Poster generation method, server, storage medium and program product

Abstract

The invention provides a poster generation method, a server, a storage medium and a program product. The poster generation method comprises the following steps: receiving prompt information, wherein the prompt information comprises at least one keyword; determining a target image feature corresponding to the at least one keyword; determining a background picture and a decoration picture corresponding to the target image feature; and adding the background picture and the decoration picture into a poster template to generate a target poster.

Description

Technical Field

[0001] The present disclosure relates to the technical field of posters, and in particular to a poster generation method, a server, a storage medium, and a program product. Background Art

[0002] In the real estate industry, property posters are a common and intuitive way of promotion. Property posters are mainly used to display slogans, promotional pictures and property information related to properties for sale.

[0003] In the process of designing real estate posters, in order to better display different properties for sale, the staff often need to spend a lot of energy and time to conceive and design real estate posters, which takes up the staff's manpower and time costs. Moreover, the background pictures and decorative pictures in the real estate posters made by the staff may not be able to well reflect the style and theme of the property for sale.

[0004] Therefore, how to automatically generate real estate posters that match the style and theme of the real estate for sale has become a problem that needs to be solved urgently. Summary of the invention

[0005] The present disclosure provides a poster generation method, a server, a storage medium and a program product.

[0006] According to a first aspect of the present disclosure, a poster generation method is provided, the method comprising: receiving prompt information, the prompt information comprising at least one keyword; determining a target image feature corresponding to the at least one keyword; determining a background picture and a decorative picture corresponding to the target image feature; and adding the background picture and the decorative picture to a poster template to generate a target poster.

[0007] According to at least one embodiment of the poster generation method of the present disclosure, determining the target image features corresponding to at least one keyword includes: using a poster generation model to determine the target image features corresponding to at least one keyword, the poster generation model is a model that has learned to obtain image features based on keywords.

[0008] According to at least one embodiment of the poster generation method of the present disclosure, background pictures and decorative pictures corresponding to target image features are determined, including: determining the background picture corresponding to the target image feature from multiple background pictures; determining the decorative picture corresponding to the target image feature from multiple decorative pictures.

[0009] According to the poster generation method of at least one embodiment of the present disclosure, a background image and a decorative image are added to a poster template to generate a target poster, including: determining a poster template based on at least one keyword, the poster template being provided with a background placeholder frame and a decorative placeholder frame; in the background placeholder frame and the decorative placeholder frame, the background image and the decorative image are added in sequence to generate the target poster.

[0010] According to at least one embodiment of the poster generation method of the present disclosure, a poster template is determined based on at least one keyword, including: using a poster generation model to determine a target layout feature corresponding to at least one keyword, the poster generation model is a model that has learned to obtain layout features based on keywords; and determining a poster template corresponding to the target layout feature.

[0011] According to the poster generation method of at least one embodiment of the present disclosure, after adding the background image and the decorative image to the poster template to generate the target poster, the method also includes: using a poster generation model to determine the poster promotional information corresponding to at least one keyword, the poster generation model is a model that has learned to obtain poster promotional information based on keywords; adding the poster promotional information to the title placeholder box of the target poster.

[0012] According to the poster generation method of at least one embodiment of the present disclosure, after adding the background image and the decorative image to the poster template to generate the target poster, the method further includes: obtaining business information; and adding the business information to the text placeholder box of the target poster.

[0013] According to the poster generation method of at least one embodiment of the present disclosure, the business information includes text information; or, the business information includes picture information; or, the business information includes text information and picture information.

[0014] According to the poster generation method of at least one embodiment of the present disclosure, before receiving the prompt information, the method also includes: obtaining multiple background pictures and multiple decorative pictures; using the poster generation model to analyze the multiple background pictures to obtain image features corresponding to the multiple background pictures; using the poster generation model to analyze the multiple decorative pictures to obtain image features corresponding to the multiple decorative pictures.

[0015] According to at least one embodiment of the poster generation method of the present disclosure, multiple background images and multiple decorative images are obtained, including: receiving at least one prompt word; using a first generation model to generate multiple background images related to the at least one prompt word, the first generation model is a model that has learned to obtain background images based on the prompt words; using a second generation model to generate multiple decorative images related to the at least one prompt word, the second generation model is a model that has learned to obtain decorative images based on the prompt words.

[0016] According to a second aspect of the present disclosure, a server is provided, comprising: a memory storing execution instructions; and a processor executing the execution instructions stored in the memory, so that the processor executes the poster generation method of any embodiment of the present disclosure.

[0017] According to a third aspect of the present disclosure, a readable storage medium is provided, in which execution instructions are stored. When the execution instructions are executed by a processor, they are used to implement the poster generation method of any embodiment of the present disclosure.

[0018] According to a fourth aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the poster generation method of any embodiment of the present disclosure is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings illustrate exemplary embodiments of the present disclosure and together with the description serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0020] Figure 1 An application scenario of a poster generation method according to an embodiment of the present disclosure is shown.

[0021] Figure 2 Shown is a schematic diagram of a poster template 10 .

[0022] Figure 3 Shown is a schematic diagram of a target poster 20 .

[0023] Figure 4 A schematic diagram of the overall process of a poster generating method M100 according to an embodiment of the present disclosure is shown.

[0024] Figure 5 A schematic diagram of the overall process of a poster generating method M200 according to another embodiment of the present disclosure is shown.

[0025] Figure 6 A schematic diagram of the overall process of a poster generating method M300 according to yet another embodiment of the present disclosure is shown.

[0026] Figure 7 It is a schematic block diagram of the structure of a server according to an embodiment of the present disclosure.

[0027] Figure 8 It is a schematic block diagram of the structure of a server 3000 according to another embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] The present disclosure is further described in detail below in conjunction with the accompanying drawings and examples. It is understood that the specific examples described herein are only used to explain the relevant content, rather than to limit the present disclosure. It should also be noted that, for ease of description, only the parts related to the present disclosure are shown in the accompanying drawings.

[0029] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure can be combined with each other. The technical solution of the present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0030] Currently, in the process of designing real estate posters, staff are not only required to manually design the real estate posters, but also required to actively find background pictures and decorative pictures that match the style and theme of the property for sale.

[0031] This method not only consumes the staff's time and energy, but also the background pictures and decorative pictures selected by the staff may not necessarily be in line with the style and theme of the property for sale.

[0032] To this end, the present disclosure proposes a poster generation method, which can not only save the time and energy of the staff, but also ensure that the background image and decorative image in the generated real estate poster are consistent with the style and theme of the real estate for sale.

[0033] In order to facilitate understanding of the contents of the embodiments of the present disclosure, some technical terms used in the embodiments of the present disclosure are described below.

[0034] Real estate poster: a visual marketing tool used to advertise and promote real estate projects. It attracts the attention of potential buyers and investors through eye-catching images, concise and powerful copywriting and key information display.

[0035] Background image in real estate poster: usually set at the bottom of the real estate poster, providing a visual foundation for the entire poster and setting the overall atmosphere and style. It can be a single color, gradient color or picture, designed to enhance the expression of the theme.

[0036] Decorative images in real estate posters: elements used to enhance visual effects and attract attention. They can include icons, borders, patterns or small illustrations related to the property, aiming to enhance the aesthetics of the poster and the hierarchy of information.

[0037] Poster template: refers to the layout framework of the poster, which defines the arrangement of background images, decorative images and text information. Poster templates usually contain title placeholders, background placeholders, decorative placeholders and text placeholders. The title placeholder is used to carry text information, the background placeholder is used to carry background images, the decorative placeholder is used to carry decorative images, and the text placeholder is used to carry business information.

[0038] LoRA: (Low-Rank Adaptation) is a model fine-tuning technique that allows the model to be quickly and effectively adjusted to new tasks or data sets while keeping most of the parameters of the pre-trained model unchanged. This method is particularly suitable for large pre-trained models because it can reduce the computing resources and time required for fine-tuning.

[0039] Figure 1 The application scenario of the poster generation method according to one embodiment of the present disclosure is shown. In the application scenario, a server 101 , a database 102 , a network 103 , a mobile phone 104 and a computer 105 are mainly shown. Both the mobile phone 104 and the computer 105 can communicate with the server 101 through the network 103 .

[0040] exist Figure 1 In the example shown, the server 101 can provide a service of generating posters for the mobile phone 104 and the computer 105 .

[0041] For example, the staff can use the mobile phone 104 to send a prompt message to the server 101, and the prompt message is: "I want to generate a real estate poster for low-price promotion."

[0042] After the server 101 receives the prompt information, the server 101 determines the keyword in the prompt information, that is, the keyword is "low price promotion".

[0043] Then, the server 101 uses the trained poster generation model to identify the meaning of the keyword "low-price promotion" and determines the image feature A of the background image and the image feature B of the decorative image corresponding to the keyword "low-price promotion".

[0044] The image feature A of the background image includes the color, style and theme of the background image, etc. Specifically, the color of the background image is red, the style of the background image is simple, and the theme of the background image is special offer.

[0045] The image feature B of the decorative picture includes the color, style and theme of the decorative picture, etc. Specifically, the color of the decorative picture is red, the style of the decorative picture is simple, and the theme of the decorative picture is special offer.

[0046] After server 101 determines image feature A of the background image and image feature B of the decorative image, server 101 finds background image X1 matching image feature A of the background image in database 102 and finds decorative image Y1 matching image feature B of the decorative image in database 102.

[0047] Please refer to Table 1 and Table 2. Table 1 shows the mapping relationship between the background pictures and image features stored in the database 102, and Table 2 shows the mapping relationship between the decoration pictures and image features stored in the database 102.

[0048] Table 1 Table 2 After server 101 obtains background image X1 and decorative image Y1, server 101 can use the poster generation model to generate poster promotional information S1 according to the keyword "low price promotion". For example, the poster promotional information S1 generated by server 101 using the poster generation model is "Limited time special offer, super value purchase".

[0049] If the staff also sends the business information H1 to the server 101 using the mobile phone 104 , the server 101 will add the background image X1 , the decorative image Y1 , the poster promotion information S1 and the business information H1 to the pre-generated poster template 10 to generate the target poster 20 .

[0050] See also Figure 2 As shown, Figure 2 Shown is a schematic diagram of a poster template 10. Figure 2 In the figure, the poster template 10 includes a background placeholder frame 11, a title placeholder frame 12, a decoration placeholder frame 13 and a text placeholder frame 14.

[0051] Please combine Figure 1 , Figure 2 As shown in Table 1 and Table 2, the background placeholder 11 is used to carry the background image X1. The title placeholder 12 is used to carry the poster promotion information S1. The decoration placeholder 13 is used to carry the decoration image Y1. The text placeholder 14 is used to carry the business information H1 sent by the staff using the mobile phone 104.

[0052] See also Figure 3 As shown, Figure 3 Shown is a schematic diagram of a target poster 20. Figure 3 In the example, the background placeholder frame 11 of the target poster 20 already carries the background image X1. Since the background image X1 is a colored image, it is not displayed in the background placeholder frame 11. Figure 3 The title placeholder frame 12 of the target poster 20 already carries the poster promotion information S1, namely "Limited time special offer, super value purchase". The decoration placeholder frame 13 of the target poster 20 already carries the decoration picture Y1. The text placeholder frame 14 of the target poster 20 already carries the business information H1, wherein the business information H1 includes picture information and text information.

[0053] Please combine Figures 1 to 3As shown, after the server 101 generates the target poster 20, the server 101 sends the target poster 20 to the mobile phone 104 through the network 103. The user can see the target poster 20 sent by the server 101 through the mobile phone 104. If the user is satisfied, the user can use the target poster 20. If the user is not satisfied, the user can use the mobile phone 104 to send new prompt information to the server 101 again, so that the server 101 generates a new poster according to the new prompt information.

[0054] Figure 4 FIG. 1 is a schematic diagram showing the overall process of a poster generation method M100 according to an embodiment of the present disclosure. Figure 4 The method shown includes steps S110 to S140. The method can be Figure 1 The server 101 shown is executed.

[0055] Specifically, Figure 4 The methods shown include: S110, receiving prompt information.

[0056] The prompt information includes at least one keyword. The prompt information can be a piece of text information input by the user, and the prompt information is used to explain the characteristics, theme or type of the poster that the user wants.

[0057] After the server receives the prompt information, the server will extract valid keywords from the prompt information.

[0058] For example, assuming that the prompt information input by the user is: "I want to generate a real estate poster with a low price promotion", the server can extract the effective keyword "low price promotion" from the prompt information.

[0059] Of course, the server can use the trained poster generation model to identify the prompt information and use the poster generation model to extract effective keywords from the prompt information. For example, the server can use a deep learning model such as a convolutional neural network to train the poster generation model.

[0060] S120: Determine a target image feature corresponding to at least one keyword.

[0061] The server may pre-establish a mapping relationship between keywords and image features, and store the established mapping relationship between keywords and image features in a database.

[0062] For example, image features may include the color of the picture, the style of the picture, and the theme of the picture.

[0063] Of course, the server can use a trained poster generation model to determine the target image feature corresponding to at least one keyword, wherein the poster generation model is a model that has learned to obtain image features based on keywords.

[0064] S130: Determine a background image and a decoration image corresponding to the target image features.

[0065] After determining the target image features, the server will determine the background image and the decoration image corresponding to the target image features in the database.

[0066] The database pre-stores mapping relationships between multiple background images and image features, and mapping relationships between multiple decoration images and image features. The server can use the mapping relationships in the database to determine the background images and decoration images corresponding to the target image features.

[0067] Specifically, the server may determine a background image corresponding to the target image feature from a plurality of background images in the database, and determine a decoration image corresponding to the target image feature from a plurality of decoration images in the database.

[0068] S140, adding the background image and the decorative image to the poster template to generate a target poster.

[0069] Among them, after the server determines the background image and the decorative image, the server will add the background image and the decorative image to the poster template to generate the target poster.

[0070] Specifically, the server determines a poster template based on at least one keyword, wherein the poster template is provided with a background placeholder frame and a decoration placeholder frame. Then, the server sequentially adds a background image and a decoration image to the background placeholder frame and the decoration placeholder frame to generate a target poster.

[0071] In the process of the server determining the poster template based on at least one keyword, the server may determine the target layout feature corresponding to the at least one keyword using a poster generation model, wherein the poster generation model is a model that has learned to obtain layout features based on keywords. Then, the server determines the poster template corresponding to the target layout feature.

[0072] exist Figure 4 In the example shown, after the server receives the prompt information input by the user, the server can automatically generate a poster based on the keywords in the prompt information, which not only saves the staff's time and energy, but also ensures that the background image and decorative images in the generated poster are in line with the style and theme of the property for sale.

[0073] exist Figure 4After S140, the server may also determine the poster promotion information corresponding to at least one keyword using a poster generation model, where the poster generation model is a model that has learned to obtain poster promotion information based on keywords. Then, the server may add the poster promotion information to the title placeholder of the target poster.

[0074] Among them, the method provided by the present disclosure can also use keywords to generate poster promotion information for the target poster, and add the poster promotion information to the target poster. Therefore, there is no need for the staff to design it personally, nor is there any need for the staff to input the poster promotion information into the target poster, so the labor cost and time cost are saved.

[0075] exist Figure 4 After S140 shown, if there is business information, the server can also obtain the business information, and then add the business information to the text placeholder box of the target poster to automatically add the business information to the target poster.

[0076] The business information may be text information, or picture information, or may include text information and picture information.

[0077] Please combine Figure 3 As shown, in Figure 3 The text placeholder frame 14 of the target poster 20 carries business information H1, which includes picture information and text information.

[0078] Figure 5 FIG. 2 is a schematic diagram showing the overall process of a poster generation method M200 according to another embodiment of the present disclosure. Figure 5 The method shown includes steps S210 to S230, Figure 5 Steps S210 to S230 in Figure 4 Before step S110. The method may be Figure 1 The server 101 shown is executed.

[0079] Specifically, Figure 5 The methods shown include: S210: Receive at least one prompt word.

[0080] S220: Generate multiple background images related to at least one prompt word using the first generation model.

[0081] Among them, the first generation model is a model that has learned to obtain a background image based on a prompt word.

[0082] S230: Generate multiple decorative pictures related to at least one prompt word using a second generation model.

[0083] Among them, the second generation model is a model that has learned to obtain decorative pictures based on prompt words.

[0084] exist Figure 5 In the example shown, in order to obtain enough background images and decorative images, the staff needs to first collect some background images and decorative images, and input the collected background images and decorative images into the server.

[0085] For example, the staff first collects 100 background images and 100 decoration images, and then the staff inputs the 100 background images and 100 decoration images into the server.

[0086] Then, the server inputs the 100 background images and the text information corresponding to the 100 images into the first generation model, so that the first generation model can learn the intrinsic connection between the background images and the text information.

[0087] The server then inputs the 100 decorative pictures and the text information corresponding to the 100 pictures into the second generation model, so that the second generation model can learn the intrinsic connection between the decorative pictures and the text information.

[0088] Among them, the first generation model and the second generation model can both be LoRA models.

[0089] After the server completes training of the first generation model and the second generation model, the staff will write some prompt words and input these prompt words into the first generation model and the second generation model of the server.

[0090] When the first generation model receives the prompt word, the first generation model may generate a plurality of background images related to the prompt word.

[0091] For example, assuming there are 10 prompt words, the first generation model can generate 100 background images for each prompt word, then the first generation model can generate 1000 background images for the 10 prompt words.

[0092] When the second generation model receives the prompt word, the second generation model can generate multiple decorative pictures related to the prompt word.

[0093] For example, assuming there are 10 prompt words, the second generation model can generate 100 decorative images for each prompt word, then the second generation model can generate 1000 decorative images for the 10 prompt words.

[0094] exist Figure 5In the example shown, the server can use the first generation model to generate multiple background images related to the prompt word, and use the second generation model to generate multiple decorative images related to the prompt word, thereby obtaining multiple background images and multiple decorative images, thereby expanding the image resources that can be used on the poster.

[0095] Figure 6 FIG. 2 is a schematic diagram showing the overall process of a poster generation method M300 according to another embodiment of the present disclosure. Figure 6 The method shown includes steps S310 to S330, Figure 6 Steps S310 to S330 in Figure 4 Before step S110. The method may be Figure 1 The server 101 shown is executed.

[0096] Specifically, Figure 6 The methods shown include: S310: Acquire multiple background images and multiple decoration images.

[0097] S320, analyzing multiple background images using a poster generation model to obtain image features corresponding to the multiple background images; S330. Analyze multiple decorative pictures using the poster generation model to obtain image features corresponding to the multiple decorative pictures.

[0098] exist Figure 6 In the example shown, in order to enable the poster generation model to determine the background image and the decorative image based on the image features, the server also needs to train the poster generation model.

[0099] After the server obtains the multiple background images generated by the first generation model and the multiple decorative images generated by the second generation model, the server will input the multiple background images generated by the first generation model into the poster generation model, so that the poster generation model analyzes the multiple background images to obtain image features corresponding to the multiple background images.

[0100] Furthermore, the server inputs the multiple decorative images generated by the second generation model into the poster generation model, so that the poster generation model analyzes the multiple decorative images to obtain image features corresponding to the multiple decorative images.

[0101] The server will store the image features corresponding to the multiple background images and the image features corresponding to the multiple decorative images output by the poster generation model in the database. At this point, the poster generation model already knows which background images and decorative images exist in the database, as well as the image features corresponding to each background image and the image features corresponding to each decorative image.

[0102] From now on, the poster generation model in the server can determine the background image and decorative image based on image features.

[0103] See also Figure 7 As shown, Figure 7 It is a schematic block diagram of the structure of a server according to an embodiment of the present disclosure.

[0104] like Figure 7 As shown, the server includes: The receiving module 110 is used to receive prompt information, where the prompt information includes at least one keyword.

[0105] The determination module 120 is used to determine a target image feature corresponding to at least one keyword, and to determine a background image and a decoration image corresponding to the target image feature.

[0106] The generating module 130 is used to add the background image and the decorative image to the poster template to generate the target poster.

[0107] The server mentioned above may be in the form of computer software, and each module of the server mentioned above may be implemented by a computer software module.

[0108] The implementation process of the functions and effects of each module in the above-mentioned server is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0109] See also Figure 8 As shown, Figure 8 It is a schematic block diagram of the structure of a server 3000 according to another embodiment of the present disclosure.

[0110] The hardware structure of the server 3000 can be implemented using a bus architecture. The bus architecture can include any number of interconnected buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus 3100 connects various circuits including one or more processors 3200, memory 3300, and / or hardware modules together. The bus 3100 can also connect various other circuits 3400 such as peripherals, voltage regulators, power management circuits, external antennas, etc.

[0111] The bus 3100 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. A bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one connecting line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0112] The present disclosure also provides a readable storage medium, in which a computer program is stored, and the computer program is used to implement the above method when executed by a processor. "Readable storage medium" can be any device that can contain, store, communicate, propagate or transmit a program for use in an instruction execution system, device or equipment or in combination with these instruction execution systems, devices or equipment. More specific examples of readable storage media include the following: an electrical connection portion (electronic device) with one or more wirings, a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM), etc.

[0113] The present disclosure also provides a computer program product. The method of the present disclosure can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed, the process or function of the present disclosure is executed in whole or in part.

[0114] The computer program or instructions may be stored in a readable storage medium or transmitted from one readable storage medium to another readable storage medium, for example, the computer program or instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The readable storage medium may be any available medium that can be accessed or a data storage device such as a server, data center, etc. that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it may also be an optical medium, such as a digital video disk; it may also be a semiconductor medium, such as a solid state drive. The computer readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0115] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0119] In the description of this specification, the description with reference to the terms "one embodiment / method", "some embodiments / methods", "example", "specific example", or "some examples" etc. means that the specific features, structures, or characteristics described in conjunction with the embodiment / method or example are included in at least one embodiment / method or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment / method or example. Moreover, the specific features, structures, or characteristics described may be combined in a suitable manner in any one or more embodiments / methods or examples. In addition, those skilled in the art may combine and combine different embodiments / methods or examples described in this specification and features of different embodiments / methods or examples, unless they are contradictory.

[0120] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0121] Those skilled in the art should understand that the above embodiments are only for the purpose of clearly illustrating the present disclosure, and are not intended to limit the scope of the present disclosure. For those skilled in the art, other changes or modifications may be made based on the above disclosure, and these changes or modifications are still within the scope of the present disclosure.

Claims

1. A poster generation method, characterized in that: include: receiving prompt information, wherein the prompt information includes at least one keyword; determining a target image feature corresponding to the at least one keyword; Determine a background image and a decoration image corresponding to the target image feature; Add the background image and the decorative image to a poster template to generate a target poster.

2. The method according to claim 1, characterized in that Determining a target image feature corresponding to the at least one keyword includes: A poster generation model is used to determine target image features corresponding to the at least one keyword, wherein the poster generation model is a model that has learned to obtain image features based on keywords.

3. The method according to claim 1, characterized in that Determining a background image and a decoration image corresponding to the target image feature includes: Determining a background picture corresponding to the target image feature from a plurality of background pictures; A decorative picture corresponding to the target image feature is determined from a plurality of decorative pictures.

4. The method according to claim 1, characterized in that Adding the background image and the decorative image to a poster template to generate a target poster includes: Determine a poster template based on the at least one keyword, wherein the poster template is provided with a background placeholder frame and a decoration placeholder frame; In the background placeholder frame and the decoration placeholder frame, the background image and the decoration image are added in sequence to generate a target poster.

5. The method according to claim 4, characterized in that Determining a poster template based on the at least one keyword includes: Determine the target layout feature corresponding to the at least one keyword using a poster generation model, wherein the poster generation model is a model that has learned to obtain layout features based on keywords; A poster template corresponding to the target layout feature is determined.

6. The method according to claim 1, characterized in that After adding the background image and the decorative image to the poster template to generate the target poster, the method further includes: Determine the poster promotion information corresponding to the at least one keyword using a poster generation model, wherein the poster generation model is a model that has learned to obtain poster promotion information based on keywords; The poster promotional information is added to the title placeholder box of the target poster.

7. The method according to claim 1, characterized in that Optionally, after adding the background image and the decorative image to the poster template to generate the target poster, the method further includes: acquiring business information; adding the business information to the text placeholder box of the target poster; Optionally, the business information includes text information; or, the business information includes picture information; or, the business information includes text information and picture information. Optionally, before receiving the prompt information, the method further includes: acquiring a plurality of background images and a plurality of decorative images; analyzing the plurality of background images using a poster generation model to obtain image features corresponding to the plurality of background images; analyzing the plurality of decorative images using the poster generation model to obtain image features corresponding to the plurality of decorative images, Optionally, obtaining multiple background images and multiple decorative images includes: receiving at least one prompt word; using a first generation model to generate multiple background images related to the at least one prompt word, the first generation model is a model that has learned to obtain background images based on prompt words; using a second generation model to generate multiple decorative images related to the at least one prompt word, the second generation model is a model that has learned to obtain decorative images based on prompt words.

8. A server, characterized in that: include: a memory storing a computer program; as well as A processor, wherein the processor executes the computer program stored in the memory, so that the processor executes the poster generation method according to any one of claims 1 to 7.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program is used to implement the poster generation method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the poster generating method according to any one of claims 1 to 7 is implemented.

Images