[0222] It is also possible to automatically generate a promotional image and add it to the delivery list based on the second processing method and the second style that the first popular image complies with.

[0223] Among them, determining the second processing method and the second style corresponding to the first hot image can be achieved, for example, through image recognition technology, for example, it can be achieved using a pre-trained image recognition model, etc., and this application does not limit this.

[0224] In addition, in some embodiments, the method may also include: providing effect viewing prompt information corresponding to at least one promotion object or a promotion task composed of at least one promotion object in the user interface; in response to the target user's effect viewing operation for any promotion object or any promotion task, displaying corresponding promotion effect prompt information in the user interface.

[0225] The promotion effect prompt information corresponding to each promotion object may include, for example, promotion cost, object conversion rate, object exposure, object click volume, etc.

[0226] The promotion effect prompt information corresponding to each promotion task may include, for example, the total promotion cost, the total object exposure, the total object clicks, the total object conversion rate, etc. corresponding to at least one promotion object under the promotion task.

[0227] FIG4 is a flowchart of another embodiment of a content generation method provided by an embodiment of the present application. The technical solution of this embodiment can be executed by a server. The method may include the following steps:

[0228] 401: Determine the target object provided by the target user.

[0229] The user end may send the target object provided by the target user to the server end.

[0230] Optionally, object prompt information of at least one promotion object may be sent to the user terminal, so that the user terminal displays the object prompt information of the at least one promotion object in a user interface and perceives the object selection operation of the target user.

[0231] Determining the target object provided by the target user is to determine the target object selected by the target user.

[0232] The method may further include: sending object prompt information of at least one promotion object to the user terminal; the user terminal may display the object prompt information of the at least one promotion object on a user interface, and may sense an object selection operation triggered by any object prompt information, thereby sending an object selection request to the server terminal. The server terminal may determine the target object selected by the target user based on the object selection request.

[0233] Optionally, the method may further include: sending an object list corresponding to the target user to the user terminal according to an adjustment request for at least one promotion object; and updating at least one promotion object according to at least one object selected by the target user from the object list.

[0234] In addition, optionally, sending object prompt information of at least one promotion object to the user terminal may include: sending promotion invitation information to the user terminal when the target user meets the promotion conditions; and sending object prompt information of at least one promotion object to the user terminal based on a confirmation operation of the target user.

[0235] The at least one promotion object may be determined from multiple objects corresponding to the target user, and may be randomly selected. In addition, optionally, at least one promotion object that meets the promotion requirements may be determined from multiple objects corresponding to the target user.

[0236] As an implementation manner, determining at least one promotion object that meets the promotion requirements from multiple objects corresponding to the target user includes:

[0237] Based on the interactive data generated by the objects published by the online system, at least one hot object that meets the first hot condition is screened; the interactive data includes object exposure information, object click information, object sales information, and / or object conversion information; at least one hot object feature of at least one hot object is counted; according to the degree of matching between multiple objects corresponding to the target user and at least one hot object feature, at least one promotion object whose matching degree meets the matching requirements is selected.

[0238] 402: Sending a prompt message for selecting at least one processing method to the user terminal.

[0239] The at least one processing method can be pre-configured and determined. In addition, optionally, the server can provide multiple processing methods and determine at least one processing method that matches at least one object image of the target promotion object according to the image requirements corresponding to different processing methods.

[0240] 403: Determine the first processing method selected by the target user.

[0241] The user end may determine the selected first processing method in response to the method selection operation, and send the first processing method to the server end.

[0242] 404: Send at least one style selection prompt to the user terminal.

[0243] Optionally, selection prompt information for at least one style corresponding to at least one processing method may be sent to the user terminal, so that the user terminal can display the selection prompt information for at least one style corresponding to at least one processing method on the user interface. The selection prompt information for at least one processing method and the selection prompt information for at least one style may be sent to the user terminal simultaneously, so that the user terminal can display the selection prompt information for at least one processing method and the selection prompt information for at least one style on the user interface simultaneously. Of course, the selection prompt information for at least one style may also be sent after the first processing method is determined. This is not limited to this in the present application, and the technical solution of the present application is not limited to the order of the operating steps listed in this embodiment.

[0244] In addition, as another optional method, in order to improve the efficiency of style selection, selection prompt information of at least one style corresponding to the first processing method may be sent to the user terminal. That is, the selection prompt information of at least one style corresponding to the first processing method is sent to the user terminal. After the first processing method is determined, the selection prompt information of at least one style corresponding to the first processing method may be sent to the user terminal.

[0245] 405: Determine the first style selected by the target user.

[0246] The user end may determine the selected first style in response to the style selection operation, and send the first style to the server end.

[0247] 406 : According to the first processing manner, generate at least one promotional content that conforms to the first style based on the object information of the target object.

[0248] Optionally, the object information may include a target picture. The target promotion object corresponds to at least one object picture. The target picture can be determined from at least one object picture. Optionally, the target picture that conforms to the first processing method and the first style can be screened from at least one object picture corresponding to the target promotion object.

[0249] In this embodiment, through human-computer interaction, users only need to select the target promotion object to automatically generate promotional images, thereby reducing image production efficiency and costs. Furthermore, to improve the accuracy of promotional content, a content generation model can be used to generate promotional content, which not only helps improve content generation efficiency but also ensures content accuracy.

[0250] As can be seen from the above description, the promotional content may include one or more of promotional pictures, promotional copy, promotional audio, promotional videos, etc., and may have multiple information types. For ease of understanding and description, one or more embodiments below will mainly use the promotional content as promotional pictures as an example to introduce the technical solutions of the embodiments of this application.

[0251] FIG5 is a flowchart of another embodiment of a method for generating an image provided by an embodiment of the present application. The technical solution of this embodiment can be executed by a server. The method may include the following steps:

[0252] 501: Determine the target object provided by the target user;

[0253] 502: Sending a prompt message for selecting at least one processing method to the user terminal;

[0254] 503: Determine the first processing method selected by the target user.

[0255] 504: Send at least one style selection prompt information to the user terminal.

[0256] Optionally, after the first processing manner is determined, selection prompt information of at least one style corresponding to the first processing manner is sent to the user terminal.

[0257] 505: Determine the first style selected by the target user.

[0258] 506 : Generate at least one promotional image that conforms to the first style based on the object information of the target object according to the first processing manner.

[0259] It should be noted that this embodiment differs from the embodiment shown in FIG. 4 in that the promotional content specifically refers to a promotional image. Specifically, based on the object information of the target promotion object, at least one promotional image conforming to the first style is generated according to the first processing method. Furthermore, the image prompt information displayed in the user interface is the at least one promotional image. Other identical or similar steps can be found in detail in the embodiment shown in FIG. 1 and are not further described here.

[0260] In some embodiments, the method may further include: sending picture prompt information of at least one promotional picture to the user terminal, so that the user terminal can display the picture prompt information of the at least one promotional picture in the user interface, and can perceive the picture selection operation triggered by the target user on any promotional picture, and can send a picture selection request to the server terminal based on the selected promotional picture, so that the server terminal determines the promotional picture selected by the target user; according to the promotional picture selected by the target user, the promotional picture is saved in the delivery list corresponding to the target promotion object; wherein, the delivery list can save at least one promotional picture corresponding to the target promotion object; sending the delivery list corresponding to at least one promotional object corresponding to the target user to the user terminal, so that the user terminal can display the delivery list corresponding to each promotional object on the user terminal, and can determine the selected at least one target promotional picture based on the picture selection operation of the target user on the delivery list of each promotional object; determining at least one target promotional picture selected by the target user for at least one promotional object; and performing object promotion operations in combination with at least one target promotion picture corresponding to at least one promotional object.

[0261] The object promotion operation may be performed by combining at least one target promotion image corresponding to at least one promotion object upon receiving a promotion request sent by the user terminal. The promotion request may be generated by the user terminal by combining at least one target promotion image corresponding to at least one promotion object.

[0262] In some embodiments, the method may include: performing image review on at least one promotional image separately; if any promotional image fails the review, setting the promotional image to an invalid state; wherein, according to the review rules, the at least one promotional image may be reviewed separately to determine whether any promotional image meets the review rules, and the review rules may, for example, include not including prohibited content, etc.

[0263] For promotional images that are in an invalid state, an invalid mark can be displayed on the delivery list, so that when the user terminal responds to the image selection operation on the delivery list, a selection failure prompt message can be displayed if the promotional image selected by the target user is in an invalid state.

[0264] In addition, optionally, for promotional images that are in an invalid state, an invalid mark can be displayed in the user interface. Thus, when the user terminal responds to an image selection operation triggered by any promotional image, a selection failure prompt message can be displayed when the promotional image is in an invalid state.

[0265] In some embodiments, in combination with at least one target promotional picture corresponding to at least one promotional object, executing an object promotion operation may include: for any promotional object, selecting a second hot picture that meets a third hot condition from at least one object picture corresponding to a similar object of the promotional object; screening a picture to be promoted that matches the second hot picture from at least one target promotional picture corresponding to the promotional object; and executing an object promotion operation for the promotion object in combination with the picture to be promoted.

[0266] The object promotion operation may, for example, generate promotion prompt information based on the image to be promoted, thereby sending the promotion prompt information to a designated consumer, or displaying the promotion prompt information on a specific object promotion page.

[0267] The third popularity condition may be, for example, that the number of clicks on the image and / or the number of exposures of the image are greater than a certain value.

[0268] Among them, similar objects of the promotion object can, for example, refer to objects that have at least some of the same object features as the promotion object, or the similarity score between the promotion object and any object can be calculated based on the object features, so that objects with a similarity score greater than a specified score can be screened as similar objects of the promotion object, etc.

[0269] In some embodiments, the method may include: sending configuration prompt information to the user terminal so that the user terminal displays the configuration prompt information on the user interface, and generating a configuration request in response to the configuration operation of the target user; receiving the configuration request sent by the user terminal, and determining the generated promotion configuration information; combining at least one target promotion picture corresponding to at least one promotion object, and executing the object promotion operation, including: combining at least one target promotion picture corresponding to at least one promotion object and the promotion configuration information, and executing the object promotion operation.

[0270] In some embodiments, the method may further include: selecting a first hot picture that meets a second hot condition from object pictures corresponding to similar objects of the target promotion object; analyzing and obtaining a second processing method and a second style corresponding to the first hot picture; generating a promotional picture that conforms to the second style based on the object information of the target promotion object according to the second processing method; and saving the promotional picture to the delivery list corresponding to the promotion object.

[0271] In some embodiments, according to the first processing method, generating at least one promotional image that conforms to the first style based on the object information of the target object may include: calling the image generation model corresponding to the first processing method, and generating at least one promotional image that conforms to the first style based on the object information of the target object.

[0272] The image generation model can be obtained by training with multiple training samples; the training samples include sample object information and sample images that conform to the sample style.

[0273] The above-mentioned first processing method includes, for example, generating text, synthesizing pictures, switching backgrounds, or changing skins, which is not specifically limited in this application.

[0274] In the case where the first processing method is to generate text, generating at least one promotional image conforming to the first style based on the object information of the target object according to the first processing method may include: generating at least one target text based on the object information of the target object; and fusing the at least one target text with the target image of the target object according to the first style to obtain at least one promotional image. The first style may include text position, so the fusing method may overlay the target text onto the target image according to the text position.

[0275] Here, at least one target copy may be generated based on the object information of the target object by utilizing the copy generation model.

[0276] When the first processing method is to synthesize pictures, switch backgrounds or change skins, the picture generation model corresponding to the first processing method can be specifically called to generate at least one promotional picture that conforms to the first style based on the object information of the target object.

[0277] The image generation model can be continuously iterated and updated. When an update operation occurs on the image generation model, the image generation model can be reused to regenerate at least one promotional image that conforms to the first style based on the object information of the target object, and the at least one regenerated promotional image can be used to update at least one historically generated promotional image corresponding to the target object.

[0278] The image generation model may be updated periodically, and thus the update cycle may be used to determine whether an update operation occurs on the image generation model.

[0279] In some embodiments, the method may further include: receiving a promotion task sent by the user end and pausing the promotion task; receiving a promotion termination request sent by the user end and pausing the object promotion operation corresponding to the promotion object.

[0280] Furthermore, in some embodiments, if a promotion deletion request for any promotion task or any promotion object is received from a user terminal, the promotion task or promotion object may be deleted.

[0281] In some embodiments, the method may further include: calculating the promotion effect corresponding to the promotion task consisting of at least one promotion object, as well as the promotion effect of any promotion object; sending effect viewing prompt information to the user terminal, so that the user terminal can display the effect viewing prompt information on a user interface; and upon receiving a request from the user terminal to view the effect of any promotion task or any promotion object, sending the promotion effect information of the promotion task or promotion object to the user terminal. The effect viewing request is generated and sent by the user terminal based on a viewing operation triggered by the target user in response to the effect viewing prompt information.

[0282] In a practical application, the promotion object in the embodiment of the present application refers to an advertising object, and the promotional picture can be an advertising picture. In an online transaction scenario, the promotion object can specifically refer to an advertising product, etc. Below, the technical solution of the embodiment of the present application is introduced with the promotion object as an advertising product and the promotional picture as an advertising picture, combined with the scene interaction diagram shown in Figure 6a.

[0283] For target merchants that meet the promotion requirements, the server 601 may send promotion invitation information to the corresponding user 602, prompting the user whether to automatically generate advertising images, etc. In response to the target merchant's confirmation operation on the promotion invitation information, the user 602 may send a confirmation request to the server 601. Based on the confirmation request, the server 601 may determine at least one advertising product that meets the advertising requirements from multiple products corresponding to the target merchant.

[0284] The server 601 may send product prompt information of at least one advertised product to the user 602 ; the user 602 may display the product prompt information of each advertised product in the user interface.

[0285] In addition, the user terminal 602 can also send an adjustment request to the server terminal 601 in response to the target merchant's adjustment operation on the at least one advertised product. The server terminal 601 can send a product list including multiple products of the target merchant to the user terminal 602 so that the user terminal 602 can display the product list. The target merchant can readjust at least one advertised product in the product list.

[0286] The user terminal 602 may determine the selected target advertised product according to the product selection operation of the target user on at least one advertised product.

[0287] The server 601 may determine at least one processing method that matches at least one product image of the target advertisement product according to the image requirements corresponding to different processing methods, and may send a selection prompt message of the at least one processing method to the user 602 .

[0288] The user terminal 602 can determine the selected first processing method in response to the method selection operation of the target merchant, and the server terminal 601 can send selection prompt information of at least one style corresponding to the first processing method to the user terminal 602, and the user terminal 602 can determine the selected first style in response to the style selection operation of the target merchant.

[0289] The server 601 can screen at least one candidate image that meets the image requirements corresponding to the first processing method based on the first processing method and the first style, and can send image prompt information of at least one candidate image back to the user end 602. The user end 602 can use any candidate image as the target image based on the target user's image selection operation for the image.

[0290] The server 601 may generate at least one advertising image that conforms to the first style based on the target image of the target advertised product in accordance with the first processing method, and send image prompt information of the at least one advertising image to the user 602 .

[0291] At the same time, the server 601 may conduct an image review on at least one advertisement image to determine whether each advertisement image is invalid, and set any advertisement image to an invalid state if the review fails.

[0292] The target merchant can select one or more promotional images through the user terminal 602 and request to add them to the delivery list corresponding to the target advertising product, and can also request to view the delivery list.

[0293] The server 601 may send the placement list corresponding to the at least one advertising product to the client 602 , so that the client 602 can display the placement list corresponding to the at least one advertising product.

[0294] The target merchant can select at least one target advertising image from the list of each advertised product through the user terminal 602. The at least one advertised product constitutes a promotion task, and the target merchant can also configure the promotion through the user terminal 602, setting the promotion task name, budget cost, etc.

[0295] The user terminal 602 can send an advertising request to the server terminal 601 for the promotion task. The server terminal 601 can filter the advertising images to be processed from at least one corresponding target advertising image for any advertising product. It can specifically perform corresponding promotion operations based on the advertising images to be processed and the promotion configuration information, such as generating advertising information based on the advertising images to be processed, sending the advertising information to a specified user, or displaying it on a specific object promotion page.

[0296] The server 601 can also count the advertising effect information of each promotion task and each advertising product, and the user end 602 can display the effect viewing prompt information, so that the server 601 can send the corresponding advertising effect information to the user end 602 based on the effect viewing request for any promotion task or any promotion object, for the target merchant to view and determine whether to delete or suspend the promotion task or advertising product.

[0297] In actual applications, the server side may include one or more servers to provide different services, such as a first server that interacts with the user side, a second server for image review, a third server that provides models, etc. In addition, the acquisition and storage of various information during the execution of the server side 601 may involve multiple databases, such as a database that provides processing method and style queries, a database that provides product information queries, a database that provides storage of advertising images, target advertising images, candidate advertising images, first processing methods, first styles, etc. In conjunction with the system architecture diagram shown in Figure 6b, the overall system architecture can be divided into three layers: the data layer, the processing layer, and the presentation layer. The data layer includes various databases that provide data query or storage, such as MySQL (a relational database management system), ODPS (Open Data Processing Service), Igraph (an online graph storage and query system), etc. The capability layer includes servers that provide different services, such as the first server that interacts with the user side, the third server that provides models, the second server for image review, the fourth server for generating advertising images, and the fifth server for performing product promotion operations.

[0298] The presentation layer may include the user end, object promotion pages, etc.

[0299] In addition, the server can also include a detection server for detecting whether the generation of the advertising image fails, whether the processing method or style fails to be obtained, whether the product information fails to be obtained, whether the promotion operation fails, whether the advertising image fails to be reviewed, etc., so that corresponding failure strategies can be executed in different failure situations, such as notifying the user end of failure prompt information, etc.

[0300] It should be noted that FIG6 b is merely an example, and the present application is not limited thereto.

[0301] FIG7 is a schematic diagram of the structure of an embodiment of a content generation device provided by an embodiment of the present application. The device may include:

[0302] The first object determination module 701 is used to determine the target promotion object provided by the target user;

[0303] The first display module 702 is used to provide a selection prompt message of at least one processing method on the user interface;

[0304] The second display module 703 is configured to determine the selected first processing method in response to the method selection operation of the target user; and provide selection prompt information of at least one style on the user interface;

[0305] A first style determining module 704 is configured to determine a selected first style in response to a style selection operation of the target user;

[0306] The image determination module 705 is configured to determine at least one promotional content that conforms to the first style and is generated according to the first processing method based on the object information of the target promotion object;

[0307] The third display module 706 is configured to provide content prompt information of the at least one promotional content on the user interface.

[0308] In some embodiments, the second display module may specifically provide selection prompt information of at least one style corresponding to the first processing method on the user interface.

[0309] In some embodiments, in an actual application, the image determination module may specifically determine at least one promotional image that conforms to the first style and is generated according to the first processing method based on the object information of the target promotion object;

[0310] The third display module may specifically provide picture prompt information of the at least one promotional picture on the user interface.

[0311] In some embodiments, the object information includes a target image, and the apparatus may further include:

[0312] A first processing module is configured to select at least one candidate image that meets the requirements of the first processing method from at least one object image corresponding to the target promotion object;

[0313] The fourth display module is used to display the picture prompt information of the at least one candidate picture on the user interface; in response to the picture selection operation of the target user on any candidate picture, the selected candidate picture is used as the target picture.

[0314] In some embodiments, the object determination module is specifically configured to provide object prompt information of at least one promotion object corresponding to the target user on the user interface; and determine the selected target promotion object in response to the object selection operation of the target user.

[0315] In some embodiments, the apparatus may further include:

[0316] The object updating module is configured to display an object list in the user interface in response to an adjustment operation on the at least one promotion object; and update the at least one promotion object according to at least one object selected by the target user from the object list.

[0317] In some embodiments, the apparatus may further include:

[0318] A promotion request module is used to save the selected promotional image to the delivery list of the target object in response to the image selection operation triggered by the target user for any promotional image; display the delivery list corresponding to at least one promotional object on the user interface; determine at least one selected target promotional image in response to the image selection operation for the delivery list; generate a promotion request in combination with at least one target promotional image corresponding to the at least one promotional object; the promotion request is used to instruct the execution of an object promotion operation in combination with at least one target promotional image corresponding to the at least one promotional object.

[0319] The content generation device shown in FIG7 can execute the content generation method described in the embodiment shown in FIG1 , and its implementation principle and technical effects are not further described. The specific manner in which the various modules and units of the content generation device in the above embodiment perform operations has been described in detail in the embodiment of the method, and will not be further elaborated here.

[0320] FIG8 is a schematic structural diagram of another embodiment of a content generation device provided in an embodiment of the present application. The device may include:

[0321] The second object determination module 801 is used to determine the target object provided by the target user;

[0322] A first sending module 802 is configured to send a selection prompt message of at least one processing method to a user terminal, and determine the first processing method selected by the target user;

[0323] The second sending module 803 is used to send at least one style selection prompt information to the user terminal;

[0324] A second style determination module 804 is configured to determine the first style selected by the target user;

[0325] The first image generating module 805 is configured to generate at least one promotional image conforming to the first style based on the object information of the target object in accordance with the first processing manner.

[0326] In some embodiments, the second sending module may send selection prompt information of at least one style corresponding to the first processing method to the user terminal.

[0327] In some embodiments, the apparatus may further include:

[0328] The object promotion module is used to send picture prompt information of the at least one promotional picture to the user terminal; save the promotional picture to the delivery list corresponding to the target object according to the promotional picture selected by the target user; send the delivery list corresponding to at least one promotional object corresponding to the target user to the user terminal; determine at least one target promotional picture selected by the target user for the at least one promotional object; and perform object promotion operations in combination with at least one target promotional picture corresponding to the at least one promotional object.

[0329] In some embodiments, the apparatus may further include:

[0330] The method determination module is used to determine at least one processing method that matches at least one object image of the target promotion object according to the image requirements corresponding to different processing methods; wherein the at least one object image is provided by the target user.

[0331] In some embodiments, the apparatus may further include:

[0332] A third sending module is configured to screen at least one hot object that meets a first popularity condition based on interaction data generated by objects published by the online system; the interaction data includes object exposure information, object click information, object sales information, and / or object conversion information; and to collect statistics on at least one hot object feature of the at least one hot object;

[0333] According to the matching degree between the multiple objects corresponding to the target user and the at least one hot object feature, at least one promotion object whose matching degree meets the matching requirement is selected; and object prompt information of the at least one promotion object is sent to the user terminal;

[0334] The second object determination module may specifically determine the target object selected by the target user.

[0335] In some embodiments, the apparatus may further include:

[0336] The second image generation module is used to select a first hot image that meets the second hotness condition from the object images corresponding to similar objects of the target promotion object; analyze and obtain the second processing method and second style corresponding to the first hot image; generate a promotional image that conforms to the second style based on the object information of the target promotion object according to the second processing method; and save the promotional image to the delivery list corresponding to the promotion object.

[0337] In some embodiments, the first image generation module may specifically call an image generation model corresponding to the first processing method to generate at least one promotional image that conforms to the first style based on the object information of the target object;

[0338] The image generation model is obtained by training with a plurality of training samples; the training samples include sample object information and sample images that conform to the sample style.

[0339] The content generation device shown in FIG8 can execute the content generation method described in the embodiment shown in FIG8 , and its implementation principle and technical effects are not further described. The specific manner in which the various modules and units of the content generation device in the above embodiment perform operations has been described in detail in the embodiment of the method, and will not be further elaborated here.

[0340] The embodiment of the present application further provides a computing device, as shown in FIG9 , which may include a storage component 901 and a processing component 902 ;

[0341] The storage component 901 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 902 to implement the content generation method described in the embodiment shown in Figure 1 or the image generation method described in the embodiment shown in Figure 2 or the content generation method described in the embodiment shown in Figure 4 or the image generation method described in the embodiment shown in Figure 5.

[0342] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0343] In the case where the processing component in the computing device is used to implement the content generation method described in the embodiment shown in FIG. 1 or the image generation method described in the embodiment shown in FIG. 2 , the computing device may further include a display component to perform corresponding display operations.

[0344] The input / output interface provides an interface between the processing component and peripheral interface modules, which may be output devices, input devices, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices.

[0345] The processing component may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method. The storage component is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The display component can be an electroluminescent (EL) element, a liquid crystal display or a microdisplay with a similar structure, or a retinal direct display or a similar laser scanning display.

[0346] It should be noted that when the above-mentioned computing device implements the content generation method described in the embodiment shown in Figure 1 or the image generation method described in the embodiment shown in Figure 2, it can be specifically implemented as an electronic device. The electronic device can refer to a device used by the user and has the computing, Internet access, communication and other functions required by the user, such as a mobile phone, tablet computer, personal computer, wearable device, etc.

[0347] When the computing device implements the content generation method described in the embodiment shown in FIG. 4 or the image generation method described in the embodiment shown in FIG. 5 , it can be implemented as a physical device or an elastic computing host provided by a cloud computing platform. It can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device.

[0348] The present application also provides a computer-readable storage medium storing a computer program. When executed by a computer, the computer program can implement the content generation method described in the embodiment shown in FIG1 , the image generation method described in the embodiment shown in FIG2 , the content generation method described in the embodiment shown in FIG4 , or the image generation method described in the embodiment shown in FIG5 . The computer-readable medium can be included in the electronic device described in the above embodiments, or it can exist independently and not be incorporated into the electronic device.

[0349] An embodiment of the present application also provides a computer program product, which includes a computer program carried on a computer-readable storage medium. When the computer program is executed by a computer, it can implement the content generation method described in the embodiment shown in Figure 1 or the image generation method described in the embodiment shown in Figure 2 or the content generation method described in the embodiment shown in Figure 4 or the image generation method described in the embodiment shown in Figure 5. In such an embodiment, the computer program can be downloaded and installed from the network, and / or installed from a removable medium. When the computer program is executed by a processor, the various functions defined in the system of the present application are executed.

[0350] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0351] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0352] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0353] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for generating an image, characterized in that: include: Determine the target promotion objects provided by target users; Providing selection prompt information of at least one processing method in the user interface; In response to the method selection operation of the target user, determining the selected first processing method; Providing at least one style of selection prompt information in the user interface; In response to a style selection operation of the target user, determining a selected first style; Determine at least one promotional picture conforming to the first style and generated according to the first processing method based on the object information of the target promotion object; The user interface provides picture prompt information of the at least one promotional picture.

2. The method according to claim 1, characterized in that The object information includes a target picture, and the method further includes: Selecting at least one candidate picture that meets the picture requirements corresponding to the first processing method from at least one object picture corresponding to the target promotion object; Displaying picture prompt information of the at least one candidate picture on the user interface; In response to a picture selection operation of the target user on any candidate picture, the selected candidate picture is used as a target picture.

3. The method according to claim 1, characterized in that The target promotion object provided by the target user is determined to include: Providing object prompt information of at least one promotion object corresponding to the target user on the user interface; In response to the object selection operation of the target user, a selected target promotion object is determined.

4. The method according to claim 3, characterized in that Also includes: In response to an adjustment operation on the at least one promotion object, displaying an object list in the user interface; The at least one promotion object is updated according to at least one object selected by the target user from the object list.

5. The method according to claim 1, characterized in that Also includes: In response to a picture selection operation triggered by the target user for any promotional picture, saving the selected promotional picture into the delivery list of the target object; Displaying, on the user interface, a delivery list corresponding to at least one promotion object; In response to the picture selection operation for the delivery list, determining at least one selected target promotion picture; A promotion request is generated in combination with at least one target promotion picture corresponding to the at least one promotion object; the promotion request is used to instruct to perform an object promotion operation in combination with at least one target promotion picture corresponding to the at least one promotion object.

6. The method according to claim 1, characterized in that Providing at least one style of selection prompt information in the user interface includes: Providing selection prompt information of at least one style corresponding to the first processing method on the user interface.

7. A content generation method, characterized in that: include: Determine the target promotion objects provided by target users; Providing selection prompt information of at least one processing method in the user interface; In response to the method selection operation of the target user, determining the selected first processing method; Providing at least one style of selection prompt information in the user interface; In response to a style selection operation of the target user, determining a selected first style; Determine at least one promotional content that conforms to the first style and is generated according to the first processing method based on the object information of the target object; Providing content prompt information of the at least one promotional content on the user interface.

8. A method for generating an image, characterized in that: include: Determine the target audience provided by the target users; Sending a selection prompt message of at least one processing method to the user terminal; Determining a first processing method selected by the target user; Sending at least one style of selection prompt information to the user terminal; Determining a first style selected by the target user; According to the first processing manner, at least one promotional image conforming to the first style is generated based on the object information of the target object.

9. The method according to claim 8, characterized in that Also includes: Sending picture prompt information of the at least one promotional picture to the user terminal; According to the promotional picture selected by the target user, the promotional picture is saved in the delivery list corresponding to the target object; Sending a delivery list corresponding to at least one promotion object corresponding to the target user to the user terminal; Determine at least one target promotion picture selected by the target user for the at least one promotion object; An object promotion operation is performed in combination with at least one target promotion picture corresponding to the at least one promotion object.

10. The method according to claim 8, characterized in that Also includes: Filter at least one hot object that meets a first hot condition according to the interactive data generated by the object published by the online system; the interactive data includes object exposure information, object click information, object sales information, and / or object conversion information; Counting at least one hot object feature of the at least one hot object; According to the matching degree between the multiple objects corresponding to the target user and the at least one hot object feature, at least one promotion object whose matching degree meets the matching requirement is selected; Sending object prompt information of at least one promotion object to the user terminal; Determining the target object provided by the target user includes: The target object selected by the target user is determined.

11. The method according to claim 9, characterized in that Also includes: Selecting a first popularity picture that meets a second popularity condition from object pictures corresponding to similar objects of the target promotion object; Analyze and obtain a second processing method and a second style corresponding to the first hot picture; According to the second processing method, a promotional picture conforming to the second style is generated based on the object information of the target promotion object; The promotional image is saved in the delivery list corresponding to the promotion object.

12. The method according to claim 8, characterized in that The step of generating at least one promotional image conforming to the first style based on the object information of the target object according to the first processing manner includes: Calling the image generation model corresponding to the first processing method to generate at least one promotional image that conforms to the first style based on the object information of the target object; The image generation model is obtained by training with a plurality of training samples; the training samples include sample object information and sample images that conform to the sample style.

13. A content generation method, characterized in that: include: Determine the target audience provided by the target users; Sending a selection prompt message of at least one processing method to the user terminal; Determining a first processing method selected by the target user; Sending at least one style of selection prompt information to the user terminal; Determining a first style selected by the target user; According to the first processing manner, at least one promotional content conforming to the first style is generated based on the object information of the target object.

14. A computing device, characterized in that including a processing component and a storage component; The storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the image generation method as described in any one of claims 1 to 6 or the content generation method as described in claim 7 or the image generation method as described in any one of claims 8 to 12 or the content generation method as described in claim 13.

15. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, it implements the image generation method as described in any one of claims 1 to 6 or the content generation method as described in claim 7 or the image generation method as described in any one of claims 8 to 12 or the content generation method as described in claim 13.

Images