Data processing method and device

Abstract

The invention discloses a data processing method and device.The data processing method comprises the steps that attribute description information of a target sub-object is obtained, and the target sub-object is at least one of at least one sub-object used for generating the target object; generating a target file including the target object according to the attribute description information; wherein the attribute description information is used for indicating the presentation effect of the target sub-object in the target file.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and in particular, relates to a data processing method and device. Background Art

[0002] AIGC (Artificial Intelligence Generated Content) is an artificial intelligence technology used to automatically generate a variety of content, including text, code, images, audio, video, etc. At present, when AIGC is used to generate required content such as images, the generated content is difficult to meet the real needs of users. Summary of the invention

[0003] To this end, this application discloses the following technical solutions:

[0004] A data processing method, comprising:

[0005] Obtaining attribute description information of a target sub-object, wherein the target sub-object is at least one of at least one sub-object used to generate the target object;

[0006] generating a target file including the target object according to the attribute description information;

[0007] The attribute description information is used to indicate the presentation effect of the target sub-object in the target file.

[0008] Optionally, obtaining the attribute description information of the target sub-object includes:

[0009] Obtaining attribute description information of at least one sub-object and a target sub-object, wherein the target sub-object is at least one of the at least one sub-object;

[0010] Correspondingly, generating a target file including the target object according to the attribute description information includes:

[0011] A target file including a target object is generated according to the sub-object and the attribute description information, wherein the target object is generated from the at least one sub-object.

[0012] Optionally, the attribute description information of the target sub-object is obtained, including at least one of the following:

[0013] Obtaining annotation information for a target sub-object input by a target user, and using the annotation information or first target information represented by the annotation information as attribute description information of the target sub-object;

[0014] Obtaining additional information input into the target area by the target user, and using the additional information or second target information represented by the additional information as attribute description information of the target sub-object;

[0015] Obtaining behavior parameters of a target user when inputting a target sub-object, and obtaining attribute description information of the target sub-object based on the behavior parameters;

[0016] Obtaining display parameters or audio parameters of a target sub-object, and obtaining attribute description information of the target sub-object based on the display parameters or audio parameters;

[0017] The time sequence information of the sub-object input by the target user and the additional information input into the target area is obtained, and the attribute description information of the target sub-object is obtained based on the time sequence information.

[0018] Optionally, obtaining attribute description information of the target sub-object based on the time series information includes:

[0019] If a first time interval exists between the first target sub-object input by the target user and the first additional information input into the first target area, the first additional information or the target information represented by the first additional information is used as the attribute description information of the first target sub-object;

[0020] If there is a second time interval between the second additional information input by the target user into the second target area and the currently existing sub-object, based on the association operation between the second additional information and the second target sub-object, the second additional information or the target information represented by it is used as the attribute description information of the second target sub-object, and the second target sub-object is at least one of the currently existing sub-objects.

[0021] Optionally, generating a target file including the target object according to the attribute description information includes:

[0022] Determine, according to the attribute description information, a pending operation for the target sub-object and a logical relationship between the pending operations;

[0023] A corresponding processing operation is performed on the target sub-object according to the logical relationship to generate a target file including the target object.

[0024] Optionally, performing a corresponding processing operation on the target sub-object according to the logical relationship to generate a target file including the target object includes at least one of the following:

[0025] In the case that the target sub-object is unique but the operation to be processed for the unique target sub-object is not unique, the target sub-object is processed according to the temporal relationship between the operations to be processed and / or the spatial relationship between the operated objects acted upon by the operations to be processed, to generate a target file including the target object;

[0026] In the case where the target sub-object is not unique but the operation to be processed for each target sub-object is unique, the target sub-object is processed according to the temporal relationship between the operations to be processed and / or the spatial relationship between the target sub-objects to generate a target file including the target object;

[0027] When the target sub-object is not unique and the operations to be processed for each target sub-object are not unique, the target sub-object is processed according to the temporal relationship between the operations to be processed, the spatial relationship between the operated objects acted upon by the operations to be processed, or the influence relationship between the target sub-objects to generate a target file including the target object.

[0028] Optionally, generating a target file including the target object according to the attribute description information includes at least one of the following:

[0029] In the case where the obtained target sub-object is unique, using an artificial intelligence model that matches the unique target sub-object or its attribute description information to generate a target file including the target object according to the attribute description information of the target sub-object;

[0030] In the case that the obtained target sub-object is not unique, a target file including the target object is generated according to the association relationship between the target sub-objects and the attribute description information using a corresponding target generation strategy.

[0031] Optionally, generating a target file including the target object according to the association relationship between the target sub-objects and the attribute description information with a corresponding target generation strategy includes at least one of the following:

[0032] adjusting the attribute description information of the target sub-objects according to the positional relationship between the target sub-objects, and generating a target file including the target object according to the adjusted attribute description information;

[0033] Adjusting the attribute description information of the target sub-objects according to the proportional relationship between the target sub-objects, and generating a target file including the target object according to the adjusted attribute description information;

[0034] The attribute description information of the target sub-object is adjusted according to the positional relationship or proportional relationship between the target sub-object and other obtained sub-objects, and a target file including the target object is generated according to the adjusted attribute description information.

[0035] Optionally, generating a target file including the target object according to the attribute description information includes at least one of the following:

[0036] After generating and processing the first target sub-object according to the first attribute description information of at least one first target sub-object to obtain a first sub-object, inputting the first sub-object and other obtained sub-objects into a corresponding artificial intelligence model, so as to generate at least one of a picture, a gif, a video, an audio, and a document including the target object by using the artificial intelligence model;

[0037] After the target sub-object is generated according to the attribute description information of the target sub-object, the generated object and other obtained sub-objects are input into a corresponding artificial intelligence model, so as to use the artificial intelligence model to generate at least one of a picture, a moving picture, a video, an audio, and a document including the target object;

[0038] After performing a first generation process according to the attribute description information and the obtained sub-object, the generated object is input into the corresponding artificial intelligence model again to generate at least one of a picture, a dynamic picture, a video, an audio, and a document including the target object;

[0039] The spatial environment information of the electronic device is obtained, and at least one of a picture, a dynamic image, a video, an audio, and a document including the target object is generated according to the spatial environment information and the attribute description information, wherein the electronic device is a device for generating a target file.

[0040] A data processing device, comprising:

[0041] An acquisition module, used to obtain attribute description information of a target sub-object, where the target sub-object is at least one of at least one sub-object used to generate the target object;

[0042] A generating module, used for generating a target file including the target object according to the attribute description information;

[0043] The attribute description information is used to indicate the presentation effect of the target sub-object in the target file. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0045] Figure 1 It is a flow chart of the data processing method provided by this application;

[0046] Figure 2 This is an example of using known technology to generate AI images;

[0047] Figure 3 It is another flow chart of the data processing method provided by the present application;

[0048] Figure 4 is an example of the target sub-object and its attribute description information provided by this application;

[0049] Figure 5 This application provides Figure 4 Examples of generated image content;

[0050] Figure 6 It is another flow chart of the data processing method provided by the present application;

[0051] Figure 7 It is another flow chart of the data processing method provided by the present application;

[0052] FIG8(a) and FIG8(b) are two other examples of target sub-objects and their attribute description information provided by the present application;

[0053] FIG8( c ) is an example of the image content generated for FIG8( a ) and FIG8( b ) provided by the present application;

[0054] FIG9( a ) is another example of a target sub-object and its attribute description information provided by the present application;

[0055] FIG9( b ) is an example of the image content generated for FIG9( a ) provided by the present application;

[0056] Fig.10 It is a structural diagram of the data processing device provided by the present application;

[0057] Fig.11 It is a structural diagram of the electronic device provided in this application. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] The present application provides a data processing method and device for solving the problem that the generated content is difficult to meet the real needs of users when the known technology uses artificial intelligence models such as AIGC to generate content. The data processing method provided by the present application can be used in many electronic devices under general or special computing device environments or configurations, such as personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor devices, etc.

[0060] See also Figure 1 The data processing method provided by the present application includes the following processing steps:

[0061] Step 101: Obtain attribute description information of a target sub-object, where the target sub-object is at least one of at least one sub-object used to generate a target object.

[0062] The target object may be, but is not limited to, various types of content objects such as images, audio, video, PPT, documents, etc. The at least one sub-object used to generate the target object may include, but is not limited to, at least one sub-object used to generate content objects such as images, audio, and videos, and specifically includes, but is not limited to, local lines, local areas, and image drawing sketches used to generate images, voice clips used to generate audio, and video material clips used to generate videos, etc.

[0063] The target sub-object is at least one of the at least one sub-object used to generate the target object. Optionally, the target sub-object can be a sub-object with property setting requirements selected or specified by the user from the at least one sub-object used to generate the target object based on a corresponding selection / specification operation. The number of target sub-objects can be one or more, without limitation, depending on actual needs.

[0064] The user can select or specify the required number of target sub-objects from the at least one sub-object used to generate the target object, and set properties for them through any one or more selection / specification operations such as, but not limited to, box selection, point selection, text input, voice input, etc., to generate property description information for the target sub-objects through the property setting operation.

[0065] The attribute description information is used to indicate the presentation effect of the target sub-object in the target file.

[0066] Optionally, the presentation effect may refer to the output effect on the target sub-object (such as local lines, local areas, etc. of the image) in the target file when outputting the target file, or it may refer to the presentation effect on the target sub-object in the target file when sharing or otherwise processing the target file. It may depend on actual needs. Generally, it mainly refers to the output effect on the target sub-object in the target file when outputting the target file, such as the display effects such as color, brightness, rendering effect and other display effects on the local lines or local areas of the image.

[0067] The attribute description information of the target sub-object may include, but is not limited to, any one or more of the display attribute description information, audio attribute description information, action attribute description information, change attribute description information, etc. of the target sub-object.

[0068] Exemplarily, the display attribute description information of the target sub-object may include, but is not limited to, the color, saturation, brightness, display style, rendering effect, size ratio between the target sub-object and other connected sub-objects, and combination characteristics with other connected sub-objects (such as the relative angle and relative direction between the target sub-object and other connected sub-objects), etc. The audio attribute description information of the target sub-object may include, but is not limited to, volume, timbre, pitch, sound effects (such as explosion sound effects, metal sound effects, water flow sound effects, funny sound effects), duration, etc. The action attribute description information of the target sub-object includes, but is not limited to, the movement of the target sub-object itself (such as running and jumping), the action applied to the use of the tool (such as holding, grabbing, lifting), etc. The change attribute description information of the target sub-object includes, but is not limited to, the change of line thickness, hue, volume / tone, etc. of the target sub-object, such as the line gradually becoming thicker and the volume gradually becoming smaller.

[0069] According to the needs, the user can select / specify the required target sub-object from the created sub-objects based on the corresponding selection / specification operations and set the properties for it to obtain the property description information of the target sub-object during the process of creating the sub-objects for generating the target object. Alternatively, the user can load an existing content object and select / specify the required target sub-object from the sub-objects contained in the loaded object based on the corresponding selection / specification operations and set the properties for it to obtain the property description information of the target sub-object. There is no limitation to this.

[0070] For example, when a user is drawing an image on an electronic device, he or she selects a corresponding line or area from the drawn local lines and local areas as a target sub-object, and sets its color, saturation, display style, rendering effect and other attributes. Alternatively, the user loads a picture locally on the electronic device or downloaded from the Internet, selects a corresponding local line or local area from the loaded picture as a target sub-object, and sets any one or more of the above display attributes as needed.

[0071] During implementation, for an image (or partial image) drawn by a user, or for an image loaded by a user, the drawn image / partial image or loaded image can be analyzed for details such as local lines and local areas to obtain various sub-objects of the drawn image / partial image or loaded image that can be used for selection and attribute editing.

[0072] Step 102: Generate a target file including the target object according to the attribute description information.

[0073] The target file may be, but is not limited to, a picture, an audio clip, a video clip, or an atlas, a PPT, a document, etc., depending on the actual application.

[0074] After obtaining the attribute description information of the target sub-object, the embodiment of the present application generates a target file including the target object according to the attribute description information, which may specifically include but is not limited to generating a presentation effect for the target sub-object based on the attribute description information of the target sub-object, and generating an overall presentation effect of the target object based on the presentation effect of the target sub-object, for example, performing local polishing on the target sub-object (such as local lines, local areas) based on the color description information of the target sub-object, generating an overall color theme for the target object based on the local polishing of the target sub-object, and so on, so as to generate a target file including the target object on this basis.

[0075] The target sub-object presents the presentation effect indicated by the attribute description information in the generated target file. Taking the target sub-object as a local line or a local area in the drawn image as an example, the line or area can present the display effect such as color, saturation and / or rendering effect indicated by its display attribute description information in the generated target image; taking the target sub-object as a voice clip as an example, the voice clip can present the audio effect such as volume, timbre, pitch and / or sound effect indicated by its audio attribute description information in the generated audio file.

[0076] Optionally, a generative artificial intelligence model, namely an AIGC model, may be used to generate a target file including the target object according to the attribute description information.

[0077] Further, when generating a target file including the target object according to the attribute description information based on the AIGC model, the attribute description information of the target sub-object can be provided to the AIGC model in the form of text description as a feature input based on the interactive method provided by AIGC, so that the AIGC model generates a target file including the target object according to the input attribute description information.

[0078] After generating the target file containing the target object, the generated target file can be output as needed. Specifically, it can be, but not limited to, outputting the generated pictures, audio, video or atlas, PPT, documents and any other types of target files on a single screen or multiple screens according to the actual needs of the application scenario. The corresponding output method can be display output, audio output or a combination of display and audio output, etc., and there is no limitation on this. For example, the generated image is output to the user's current display interface on a single screen, or the generated video is output by combining display and audio, and output on multiple screens synchronously or asynchronously, etc.

[0079] To summarize, the data processing method provided in the embodiment of the present application, by obtaining the attribute description information of the target sub-object (the attribute description information is used to indicate the presentation effect of the target sub-object in the target file), and generating a target file including the target object according to the attribute description information, can realize, when generating content, on-demand refined attribute description and presentation effect generation / adjustment of local details of the target object in the generated content (such as local lines and local areas of the image), thereby effectively meeting the real needs of users for the generated content when generating content.

[0080] In particular, when the known technology uses AIGC to generate required content such as images, it is necessary to describe the overall requirements of the content to be generated. For example, it is necessary to describe the overall picture style, color, and rendering effect of the image to be generated. Then, the AIGC model generates the target object image corresponding to the overall picture display effect based on the overall description information, such as Figure 2 In the example provided, the overall attributes of the drawn panda are described to generate a picture of the corresponding overall picture effect, but local details cannot be specially processed. The data processing method provided in the embodiment of the present application overcomes this problem. Based on the present application, the local details of the target object in the generated content can be refined in the attribute description and presentation effect generation / adjustment as needed, which further improves the accuracy and precision of content generation, and can effectively meet the personalized requirements of users for local details in content generation, solving the problem that known technologies are difficult to meet the real needs of users when generating content.

[0081] In an alternative embodiment, see Figure 3 In the data processing method flow chart shown in FIG. 1 , step 101, i.e. obtaining the attribute description information of the target sub-object, can be implemented as follows:

[0082] Step 301: Obtain attribute description information of at least one sub-object and a target sub-object, wherein the target sub-object is at least one of the at least one sub-object.

[0083] The at least one sub-object is respectively a corresponding sub-object used to generate the target object, such as a local line, a local drawing area, an overall drawing sketch, etc. used to generate an image.

[0084] In this step, specifically, at least one sub-object used to generate the target object can be obtained, as well as the attribute description information of the target sub-object, such as obtaining each local line and each local area used to generate the image, and obtaining the display attribute description information such as color, saturation, style, rendering effect, etc. of the specified target local lines or target local areas, so as to provide a data basis for the subsequent generation of a target file including the target object.

[0085] Correspondingly, see Figure 3 The step 102, i.e. generating a target file including the target object according to the attribute description information, can be specifically implemented as follows:

[0086] Step 302: Generate a target file including a target object according to the at least one sub-object and the attribute description information of the target sub-object, wherein the target object is generated from the at least one sub-object.

[0087] The step 302 may be further implemented as at least part of the following processing steps 11)-13):

[0088] 11) Generate a target object using the at least one sub-object obtained.

[0089] For example, the obtained panda head image is used to generate the panda trunk and limbs to further generate a complete panda image, or the obtained panda trunk image is used to generate a complete panda image including the trunk, head and limbs, or the obtained panda head, trunk, limbs and other sub-object images are directly used to generate a complete panda image, and so on.

[0090] 12) According to the obtained attribute description information of the target sub-object, the corresponding effect parameters of the target sub-object in the target object (the effect parameters corresponding to the attribute description information) are adjusted so that the target sub-object presents the presentation effect indicated by the attribute description information in the target object.

[0091] Specifically including but not limited to adjusting the corresponding display parameters and / or audio parameters of the target sub-object in the target object (the display parameters and / or audio parameters corresponding to the attribute description information), so that the target sub-object presents the display effect and / or audio effect indicated by the attribute description information in the target object.

[0092] For example, see Figure 4For example, assuming that the target sub-object is a panda's eye, and its attribute description information includes "panda eyes - color red", the display color of the panda's eyes in the generated panda image can be adjusted to red, thereby obtaining the display effect indicated by the attribute description information of the panda's eyes.

[0093] 12) Using the obtained attribute description information of the target sub-object, the presentation effects of the existing sub-objects of the target object are completed to obtain a complete target object, so as to generate an object file containing the target object.

[0094] Among them, the attribute information of other sub-objects other than the target sub-object in the current sub-objects of the target object can be first determined according to the attribute description information of the target sub-object, including but not limited to determining the display parameters and / or audio parameters and other rendering effect parameters of the other sub-objects, and then adjusting the current rendering effect parameters of the other sub-objects in the target object according to the determined display parameters and / or audio parameters and other rendering effect parameters. Preferably, the display parameters and / or audio parameters of the other sub-objects match the display parameters and / or audio parameters corresponding to the attribute description information of the target sub-object, so as to obtain a target object with coordinated overall rendering effects of various local details.

[0095] For example, suppose the target object is a panda image and the target sub-object is a panda eye. Figure 4 After adjusting the display parameters of the panda's eyes, the color theme and display style of other components of the panda, such as the head, trunk, and limbs, can be further determined based on the attribute description information of the panda's eyes. Based on the determined color theme and display style, the display parameters of components other than the eyes are adjusted, and finally a panda image with the corresponding color theme and display style is obtained. Specifically, Figure 5 shown.

[0096] In actual applications, the user can set the properties of the target sub-objects in the process of constructing each sub-object of the target object to obtain the property description information of the target sub-object, and adjust the effect parameters of the target sub-object based on the property description information. With the construction process of each sub-object of the target object and the gradual adjustment of the effect parameters of each target sub-object, a target file containing the target object is finally generated, and each target sub-object presents the presentation effect indicated by its property description information in the target file. Alternatively, it is also possible to load an existing content object, and select / specify the required target sub-object to set the properties to obtain the property description information of the target sub-object, and then adjust the display / audio and other effect parameters of the target sub-object based on the property description information of the target sub-object, and finally generate a target file containing the target object. In the case where the loaded content object is an image, the local and overall synchronous AI image generation can be performed based on the property description information of the target sub-object, or the AI ​​image generation can be performed in layers. The image generation here refers to the image content generation.

[0097] For example, during the drawing process, the user can assign AI feature attributes to each local line and each local area drawn, thereby generating attribute description information for each local line and local area, such as color, style, rendering effect, etc., and scheduling the AIGC model to input the attribute description information into the model. The AIGC model can capture the user's attribute description information of the drawn lines and local areas through multiple levels, and perform AI image generation in layers. As the drawing process progresses, an image that meets the user's requirements is finally obtained, achieving the effect of AI empowerment while drawing.

[0098] For another example, the user injects AI attribute description into the loaded existing image. The AI ​​attribute description is the attribute description of the entire image. Based on the overall attribute description information of the existing image, the AIGC model generates a new AI image that conforms to the overall attribute description information. Then, the local attributes of the local lines, local areas, etc. in the generated image are further described as needed. Then, the AIGC model adjusts the local detail effects based on the injected local attribute description information, and generates hierarchical images that meet the user's overall and local needs.

[0099] For example, for an existing image that has been loaded, the overall image attribute description and the local attribute description are performed, and the image with the overall and local attribute descriptions is loaded into the AIGC model. The model directly generates an image that meets the user's expectations by reading the attribute description information of local details such as local lines and local areas, as well as the overall attribute description information of the image. Both the overall and detailed designs meet the user's needs.

[0100] In summary, this embodiment can perform refined attribute description and presentation effect generation / adjustment on the local details of the target object in the generated content as needed, further improving the accuracy and precision of content generation, and can effectively meet the personalized requirements of users for local details during content generation, solving the problem that the content generated by the known technology is difficult to meet the real needs of users during content generation. In addition, the presentation effect of each sub-object currently existing in the target object can be supplemented according to the attribute description information of the target sub-object, so as to obtain the generated content (such as image content) with a coordinated and natural overall presentation effect.

[0101] In an optional embodiment, step 101 in the method provided by the present application, i.e., obtaining the attribute description information of the target sub-object, includes but is not limited to at least one of the following:

[0102] 21) Obtaining annotation information for a target sub-object input by a target user, and using the annotation information or first target information represented by the annotation information as attribute description information of the target sub-object.

[0103] The target user may be a user who has operation authority and has passed authority verification, or may be a user who is currently performing operations such as image drawing or voice input.

[0104] Optionally, for each sub-object used to generate the target object, a comment box, annotation position or annotation layer that can be used to set the properties of the sub-object can be set respectively, and optionally, the set comment box, annotation position or annotation layer is hidden by default. When the user needs to set the properties of the corresponding target sub-object, the comment box, annotation position or annotation layer of the target sub-object can be called up (for example, by box-selecting or clicking the desired target sub-object to call up the comment box corresponding to the target sub-object) to enter the desired annotation information into the called up comment box, annotation position or annotation layer. The annotation information can specifically include setting information of the property settings performed on target sub-objects such as certain local lines or voice fragments.

[0105] On this basis, the annotation information input to the target sub-object can be directly used as the attribute description information of the target sub-object, but it is not limited to this. In other embodiments, the first target information represented by the annotation information can also be used as the attribute description information of the target sub-object. Specifically, the semantic content of the annotation information can be obtained first, and then the attribute description information in a standard format (that is, the first target information represented by the annotation information) can be generated based on the semantic content, such as various parameter values ​​such as display attribute parameters and / or audio attribute parameters, and the attribute description information in the standard format can be used as the attribute description information of the target sub-object.

[0106] 22) Obtaining additional information input into the target area by the target user, and using the additional information or second target information represented by the additional information as attribute description information of the target sub-object.

[0107] Optionally, the target area may be an area associated with the target user's current application interface and may be used for information input to set properties of a sub-object in the current application interface (a sub-object used to generate the target object). The target user may input additional information about the target sub-object (such as prompt information or instruction information) into the target area to set the properties of the target sub-object, so as to obtain property description information of the target sub-object.

[0108] The obtained additional information can be directly used as the attribute description information of the target sub-object. Alternatively, the second target information represented by the additional information can be used as the attribute description information of the target sub-object. Specifically, the semantic content of the additional information can be obtained first, and then the attribute description information in a standard format (i.e., the second target information represented by the additional information) can be generated based on the semantic content, such as various parameter values ​​such as display attribute parameters and / or audio attribute parameters, and the attribute description information in the standard format can be used as the attribute description information of the target sub-object.

[0109] 23) Obtaining behavior parameters of the target user when inputting the target sub-object, and obtaining attribute description information of the target sub-object based on the behavior parameters.

[0110] The behavior parameters include, but are not limited to, any one or more of the strength, speed, tone, intonation, etc., when the target user inputs the target sub-object.

[0111] In this implementation, the target user's behavior parameters such as strength, speed, tone and / or intonation when inputting the target sub-object can be obtained, and the attribute description information of the target sub-object can be determined based on the above behavior parameters. For example, strong force indicates anger, fast speed indicates happiness, high tone indicates anger, and so on.

[0112] 24) Obtain display parameters and / or audio parameters of the target sub-object, and obtain attribute description information of the target sub-object based on the display parameters or audio parameters.

[0113] The display parameters include but are not limited to line thickness, color brightness, color concentration and other information configured for the target sub-object, and the audio parameters include but are not limited to volume, timbre, pitch, sound effect and other information configured for the target sub-object.

[0114] In this implementation, the display parameters and / or audio parameters set for the target sub-object can be obtained, and the obtained display parameters and / or audio parameters can be directly used as the attribute description information of the target sub-object. Alternatively, the obtained display parameters and / or audio parameters can be standardized and the obtained standardized parameter information can be used as the attribute description information of the target sub-object.

[0115] 25) Obtaining time sequence information of the sub-object input by the target user and the additional information input into the target area, and obtaining attribute description information of the target sub-object based on the time sequence information.

[0116] In this implementation, obtaining the attribute description information of the target sub-object based on the timing information can be further implemented as the following 31)-32)

[0117] 31) If a first time interval exists between the first target sub-object input by the target user and the first additional information input into the first target area, the first additional information or the target information represented by the first additional information is used as the attribute description information of the first target sub-object.

[0118] The first duration is less than the first threshold.

[0119] Optionally, this situation 31) can correspond to an application scenario in which the user inputs / constructs the first target sub-object while empowering it with AI attributes, for example, empowering the drawn partial lines / local areas, etc. with AI attributes while drawing. In this way, the target user can input / construct a part of the line or drawing area or voice segment, annotate the line, drawing area or voice segment or add additional information, and use the annotation information / additional information, or the target information represented by the annotation information / additional information (such as standardized display parameters / audio parameters, etc.) as the attribute description information of the line or drawing area or voice segment.

[0120] 32) If the second additional information input by the target user into the second target area is separated from the currently existing sub-object by a second time length, based on the association operation between the second additional information and the second target sub-object, the second additional information or the target information represented by it is used as the attribute description information of the second target sub-object, and the second target sub-object is at least one of the currently existing sub-objects.

[0121] The second duration is greater than the second threshold.

[0122] This situation 32) is equivalent to the target user adding / setting attribute information to the corresponding sub-object constructed previously after completing the construction of the entire target object or its partial sub-object, such as adding attribute information to the corresponding sub-object drawn previously after completing the drawing of the entire image or part of the image.

[0123] The association operation may be an operation of adding a comment after the target user clicks on a related sub-object, or an operation of inputting related information that can characterize the target sub-object, or an operation of adding additional information to a target area near the target sub-object, and the like.

[0124] In this case, based on the association operation between the second additional information and the second target sub-object, the second additional information or the target information represented by it can be used as the attribute description information of the second target sub-object, and the second target sub-object is at least one of the currently existing sub-objects.

[0125] Based on this embodiment, the attribute description information of the target sub-object can be obtained in a variety of ways. Correspondingly, the target user can configure / input the attributes of the target sub-object through a variety of operation methods as needed, further improving the flexibility and convenience of user operations. It is convenient for users to efficiently and quickly assign required attributes to local details as needed for their application scenarios (such as AI empowerment while drawing, or setting attributes of sub-objects for the completed target object) to adjust the presentation effect in a refined manner, thereby improving the efficiency and effect of content generation, reducing user operation steps and saving time.

[0126] In an alternative embodiment, see Figure 6 The data processing method flow shown in the figure, step 102 in the method provided by the present application, that is, generating a target file including the target object according to the attribute description information, can be specifically implemented as follows:

[0127] Step 601: Determine the pending operation for the target sub-object and the logical relationship between the pending operations according to the attribute description information.

[0128] Specifically, the pending operation for the target sub-object may be determined based on the display attribute description information, audio attribute description information, action attribute description information and / or change attribute description information of the target sub-object. For example, based on the display attribute description information such as color and rendering effect of the target sub-object, the pending operation for the target sub-object may be determined to be the adjustment / addition operation of display parameters such as color and rendering effect; based on the audio attribute description information such as volume, pitch, special effect sound of the target sub-object, the pending operation for the target sub-object may be determined to be the adjustment / addition operation of audio parameters such as volume, pitch, special effect sound, etc.

[0129] On this basis, the logical relationship between the pending operations can be further determined, including but not limited to the sequence and hierarchical relationship between different pending operations, such as the hierarchical relationship or sequence relationship caused by different operations targeting different layers when generating an image.

[0130] Step 602: Perform corresponding processing operations on the target sub-object according to the logical relationship to generate a target file including the target object.

[0131] Based on step 601, corresponding processing operations may continue to be performed on the target sub-object according to the logical relationship between the operations to be processed, for example, corresponding color adjustment operations, audio volume adjustment operations, rendering effect adjustment operations, etc. may be performed on the target sub-object according to the corresponding sequence or hierarchical relationship.

[0132] Further, step 602 may be specifically implemented as including at least one of the following:

[0133] 41) When the target sub-object is unique but the operation to be processed for the unique target sub-object is not unique, the target sub-object is processed according to the temporal relationship between the operations to be processed and / or the spatial relationship between the operated objects acted upon by the operations to be processed, to generate a target file including the target object.

[0134] The timing relationship is used to characterize the sequence between different operations to be processed.

[0135] The spatial relationship between the operated objects acted upon by the pending operations may be understood as the hierarchical relationship between the layers where different operated objects acted upon by different pending operations are located, or the relationship between the tracks where they are located, and the like.

[0136] Exemplarily, assuming that the target sub-object is a video clip, and assuming that the operations to be processed on the video clip include color tone adjustment, rendering effect adjustment, volume adjustment, special effect addition, etc., then according to the sequence, hierarchical relationship, relationship between the tracks, etc. of different operated objects such as video materials, audio tracks, display special effects, special effect sounds, etc. acted upon by the above-mentioned different operations to be processed, corresponding color tone adjustment, rendering effect addition, volume adjustment, special effect addition and other processing can be performed on the video clip, thereby generating a video file including the video clip.

[0137] 42) When the target sub-object is not unique but the operations to be processed for each target sub-object are unique, the target sub-object is processed according to the temporal relationship between the operations to be processed and / or the spatial relationship between the target sub-objects to generate a target file including the target object.

[0138] The temporal relationship and spatial relationship here can be found in the above description.

[0139] In this case 42), the corresponding target sub-objects can be processed specifically according to the sequence of each pending operation represented by the temporal relationship, the hierarchical relationship between the layers of different operated objects acted on by different pending operations represented by the spatial relationship, or the relationship between the tracks, so as to generate a target file including the target object.

[0140] For example, assuming that multiple target sub-objects are different local lines and / or local areas in the drawn panda image, and each local line or local area corresponds to a pending operation in operations such as tone adjustment or rendering effect addition, then each local line or local area can be processed separately according to the order of the pending operations corresponding to different local lines and / or local areas, the hierarchical relationship between the layers they are in, etc., such as adjusting the color of the local lines, applying corresponding rendering effects to the local areas, etc., to generate an image file including the panda image.

[0141] 43) When the target sub-object is not unique and the operations to be processed for each target sub-object are not unique, the target sub-object is processed according to the temporal relationship between the operations to be processed, the spatial relationship between the operated objects acted upon by the operations to be processed, or the influence relationship between the target sub-objects, to generate a target file including the target object.

[0142] The temporal relationship and spatial relationship here can also be found in the relevant descriptions above.

[0143] The influence relationship between the target sub-objects includes but is not limited to whether there is influence between the target sub-objects, and the influence ratio when there is influence, etc. For example, whether the size and hue of two interconnected local areas have an influence, and if there is an influence, when the size and hue of one area need to be adjusted, the influence ratio of the size and hue value of the other area is affected, etc.

[0144] In this case 43), the corresponding target sub-objects can be processed according to the sequence of each pending operation represented by the temporal relationship, the hierarchical relationship between the layers of different operated objects acted on by different pending operations represented by the spatial relationship or the relationship between the tracks, and / or whether there is any influence between different target sub-objects and the influence ratio if so, so as to generate a target file including the target object.

[0145] For example, assuming that multiple target sub-objects respectively include different local lines and / or local areas in the drawn panda image, and each local line or local area corresponds to multiple pending operations such as tone adjustment or rendering effect application, then multiple operations can be performed on different local lines or local areas according to the order of the pending operations corresponding to different target sub-objects, the hierarchical relationship between the layers, whether there is any influence between different target sub-objects, and the proportion of influence when there is influence, etc., such as color adjustment and rendering effect application to a local area, and adjustment of the size and tone of a local area according to the affected proportion, so as to generate an image file including the panda image.

[0146] Since this embodiment can generate / adjust the presentation effect of the local details of the target object in the generated content in a refined manner based on the attribute description information of the target sub-object, the accuracy and refinement of content generation can be improved, and the personalized requirements of users for local details in content generation can be effectively met. In combination with the description of the above embodiments, this application can support users to assign required attributes to local details through a convenient operation method to adjust their presentation effects in a refined manner, thereby improving the efficiency and effect of content generation, reducing the user operation steps and saving time.

[0147] In an alternative embodiment, see Figure 7 The data processing method flow shown in the figure, step 102 in the method provided by the present application, that is, generating a target file including the target object according to the attribute description information, can be specifically implemented as follows:

[0148] Step 701: When the obtained target sub-object is unique, an artificial intelligence model matching the unique target sub-object or its attribute description information is used to generate a target file including the target object according to the attribute description information of the target sub-object.

[0149] The artificial intelligence model that matches the target sub-object or its attribute description information may be, but is not limited to, a professional model or a refined processing model that matches the target sub-object or its attribute description information. In the case where the obtained target sub-object is unique, the corresponding professional model or refined processing model may be specifically called, and the called model may be used to generate a target file including the target object according to the attribute description information of the target sub-object.

[0150] For example, for image generation, the image generation model is called, for speech generation, the audio model is called, and if there is an attribute for applying an action, the video generation model or the dynamic image generation model can be called, and the attribute description information of the target sub-object is input as an input feature into the called model, so that the model generates a target file including the target object based on the attribute description information of the target sub-object. It is easy to understand that in the generated target file, the target sub-object presents the presentation effect indicated by the attribute description information.

[0151] Step 702: When the obtained target sub-object is not unique, generate a target file including the target object according to the association relationship between the target sub-objects and the attribute description information using a corresponding target generation strategy.

[0152] The association relationship between the target sub-objects includes, but is not limited to, a position relationship or a ratio relationship between the target sub-objects.

[0153] This step can be further implemented by including at least one of the following:

[0154] 51) adjusting the attribute description information of the target sub-objects according to the positional relationship between the target sub-objects, and generating a target file including the target object according to the adjusted attribute description information.

[0155] Optionally, the association information or difference information between the attribute description information of different target sub-objects can be adjusted according to the positional relationship between different target sub-objects, such as increasing or decreasing the difference information, or enhancing or weakening the association information, etc., but is not limited to.

[0156] For example, according to the positional relationship between different local areas in the panda image, the color difference between different local areas is enhanced or the color difference between different local areas is reduced.

[0157] On this basis, a target file including the target object is generated according to the adjusted attribute description information corresponding to the target sub-object. In the generated target file, the target sub-object correspondingly presents the presentation effect indicated by the adjusted attribute description information.

[0158] 52) adjusting the attribute description information of the target sub-objects according to the proportional relationship between the target sub-objects, and generating a target file including the target object according to the adjusted attribute description information.

[0159] In addition to the positional relationship, the attribute description information of the target sub-objects may also be adjusted according to the proportional relationship between the target sub-objects. Specifically, the association information or difference information between the attribute description information of different target sub-objects may be adjusted according to the proportional relationship between the different target sub-objects, such as increasing the difference information or reducing the difference information, or enhancing the association information or weakening the association information, etc.

[0160] For example, according to the proportional relationship between different local areas in the panda image, the special effect difference between different local areas is enhanced or reduced, and the width of the boundary lines between different local areas is enhanced or reduced.

[0161] On this basis, a target file including the target object is generated according to the adjusted attribute description information corresponding to the target sub-object. In the generated target file, the target sub-object correspondingly presents the presentation effect indicated by the adjusted attribute description information.

[0162] 53) adjusting the attribute description information of the target sub-object according to the positional relationship or proportional relationship between the target sub-object and other obtained sub-objects, and generating a target file including the target object according to the adjusted attribute description information.

[0163] Specifically, the attribute description information of the target sub-object and the other sub-objects can be optimized and adjusted according to the positional relationship or proportional relationship between the target sub-object and the other sub-objects obtained, so as to avoid the positional relationship or proportional relationship between the target sub-object and the other sub-objects from affecting the boundary or clarity between the target sub-object and the other sub-objects obtained. For example, the contrast of the local area of ​​the panda target and other local areas is improved, the sharpness is improved, etc., so as to avoid affecting the clarity or boundary of different local areas.

[0164] In the implementation, in case that the target sub-object obtained is not unique, a generative AI model, i.e., an AIGC model, can be used to generate a target file including the target object through the above processing process. Alternatively, multiple generative AI models, i.e., multiple AIGC models, can be used to generate corresponding local content for each target sub-object, and finally the target file including the target object is obtained through merging. For example, for each target sub-object, a professional model or refined processing that matches the target sub-object or its attribute description information is called respectively, and the refined presentation effect adjustment and generation for the target sub-object are performed. Finally, the target file including the target object is obtained by merging the generation results of the refined presentation effects of each model for different target sub-objects.

[0165] In view of the situation where the obtained target sub-object is not unique, this embodiment also takes into account the positional relationship, proportional relationship and other association relationships between the target sub-objects when generating the target file including the target object according to the attribute description information of the target sub-object. Accordingly, it can better reflect the differences between different target sub-objects or synchronously adjust the associated attributes of related sub-objects, thereby further improving the overall presentation effect of the object content (such as image content) in the finally generated target object.

[0166] In an optional embodiment, step 102 in the method provided by the present application, i.e., generating a target file including the target object according to the attribute description information, may be specifically implemented as including at least one of the following:

[0167] 61) After generating and processing the first target sub-object according to the first attribute description information of at least one first target sub-object to obtain a first sub-object, the first sub-object and other obtained sub-objects are input into a corresponding artificial intelligence model to use the artificial intelligence model to generate at least one of the pictures, animated images, videos, audios, and documents including the target object.

[0168] The other sub-objects include other target sub-objects other than the first target sub-object, for example, a second target sub-object.

[0169] Specifically, the first target sub-object can be generated and processed according to the first attribute description information of at least one first target sub-object to obtain a corresponding first sub-object. For example, referring to the example of Figure 8(a), assuming that the target sub-objects include panda eyes, a panda belly and panda feet, and assuming that the first target sub-object is a panda belly, as shown in Figure 8(b), a panda belly with a corresponding presentation effect can be generated according to the first attribute description information of the panda belly, such as "round, bulging and elastic". On this basis, the generated panda belly with a corresponding presentation effect and other sub-objects are input into an artificial intelligence model such as AIGC. For example, the second target sub-objects such as the panda belly and panda feet carrying attribute description information in Figure 8(a) and sub-objects other than the target sub-objects, such as panda arms, are input into AIGC, so as to use artificial intelligence models such as AIGC to generate at least one of the pictures, animated images, videos, audios and documents including the target objects, for example, to generate a panda image as shown in Figure 8(c).

[0170] 62) After the target sub-object is generated according to the attribute description information of the target sub-object, the generated object and other obtained sub-objects are input into the corresponding artificial intelligence model, so as to use the artificial intelligence model to generate at least one of the pictures, animated images, videos, audios, and documents including the target object.

[0171] Different from 61), in the processing method of 62), after considering the local content generation of all target sub-objects, the content generation is performed in combination with other non-target sub-objects. For example, after considering the raw images of all target sub-objects, the raw images are combined with other non-target sub-objects. The raw images here refer to the generation of image content.

[0172] For example, referring to the example of Figure 9(a), assuming that the user sets the panda head area, arms, and tools in the drawn panda image as target sub-objects and enters corresponding attribute description information for them respectively, the local image content of these three target sub-objects can be generated according to the corresponding attribute description information. On this basis, the generated local area image and other sub-objects are input into artificial intelligence models such as AIGC, so as to use artificial intelligence models such as AIGC to generate at least one of the pictures, animated images, videos, audios, and documents including the target objects, for example, to generate a panda image as shown in Figure 9(b).

[0173] 63) After the first generation process is performed based on the attribute description information and the obtained sub-object, the generated object is input into the corresponding artificial intelligence model again to generate at least one of the pictures, animated images, videos, audios, and documents including the target object.

[0174] Among them, the two generation processes involved here can use different AI models, or can also use the same AI model, such as using the same or different AIGC models, etc., and there is no limitation to this.

[0175] For example, after inputting the attribute description information of the panda's eyes and belly and the obtained sub-objects such as the panda's eyes, arms, belly, feet, and tools into the AIGC model and using the model to generate a panda image with the required attributes, the same AIGC model is used again to generate a dynamic image or video with the panda image.

[0176] 64) Obtaining the spatial environment information of the electronic device, and generating at least one of a picture, a dynamic image, a video, an audio, and a document including the target object according to the spatial environment information and the attribute description information, wherein the electronic device is a device for generating the target file.

[0177] The spatial environment information of the electronic device may include, but is not limited to, any one or more of the brightness, color, volume, tone, etc. of the space where the electronic device is located.

[0178] In this embodiment, the target file is generated by taking into account the environmental factors of the environment in which the electronic device is located. Specifically, the attribute description information of the target sub-object can be adjusted according to the spatial environment information such as the brightness, color, volume, and tone of the space in which the electronic device is located. For example, if the spatial brightness is too high, the brightness value in the attribute description information is increased; if the spatial volume is too high, the volume value in the attribute description information is increased, and at least one of the pictures, animated images, videos, audio, and documents of the target object can be generated according to the adjusted attribute description information. However, it is not limited to this. In actual applications, the target object can also be generated according to the attribute description information of the target sub-object first, and then the overall brightness, color, volume, tone, etc. of the target object can be adjusted according to the spatial environment information such as the spatial brightness, color, volume, and tone.

[0179] Based on this embodiment, the required target files including pictures, animated images, videos, audios, documents, etc. of the target objects can be obtained in various ways and through one or two content generation. In the content generation, the user is supported to make fine settings for local details as required, and the content generation process can be optimized and adjusted in combination with the spatial environment information of the space where the electronic device is located. This not only effectively meets the user's personalized requirements for local details in content generation, but also solves the problem that the known technology is difficult to meet the user's real needs when generating content, and can also match the generated content with the spatial environment of the space described by the user, further improving the presentation effect of the generated content.

[0180] Corresponding to the above-mentioned data processing method, the embodiment of the present application also provides a data processing device, whose composition structure is as follows: Fig.10 As shown, including:

[0181] An acquisition module 1001 is used to obtain attribute description information of a target sub-object, where the target sub-object is at least one of at least one sub-object used to generate a target object;

[0182] A generating module 1002, configured to generate a target file including the target object according to the attribute description information;

[0183] The attribute description information is used to indicate the presentation effect of the target sub-object in the target file.

[0184] In an optional implementation manner, the acquisition module 1001 is specifically configured to: obtain attribute description information of at least one sub-object and a target sub-object, wherein the target sub-object is at least one of the at least one sub-object;

[0185] The generating module 1002 is specifically used to generate a target file including a target object according to the sub-object and the attribute description information, wherein the target object is generated from the at least one sub-object.

[0186] In an optional implementation, the acquisition module 1001 is specifically configured to perform at least one of the following:

[0187] Obtaining annotation information for a target sub-object input by a target user, and using the annotation information or first target information represented by the annotation information as attribute description information of the target sub-object;

[0188] Obtaining additional information input into the target area by the target user, and using the additional information or second target information represented by the additional information as attribute description information of the target sub-object;

[0189] Obtaining behavior parameters of a target user when inputting a target sub-object, and obtaining attribute description information of the target sub-object based on the behavior parameters;

[0190] Obtaining display parameters or audio parameters of a target sub-object, and obtaining attribute description information of the target sub-object based on the display parameters or audio parameters;

[0191] The time sequence information of the sub-object input by the target user and the additional information input into the target area is obtained, and the attribute description information of the target sub-object is obtained based on the time sequence information.

[0192] In an optional implementation manner, when obtaining the attribute description information of the target sub-object based on the time series information, the acquisition module 1001 is specifically configured to:

[0193] If a first time interval exists between the first target sub-object input by the target user and the first additional information input into the first target area, the first additional information or the target information represented by the first additional information is used as the attribute description information of the first target sub-object;

[0194] If there is a second time interval between the second additional information input by the target user into the second target area and the currently existing sub-object, based on the association operation between the second additional information and the second target sub-object, the second additional information or the target information represented by it is used as the attribute description information of the second target sub-object, and the second target sub-object is at least one of the currently existing sub-objects.

[0195] In an optional implementation manner, the generating module 1002 is specifically configured to:

[0196] Determine, according to the attribute description information, a pending operation for the target sub-object and a logical relationship between the pending operations;

[0197] A corresponding processing operation is performed on the target sub-object according to the logical relationship to generate a target file including the target object.

[0198] In an optional implementation manner, the generating module 1002, when performing a corresponding processing operation on the target sub-object according to the logical relationship to generate a target file including the target object, is specifically configured to perform at least one of the following:

[0199] In the case that the target sub-object is unique but the operation to be processed for the unique target sub-object is not unique, the target sub-object is processed according to the temporal relationship between the operations to be processed and / or the spatial relationship between the operated objects acted upon by the operations to be processed, to generate a target file including the target object;

[0200] In the case where the target sub-object is not unique but the operation to be processed for each target sub-object is unique, the target sub-object is processed according to the temporal relationship between the operations to be processed and / or the spatial relationship between the target sub-objects to generate a target file including the target object;

[0201] When the target sub-object is not unique and the operations to be processed for each target sub-object are not unique, the target sub-object is processed according to the temporal relationship between the operations to be processed, the spatial relationship between the operated objects acted upon by the operations to be processed, or the influence relationship between the target sub-objects to generate a target file including the target object.

[0202] In an optional implementation manner, the generating module 1002 is specifically configured to perform at least one of the following:

[0203] In the case where the obtained target sub-object is unique, using an artificial intelligence model that matches the unique target sub-object or its attribute description information to generate a target file including the target object according to the attribute description information of the target sub-object;

[0204] In the case that the obtained target sub-object is not unique, a target file including the target object is generated according to the association relationship between the target sub-objects and the attribute description information using a corresponding target generation strategy.

[0205] In an optional implementation manner, the generating module 1002, when generating the target file including the target object according to the association relationship between the target sub-objects and the attribute description information with the corresponding target generation strategy, is specifically configured to perform at least one of the following:

[0206] adjusting the attribute description information of the target sub-objects according to the positional relationship between the target sub-objects, and generating a target file including the target object according to the adjusted attribute description information;

[0207] Adjusting the attribute description information of the target sub-objects according to the proportional relationship between the target sub-objects, and generating a target file including the target object according to the adjusted attribute description information;

[0208] The attribute description information of the target sub-object is adjusted according to the positional relationship or proportional relationship between the target sub-object and other obtained sub-objects, and a target file including the target object is generated according to the adjusted attribute description information.

[0209] In an optional implementation manner, the generating module 1002 is specifically configured to perform at least one of the following:

[0210] After generating and processing the first target sub-object according to the first attribute description information of at least one first target sub-object to obtain a first sub-object, inputting the first sub-object and other obtained sub-objects into a corresponding artificial intelligence model, so as to generate at least one of a picture, a gif, a video, an audio, and a document including the target object by using the artificial intelligence model;

[0211] After the target sub-object is generated according to the attribute description information of the target sub-object, the generated object and other obtained sub-objects are input into a corresponding artificial intelligence model, so as to use the artificial intelligence model to generate at least one of a picture, a moving picture, a video, an audio, and a document including the target object;

[0212] After performing a first generation process according to the attribute description information and the obtained sub-object, the generated object is input into the corresponding artificial intelligence model again to generate at least one of a picture, a dynamic picture, a video, an audio, and a document including the target object;

[0213] The spatial environment information of the electronic device is obtained, and at least one of a picture, a dynamic image, a video, an audio, and a document including the target object is generated according to the spatial environment information and the attribute description information, wherein the electronic device is a device for generating a target file.

[0214] The present application also provides an electronic device, the composition structure of the electronic device is as follows: Fig.11 As shown, including at least:

[0215] A memory 10, for storing a computer instruction set;

[0216] A set of computer instructions can be implemented in the form of a computer program.

[0217] The processor 20 is used to implement the data processing method provided by any of the above method embodiments by executing a computer instruction set.

[0218] The processor 20 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a neural network processor (NPU), a deep learning processor (DPU) or other programmable logic devices, etc.

[0219] The electronic device includes a display device and / or includes a display interface and can be connected to an external display device.

[0220] Optionally, the electronic device also includes a camera assembly, and / or is connected to an external camera assembly.

[0221] In addition, the electronic device may also include components such as a communication interface and a communication bus. The memory, the processor and the communication interface communicate with each other through the communication bus.

[0222] The communication interface is used for communication between electronic devices and other devices. The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0223] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0224] For the convenience of description, the above system or device is described by dividing it into various modules or units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0225] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or the part that makes a creative contribution can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0226] Finally, it should be noted that, in this article, relational terms such as first, second, third and fourth are used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0227] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A data processing method, comprising: Obtaining attribute description information of a target sub-object, wherein the target sub-object is at least one of at least one sub-object used to generate the target object; generating a target file including the target object according to the attribute description information; The attribute description information is used to indicate the presentation effect of the target sub-object in the target file.

2. The method according to claim 1, wherein: The obtaining of the attribute description information of the target sub-object includes: Obtaining attribute description information of at least one sub-object and a target sub-object, wherein the target sub-object is at least one of the at least one sub-object; Correspondingly, generating a target file including the target object according to the attribute description information includes: A target file including a target object is generated according to the sub-object and the attribute description information, wherein the target object is generated from the at least one sub-object.

3. The method according to claim 1 or 2, wherein: Obtain the property description information of the target sub-object, including at least one of the following: Obtaining annotation information for a target sub-object input by a target user, and using the annotation information or first target information represented by the annotation information as attribute description information of the target sub-object; Obtaining additional information input into the target area by the target user, and using the additional information or second target information represented by the additional information as attribute description information of the target sub-object; Obtaining behavior parameters of a target user when inputting a target sub-object, and obtaining attribute description information of the target sub-object based on the behavior parameters; Obtaining display parameters or audio parameters of a target sub-object, and obtaining attribute description information of the target sub-object based on the display parameters or audio parameters; The time sequence information of the sub-object input by the target user and the additional information input into the target area is obtained, and the attribute description information of the target sub-object is obtained based on the time sequence information.

4. The method according to claim 3, wherein: Obtaining attribute description information of the target sub-object based on the time series information includes: If a first time interval exists between the first target sub-object input by the target user and the first additional information input into the first target area, the first additional information or the target information represented by the first additional information is used as the attribute description information of the first target sub-object; If there is a second time interval between the second additional information input by the target user into the second target area and the currently existing sub-object, based on the association operation between the second additional information and the second target sub-object, the second additional information or the target information represented by it is used as the attribute description information of the second target sub-object, and the second target sub-object is at least one of the currently existing sub-objects.

5. The method according to claim 1 or 2, wherein: Generating a target file including the target object according to the attribute description information includes: Determine, according to the attribute description information, a pending operation for the target sub-object and a logical relationship between the pending operations; A corresponding processing operation is performed on the target sub-object according to the logical relationship to generate a target file including the target object.

6. The method according to claim 5, wherein: Performing corresponding processing operations on the target sub-object according to the logical relationship to generate a target file including the target object includes at least one of the following: In the case that the target sub-object is unique but the operation to be processed for the unique target sub-object is not unique, the target sub-object is processed according to the temporal relationship between the operations to be processed and / or the spatial relationship between the operated objects acted upon by the operations to be processed, to generate a target file including the target object; In the case where the target sub-object is not unique but the operation to be processed for each target sub-object is unique, the target sub-object is processed according to the temporal relationship between the operations to be processed and / or the spatial relationship between the target sub-objects to generate a target file including the target object; When the target sub-object is not unique and the operations to be processed for each target sub-object are not unique, the target sub-object is processed according to the temporal relationship between the operations to be processed, the spatial relationship between the operated objects acted upon by the operations to be processed, or the influence relationship between the target sub-objects to generate a target file including the target object.

7. The method according to claim 1 or 2, wherein: Generating a target file including the target object according to the attribute description information includes at least one of the following: In the case where the obtained target sub-object is unique, using an artificial intelligence model that matches the unique target sub-object or its attribute description information to generate a target file including the target object according to the attribute description information of the target sub-object; In the case that the obtained target sub-object is not unique, a target file including the target object is generated according to the association relationship between the target sub-objects and the attribute description information using a corresponding target generation strategy.

8. The method according to claim 7, wherein: Generating a target file including the target object according to the association relationship between the target sub-objects and the attribute description information with a corresponding target generation strategy includes at least one of the following: adjusting the attribute description information of the target sub-objects according to the positional relationship between the target sub-objects, and generating a target file including the target object according to the adjusted attribute description information; Adjusting the attribute description information of the target sub-objects according to the proportional relationship between the target sub-objects, and generating a target file including the target object according to the adjusted attribute description information; The attribute description information of the target sub-object is adjusted according to the positional relationship or proportional relationship between the target sub-object and other obtained sub-objects, and a target file including the target object is generated according to the adjusted attribute description information.

9. The method according to claim 1 or 2, wherein: Generating a target file including the target object according to the attribute description information includes at least one of the following: After generating and processing the first target sub-object according to the first attribute description information of at least one first target sub-object to obtain a first sub-object, inputting the first sub-object and other obtained sub-objects into a corresponding artificial intelligence model, so as to generate at least one of a picture, a gif, a video, an audio, and a document including the target object by using the artificial intelligence model; After the target sub-object is generated according to the attribute description information of the target sub-object, the generated object and other obtained sub-objects are input into a corresponding artificial intelligence model, so as to use the artificial intelligence model to generate at least one of a picture, a gif, a video, an audio, and a document including the target object; After performing a first generation process according to the attribute description information and the obtained sub-object, the generated object is input into the corresponding artificial intelligence model again to generate at least one of a picture, a dynamic picture, a video, an audio, and a document including the target object; The spatial environment information of the electronic device is obtained, and at least one of a picture, a dynamic image, a video, an audio, and a document including the target object is generated according to the spatial environment information and the attribute description information, wherein the electronic device is a device for generating a target file.

10. A data processing device, comprising: An acquisition module, used to obtain attribute description information of a target sub-object, where the target sub-object is at least one of at least one sub-object used to generate the target object; A generating module, used for generating a target file including the target object according to the attribute description information; The attribute description information is used to indicate the presentation effect of the target sub-object in the target file.

Images