Methods for generating customized images, computer devices, non-transitory computer-readable recording media, and computer program products.

Abstract

This application proposes a method for generating customized images, which is executed after a computer program product is loaded and executed via a computer device. The method includes the following steps: receiving customized requirement information; inputting the customized requirement information into a semantic analysis model; performing semantic analysis on the customized requirement information through the semantic analysis model, and generating and outputting customized analysis information based on the customized requirement information; searching for a plurality of semantic search images associated with the customized analysis information from an image classification database, and receiving the plurality of semantic search images, and / or inputting at least one of the customized requirement information and the customized analysis information into an image generation model, and generating and outputting customized analysis information based on the customized requirement information and the customized analysis information through the image generation model. The method involves generating and outputting at least one initially generated image; inputting a plurality of semantic search images and / or at least one initially generated image into an image analysis and filtering model; and using the image analysis and filtering model to perform image analysis and filtering on the plurality of semantic search images and / or at least one initially generated image, and selecting at least one search and filtering image from the plurality of semantic search images and / or at least one initially generated image based on at least one of customized requirement information and customized analysis information; wherein the semantic analysis model, the image generation model, and the image analysis and filtering model are all trained artificial intelligence engines. Therefore, the method is applicable to generating customized images and solves the problem that users cannot effectively generate customized images. Additionally, a computer device for generating customized images, a non-transitory computer-readable recording medium, and a computer program product are also proposed.

Claims

1. A method for generating customized images, the method being executed after loading and executing a computer program product via a computer device, the method comprising the steps of: receiving customization request information; inputting the customization request information into a semantic analysis model; performing semantic analysis on the customization request information through the semantic analysis model, and generating and outputting customized analysis information based on the customization request information; searching for a plurality of semantic search images associated with the customized analysis information from an image classification database, and receiving the plurality of semantic search images, and / or inputting at least one of the customization request information and the customized analysis information into an image generation model, and generating and outputting at least one initial generated image through the image generation model based on at least one of the customization request information and the customized analysis information; The plurality of semantic search images and / or the at least one initially generated image are input into an image analysis and filtering model; and through the image analysis and filtering model, image analysis and filtering are performed on the plurality of semantic search images and / or the at least one initially generated image, and at least one search and filtering image is selected from the plurality of semantic search images and / or the at least one initially generated image based on at least one of the customized requirement information and the customized analysis information; wherein... The semantic analysis model, the image generation model, and the image analysis and screening model are all artificial intelligence engines that have been trained.

2. The method as described in request item 1, wherein, The method further includes the following steps: determining whether the total number of the at least one searched and filtered images is less than a predetermined number value; and when the total number of the at least one searched and filtered images is less than the predetermined number value, inputting at least one of the customized requirement information and the customized analysis information into the image generation model, and generating and outputting at least one newly generated image based on the customized requirement information and the customized analysis information through the image generation model; wherein the total number of the at least one newly generated image is greater than or equal to a number difference between the total number of the at least one searched and filtered images and the predetermined number value.

3. The method as described in claim 2, wherein, The method further includes the following steps: inputting the at least one newly generated image into the image analysis and filtering model; performing image analysis and filtering on the at least one newly generated image through the image analysis and filtering model, and filtering at least one generated and filtered image from the at least one newly generated image based on at least one of the customized requirement information and the customized analysis information; determining whether the total number of the at least one generated and filtered image is less than the quantity difference; and when the total number of the at least one generated and filtered image is less than the quantity difference, generating and outputting the at least one newly generated image again through the image generation model based on at least one of the customized requirement information and the customized analysis information, and filtering at least one generated and filtered image from the at least one newly generated image again through the image analysis and filtering model based on at least one of the customized requirement information and the customized analysis information, until the total number of the at least one generated and filtered image is greater than or equal to the quantity difference.

4. The method described in claim 1, wherein the step of performing semantic analysis on the customized requirement information through the semantic analysis model and generating and outputting customized analysis information based on the customized requirement information includes the following sub-steps: performing language translation on the content of the customized requirement information through the semantic analysis model and generating customized translation information based on the customized requirement information; and performing semantic decomposition on the customized translation information through the semantic analysis model and generating and outputting customized analysis information based on the customized translation information.

5. The method as described in request item 1, wherein, The method further includes the following steps: inputting the at least one search filter image into an image editing model; and performing image editing on the at least one search filter image through the image editing model, and generating and outputting at least one filtered edited image based on the at least one search filter image; wherein the image editing model is a trained artificial intelligence engine.

6. The method as described in request item 1, wherein, The method further includes the following steps: receiving a customized product image corresponding to customized product information; inputting the at least one search filter image and the customized product image into an image synthesis model; and through the image synthesis model, performing image synthesis on the at least one search filter image and the customized product image, and generating and outputting at least one filtered composite image based on the at least one search filter image and the customized product image; wherein the image synthesis model is a trained artificial intelligence engine.

7. The method as described in claim 6, wherein, The method also includes the step of: outputting a composite determined image selected by a user from the at least one screened composite images to an ordering system.

8. A computer apparatus for generating customized images, comprising: a storage module configured to store a computer program product; and a processing module configured to be coupled to the storage module; wherein, After loading and executing the computer program product, the processing module is able to perform the method for generating customized images as described in any one of claims 1 to 7.

9. A non-transitory computer-readable recording medium for generating customized images, wherein after a computer device loads and executes a computer program product stored in the non-transitory computer-readable recording medium, the computer device is capable of performing the method for generating customized images as described in any one of claims 1 to 7.

10. A computer program product for generating customized images, wherein after the computer program product is loaded and executed on a computer device, the computer device is able to perform the method for generating customized images as described in any one of claims 1 to 7.

Images