Picture generation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a pictorial generation method, device and equipment and a storage medium, and the generation method comprises the steps: receiving a target pictorial theme input by a user; obtaining a target pictorial template corresponding to the target pictorial subject, wherein a target keyword attribute, a target text writing specification and a target platform publishing specification corresponding to the target pictorial subject are set in the target pictorial template; extracting a target text keyword corresponding to the target keyword attribute in the target pictorial theme; filling the target text keyword into a target pictorial template, and inputting the target pictorial template into an artificial intelligence generation content model to generate a target pictorial text; and placing the target pictorial text in a preset pictorial background, and generating a target pictorial which needs to be published on a target pictorial platform. The problems that in the prior art, a pictorial manufacturing mode is high in manufacturing cost and low in manufacturing cost efficiency, and large-scale mass production is difficult are solved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for generating a pictorial. Background Art

[0002] In recent years, with the rapid popularity of streaming media, users need to make pictorials and publish them on relevant streaming media platforms so that users can spread the content they need. For example, in the field of financial technology, banks need to publish pictorials (posters) of relevant financial projects on their online banks to attract consumers' attention to relevant financial projects.

[0003] In traditional pictorial creation, creators usually need to manually write the copy of the pictorial, or use manual words to extract the text input by the creator to form the copy. In addition, the above schemes have very high threshold requirements for creators. Creators need to independently design the entire wording, then select the cover of the pictorial, and use professional tools to generate the corresponding pictorial.

[0004] Obviously, the above scheme is too dependent on manual work, which will make the production cost of the pictorial high and the production efficiency low, and manual design is difficult to adapt to the needs of large-scale and efficient creation. In summary, there is an urgent need in the prior art for a pictorial generation scheme that can overcome the technical problems of the above scheme. Summary of the invention

[0005] The present invention provides a method, device, computer equipment and storage medium for generating a pictorial, so as to solve the problems of high production cost, low production cost efficiency and difficulty in large-scale mass production in the prior art pictorial production method.

[0006] In a first aspect, a method for generating a pictorial is provided, comprising:

[0007] Receive the target pictorial theme input by the user;

[0008] Acquire a target pictorial template corresponding to the target pictorial theme, wherein the target pictorial template is provided with target keyword attributes, target text writing specifications, and target platform publishing specifications corresponding to the target pictorial theme;

[0009] Extracting target text keywords corresponding to the target keyword attributes in the target pictorial theme;

[0010] Filling the target text keywords into the target pictorial template, and inputting the target pictorial template into an artificial intelligence generated content model to generate a target pictorial text;

[0011] The target pictorial text is placed in a preset pictorial background to generate a target pictorial that needs to be published on a target pictorial platform.

[0012] In a second aspect, a device for generating a pictorial is provided, comprising:

[0013] A receiving module, used for receiving a target pictorial theme input by a user;

[0014] An acquisition module, used for acquiring a target pictorial template corresponding to the target pictorial theme, wherein the target pictorial template is provided with target keyword attributes, target text writing specifications and target platform publishing specifications corresponding to the target pictorial theme;

[0015] An extraction module, used for extracting target text keywords corresponding to the target keyword attributes in the target pictorial theme;

[0016] A first generating module is used to fill the target text keywords into the target pictorial template, and input the target pictorial template into an artificial intelligence generated content model to generate a target pictorial text;

[0017] The second generating module is used to place the target pictorial text in a preset pictorial background to generate a target pictorial that needs to be published on a target pictorial platform.

[0018] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for generating a pictorial when executing the computer program.

[0019] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for generating a pictorial are implemented.

[0020] In the scheme implemented by the above-mentioned pictorial generation method, the creator (i.e., the user) only needs to input the target pictorial theme, and the server can obtain the target pictorial template corresponding to the target pictorial theme, and extract the target text keywords in the target pictorial theme corresponding to the target keyword attributes in the target pictorial template. After inputting the obtained target text keywords into the target pictorial template, the target pictorial template has the target keywords, target text writing specifications, and target platform publishing specifications for generating the target pictorial theme. In this way, when the target pictorial template is input into the artificial intelligence generated content model, the artificial intelligence generated content model can generate the target pictorial text based on the target keywords, target text writing specifications, and target platform publishing specifications in the target pictorial template.

[0021] In summary, the present invention only requires the user to input the target pictorial theme, and the server can generate the complete pictorial text required by the user. In this way, the pictorial can be generated by simply placing the pictorial text on the pictorial background sheet, thereby avoiding the problem in the prior art that the user needs to input all the content when generating the pictorial text, resulting in high production cost, low production cost efficiency and difficulty in large-scale mass production of the pictorial production method in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0023] Figure 1 is a schematic diagram of an application environment of a method for generating a pictorial in an embodiment of the present invention;

[0024] Figure 2 is a flow chart of a method for generating a pictorial in one embodiment of the present invention;

[0025] Figure 3 yes Figure 2 A schematic flow chart of a specific implementation of step S30;

[0026] Figure 4 is a structural schematic diagram of a pictorial generating device in one embodiment of the present invention;

[0027] Figure 5 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0028] Figure 6 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] The method for generating a pictorial provided by the embodiment of the present invention can be applied in the following aspects: Figure 1In an application environment, the client communicates with the server through a network. The server can receive a target pictorial theme input by a user through the client; obtain a target pictorial template corresponding to the target pictorial theme, wherein the target pictorial template is provided with a target keyword attribute, a target text writing specification, and a target platform publishing specification corresponding to the target pictorial theme; extract the target text keyword corresponding to the target keyword attribute in the target pictorial theme; fill the target text keyword into the target pictorial template, and input the target pictorial template into an artificial intelligence generated content model to generate a target pictorial text; place the target pictorial text in a preset pictorial background to generate a target pictorial that needs to be published on the target pictorial platform. Among them, the client can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server can be implemented with an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0031] See also Figure 2 As shown, Figure 2 A flowchart of a method for generating a pictorial provided by an embodiment of the present invention includes the following steps:

[0032] S10: receiving a target pictorial theme input by a user.

[0033] It should be noted that the target pictorial theme in this step is the relevant theme of the target pictorial that the user ultimately wants to generate, and the theme can be set according to the specific needs of the user during application. For example, if the user wants to generate a target pictorial that is used to promote a financial activity where travel insurance with a 30% discount is given when the amount exceeds a certain amount, the target pictorial theme entered by the user can be "Travel insurance with a 30% discount when the amount exceeds a preset amount".

[0034] It should be noted that the user may input the target pictorial theme in any feasible manner, for example, a pictorial theme input box may be set on the display interface of the client, and the user may manually input the target pictorial theme in the pictorial theme input box, or the user may input the target pictorial theme by voice.

[0035] In one embodiment of the present invention, step S10 may include the following steps:

[0036] Step S11, in response to a user's selection instruction for a target topic type, displaying a control of topic keywords corresponding to the target topic type on a user interface;

[0037] Step S12, in response to a selection instruction of a control for the subject keyword by the user, receiving a subject keyword selected by the user;

[0038] Step S13, inputting the topic keywords into a large language model to generate the target pictorial topic.

[0039] Regarding steps S11 to S13, when receiving the target pictorial theme input by the user, the user may be guided to input the desired target pictorial theme step by step.

[0040] In step S11, a control for selecting a subject type may be pre-set on the user interface of the client, so that the user can select the desired target subject type by triggering the corresponding control of the desired target subject type. After receiving the user's selection instruction for the target subject type, the server may display the set subject keyword control corresponding to the target subject type in the user interface. It should be noted that the subject keyword corresponding to the target subject type may be set according to actual needs. For example, if the target subject type is vehicle insurance, the corresponding subject keyword may be liability insurance, collision insurance, comprehensive insurance, third party liability insurance, and full insurance, etc.

[0041] Thus, in step S12, the user can trigger the control corresponding to the selected subject keyword and send a selection instruction for the subject keyword to the server through the client, and the server determines the subject keyword selected by the user according to the selection instruction.

[0042] It should be noted that the large language model in step S13 is a language model that can convert topic keywords into complete topics with natural language attributes, that is, the final complete topic can fully reflect the topic keywords. For example, the large language model in step S13 can be GPT, BERT or T5, etc. As a specific example, for example, the target topic type selected by the user can be vehicle insurance, and the topic keywords corresponding to the selected vehicle insurance are collision insurance and insurance amount. For these two topic keywords, the target pictorial theme generated by the large language model can be "Vehicle collision insurance protection, insurance amount up to xx amount".

[0043] Optionally, after receiving the topic keyword selected by the user, the server can also display the sub-topic keyword control corresponding to the topic keyword in the user interface, so that the user can convey the sub-topic keyword he wants to select to the server by triggering the sub-topic keyword control. As a specific example, the topic keywords corresponding to vehicle insurance are collision insurance and insurance amount. The insurance amount can correspond to multiple sub-topic keywords, such as 5,000 yuan, 10,000 yuan, and 20,000 yuan. If 10,000 yuan is selected, the pictorial theme generated by the large language model can be "Vehicle collision insurance protection, insurance amount up to 10,000 yuan".

[0044] It can be understood that, by utilizing steps S11 to S13, when the user does not know what pictorial theme to input, the user can be helped to obtain the pictorial theme that the user wants step by step, thereby improving the user experience.

[0045] S20: Acquire a target pictorial template corresponding to the target pictorial theme.

[0046] The target pictorial template is provided with target keyword attributes, target text writing specifications and target platform publishing specifications corresponding to the target pictorial theme.

[0047] It should be noted that in this step, the target keyword attributes are the required keyword attributes of the target pictorial text that the user wants to generate, the target text writing specifications are the format requirements of the target pictorial text that the user ultimately needs to obtain, and the target platform publishing specifications are the format requirements for the pictorial text of the platform where the target text needs to be published.

[0048] It should be noted that the correspondence between the pictorial theme and the pictorial template can be set according to the specific needs of the application. For example, the pictorial theme can be analyzed to extract the main requirements of the pictorial theme, and the pictorial template can be set according to the main requirements. For example, the pictorial theme is "a brief introduction to the vehicle insurance business of xx company in the third quarter". After analyzing the pictorial theme, it is known that the final generated pictorial copy needs to be "brief", so the target text writing specification in the pictorial template formed can be "writing a text summary, and the resulting text summary is required to be no more than 300 words, and it is required to be concise, brilliant and easy to understand". Based on the need to write a text summary, the target keyword attributes can be set to be the target object of the theme, the action performed by the theme, and the time when the theme is mentioned.

[0049] In one embodiment of the present invention, step S20 may include the following steps.

[0050] Step S21, analyzing the pictorial application scenario corresponding to the target pictorial theme;

[0051] Step S22, obtaining target text writing specifications, target keyword attributes and target platform publishing specifications corresponding to the pictorial application scenario;

[0052] Step S23, placing the target text writing specification, target keyword attributes and the target platform publishing specification in a blank template to form a target pictorial template.

[0053] It should be noted that, in step S21, the pictorial application scenario corresponding to the pictorial theme can be obtained based on the core demand analysis of the pictorial theme. For example, if the core demand of the pictorial theme is "a brief introduction to xxx", the pictorial application scenario can be "writing a summary of xxx", and if the core demand of the pictorial theme is "a detailed introduction to xxx", the pictorial application scenario can be "writing specific information on various dimensions of xxx".

[0054] In step S22, the target text writing specification, target keyword attributes and the target platform publishing specification corresponding to any pictorial application scenario can be specifically set as needed. For example, if the pictorial application scenario is "writing a summary for xxx", the text writing specification can be "writing a text summary, and the text summary required to be obtained is not more than 300 words, and it is required to be concise, brilliant and easy to understand", the keyword attributes can be "the theme is targeted at the object, the theme performs the action and the time when the theme is mentioned", and the platform publishing specification is the publishing specification of the pictorial publishing platform; if the pictorial application scenario is "writing specific information on each dimension of xxx", the text writing specification can be "detailed description of the target, and a specific introduction to the classification of the target, the fields involved and the impact brought about", the keyword attributes can be "the theme is targeted at the object, the theme dimension information and the theme performs the action", and the platform publishing specification is the publishing specification of the pictorial publishing platform.

[0055] It can be understood that through steps S21-S23, the pictorial application scenario can be determined by determining the pictorial theme, and the corresponding pictorial template can be obtained according to the pictorial application scenario, so that one type of pictorial application scenario can have a corresponding type of pictorial template. This can greatly save resources compared to one pictorial theme corresponding to one pictorial template.

[0056] S30: extracting target text keywords corresponding to the target keyword attributes in the target pictorial theme.

[0057] It should be noted that the method of extracting the target text keywords corresponding to the target keyword attributes in the target pictorial theme can be any feasible method. As a specific example, the target pictorial theme can be segmented, and the words obtained by the segmentation can be matched with the target keyword attributes to obtain the target text keywords. For example, the target pictorial theme is "a brief introduction to the vehicle insurance business of xx company in the third quarter", and the result of the segmentation of the target pictorial theme is "a brief introduction, xx company, third quarter, vehicle insurance business", and the target keyword attributes are "the object of the theme, the action performed by the theme, and the time mentioned by the theme". By matching the result obtained by the segmentation with the target keyword, it can be obtained that the target keywords corresponding to the object of the theme are "xx company" and "vehicle insurance business", the action performed by the theme is "a brief introduction", and the time mentioned by the theme is "the third quarter".

[0058] In some embodiments of the invention, Figure 3 In S30, the following steps S31-S34 are specifically included:

[0059] Step S31, extracting keywords from the pictorial theme and analyzing to obtain keyword attributes corresponding to the keywords;

[0060] Step S32, associating the keyword attribute with the corresponding keyword to form a keyword key-value pair;

[0061] Step S33, obtaining the target keyword attribute corresponding to the first slot preset in the target pictorial template;

[0062] Step S34: Fill the first slot with the value corresponding to the target keyword attribute in the keyword key-value pair.

[0063] The key in the keyword key-value pair is the keyword attribute, and the value in the key-value pair is the keyword.

[0064] It should be noted that the method of extracting keywords of the pictorial theme in step S31 can be any achievable method. For example, the method of extracting keywords of the pictorial theme in step S31 can be to input the pictorial theme into a large language model and extract keywords of the pictorial theme through the large language model. The method of analyzing and obtaining keyword attributes of keywords in step S31 can be any achievable method. For example, the keyword attributes of keywords can be obtained by identifying a named entity recognition model.

[0065] It should be noted that the first slot in step S33 is a placeholder for filling the target keyword corresponding to the target keyword attribute, and the number of the first slot is the same as the number of the target keyword attributes.

[0066] It is understandable that by setting the first slot in the pictorial template, when adjusting the required target keyword attributes, there is no need to reconstruct the entire pictorial template. Only the target keyword attributes corresponding to the first slot in the pictorial template need to be changed, thereby making it easier to achieve more diverse pictorial forms and contents.

[0067] In some embodiments of the present invention, after step S20 and before step S50, the method further includes:

[0068] Step S41, obtaining a pictorial platform identification value filled in a second slot preset in the target pictorial template;

[0069] Step S42, obtaining a target platform publishing specification corresponding to the pictorial platform in the pictorial platform corresponding to the pictorial platform identification value.

[0070] It should be noted that the correspondence between the pictorial platform identification value and the pictorial platform can be specifically set according to user needs. For example, when the pictorial platform identification value is 1, the corresponding pictorial platform may be the first pictorial platform, and when the pictorial platform identification value is 2, the corresponding pictorial platform may be the second pictorial platform.

[0071] It should be noted that, in step S42, the target platform publishing specification corresponding to the pictorial platform may be a pre-set and stored in the pictorial platform, or may be a platform publishing specification inherently used by the pictorial platform.

[0072] It should be noted that the platform release specifications are the format requirements of the pictorial platform, for example, requiring that the pictorial copy should be less than 200 words and the line spacing should be one line.

[0073] It can be understood that by setting the second slot in the pictorial template, when obtaining the platform publishing specifications of the pictorial platform to be published, there is no need to reconstruct the entire pictorial template. It is only necessary to change the pictorial platform identification value corresponding to the second slot in the pictorial template, thereby making it easier to realize more diverse pictorial forms and contents.

[0074] Optionally, the pictorial platform includes configuration items, a database, and a third-party content platform.

[0075] It should be noted that the configuration items may pre-store platform publishing specifications configured by technical personnel, and the database may also pre-store set platform publishing specifications. The third-party content platform is an independent company or tool that provides content creation, distribution and management services. The corresponding platform publishing specifications are the format requirements of these platforms for the pictorials published.

[0076] Step S50, filling the target text keywords into the target pictorial template, and inputting the target pictorial template into an artificial intelligence generated content model to generate a target pictorial text.

[0077] It should be noted that AI-generated content models refer to system models that use AI technology to automatically generate text. These models are based on deep learning algorithms, especially neural networks. For example, AI-generated content models can be GPT, BERT, or T5.

[0078] In this step, the target pictorial template is input into the artificial intelligence generated content model. Naturally, the artificial intelligence generated content model can obtain the target keywords, target text writing specifications and target platform publishing specifications in the target pictorial template. The artificial intelligence generated content model can generate suitable target pictorial text based on the target keywords, target text writing specifications and target platform publishing specifications.

[0079] In one embodiment of the present invention, after step S50 and before step S70, the method further includes:

[0080] Step S61, obtaining a pictorial background identifier filled in a third slot preset in the target pictorial template;

[0081] Step S62, according to the pictorial background identifier, obtaining the pictorial background basic component corresponding to the pictorial background identifier in the configuration item;

[0082] Step S63, generating the pictorial background according to the pictorial background basic components.

[0083] It should be noted that the correspondence between the pictorial background identifier and the pictorial background basic component can be set according to the specific needs of the application, so that different pictorial backgrounds can be generated by filling different pictorial background identifiers in the third slot.

[0084] It should be noted that the basic components of the pictorial background are all the basic components that form a complete pictorial background, for example, they may include colors and tones, textures and patterns, as well as images and illustrations.

[0085] It can be understood that, through steps S61-S63, the user can easily call the required pictorial background to enhance the richness of the pictorial.

[0086] Step S70, placing the target pictorial text in a preset pictorial background, and generating a target pictorial to be published on a target pictorial platform.

[0087] In this way, the target pictorial text is placed in the pictorial background obtained in step S63, and the target pictorial to be published on the target pictorial platform can be generated.

[0088] In this way, the creator (i.e., the user) only needs to input the target pictorial theme, and the server can obtain the target pictorial template corresponding to the target pictorial theme, and extract the target text keywords in the target pictorial theme corresponding to the target keyword attributes in the target pictorial template. After inputting the obtained target text keywords into the target pictorial template, the target pictorial template has the target keywords, target text writing specifications, and target platform publishing specifications for generating the target pictorial theme. In this way, when the target pictorial template is input into the artificial intelligence generated content model, the artificial intelligence generated content model can generate the target pictorial text based on the target keywords, target text writing specifications, and target platform publishing specifications in the target pictorial template.

[0089] To sum up, the embodiment of the present invention only requires the user to input the target pictorial theme, and the server can generate the complete pictorial copy required by the user. In this way, the pictorial can be generated by simply placing the pictorial copy on the pictorial background sheet, thereby avoiding the problem in the prior art that the user needs to input all the content when generating the pictorial copy, resulting in high production cost, low production cost efficiency and difficulty in large-scale mass production of the pictorial production method in the prior art.

[0090] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0091] In one embodiment, a device for generating a pictorial is provided, and the device for generating a pictorial corresponds one-to-one to the method for generating a pictorial in the above embodiment. Figure 4 As shown, the generation of the pictorial includes a receiving module 410, an acquisition module 420, an extraction module 430, a first generation module 440 and a second generation module 450. The detailed description of each functional module is as follows:

[0092] The receiving module 410 is used to receive a target pictorial theme input by a user;

[0093] An acquisition module 420 is used to acquire a target pictorial template corresponding to the target pictorial theme, wherein the target pictorial template is provided with target keyword attributes, target text writing specifications, and target platform publishing specifications corresponding to the target pictorial theme;

[0094] An extraction module 430 is used to extract target text keywords corresponding to the target keyword attributes in the target pictorial theme;

[0095] The first generating module 440 is used to fill the target text keywords into the target pictorial template, and input the target pictorial template into the artificial intelligence generated content model to generate the target pictorial text;

[0096] The second generating module 450 is used to place the target pictorial text in a preset pictorial background to generate a target pictorial that needs to be published on a target pictorial platform.

[0097] In one embodiment, the extraction module 430 is specifically used to:

[0098] Extracting keywords from the pictorial theme and analyzing to obtain keyword attributes corresponding to the keywords;

[0099] Associating the keyword attribute with the corresponding keyword to form a keyword key-value pair, wherein the key in the keyword key-value pair is the keyword attribute, and the value in the key-value pair is the keyword;

[0100] Obtaining a target keyword attribute corresponding to the first slot preset in the target pictorial template;

[0101] The value corresponding to the target keyword attribute in the keyword key-value pair is filled into the first slot.

[0102] In one embodiment, the second generating module 450 is further configured to:

[0103] Obtaining a pictorial background identifier filled in a third slot preset in the target pictorial template;

[0104] According to the pictorial background identifier, obtaining a pictorial background basic component corresponding to the pictorial background identifier in the configuration item;

[0105] The pictorial background is generated according to the pictorial background basic component.

[0106] In one embodiment, the acquisition module 420 is further used for:

[0107] Obtaining a pictorial platform identification value filled in a second slot preset in the target pictorial template;

[0108] In the pictorial platform corresponding to the pictorial platform identification value, a target platform publishing specification corresponding to the pictorial platform is obtained.

[0109] In one embodiment, the pictorial platform includes configuration items, a database, and a third-party content platform.

[0110] In one embodiment, the acquisition module 420 is further used to:

[0111] Analyzing the pictorial application scenario corresponding to the target pictorial theme;

[0112] Acquire target text writing specifications, target keyword attributes and target platform publishing specifications corresponding to the pictorial application scenario;

[0113] The target text writing specification, target keyword attributes and target platform publishing specification are placed in a blank template to form a target pictorial template.

[0114] In one embodiment, the receiving module 410 is specifically configured to:

[0115] In response to a user's selection instruction for a target topic type, displaying a control of topic keywords corresponding to the target topic type on the user interface;

[0116] In response to a selection instruction of a control for the subject keyword by a user, receiving a subject keyword selected by the user;

[0117] The subject keywords are input into a large language model to generate the target pictorial subject.

[0118] The present invention provides a pictorial generation device, so that the creator (i.e., the user) only needs to input a target pictorial theme, and the server can obtain a target pictorial template corresponding to the target pictorial theme, and extract target text keywords in the target pictorial theme corresponding to the target keyword attributes in the target pictorial template. After the obtained target text keywords are input into the target pictorial template, the target pictorial template has the target keywords, target text writing specifications, and target platform publishing specifications for generating the target pictorial theme. In this way, when the target pictorial template is input into an artificial intelligence generated content model, the artificial intelligence generated content model can generate the target pictorial text based on the target keywords, target text writing specifications, and target platform publishing specifications in the target pictorial template.

[0119] For the specific definition of the pictorial generation device, please refer to the definition of the pictorial generation method above, which will not be repeated here. Each module in the above-mentioned pictorial generation device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0120] Based on the above pictorial generation method, Figure 5 As shown, an embodiment of the present invention further provides a schematic diagram of the structure of a pictorial generation device, the generation device includes a processor 51 and a memory 52 coupled to the processor 51. The memory 52 stores a computer program, and when the computer program is executed by the processor 51, the processor 51 executes the steps of the pictorial generation method in the above embodiment.

[0121] For other details about how the processor 51 in the above-mentioned pictorial generation device implements the above-mentioned technical solution, please refer to the description of the pictorial generation method provided in the above-mentioned invention embodiment, which will not be repeated here.

[0122] Among them, the processor 51 can also be called a CPU (Central Processing Unit), and the processor 51 may be an integrated circuit chip with signal processing capabilities; the processor 51 can also be a general-purpose processor, DSP (Digital Signal Process), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, among which the general-purpose processor can be a microprocessor or the processor 51 can also be any conventional processor, etc.

[0123] like Figure 6 As shown, the embodiment of the present invention also provides a schematic diagram of the structure of a computer-readable storage medium, on which a readable computer program 61 is stored; wherein the computer program 61 can be stored in the above storage medium in the form of a software product, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, magnetic disk or optical disk, ROM (Read-Only Memory), RAM (Random Access Memory) and other media that can store program codes, or terminal devices such as computers, servers, mobile phones, and tablets.

[0124] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0125] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] In addition, each functional module in each embodiment of the present invention may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0127] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0128] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium), or a semiconductor medium (e.g., an SSD (solid state disk, solid state hard disk)).

[0129] The technical solution provided by the present invention is introduced in detail above. The present invention applies specific examples to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

[0130] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention 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, optical storage, etc.) containing computer-usable program code.

[0131] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present invention. 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.

[0132] 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.

[0133] 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.

[0134] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations. The non-Company software tools or components that appear in the embodiments of the present invention are merely examples and do not represent actual use.

Claims

1. A method for generating a pictorial, characterized in that: include: Receive the target pictorial theme input by the user; Acquire a target pictorial template corresponding to the target pictorial theme, wherein the target pictorial template is provided with target keyword attributes, target text writing specifications, and target platform publishing specifications corresponding to the target pictorial theme; Extracting target text keywords corresponding to the target keyword attributes in the target pictorial theme; Filling the target text keywords into the target pictorial template, and inputting the target pictorial template into an artificial intelligence generated content model to generate a target pictorial text; The target pictorial text is placed in a preset pictorial background to generate a target pictorial that needs to be published on a target pictorial platform.

2. The method for generating a pictorial according to claim 1, characterized in that: The step of extracting the target text keyword corresponding to the target keyword attribute in the pictorial theme includes: Extracting keywords from the pictorial theme and analyzing to obtain keyword attributes corresponding to the keywords; Associating the keyword attribute with the corresponding keyword to form a keyword key-value pair, wherein the key in the keyword key-value pair is the keyword attribute, and the value in the key-value pair is the keyword; Obtaining the target keyword attribute corresponding to the first slot preset in the target pictorial template; The value corresponding to the target keyword attribute in the keyword key-value pair is filled into the first slot.

3. The method for generating a pictorial according to claim 1, characterized in that: After inputting the target pictorial template into the artificial intelligence generated content model to generate the target pictorial text, before placing the pictorial text in a preset pictorial background and generating the target pictorial to be published on the target pictorial platform, the method further includes: Obtaining a pictorial background identifier filled in a third slot preset in the target pictorial template; According to the pictorial background identifier, obtaining a pictorial background basic component corresponding to the pictorial background identifier in the configuration item; The pictorial background is generated according to the pictorial background basic component.

4. The method for generating a pictorial according to claim 1, characterized in that: After acquiring the target pictorial template corresponding to the target pictorial theme, filling the target text keywords into the target pictorial template, and inputting the target pictorial template into the artificial intelligence generated content model, before generating the target pictorial text, the method further includes: Obtaining a pictorial platform identification value filled in a second slot preset in the target pictorial template; In the pictorial platform corresponding to the pictorial platform identification value, a target platform publishing specification corresponding to the pictorial platform is obtained.

5. The method for generating a pictorial according to claim 4, characterized in that: The pictorial platform includes configuration items, a database and a third-party content platform.

6. The method for generating a pictorial according to claim 1, characterized in that: The step of acquiring a target pictorial template corresponding to the target pictorial theme includes: Analyzing the pictorial application scenario corresponding to the target pictorial theme; Acquire target text writing specifications, target keyword attributes and target platform publishing specifications corresponding to the pictorial application scenario; The target text writing specification, target keyword attributes and target platform publishing specification are placed in a blank template to form a target pictorial template.

7. The method for generating a pictorial according to claim 1, characterized in that: The receiving of the target pictorial theme input by the user includes: In response to a user's selection instruction for a target topic type, displaying a control of topic keywords corresponding to the target topic type on the user interface; In response to a selection instruction of a control for the subject keyword by a user, receiving a subject keyword selected by the user; The subject keywords are input into a large language model to generate the target pictorial subject.

8. A device for generating a pictorial, characterized in that: include: A receiving module, used for receiving a target pictorial theme input by a user; An acquisition module, used for acquiring a target pictorial template corresponding to the target pictorial theme, wherein the target pictorial template is provided with target keyword attributes, target text writing specifications and target platform publishing specifications corresponding to the target pictorial theme; An extraction module, used for extracting target text keywords corresponding to the target keyword attributes in the target pictorial theme; A first generating module is used to fill the target text keywords into the target pictorial template, and input the target pictorial template into an artificial intelligence generated content model to generate a target pictorial text; The second generating module is used to place the target pictorial text in a preset pictorial background to generate a target pictorial that needs to be published on a target pictorial platform.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for generating a pictorial according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for generating a pictorial according to any one of claims 1 to 7 are implemented.

Images