Image generation data processing method and system based on artificial intelligence

Abstract

The present invention discloses a method and system for processing image generation data based on artificial intelligence, the method comprising: obtaining design requirement data and basic text input by a target user; determining text processing requirements and background image requirements according to the design requirement data based on a prediction algorithm model; processing the basic text according to the text processing requirements to obtain processed text; generating a promotional design image based on the processed text and the background image requirements based on a GPT algorithm model. It can be seen that the present invention can effectively improve the efficiency of making promotional design images, reduce the time cost and labor cost caused by manual intervention, and generate promotional images with better effects.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an artificial intelligence-based picture generation data processing method and system. Background Art

[0002] With the development of artificial intelligence technology, a large number of text-based image algorithm models have begun to appear. These models can generally generate corresponding images based on the text and descriptions input by users, but there are still common problems such as the generated images are not beautiful enough and logical errors. The current publicity text design work has also begun to use text-based image algorithm models to improve design efficiency. For example, an algorithm model is used to generate publicity design images with text based on descriptions. However, the existing text-based image data processing technology does not fully consider the characteristics of text and background images in the publicity text design requirements. Therefore, it does not combine the advance processing of text requirements and the separate processing of background images to improve the design effect and design efficiency. The design effect is general, the efficiency is low, and manual intervention and adjustment are often required, which has high labor costs. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an artificial intelligence-based image generation data processing method and system, which can effectively improve the efficiency of producing promotional design images, reduce the time cost and labor cost caused by manual intervention, and generate promotional images with better effects.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for processing picture generation data based on artificial intelligence, the method comprising:

[0005] Obtain design requirement data and basic text input by target users;

[0006] Based on the prediction algorithm model, determine the text processing requirements and background image requirements according to the design requirement data;

[0007] Processing the basic text according to the text processing requirement to obtain a processed text;

[0008] According to the processed text and the background image requirements, a promotional design image is generated based on the GPT algorithm model.

[0009] As an optional implementation, in the first aspect of the present invention, the determining of text processing requirements and background image requirements based on the design requirement data based on the prediction algorithm model includes:

[0010] Determine a corresponding text extraction algorithm model according to the data type of the design requirement data; the data type is image data, voice data or text data;

[0011] Inputting the design requirement data into the text extraction algorithm model to obtain the directly included text and the indirect feature text corresponding to the design requirement data;

[0012] According to the directly included text and the indirectly featured text, based on the keyword matching rule, the text processing requirements and the background image requirements corresponding to the design requirement data are determined.

[0013] As an optional implementation, in the first aspect of the present invention, the text processing requirements include text display direction, text display font, text display font size, text display position and text distortion effect.

[0014] As an optional implementation, in the first aspect of the present invention, the background image requirements include background image type, background image content, background image focus position and background image color.

[0015] As an optional implementation, in the first aspect of the present invention, the step of inputting the design requirement data into the text extraction algorithm model to obtain the directly included text and the indirectly featured text corresponding to the design requirement data comprises:

[0016] Input the design requirement data into the text direct recognition model in the text extraction algorithm model to obtain the output directly included text; the text direct recognition model is trained by a first training data set including training requirement data of the same data type and corresponding visual text annotations;

[0017] The design requirement data is input into the data description text recognition model in the text extraction algorithm model to obtain the output indirect feature text; the data description text recognition model is trained by a second training data set including training requirement data of the same data type and corresponding text annotations describing the data features of the training requirement data; the data features include tone features, content features, emotional features and metaphorical suggestion features.

[0018] As an optional implementation, in the first aspect of the present invention, the determining, based on the directly included text and the indirectly featured text and keyword matching rules, the text processing requirements and background image requirements corresponding to the design requirement data includes:

[0019] Matching the directly included text based on the text processing keyword to obtain a first keyword matching result;

[0020] Matching the directly included text based on the image processing keyword to obtain a second keyword matching result;

[0021] Matching the indirect feature text based on the image processing keyword to obtain a third keyword matching result;

[0022] Determining text processing requirements corresponding to the design requirement data according to the first keyword matching result;

[0023] The background image requirement corresponding to the design requirement data is determined according to the intersection of the second keyword matching result and the third keyword matching result.

[0024] As an optional implementation, in the first aspect of the present invention, the step of processing the basic text according to the text processing requirement to obtain a processed text includes:

[0025] Determining text processing parameters according to the text processing requirements;

[0026] Based on the pre-written automated python code, the text processing API is called, and the basic text is processed according to the processing parameters to obtain the processed text.

[0027] As an optional implementation, in the first aspect of the present invention, generating a promotional design picture based on the GPT algorithm model according to the processed text and the background picture requirements includes:

[0028] Input the background image requirement into the pre-trained Wenshengtu GPT algorithm model to obtain the corresponding background image;

[0029] The processed text is combined with the background image to obtain a promotional design image.

[0030] A second aspect of an embodiment of the present invention discloses an artificial intelligence-based picture generation data processing system, the system comprising:

[0031] An acquisition module is used to obtain design requirement data and basic text input by target users;

[0032] A determination module, used to determine text processing requirements and background image requirements according to the design requirement data based on a prediction algorithm model;

[0033] A processing module, used for processing the basic text according to the text processing requirement to obtain a processed text;

[0034] A generation module is used to generate a promotional design picture based on the GPT algorithm model according to the processed text and the background picture requirements.

[0035] As an optional implementation, in the second aspect of the present invention, the determining of text processing requirements and background image requirements based on the design requirement data based on the prediction algorithm model includes:

[0036] Determine a corresponding text extraction algorithm model according to the data type of the design requirement data; the data type is image data, voice data or text data;

[0037] Inputting the design requirement data into the text extraction algorithm model to obtain the directly included text and the indirect feature text corresponding to the design requirement data;

[0038] According to the directly included text and the indirectly featured text, based on the keyword matching rule, the text processing requirements and the background image requirements corresponding to the design requirement data are determined.

[0039] As an optional implementation, in the second aspect of the present invention, the text processing requirements include text display direction, text display font, text display font size, text display position and text distortion effect.

[0040] As an optional implementation, in the second aspect of the present invention, the background image requirements include background image type, background image content, background image focus position and background image color.

[0041] As an optional implementation, in the second aspect of the present invention, the determination module inputs the design requirement data into the text extraction algorithm model to obtain the specific manner of directly including the text and indirectly including the text corresponding to the design requirement data, including:

[0042] Input the design requirement data into the text direct recognition model in the text extraction algorithm model to obtain the output directly included text; the text direct recognition model is trained by a first training data set including training requirement data of the same data type and corresponding visual text annotations;

[0043] The design requirement data is input into the data description text recognition model in the text extraction algorithm model to obtain the output indirect feature text; the data description text recognition model is trained by a second training data set including training requirement data of the same data type and corresponding text annotations describing the data features of the training requirement data; the data features include tone features, content features, emotional features and metaphorical suggestion features.

[0044] As an optional implementation, in the second aspect of the present invention, the determination module determines the specific manner of the text processing requirements and the background image requirements corresponding to the design requirement data based on the keyword matching rules according to the directly included text and the indirectly featured text, including:

[0045] Matching the directly included text based on the text processing keyword to obtain a first keyword matching result;

[0046] Matching the directly included text based on the image processing keyword to obtain a second keyword matching result;

[0047] Matching the indirect feature text based on the image processing keyword to obtain a third keyword matching result;

[0048] Determining text processing requirements corresponding to the design requirement data according to the first keyword matching result;

[0049] The background image requirement corresponding to the design requirement data is determined according to the intersection of the second keyword matching result and the third keyword matching result.

[0050] As an optional implementation, in the second aspect of the present invention, the specific manner in which the processing module processes the basic text according to the text processing requirement to obtain the processed text includes:

[0051] Determining text processing parameters according to the text processing requirements;

[0052] Based on the pre-written automated python code, the text processing API is called, and the basic text is processed according to the processing parameters to obtain the processed text.

[0053] As an optional implementation, in the second aspect of the present invention, the specific manner in which the generation module generates the promotional design picture based on the GPT algorithm model according to the processed text and the background picture requirements includes:

[0054] Input the background image requirement into the pre-trained Wenshengtu GPT algorithm model to obtain the corresponding background image;

[0055] The processed text is combined with the background image to obtain a promotional design image.

[0056] The third aspect of the present invention discloses another picture generation data processing system based on artificial intelligence, the system comprising:

[0057] A memory storing executable program code;

[0058] a processor coupled to the memory;

[0059] The processor calls the executable program code stored in the memory to execute part or all of the steps in the artificial intelligence-based image generation data processing method disclosed in the first aspect of the present invention.

[0060] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the artificial intelligence-based image generation data processing method disclosed in the first aspect of the present invention.

[0061] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0062] The present invention can respectively determine the text processing requirements and the background image requirements according to the design requirement data through a predictive algorithm model, and then process the basic text based on the text processing requirements and generate a promotional design image based on the background image requirements and the processed text based on the GPT model, thereby effectively improving the efficiency of producing promotional design images, reducing the time cost and labor cost caused by manual intervention, and generating promotional images with better effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0064] Figure 1 It is a flowchart of an artificial intelligence-based picture generation data processing method disclosed in an embodiment of the present invention.

[0065] Figure 2 It is a structural schematic diagram of an artificial intelligence-based picture generation data processing system disclosed in an embodiment of the present invention.

[0066] Figure 3 It is a structural schematic diagram of another artificial intelligence-based picture generation data processing system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0068] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0069] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0070] The present invention discloses a method and system for processing image generation data based on artificial intelligence, which can determine text processing requirements and background image requirements respectively according to design requirement data through a prediction algorithm model, and then process the basic text based on the text processing requirements and generate a promotional design image based on the background image requirements and the processed text based on the GPT model, thereby effectively improving the efficiency of making promotional design images, reducing the time cost and labor cost caused by manual intervention, and generating promotional images with better effects. The following are detailed descriptions.

[0071] Embodiment 1

[0072] See also Figure 1 , Figure 1 1 is a flow chart of a method for processing image generation data based on artificial intelligence disclosed in an embodiment of the present invention. Figure 1 The described artificial intelligence-based image generation data processing method can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the artificial intelligence-based image generation data processing method may include the following operations:

[0073] 101. Obtain design requirement data and basic text input by target users.

[0074] 102. Based on the predictive algorithm model, determine the text processing requirements and background image requirements according to the design requirement data.

[0075] 103. Process the basic text according to text processing requirements to obtain processed text.

[0076] 104. Generate promotional design pictures based on the GPT algorithm model according to the requirements of processed text and background pictures.

[0077] It can be seen that the above-mentioned embodiments of the invention can respectively determine the text processing requirements and background image requirements according to the design requirement data through the prediction algorithm model, and then process the basic text based on the text processing requirements and generate promotional design pictures based on the background image requirements and the processed text based on the GPT model, thereby effectively improving the efficiency of producing promotional design pictures, reducing the time cost and labor cost caused by manual intervention, and generating better promotional pictures.

[0078] As an optional embodiment, in the above steps, determining the text processing requirements and the background image requirements based on the prediction algorithm model and the design requirement data includes:

[0079] Determine the corresponding text extraction algorithm model according to the data type of the design requirement data; optionally, the data type is image data, voice data or text data;

[0080] Input the design requirement data into the text extraction algorithm model to obtain the directly included text and the indirect feature text corresponding to the design requirement data;

[0081] According to the directly included text and indirectly featured text, based on the keyword matching rules, the text processing requirements and background image requirements corresponding to the design requirement data are determined.

[0082] It can be seen that through the above-mentioned optional embodiments, the text extraction algorithm model determined by the data type of the design requirement data can be used to determine the directly included text and the indirectly included feature text, so as to accurately determine the text processing requirements and background image requirements, so as to facilitate the subsequent accurate generation of promotional design images, assist in improving the efficiency of producing promotional design images, reduce the time cost and labor cost caused by manual intervention, and generate promotional images with better effects.

[0083] As an optional embodiment, in the above steps, the text processing requirements include text display direction, text display font, text display font size, text display position and text distortion effect.

[0084] It can be seen that through the above optional embodiments, the content of the text processing requirements is clarified to accurately characterize the user's text requirements, facilitate the subsequent accurate generation of promotional design pictures, assist in improving the efficiency of producing promotional design pictures, reduce the time and labor costs caused by manual intervention, and generate promotional pictures with better effects.

[0085] As an optional embodiment, in the above steps, the background image requirements include background image type, background image content, background image focus position and background image color.

[0086] It can be seen that through the above optional embodiments, the content of the background image requirements is clarified to accurately characterize the user's background image requirements, which is convenient for the subsequent accurate generation of promotional design pictures, assists in improving the efficiency of producing promotional design pictures, reduces the time and labor costs caused by manual intervention, and generates promotional pictures with better effects.

[0087] As an optional embodiment, in the above step, the design requirement data is input into the text extraction algorithm model to obtain the directly included text and the indirect feature text corresponding to the design requirement data, including:

[0088] Input the design requirement data into the text direct recognition model in the text extraction algorithm model to obtain the output directly included text; optionally, the text direct recognition model is trained by a first training data set including training requirement data of the same data type and corresponding visual text annotations;

[0089] The design requirement data is input into the data description text recognition model in the text extraction algorithm model to obtain the output indirect feature text; optionally, the data description text recognition model is trained by a second training data set including training requirement data of the same data type and corresponding text annotations that describe the data features of the training requirement data; the data features include tone features, content features, emotional features and metaphorical suggestion features.

[0090] It can be seen that through the above-mentioned optional embodiments, the direct included text and indirect feature text corresponding to the design requirement data can be respectively identified based on the text direct recognition model and the data description text recognition model, which is convenient for the subsequent accurate generation of promotional design pictures, and assists in improving the efficiency of producing promotional design pictures, reducing the time cost and labor cost caused by manual intervention, and generating better promotional pictures.

[0091] As an optional embodiment, in the above steps, determining the text processing requirements and background image requirements corresponding to the design requirement data based on the directly included text and the indirectly featured text and the keyword matching rule includes:

[0092] Matching the directly included text based on the text processing keyword to obtain a first keyword matching result;

[0093] Match the directly included text based on the image processing keyword to obtain a second keyword matching result;

[0094] Match the indirect feature text based on the image processing keyword to obtain a third keyword matching result;

[0095] Determine the text processing requirements corresponding to the design requirement data according to the first keyword matching result;

[0096] According to the intersection of the second keyword matching result and the third keyword matching result, the background image requirement corresponding to the design requirement data is determined.

[0097] Specifically, the text sentence entities corresponding to all the matching results in the first keyword matching results may be determined as the text processing requirements corresponding to the design requirement data.

[0098] Specifically, the text sentence entities corresponding to all the results in the result set of the intersection of the second keyword matching result and the third keyword matching result may be determined as the background image requirement corresponding to the design requirement data.

[0099] It can be seen that through the above-mentioned optional embodiments, text can be matched by pre-determining keywords related to text processing and image processing, wherein most users' text processing requirements will be directly expressed through text, while the requirements for background images may be expressed through indirect images or metaphorical hints of the text. Therefore, the image processing requirements must be determined through both direct text and indirect text to more accurately identify text processing requirements and background image requirements, so as to facilitate the subsequent accurate generation of promotional design images, assist in improving the efficiency of producing promotional design images, reduce the time cost and labor cost caused by manual intervention, and generate better promotional images.

[0100] As an optional embodiment, in the above steps, processing the basic text according to the text processing requirements to obtain the processed text includes:

[0101] Determine text processing parameters based on text processing requirements;

[0102] Based on the pre-written automated python code, the text processing API is called, and the basic text is processed according to the processing parameters to obtain the processed text.

[0103] Specifically, the existing python text processing toolkit may be used to process the basic text according to the processing parameters to obtain the processed text.

[0104] It can be seen that through the above-mentioned optional embodiments, the pre-written automated python code can call the text processing API, and process the text according to the processing parameters to obtain the processed text, so that the text in the subsequent promotional design pictures is more in line with the needs, and assist in improving the efficiency of producing promotional design pictures, reducing the time cost and labor cost caused by manual intervention, and generating better promotional pictures.

[0105] As an optional embodiment, in the above steps, according to the requirements of the processed text and background image, based on the GPT algorithm model, generating a promotional design image includes:

[0106] Input the background image requirements into the pre-trained Wenshengtu GPT algorithm model to obtain the corresponding background image;

[0107] Combine the processed text with the background image to obtain a promotional design image.

[0108] It can be seen that through the above-mentioned optional embodiments, the corresponding background image can be obtained through the pre-trained text-image GPT algorithm model, so as to combine the processed text with the background image to obtain a promotional design image, thereby improving the efficiency of making promotional design images, reducing the time cost and labor cost caused by manual intervention, and generating promotional images with better effects.

[0109] Embodiment 2

[0110] See also Figure 2 , Figure 2 : is a schematic diagram of a structure of an artificial intelligence-based picture generation data processing system disclosed in an embodiment of the present invention. Figure 2 The described artificial intelligence-based image generation data processing system can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the artificial intelligence-based picture generation data processing system may include:

[0111] The acquisition module 201 is used to acquire the design requirement data and basic text input by the target user.

[0112] The determination module 202 is used to determine the text processing requirements and the background image requirements based on the prediction algorithm model and the design requirement data.

[0113] The processing module 203 is used to process the basic text according to the text processing requirements to obtain the processed text.

[0114] The generation module 204 is used to generate a promotional design image based on the GPT algorithm model according to the requirements of the processed text and background image.

[0115] It can be seen that the above-mentioned embodiments of the invention can respectively determine the text processing requirements and background image requirements according to the design requirement data through the prediction algorithm model, and then process the basic text based on the text processing requirements and generate promotional design pictures based on the background image requirements and the processed text based on the GPT model, thereby effectively improving the efficiency of producing promotional design pictures, reducing the time cost and labor cost caused by manual intervention, and generating better promotional pictures.

[0116] As an optional embodiment, based on the prediction algorithm model, determining the text processing requirements and the background image requirements according to the design requirement data includes:

[0117] Determine the corresponding text extraction algorithm model according to the data type of the design requirement data; optionally, the data type is image data, voice data or text data;

[0118] Input the design requirement data into the text extraction algorithm model to obtain the directly included text and the indirect feature text corresponding to the design requirement data;

[0119] According to the directly included text and indirectly featured text, based on the keyword matching rules, the text processing requirements and background image requirements corresponding to the design requirement data are determined.

[0120] It can be seen that through the above-mentioned optional embodiments, the text extraction algorithm model determined by the data type of the design requirement data can be used to determine the directly included text and the indirectly included feature text, so as to accurately determine the text processing requirements and background image requirements, so as to facilitate the subsequent accurate generation of promotional design images, assist in improving the efficiency of producing promotional design images, reduce the time cost and labor cost caused by manual intervention, and generate promotional images with better effects.

[0121] As an optional embodiment, the text processing requirements include text display direction, text display font, text display font size, text display position and text distortion effect.

[0122] It can be seen that through the above optional embodiments, the content of the text processing requirements is clarified to accurately characterize the user's text requirements, facilitate the subsequent accurate generation of promotional design pictures, assist in improving the efficiency of producing promotional design pictures, reduce the time and labor costs caused by manual intervention, and generate promotional pictures with better effects.

[0123] As an optional embodiment, the background image requirements include background image type, background image content, background image focus position and background image color.

[0124] It can be seen that through the above optional embodiments, the content of the background image requirements is clarified to accurately characterize the user's background image requirements, which is convenient for the subsequent accurate generation of promotional design pictures, assists in improving the efficiency of producing promotional design pictures, reduces the time and labor costs caused by manual intervention, and generates promotional pictures with better effects.

[0125] As an optional embodiment, the determination module inputs the design requirement data into the text extraction algorithm model to obtain the specific manner in which the direct included text and the indirect feature text corresponding to the design requirement data are obtained, including:

[0126] Input the design requirement data into the text direct recognition model in the text extraction algorithm model to obtain the output directly included text; optionally, the text direct recognition model is trained by a first training data set including training requirement data of the same data type and corresponding visual text annotations;

[0127] The design requirement data is input into the data description text recognition model in the text extraction algorithm model to obtain the output indirect feature text; optionally, the data description text recognition model is trained by a second training data set including training requirement data of the same data type and corresponding text annotations that describe the data features of the training requirement data; the data features include tone features, content features, emotional features and metaphorical suggestion features.

[0128] It can be seen that through the above-mentioned optional embodiments, the direct included text and indirect feature text corresponding to the design requirement data can be respectively identified based on the text direct recognition model and the data description text recognition model, which is convenient for the subsequent accurate generation of promotional design pictures, and assists in improving the efficiency of producing promotional design pictures, reducing the time cost and labor cost caused by manual intervention, and generating better promotional pictures.

[0129] As an optional embodiment, the determination module determines the specific manner of text processing requirements and background image requirements corresponding to the design requirement data based on the directly included text and the indirectly featured text and the keyword matching rule, including:

[0130] Matching the directly included text based on the text processing keyword to obtain a first keyword matching result;

[0131] Match the directly included text based on the image processing keyword to obtain a second keyword matching result;

[0132] Match the indirect feature text based on the image processing keyword to obtain a third keyword matching result;

[0133] Determine the text processing requirements corresponding to the design requirement data according to the first keyword matching result;

[0134] According to the intersection of the second keyword matching result and the third keyword matching result, the background image requirement corresponding to the design requirement data is determined.

[0135] It can be seen that through the above-mentioned optional embodiments, text can be matched by pre-determining keywords related to text processing and image processing, wherein most users' text processing requirements will be directly expressed through text, while the requirements for background images may be expressed through indirect images or metaphorical hints of the text. Therefore, the image processing requirements must be determined through both direct text and indirect text to more accurately identify text processing requirements and background image requirements, so as to facilitate the subsequent accurate generation of promotional design images, assist in improving the efficiency of producing promotional design images, reduce the time cost and labor cost caused by manual intervention, and generate better promotional images.

[0136] As an optional embodiment, the specific manner in which the processing module processes the basic text according to the text processing requirement to obtain the processed text includes:

[0137] Determine text processing parameters based on text processing requirements;

[0138] Based on the pre-written automated python code, the text processing API is called, and the basic text is processed according to the processing parameters to obtain the processed text.

[0139] It can be seen that through the above-mentioned optional embodiments, the pre-written automated python code can call the text processing API, and process the text according to the processing parameters to obtain the processed text, so that the text in the subsequent promotional design pictures is more in line with the needs, and assist in improving the efficiency of producing promotional design pictures, reducing the time cost and labor cost caused by manual intervention, and generating better promotional pictures.

[0140] As an optional embodiment, the generation module generates a specific method of generating a promotional design image based on the GPT algorithm model according to the requirements of the processed text and background image, including:

[0141] Input the background image requirements into the pre-trained Wenshengtu GPT algorithm model to obtain the corresponding background image;

[0142] Combine the processed text with the background image to obtain a promotional design image.

[0143] It can be seen that through the above-mentioned optional embodiments, the corresponding background image can be obtained through the pre-trained text-image GPT algorithm model, so as to combine the processed text with the background image to obtain a promotional design image, thereby improving the efficiency of making promotional design images, reducing the time cost and labor cost caused by manual intervention, and generating promotional images with better effects.

[0144] Embodiment 3

[0145] See also Figure 3 , Figure 3 It is another picture generation data processing system based on artificial intelligence disclosed in an embodiment of the present invention. Figure 3 The described artificial intelligence-based image generation data processing system is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the artificial intelligence-based picture generation data processing system may include:

[0146] A memory 301 storing executable program codes;

[0147] a processor 302 coupled to the memory 301;

[0148] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the artificial intelligence-based image generation data processing method described in the first embodiment.

[0149] Embodiment 4

[0150] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the artificial intelligence-based image generation data processing method described in the first embodiment.

[0151] Embodiment 5

[0152] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the artificial intelligence-based image generation data processing method described in Example 1.

[0153] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0154] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0155] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0156] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0157] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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.

[0158] 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.

[0159] 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.

[0160] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0161] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0162] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0163] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0164] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0165] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0166] Finally, it should be noted that the artificial intelligence-based image generation data processing method and system disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for processing image generation data based on artificial intelligence, characterized in that: The method comprises: Obtain design requirement data and basic text input by target users; Based on the prediction algorithm model, determining text processing requirements and background image requirements according to the design requirement data, including: Determine a corresponding text extraction algorithm model according to the data type of the design requirement data; the data type is image data, voice data or text data; Input the design requirement data into the text direct recognition model in the text extraction algorithm model to obtain the output directly included text; the text direct recognition model is trained by a first training data set including training requirement data of the same data type and corresponding visual text annotations; The design requirement data is input into the data description text recognition model in the text extraction algorithm model to obtain an output indirect feature text; the data description text recognition model is trained by a second training data set including training requirement data of the same data type and corresponding text annotations describing data features of the training requirement data; the data features include tone features, content features, emotional features and metaphorical hint features; According to the directly included text and the indirectly featured text, based on the keyword matching rule, determining the text processing requirements and background image requirements corresponding to the design requirement data; Processing the basic text according to the text processing requirement to obtain a processed text; According to the processed text and the background image requirements, a promotional design image is generated based on the GPT algorithm model.

2. The method for processing image data based on artificial intelligence according to claim 1, characterized in that: The text processing requirements include text display direction, text display font, text display font size, text display position and text distortion effect.

3. The method for processing image generation data based on artificial intelligence according to claim 1, characterized in that: The background image requirements include background image type, background image content, background image focus position and background image color.

4. The method for processing image generation data based on artificial intelligence according to claim 1, characterized in that: The determining, based on the directly included text and the indirectly featured text and the keyword matching rule, the text processing requirements and the background image requirements corresponding to the design requirement data includes: Matching the directly included text based on the text processing keyword to obtain a first keyword matching result; Matching the directly included text based on the image processing keyword to obtain a second keyword matching result; Matching the indirect feature text based on the image processing keyword to obtain a third keyword matching result; Determining text processing requirements corresponding to the design requirement data according to the first keyword matching result; The background image requirement corresponding to the design requirement data is determined according to the intersection of the second keyword matching result and the third keyword matching result.

5. The method for processing image generation data based on artificial intelligence according to claim 1, characterized in that: The step of processing the basic text according to the text processing requirement to obtain a processed text includes: Determining text processing parameters according to the text processing requirements; Based on the pre-written automated python code, the text processing API is called, and the basic text is processed according to the processing parameters to obtain the processed text.

6. The method for processing image generation data based on artificial intelligence according to claim 1, characterized in that: The generating of the promotional design picture based on the processed text and the background picture requirement and based on the GPT algorithm model includes: Input the background image requirement into the pre-trained Wenshengtu GPT algorithm model to obtain the corresponding background image; The processed text is combined with the background image to obtain a promotional design image.

7. An artificial intelligence-based picture generation data processing system, characterized in that: The system comprises: An acquisition module is used to obtain design requirement data and basic text input by target users; A determination module, used to determine text processing requirements and background image requirements according to the design requirement data based on a prediction algorithm model, including: Determine a corresponding text extraction algorithm model according to the data type of the design requirement data; the data type is image data, voice data or text data; Input the design requirement data into the text direct recognition model in the text extraction algorithm model to obtain the output directly included text; the text direct recognition model is trained by a first training data set including training requirement data of the same data type and corresponding visual text annotations; The design requirement data is input into the data description text recognition model in the text extraction algorithm model to obtain an output indirect feature text; the data description text recognition model is trained by a second training data set including training requirement data of the same data type and corresponding text annotations describing data features of the training requirement data; the data features include tone features, content features, emotional features and metaphorical hint features; According to the directly included text and the indirectly featured text, based on the keyword matching rule, determining the text processing requirements and background image requirements corresponding to the design requirement data; A processing module, used for processing the basic text according to the text processing requirement to obtain a processed text; A generation module is used to generate a promotional design picture based on the processed text and the background picture requirements and based on the GPT algorithm model.

8. An artificial intelligence-based picture generation data processing system, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the artificial intelligence-based image generation data processing method as described in any one of claims 1-6.

Images