Method and apparatus for generating latent image, computer storage medium, and electronic device

An apparatus for generating and displaying a latent image, the apparatus comprising:

• a state and attribute acquisition device,
• a basic image processor,
• a filter,
• a semantic script generation model processor,
• a conditional image generation model processor, and
• a display,
• wherein the state and attribute acquisition device is configured to acquire a behavior text vector representing different behavior states of a device and an attribute text vector representing different display attributes of the device,
• wherein the basic image processor is configured to acquire an image text vector and an image feature element of a basic image,
• wherein the filter is configured to combine vector values of the behavior text vector, the attribute text vector, and the image text vector to obtain a relevant vector combination, the relevant vector combination comprising a combination including a value of the behavior text vector, a value of the attribute text vector, and a value of the image text vector,
• wherein the semantic script generation model processor is configured to input all the relevant vector combinations into a pre-trained semantic script generation model for processing to generate a semantic script text for describing latent image generation requirements,
• wherein the conditional image generation model processor is configured to input the semantic script text and the image feature element into a pre-trained conditional image generation model for processing to generate latent images corresponding to the different behavior states of the device, and
• wherein the display is configured to display the corresponding latent image based on the behavior state of the device.

One or more non-transitory computer-readable storage media storing computer-executable instructions that, when executed by one or more processors of an apparatus, cause the apparatus to perform operations, the operations comprising:

• acquiring a behavior text vector representing a behavior state of a device and an attribute text vector representing a display attribute of the device;
• acquiring an image text vector and an image feature element of a basic image;
• combining vector values of the behavior text vector, the attribute text vector, and the image text vector to obtain a relevant vector combination, the relevant vector combination being a combination including a value of the behavior text vector, a value of the attribute text vector, and a value of the image text vector;
• inputting all the relevant vector combinations into a pre-trained semantic script generation model for processing to generate a semantic script text for describing latent image generation requirements;
• inputting the semantic script text and the image feature element into a pre-trained conditional image generation model for processing to generate a latent image corresponding to the behavior state of the device;
• and
• displaying the corresponding latent image based on the behavior state of the device.

An electronic device comprising:

• memory storing one or more computer programs;
• and
• one or more processors communicatively coupled to the memory,
• wherein the one or more computer programs include computer-executable instructions that, when executed by the one or more processors, cause the electronic device to:
• acquire a behavior text vector representing a behavior state of a device and an attribute text vector representing a display attribute of the device,
• acquire an image text vector and an image feature element of a basic image,
• combine vector values of the behavior text vector, the attribute text vector, and the image text vector to obtain a relevant vector combination, the relevant vector combination being a combination including a value of the behavior text vector, a value of the attribute text vector, and a value of the image text vector,
• input all the relevant vector combinations into a pre-trained semantic script generation model for processing to generate a semantic script text for describing latent image generation requirements,
• input the semantic script text and the image feature element into a pre-trained conditional image generation model for processing to generate a latent image corresponding to the behavior state of the device, and
• display the corresponding latent image based on the behavior state of the device.