CN117710527A

CN117710527A - Image processing method, device and product based on artificial intelligence large model

Info

Publication number: CN117710527A
Application number: CN202311713873.2A
Authority: CN
Inventors: 李志强
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-12-13
Filing date: 2023-12-13
Publication date: 2024-03-15

Abstract

The disclosure provides an image processing method, an image processing device, electronic equipment, a storage medium and a program product based on an artificial intelligence large model, relates to the technical field of artificial intelligence, in particular to the technical field of image processing, and can be applied to an image processing scene. The specific implementation scheme is as follows: acquiring a target image and an image processing request of a user for the target image; respectively analyzing the target image and the image processing request through the artificial intelligent large model to obtain an image analysis result and a request analysis result; and processing the target image according to the image analysis result by using the artificial intelligence large model according to the processing requirement represented by the request analysis result. The method and the device improve the flexibility and convenience of the image processing process and improve the experience of the user in the image processing process.

Description

Image processing method, device and product based on artificial intelligence large model

Technical Field

The disclosure relates to the technical field of artificial intelligence, in particular to the technical field of image processing, and especially relates to an image processing method, device, electronic equipment, storage medium and computer program product based on an artificial intelligence large model, which can be applied to an image processing scene.

Background

Currently, mobile terminals have a high popularity, and there is a strong need for processing images at the mobile terminals. However, the threshold for people to handle pictures at the mobile end is high. For example, photoShop and other image processing tools have high requirements on professional skills, and people cannot simply and conveniently process images.

Disclosure of Invention

The present disclosure provides an image processing method, apparatus, electronic device, storage medium and computer program product based on artificial intelligence large model.

According to a first aspect, there is provided an image processing method based on an artificial intelligence large model, comprising: acquiring a target image and an image processing request of a user for the target image; respectively analyzing the target image and the image processing request through the artificial intelligent large model to obtain an image analysis result and a request analysis result; and processing the target image according to the image analysis result by using the artificial intelligence large model according to the processing requirement represented by the request analysis result.

According to a second aspect, there is provided an image processing apparatus based on an artificial intelligence large model, comprising: an acquisition unit configured to acquire a target image and an image processing request of a user for the target image; the analysis unit is configured to analyze the target image and the image processing request through the artificial intelligent large model respectively to obtain an image analysis result and a request analysis result; and the processing unit is configured to process the target image according to the image analysis result through the artificial intelligence large model according to the processing requirement represented by the request analysis result.

According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method as described in any one of the implementations of the first aspect.

According to a fourth aspect, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform a method as described in any implementation of the first aspect.

According to a fifth aspect, there is provided a computer program product comprising: a computer program which, when executed by a processor, implements a method as described in any of the implementations of the first aspect.

According to the technology disclosed by the invention, the image processing method and the device based on the artificial intelligence large model are provided, a user only needs to send an image processing request to the artificial intelligence large model, the artificial intelligence large model can process the target image according to the processing requirement represented by the request analysis result, the image processing effect expected by the user is achieved, the flexibility and the convenience of the image processing process are improved, and the experience degree of the user in the image processing process is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is an exemplary system architecture diagram to which an embodiment according to the present disclosure may be applied;

FIG. 2 is a flow chart of one embodiment of an artificial intelligence large model based image processing method according to the disclosure;

fig. 3 is a schematic diagram of an application scenario of an image processing method based on an artificial intelligence large model according to the present embodiment;

FIG. 4 is a flow chart of yet another embodiment of an artificial intelligence large model based image processing method according to the disclosure;

FIG. 5 is a block diagram of one embodiment of an artificial intelligence large model based image processing apparatus according to the disclosure;

FIG. 6 is a schematic diagram of a computer system suitable for use in implementing embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

FIG. 1 illustrates an exemplary architecture 100 to which the artificial intelligence large model based image processing methods and apparatus of the present disclosure may be applied.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The communication connection between the terminal devices 101, 102, 103 constitutes a topology network, the network 104 being the medium for providing the communication link between the terminal devices 101, 102, 103 and the server 0105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The terminal devices 101, 102, 103 may be hardware devices or software supporting network connections for data interaction and data processing. When the terminal device 101, 102, 103 is hardware, it may be various electronic devices supporting network connection, information acquisition, interaction, display, processing, etc., including but not limited to smartphones, tablet computers, electronic book readers, laptop and desktop computers, etc. When the terminal devices 101, 102, 103 are software, they can be installed in the above-listed electronic devices. It may be implemented as a plurality of software or software modules, for example, for providing distributed services, or as a single software or software module. The present invention is not particularly limited herein.

The server 105 may be a server providing various services, for example, a background processing server that acquires a target image transmitted by the terminal devices 101, 102, 103 and an image processing request of a user for the target image, processes the target image according to a processing requirement characterized by a request analysis result through an artificial intelligence large model, and processes the target image according to the image analysis result for the target image. As an example, the server 105 may be a cloud server.

The server may be hardware or software. When the server is hardware, the server may be implemented as a distributed server cluster formed by a plurality of servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules (e.g., software or software modules for providing distributed services), or as a single software or software module. The present invention is not particularly limited herein.

It should also be noted that, the image processing method based on the artificial intelligence large model provided by the embodiment of the present disclosure may be executed by a server, may be executed by a terminal device, or may be executed by a server and the terminal device in cooperation with each other. Accordingly, each part (for example, each unit) included in the image processing apparatus based on the artificial intelligence large model may be provided in the server, may be provided in the terminal device, or may be provided in the server and the terminal device, respectively.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. When the electronic device on which the image processing method based on the artificial intelligence large model operates does not need to perform data transmission with other electronic devices, the system architecture may include only the electronic device (e.g., a terminal device or a server) on which the image processing method based on the artificial intelligence large model operates.

Referring to fig. 2, fig. 2 is a flowchart of an image processing method based on an artificial intelligence large model according to an embodiment of the disclosure. Wherein, in the process 200, the following steps are included:

step 201, a target image and an image processing request of a user for the target image are acquired.

In this embodiment, the execution subject (e.g., the terminal device or the server in fig. 1) of the image processing method based on the artificial intelligence large model may acquire the target image and the image processing request of the user for the target image from a remote location, or from a local location, through a wired network connection or a wireless network connection.

The target image is an image to be processed selected by a user, and can be an image frame in a dynamic image sequence or a single static image. The target image may be various types of images divided based on various division standards. Under color-based partitioning criteria, images include, but are not limited to, black-and-white images, color images; under content-based partitioning criteria, images include, but are not limited to, character images, scene images, building images, pet images, product images, sports images, art images, science fiction images, cartoon images.

The image processing request characterizes the user's processing needs for the target image, which may be issued in various ways supported by existing or future technologies, including but not limited to speech, text, actions (e.g., gesture actions), and so forth. For example, the image processing request is to delete the XX object in the target image, and combine a plurality of target images into the same image.

And 202, respectively analyzing the target image and the image processing request through the artificial intelligent large model to obtain an image analysis result and a request analysis result.

In this embodiment, the execution subject may analyze the target image and the image processing request through the artificial intelligence large model, to obtain an image analysis result and a request analysis result.

The artificial intelligence large model specifically refers to an artificial intelligence pre-training large model, and has large-scale or super-large-scale parameters. The artificial intelligence large model comprises two layers of meanings, one layer is 'pre-training', and the other layer is 'large model', and the two layers are combined to generate a new artificial intelligence mode, namely, after the model finishes pre-training on a large-scale data set, various applications can be directly supported without or only by fine adjustment of a small amount of data. The artificial intelligence large model has excellent context understanding capability, language generation capability, learning capability, and mobility.

The execution subject can sequentially input the target image and the image processing request into the artificial intelligent large model, and analyze the target image through the artificial intelligent large model to obtain an image analysis result; and analyzing the image processing request through the artificial intelligent large model to obtain a request analysis result.

As an example, the artificial intelligence large model may perform feature extraction on the target image to obtain a feature map; and then, semantic information, scene information and the like represented by the target image are determined based on the feature map, and an image analysis result is obtained.

The artificial intelligent large model can perform feature extraction on the image processing request to obtain feature data; and determining the processing requirement characterized by the image processing request based on the characteristic data to obtain a request analysis result.

In some optional implementations of this embodiment, the executing body may execute the parsing operation of the target image by: and analyzing the target image through the artificial intelligence large model, and determining the object and the position of the object included in the target image to obtain an image analysis result.

The object may be all objects included in the target image, the position of the object typically being characterized by a range of regions in the image.

As an example, the artificial intelligence large model may perform feature extraction on the target image to obtain a feature map; and determining each object and the position of each object included in the target image based on the feature map to obtain an image analysis result.

In the implementation mode, the image analysis result comprises the object in the target image and the position of the object, so that data preparation is provided for meeting the processing requirement of a user on the object in the target image based on the artificial intelligence large model, and the response speed and the accuracy of the image processing process based on the artificial intelligence large model are improved.

In some optional implementations of this embodiment, the executing body may further execute the analysis operation of the target image by: and analyzing the target image through the artificial intelligence large model, and determining the object included in the target image, the position of the object and the interaction relation among the objects to obtain an image analysis result.

When a plurality of objects are included in the target image, there may be interactions between the plurality of objects. The interaction relationship between the plurality of objects includes, but is not limited to, occlusion relationship, collision relationship, dependency relationship, spatial relationship, temporal relationship, combination relationship, background relationship, and the like.

The artificial intelligence large model can further determine the interaction relationship between each two objects on the basis of determining each object and the position of each object included in the target image by analyzing the target image, so as to obtain an image analysis result.

When a user has processing requirements for a target object in a target image, adjustment of the target object will generally affect other objects that have an interactive relationship with the target object. In the implementation mode, the image analysis result comprises the object in the target image, the position of the object and the interaction relation among the objects, so that data preparation is provided for meeting the processing requirement of a user on the object in the target image based on the artificial intelligence large model, and the response speed and accuracy of the image processing process based on the artificial intelligence large model are further improved.

In some optional implementations of this embodiment, the executing body may execute the parsing operation of the image processing request by: and analyzing the image processing request through the artificial intelligence large model, determining the processing requirement of a user on the target image and/or the object in the target image, and obtaining a request analysis result.

In the implementation mode, the artificial intelligent large model can perform feature extraction on the image processing request to obtain feature data; and further determining the processing requirements of the user represented by the image processing request on the target image and/or the object in the target image based on the feature data, and obtaining a request analysis result.

For example, the processing requirements may be processing requirements for at least one object in the target image under which the artificial intelligence large model only needs to process the at least one object; as another example, the processing requirement may be a processing requirement for an entire target image, under which the artificial intelligence large model needs to process the entire target image, for example, super-resolution processing of the target image.

In the implementation manner, the object to be processed (the target image and/or the object in the target image) aimed by the image processing request can be definitely determined through the artificial intelligence large model, so that the accuracy of the analysis result of the request is improved, and the subsequent processing effect on the target image and the experience of the user are improved.

And 203, processing the target image according to the image analysis result through the artificial intelligence large model according to the processing requirement represented by the request analysis result.

In this embodiment, the execution subject may process the target image according to the image analysis result by using the artificial intelligence large model according to the processing requirement represented by the request analysis result.

As an example, the processing requirement characterized by the request analysis result adjusts the style of the target image to the style of the specific image, wherein the specific image can be an image with a certain style specified by the user; the artificial intelligence large model can analyze style information of a specific image, and adjust the style of the target image based on an image analysis result to obtain the target image with the adjusted style.

In some alternative implementations of the present embodiment, the processing requirement is a first attribute adjustment requirement for attribute information of the target image. The attribute information of the target image includes, but is not limited to, information of resolution, size, color, bit depth, transparency, gray level, brightness, contrast, saturation, and the like.

For example, the first attribute adjustment requirement is a super resolution requirement, a zoom-in or zoom-out requirement, and a contrast adjustment requirement for the target object.

In this implementation manner, the execution body may execute the step 203 as follows: and adjusting the attribute information of the target image according to the first attribute adjustment requirement represented by the request analysis result and the image analysis result through the artificial intelligence large model.

As an example, the executing body may determine, according to the request analysis result, attribute information and an adjustment direction to be adjusted by the first attribute adjustment requirement through the artificial intelligence large model; further, attribute information of the target image is adjusted in accordance with the adjustment direction. For example, for attribute information such as resolution, size, transparency, etc., adjusting the direction includes adjusting the size and the size; for attribute information such as color, adjustment includes dimming, darkening, and adjustment to other colors.

In the implementation mode, an image processing mode aiming at the attribute information of the target image is provided under the requirement of attribute adjustment, and convenience and flexibility of the adjustment process of the attribute information of the target image are improved based on the artificial intelligence large model.

In some alternative implementations of the present embodiment, the processing requirement is a second attribute adjustment requirement for attribute information of a target object in the target image. The target object may be at least one object in the target image. Similarly, the attribute information of the target object includes, but is not limited to, resolution, size, color, bit depth, transparency, gray scale, brightness, contrast, saturation, and the like.

As an example, the executing body may determine, according to the request analysis result, a target object to be adjusted by the second attribute adjustment requirement, attribute information of the target object, and an adjustment direction of the attribute information through the artificial intelligence large model; further, attribute information of the target object in the target image is adjusted in accordance with the adjustment direction.

When the adjustment of the attribute information of the target object affects other objects having an interactive relationship with the target object, after the attribute information of the target object in the target image is adjusted, the other objects having an interactive relationship with the target object need to be adjusted according to the interactive relationship. For example, enlarging the target object a in the target object, the portion of the target object B having the occlusion relationship with the target object a that is occluded becomes large, and adjustment of the occluded portion of the target object B, and the interaction portion between the target object a and the target object B (for example, projection information of the target object a on the target object B) are required.

In the implementation mode, an image processing mode aiming at the attribute information of the target object in the target image is provided under the requirement of attribute adjustment, and convenience and flexibility of the adjustment process of the attribute information of the target object in the target image are improved based on the artificial intelligence large model.

In some alternative implementations of the present embodiment, the processing requirements are object adjustment requirements for a target object in the target image. The target object may be at least one object in the target image. Object adjustment requirements include, but are not limited to, movement requirements, deletion requirements, replacement requirements for the target object.

In the moving requirement, a user expects to move target objects in a target image, and the structural relation among the target objects in the target image is changed under the condition that the number of the objects is not changed; in the deletion requirement, a user desires to delete target objects in a target image, and in the case of changing the number of objects, the structural relationship between the target objects in the target image is changed; in the replacement requirement, the user desires to replace the target object in the target image by the specified object.

As an example, the execution subject may determine, according to the request analysis result, a target object to be adjusted by the object adjustment requirement and an adjustment manner for the target object through the artificial intelligence large model; further, the target object in the target image is adjusted according to the adjustment method.

When the adjustment of the target object affects other objects having an interactive relationship with the target object, after the target object in the target image is adjusted, the other objects also need to be adjusted according to the interactive relationship. For example, a target object a in a target image is moved from a first position, where the target object a has an occlusion relationship with an object B, to a second position, where the target object a has an occlusion relationship with an object C. At this time, the interaction part between the target object a and the object B, and the interaction part between the target object a and the object C need to be adjusted.

In the implementation mode, the image processing mode aiming at the target object in the target image is provided under the object adjustment requirement, and the convenience and the flexibility of the adjustment process of the target object in the target image are improved based on the artificial intelligence large model.

In some optional implementations of this embodiment, for a case where the object adjustment requirement is an object deletion requirement for a target object in the target image, the execution body may execute the object adjustment process based on the object adjustment requirement by:

first, deleting a target object in a target image according to an object deletion requirement represented by a request analysis result through an artificial intelligence large model and an image analysis result.

As an example, the execution subject may determine, through an artificial intelligence large model, a target object that is desired to be deleted in the object deletion requirement, and determine, from the image analysis result, whether the target object includes the target object; and deleting the target object in the target image according to the position of the target object in response to determining that the target object is included in the target image.

Second, the deleted region is pixel-filled based on pixels in the surrounding region of the deleted region.

The deleted region is a region obtained after the target object is deleted in the target image.

And the deleted area is generally blank pixels, and the artificial intelligent large model predicts the background information of the original target object according to the pixels in the surrounding area of the deleted area, so that the deleted area presents the background information shielded by the original target object in a pixel filling mode.

Thirdly, according to the interaction relation, adjusting objects outside the target object in the target image.

Before the target object is deleted, there may be other objects with which there is an interactive relationship. At this time, after deleting the target object and filling the deleted region, it is necessary to adjust the object having an interactive relationship with the target object in the target image. For example, before deleting the target object a, the object B has projection information of the target object a thereon; after deleting the target object a, it is necessary to adjust the shadow information on the object B so that the shadow disappears.

In the implementation mode, the image processing mode aiming at the target object in the target image is provided under the object deleting requirement, and convenience and flexibility of a deleting process of the target object in the target image are improved based on the artificial intelligence large model.

In some alternative implementations of the present embodiment, the processing requirements increase the requirements for adding objects of the specified object to the target image. The specified object may be any object, such as a cartoon pattern, a real person object. The number of specified objects may be one or more.

The execution body or an electronic device communicatively connected to the execution body may be provided with a specified object library including a plurality of specified objects. When it is determined that the processing requirement is an object increasing requirement for adding a specified object in the target image, the artificial intelligence large model may determine the specified object to be added from the specified object library.

The user can supplement the specified object library based on the addition operation of the specified object. For example, a user may object-segment a video frame of a browsed image or video through an artificial intelligence large model, and further add a target segment selected by the user to a specified object library.

In this implementation manner, the execution subject may execute the image processing procedure based on the processing requirement by:

first, through artificial intelligence big model, according to the object increase demand that request analysis result characterized, add appointed object in the target image.

By way of example, a specified object to be added in an object addition requirement and an addition position of the specified object are determined through an artificial intelligence large model; further, at the determined addition position, a specified object is added.

Second, according to the image analysis result, the specified object and the object in the target image are adjusted.

By way of example, the artificial intelligence large model adjusts the specified object and the object in the target image by:

and adjusting the attribute information of the added specified object according to the attribute information of the object in the target image in the image analysis result so that the attribute information of the added specified object is matched with the attribute information of the object in the target image.

And adjusting the projection relation, transition information and the like of the added interaction part between the specified object and the object in the target image according to the interaction relation between the objects in the target image in the image analysis result.

In the implementation mode, the image processing mode of adding the specified object in the target image is provided under the condition that the object increasing requirement, and the convenience and the flexibility of the adding process of adding the specified object in the target image are improved based on the artificial intelligence large model.

In some alternative implementations of the present embodiment, the processing requirements are animation requirements for the target image. In this implementation manner, the execution body may execute the step 203 as follows: and generating a dynamic image sequence corresponding to the target image according to the image analysis result by using the artificial intelligent large model according to the animation production requirement represented by the request analysis result.

As an example, the execution subject may predict, through the artificial intelligence large model, a previous or future behavior track or morphology information of each object in the target image according to semantic information and scene information represented by the target image, and generate, at each preset time interval, a predicted image of the target object at the predicted time based on the predicted behavior track or morphology information; further, the plurality of predicted images and the target image are combined in accordance with the time-series relationship of the images between the plurality of predicted images, and a moving image sequence corresponding to the target image is generated.

In the implementation mode, the image processing mode aiming at the target image is provided under the requirement of animation production, and convenience and flexibility of the animation production process are improved based on the artificial intelligence large model.

In some optional implementations of this embodiment, the executing body may execute the generation process of the dynamic image sequence by:

first, through the artificial intelligence big model, according to the animation production requirement represented by the request analysis result, determining the animation type corresponding to each object in the image analysis result.

By way of example, objects such as sea, blue sky, white clouds, and birds are included in the target image, and the animation requirements expect that sea waves, white clouds, and birds fly in a distant direction as the wind moves.

The execution body may determine each object indicated by the request resolution result and the type of animation desired for each object through the artificial intelligence large model.

Secondly, for each object in the image analysis result, generating a dynamic object according to the animation type corresponding to the object, generating a dynamic image sequence, and adjusting the dynamic object according to the interaction relation.

For example, for each object in the image analysis result, the execution body may predict the behavior track and/or form information of the object before or in the future according to the animation type corresponding to the object through the artificial intelligence large model, and sample the behavior track and/or form information corresponding to each of a plurality of time points according to a preset time interval, so as to generate a dynamic object. And after each dynamic object indicated by the animation production requirement is obtained, combining a plurality of dynamic objects to obtain a dynamic image sequence.

When there is an interactive relationship between a plurality of dynamic objects, the plurality of dynamic objects need to be adjusted according to the interactive relationship. For example, the projection relationship and the collision relationship between a plurality of dynamic objects are adjusted.

In the implementation mode, the image processing mode aiming at the target image is provided under the requirement of animation production, and convenience and flexibility of the animation production process are further improved based on the artificial intelligence large model.

In some alternative implementations of the present embodiment, the processing requirements are image composition requirements for multiple target images. Image composition requirements include, but are not limited to, stitching multiple target images into a composite image in a manner, determining at least a portion of an area from each target image to stitch into a composite image, and the like.

The execution body may execute the step 203 as follows: and processing the plurality of target images according to the image analysis results corresponding to the plurality of target images respectively according to the image synthesis requirements represented by the request analysis results through the artificial intelligence large model to obtain a synthesized image.

Taking an example that the image synthesis requirement is to splice a plurality of target images into a synthesized image according to a certain mode, the execution subject can determine the splicing mode and the splicing sequence of the plurality of target images through the artificial intelligent large model, and then splice the plurality of target images according to the splicing mode and the splicing mode to obtain the synthesized image.

Taking the image composition requirement as an example, determining at least partial areas from each target image and taking a composition image as a composition example, the execution subject can determine the composition part of each target image, the composition sequence and the composition mode of the composition parts through an artificial intelligence large model according to the image analysis results and the image composition requirement corresponding to each of a plurality of target images, and then, the composition images are obtained by the composition of the target images according to the composition sequence and the composition mode.

In the implementation mode, the image processing mode aiming at the target image is provided under the requirement of image synthesis, and convenience and flexibility of the image synthesis process are further improved based on the artificial intelligence large model.

In some optional implementations of this embodiment, the above-described execution body may execute the image synthesis process by:

firstly, determining an object group formed by mutually fused objects among a plurality of target images according to the image synthesis requirement represented by a request analysis result through an artificial intelligence large model.

For example, each object in each target image, the executing body may randomly determine the object fused with the object from other target images through the artificial intelligence large model, so as to obtain an object group. For another example, the object group may be obtained by determining the object in which the plurality of target images are fused with each other based on the selection operation of the user.

Secondly, fusing the objects in each object group in at least one object group according to the image synthesis requirement through the artificial intelligence large model to obtain a synthesized image.

The fusion is, for example, to fuse the features of each object in the object group to obtain a new fused object, and to form the new object into the composite image.

In the implementation mode, another image processing mode aiming at the target image is provided under the requirement of image synthesis, the image processing mode is enriched, and the convenience and the flexibility of the image synthesis process are further improved based on the artificial intelligence large model.

In some alternative implementations of the present embodiment, the processing requirements are video composition requirements for multiple target images. In this implementation manner, the execution body may execute the step 203 as follows: and determining a plurality of images to be processed from the plurality of target images according to the video synthesis requirements represented by the request analysis results and the image analysis results corresponding to the plurality of target images through the artificial intelligence large model, and generating a synthesized video based on the plurality of images to be processed.

By way of example, through the artificial intelligence large model, the selection mode and the synthesis order of the images to be processed can be determined according to the video synthesis requirement, then the images to be processed are determined from the target images according to the selection mode, and the synthesis video is generated based on the images to be processed according to the synthesis order,

The selection mode includes, but is not limited to, a selection mode based on shooting time corresponding to the target image, and a selection mode based on an object in the target image.

In the implementation mode, the image processing mode aiming at the target image is enriched under the video synthesis requirement, and the convenience and the flexibility of the video synthesis process are further improved based on the artificial intelligence large model.

In some alternative implementations of the present embodiment, the processing requirements include multiple processing sub-requirements for the target image. Each processing sub-requirement of the plurality of processing sub-requirements may be a first attribute adjustment requirement, a second attribute adjustment requirement, an object addition requirement, an animation requirement, an image composition requirement, or a video composition requirement described above.

In this implementation manner, the execution body may execute the step 203 as follows:

first, for each processing sub-requirement of the plurality of processing sub-requirements, processing the target image according to the processing sub-requirement through the artificial intelligence large model to obtain a processed image.

Second, a target video is generated based on the plurality of processed images through the artificial intelligence large model.

As an example, the execution subject may combine the plurality of processed images obtained based on the plurality of processing sub-demands in order of the plurality of processing sub-demands to generate the target video.

As yet another example, the execution subject may receive a sequence designating operation by the user after obtaining the plurality of processed images, and then combine the plurality of processed images according to the sequence determined by the sequence designating operation to generate the target video.

In the implementation mode, the image processing mode aiming at the target image under the requirements of a plurality of processing sub-modes is provided, the image processing mode is enriched, and the convenience and the flexibility of image processing are further improved based on the artificial intelligence large model.

With continued reference to fig. 3, fig. 3 is a schematic diagram 300 of an application scenario of the image processing method based on the artificial intelligence large model according to the present embodiment. In the application scenario of fig. 3, a user 301 selects a target image in an album of a mobile terminal 302, and inputs an image processing request for the target image in the mobile terminal 302. After acquiring the target image and the image processing request of the user 301 for the target image, the terminal device 302 transmits the target image and the image processing request to the server 303. After determining a target image and an image processing request of a user on the target image, the server firstly analyzes the target image and the image processing request respectively through an artificial intelligent large model to obtain an image analysis result and a request analysis result; then, the target image is processed according to the processing requirement represented by the request analysis result through the artificial intelligence large model, and the processed image or the processed video is generated and fed back to the terminal equipment 302.

In this embodiment, an image processing method and apparatus based on an artificial intelligence large model are provided, where a user only needs to send an image processing request to the artificial intelligence large model, and the artificial intelligence large model can process a target image according to a processing requirement represented by a request analysis result, so as to achieve an image processing effect expected by the user, improve flexibility and convenience of an image processing process, and improve experience of the user in the image processing process.

With continued reference to FIG. 4, there is shown a schematic flow 400 of yet another embodiment of an artificial intelligence large model based image processing method according to the present disclosure. In flow 400, the following steps are included:

step 401, acquiring a target image and an image processing request of a user for the target image.

And step 402, analyzing the target image through the artificial intelligence large model, and determining the object included in the target image, the position of the object and the interaction relation among the objects to obtain an image analysis result.

Step 403, analyzing the image processing request through the artificial intelligence large model, determining the processing requirement of the user on the target image and/or the object in the target image, and obtaining the request analysis result.

Step 404, processing the target image according to the processing requirement represented by the request analysis result and the image analysis result through the artificial intelligence large model.

The processing requirement may be the first attribute adjustment requirement, the second attribute adjustment requirement, the object addition requirement, the animation requirement, the image composition requirement or the video composition requirement.

As can be seen from this embodiment, compared with the embodiment corresponding to fig. 2, the flow 400 of the image processing method based on the artificial intelligence large model in this embodiment specifically illustrates the image analysis process based on the artificial intelligence large model and the request analysis process of the image processing request, so as to accurately determine the image analysis result and the request analysis result, thereby being beneficial to further improving the flexibility and convenience of the image processing process and improving the experience of the user in the image processing process.

With continued reference to fig. 5, as an implementation of the method illustrated in the foregoing figures, the present disclosure provides an embodiment of an image processing apparatus based on an artificial intelligence large model, which corresponds to the method embodiment illustrated in fig. 2, and which is particularly applicable to various electronic devices.

As shown in fig. 5, an image processing apparatus 500 based on an artificial intelligence large model includes: an acquisition unit 501 configured to acquire a target image and an image processing request of a user for the target image; the analyzing unit 502 is configured to analyze the target image and the image processing request through the artificial intelligence large model respectively to obtain an image analysis result and a request analysis result; the processing unit 503 is configured to process the target image according to the image analysis result through the artificial intelligence large model according to the processing requirement characterized by the request analysis result.

In some optional implementations of the present embodiment, the parsing unit 502 is further configured to: and analyzing the target image through the artificial intelligence large model, and determining the object and the position of the object included in the target image to obtain an image analysis result.

In some optional implementations of the present embodiment, the parsing unit 502 is further configured to: and analyzing the target image through the artificial intelligence large model, and determining the object included in the target image, the position of the object and the interaction relation among the objects to obtain an image analysis result.

In some optional implementations of the present embodiment, the parsing unit 502 is further configured to: and analyzing the image processing request through the artificial intelligence large model, determining the processing requirement of a user on the target image and/or the object in the target image, and obtaining a request analysis result.

In some optional implementations of the present embodiment, the processing requirement is a first attribute adjustment requirement for attribute information of the target image, and the processing unit 503 is further configured to: and adjusting the attribute information of the target image according to the first attribute adjustment requirement represented by the request analysis result and the image analysis result through the artificial intelligence large model.

In some optional implementations of the present embodiment, the processing requirement is a second attribute adjustment requirement for attribute information of a target object in the target image, and the processing unit 503 is further configured to: and adjusting the attribute information of the target object in the target image according to the second attribute adjustment requirement represented by the request analysis result by the artificial intelligence large model.

In some optional implementations of the present embodiment, the processing requirement is an object adjustment requirement for a target object in the target image, and the processing unit 503 is further configured to: and adjusting the target object in the target image according to the object adjustment requirement represented by the request analysis result by using the artificial intelligence large model and the image analysis result.

In some optional implementations of the present embodiment, the object adjustment requirement is an object deletion requirement for a target object in the target image, and the processing unit 503 is further configured to: deleting a target object in the target image according to the object deletion requirement represented by the request analysis result and the image analysis result through the artificial intelligence large model; filling pixels in the deleted region according to pixels in the surrounding region of the deleted region, wherein the deleted region is a region obtained after deleting the target object in the target image; and adjusting objects outside the target object in the target image according to the interaction relation.

In some optional implementations of the present embodiment, the processing requirement is an object addition requirement to add a specified object in the target image, and the processing unit 503 is further configured to: adding a specified object in the target image according to the object increasing requirement represented by the request analysis result through the artificial intelligence large model; and adjusting the specified object and the object in the target image according to the image analysis result.

In some optional implementations of the present embodiment, the processing requirements are animation requirements for the target image, and the processing unit 503 is further configured to: and generating a dynamic image sequence corresponding to the target image according to the image analysis result by using the artificial intelligent large model according to the animation production requirement represented by the request analysis result.

In some optional implementations of the present embodiment, the processing unit 503 is further configured to: determining the animation type corresponding to each object in the image analysis result according to the animation production requirement represented by the request analysis result through the artificial intelligence large model; and for each object in the image analysis result, generating a dynamic object according to the animation type corresponding to the object, and adjusting the dynamic object according to the interaction relation.

In some optional implementations of the present embodiment, the processing requirement is an image composition requirement for a plurality of target images, and the processing unit 503 is further configured to: and processing the plurality of target images according to the image analysis results corresponding to the plurality of target images respectively according to the image synthesis requirements represented by the request analysis results through the artificial intelligence large model to obtain a synthesized image.

In some optional implementations of the present embodiment, the processing unit 503 is further configured to: determining an object group formed by mutually fused objects among a plurality of target images according to the image synthesis requirement represented by a request analysis result through an artificial intelligence large model; and fusing the objects in each object group in at least one object group according to the image synthesis requirement through the artificial intelligence large model to obtain a synthesized image.

In some optional implementations of the present embodiment, the processing requirement is a video composition requirement for a plurality of target images, and the processing unit 503 is further configured to: and determining a plurality of images to be processed from the plurality of target images according to the video synthesis requirements represented by the request analysis results and the image analysis results corresponding to the plurality of target images through the artificial intelligence large model, and generating a synthesized video based on the plurality of images to be processed.

In some alternative implementations of the present embodiment, the processing requirements include a plurality of processing sub-requirements for the target image, and the processing unit 503 is further configured to: processing the target image according to each processing sub-requirement in the plurality of processing sub-requirements through the artificial intelligence large model to obtain a processed image; and generating a target video based on the plurality of processed images through the artificial intelligence large model.

In this embodiment, an image processing device based on an artificial intelligence large model is provided, a user only needs to send an image processing request to the artificial intelligence large model, the artificial intelligence large model can process a target image according to a processing requirement represented by a request analysis result, an image processing effect expected by the user is achieved, flexibility and convenience of an image processing process are improved, and experience of the user in the image processing process is improved.

According to an embodiment of the present disclosure, the present disclosure further provides an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to implement the artificial intelligence large model based image processing method described in any of the embodiments above.

According to an embodiment of the present disclosure, there is also provided a readable storage medium storing computer instructions for enabling a computer to implement the artificial intelligence large model-based image processing method described in any of the above embodiments when executed.

The presently disclosed embodiments provide a computer program product that, when executed by a processor, enables the artificial intelligence large model based image processing method described in any of the above embodiments.

Fig. 6 illustrates a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as image processing methods based on artificial intelligence large models. For example, in some embodiments, the image processing method based on the artificial intelligence large model may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the artificial intelligence large model based image processing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the image processing method based on the artificial intelligence large model in any other suitable way (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called as a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of large management difficulty and weak service expansibility in the traditional physical host and virtual special server (VPS, virtual Private Server) service; or may be a server of a distributed system or a server incorporating a blockchain.

According to the technical scheme of the embodiment of the disclosure, the image processing method and the device based on the artificial intelligence large model are provided, a user only needs to send an image processing request to the artificial intelligence large model, the artificial intelligence large model can process a target image according to the processing requirement represented by the request analysis result, the image processing effect expected by the user is achieved, the flexibility and the convenience of the image processing process are improved, and the experience degree of the user in the image processing process is improved.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions provided by the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. An image processing method based on an artificial intelligence large model, comprising:

acquiring a target image and an image processing request of a user for the target image;

respectively analyzing the target image and the image processing request through an artificial intelligent large model to obtain an image analysis result and a request analysis result;

and processing the target image according to the image analysis result by the artificial intelligence large model according to the processing requirement represented by the request analysis result.

2. The method of claim 1, wherein resolving the target image by an artificial intelligence large model results in an image resolution result, comprising:

and analyzing the target image through the artificial intelligence large model, and determining the object included in the target image and the position of the object to obtain the image analysis result.

3. The method of claim 2, wherein the analyzing the target image by the artificial intelligence large model, determining an object included in the target image and a position of the object, and obtaining the image analysis result, includes:

and analyzing the target image through the artificial intelligent large model, and determining an object included in the target image, the position of the object and the interaction relation among the objects to obtain the image analysis result.

4. The method of claim 1, wherein parsing the image processing request through an artificial intelligence large model to obtain a request parsing result comprises:

and analyzing the image processing request through the artificial intelligence large model, determining the processing requirement of the user on the target image and/or the object in the target image, and obtaining the request analysis result.

5. The method of claim 4, wherein the processing requirement is a first attribute adjustment requirement for attribute information of the target image, and

the processing the target image according to the processing requirement represented by the request analysis result through the artificial intelligence large model and the image analysis result comprises the following steps:

and adjusting the attribute information of the target image according to the first attribute adjustment requirement represented by the request analysis result and the image analysis result through the artificial intelligent large model.

6. The method of claim 4, wherein the processing requirement is a second attribute adjustment requirement for attribute information of a target object in the target image, and

And adjusting the attribute information of the target object in the target image according to the second attribute adjustment requirement represented by the request analysis result through the artificial intelligence large model and the image analysis result.

7. The method of claim 4, wherein the processing requirement is an object adjustment requirement for a target object in the target image, and

and adjusting a target object in the target image according to the object adjustment requirement represented by the request analysis result through the artificial intelligence large model and the image analysis result.

8. The method of claim 7, wherein the object adjustment requirement is an object deletion requirement for a target object in the target image, and

the adjusting, by the artificial intelligence large model, the target object in the target image according to the object adjustment requirement represented by the request analysis result and the image analysis result, including:

deleting a target object in the target image according to the object deletion requirement represented by the request analysis result and the image analysis result through the artificial intelligent large model;

Filling pixels in the deleted region according to pixels in the surrounding region of the deleted region, wherein the deleted region is a region obtained after deleting the target object in the target image;

and adjusting objects outside the target object in the target image according to the interaction relation.

9. The method of claim 4, wherein the processing requirement is an object add requirement to add a specified object in the target image, and

adding the specified object in the target image according to the object increasing requirement represented by the request analysis result through the artificial intelligence large model;

and adjusting the specified object and the object in the target image according to the image analysis result.

10. The method of claim 4, wherein the processing requirements are animation requirements for the target image, and

And generating a dynamic image sequence corresponding to the target image according to the image analysis result by the artificial intelligent large model according to the animation production requirement represented by the request analysis result.

11. The method of claim 10, wherein the generating, by the artificial intelligence large model, the dynamic image sequence corresponding to the target image according to the animation requirements characterized by the request resolution result, includes:

determining the animation type corresponding to each object in the image analysis result according to the animation production requirement represented by the request analysis result through the artificial intelligent large model;

and generating a dynamic object according to the animation type corresponding to each object in the image analysis result, generating the dynamic image sequence, and adjusting the dynamic object according to the interaction relation.

12. The method of claim 4, wherein the processing requirement is an image composition requirement for a plurality of target images, and

And processing the plurality of target images according to the image analysis results corresponding to the plurality of target images according to the image synthesis requirements represented by the request analysis results through the artificial intelligence large model to obtain a synthesized image.

13. The method of claim 12, wherein the processing, by the artificial intelligence large model, the plurality of target images according to the image composition requirement characterized by the request resolution result and the image resolution result corresponding to each of the plurality of target images to obtain the composite image includes:

determining an object group formed by mutually fused objects among the plurality of target images according to the image synthesis requirement represented by the request analysis result through the artificial intelligence large model;

and fusing the objects in each object group in at least one object group according to the image synthesis requirement through the artificial intelligence large model to obtain the synthesized image.

14. The method of claim 4, wherein the processing requirement is a video composition requirement for a plurality of target images, and

And determining a plurality of images to be processed from the plurality of target images according to the video synthesis requirements represented by the request analysis results and the image analysis results corresponding to the plurality of target images through the artificial intelligence large model, and generating a synthesized video based on the plurality of images to be processed.

15. The method of any of claims 1-14, wherein the processing requirements include a plurality of processing sub-requirements for the target image, and

for each processing sub-requirement in the plurality of processing sub-requirements, processing the target image according to the processing sub-requirement through the artificial intelligence large model to obtain a processed image;

and generating a target video based on the plurality of processed images through the artificial intelligence large model.

16. An image processing apparatus based on an artificial intelligence large model, comprising:

an acquisition unit configured to acquire a target image and an image processing request of a user for the target image;

The analysis unit is configured to analyze the target image and the image processing request through the artificial intelligent large model respectively to obtain an image analysis result and a request analysis result;

and the processing unit is configured to process the target image according to the processing requirement represented by the request analysis result through the artificial intelligence large model and the image analysis result.

17. The apparatus of claim 16, wherein the parsing unit is further configured to:

18. The apparatus of claim 17, wherein the parsing unit is further configured to:

19. The apparatus of claim 16, wherein the parsing unit is further configured to:

20. The apparatus of claim 19, wherein the processing requirement is a first attribute adjustment requirement for attribute information of the target image, and

the processing unit is further configured to:

21. The apparatus of claim 19, wherein the processing requirement is a second attribute adjustment requirement for attribute information of a target object in the target image, and

the processing unit is further configured to:

22. The apparatus of claim 19, wherein the processing requirement is an object adjustment requirement for a target object in the target image, and

the processing unit is further configured to:

23. The apparatus of claim 22, wherein the object adjustment requirement is an object deletion requirement for a target object in the target image, and

the processing unit is further configured to:

deleting a target object in the target image according to the object deletion requirement represented by the request analysis result and the image analysis result through the artificial intelligent large model; filling pixels in the deleted region according to pixels in the surrounding region of the deleted region, wherein the deleted region is a region obtained after deleting the target object in the target image; and adjusting objects outside the target object in the target image according to the interaction relation.

24. The apparatus of claim 19, wherein the processing requirement is an object add requirement to add a specified object in the target image, an

The processing unit is further configured to:

adding the specified object in the target image according to the object increasing requirement represented by the request analysis result through the artificial intelligence large model; and adjusting the specified object and the object in the target image according to the image analysis result.

25. The apparatus of claim 19, wherein the processing requirement is an animation requirement for the target image, and

the processing unit is further configured to:

26. The apparatus of claim 25, wherein the processing unit is further configured to:

determining the animation type corresponding to each object in the image analysis result according to the animation production requirement represented by the request analysis result through the artificial intelligent large model; and generating a dynamic object for each object in the image analysis result according to the animation type corresponding to the object, and adjusting the dynamic object according to the interaction relation.

27. The apparatus of claim 19, wherein the processing requirement is an image composition requirement for a plurality of target images, and

the processing unit is further configured to:

28. The apparatus of claim 27, wherein the processing unit is further configured to:

determining an object group formed by mutually fused objects among the plurality of target images according to the image synthesis requirement represented by the request analysis result through the artificial intelligence large model; and fusing the objects in each object group in at least one object group according to the image synthesis requirement through the artificial intelligence large model to obtain the synthesized image.

29. The apparatus of claim 19, wherein the processing requirement is a video composition requirement for a plurality of target images, and

the processing unit is further configured to:

30. The apparatus of any of claims 16-29, wherein the processing requirements include a plurality of processing sub-requirements for the target image, and

The processing unit is further configured to:

for each processing sub-requirement in the plurality of processing sub-requirements, processing the target image according to the processing sub-requirement through the artificial intelligence large model to obtain a processed image; and generating a target video based on the plurality of processed images through the artificial intelligence large model.

31. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-15.

32. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-15.

33. A computer program product comprising: computer program which, when executed by a processor, implements the method according to any of claims 1-15.