CN116824011A

CN116824011A - Animation generation method, device, equipment and storage medium

Info

Publication number: CN116824011A
Application number: CN202310830197.0A
Authority: CN
Inventors: 胡骏杰
Original assignee: Kangjian Information Technology Shenzhen Co Ltd
Current assignee: Kangjian Information Technology Shenzhen Co Ltd
Priority date: 2023-07-06
Filing date: 2023-07-06
Publication date: 2023-09-29

Abstract

The invention relates to artificial intelligence technology in the field of digital medical treatment, and discloses an animation generation method, which comprises the following steps: acquiring animation picture information, animation text information, animation theme information and a plurality of animation template information; extracting picture characteristic information of the animation picture information and text characteristic information of the animation text information, and determining picture style information of the animation and picture content information of the animation based on the picture characteristic information and the text characteristic information; and based on the picture style information and the animation theme information, screening target animation template information corresponding to the picture style information in the animation main body information from the animation template information, and inputting the animation picture information, the animation text information, the picture content information and the target animation template information into an animation generation model to obtain target animation information. The present invention also relates to blockchain techniques, where the target animation information may be stored in nodes of the blockchain. By adopting the method, the efficiency of drawing the MG animation of the medical technology can be improved.

Description

Animation generation method, device, equipment and storage medium

Technical Field

The present invention relates to the field of digital medical and artificial intelligence technologies, and in particular, to an animation generation method, an animation generation device, an electronic device, and a readable storage medium.

Background

With the continuous development of medical technology, the traditional medical technology needs to be popularized to the masses, and the content of the traditional medical technology is popularized to the masses, so that the popularity of the medical technology is improved, and therefore, how to popularize the traditional medical technology to the masses is the current research focus.

In the process of popularizing the medical technology, the medical technology is often popularized to the masses in a mode of drawing the MG animation, but the traditional mode of drawing the MG animation is through manual drawing, so that a large amount of manpower and financial resources are consumed, and a large amount of time and cost are required for drawing, and the efficiency of drawing the MG animation of the medical technology is low.

Disclosure of Invention

The invention provides an animation generation method, an animation generation device, an electronic device and a readable storage medium, and aims to improve the generation efficiency of MG animation in the medical field.

In order to achieve the above object, the present invention provides an animation generation method, including:

acquiring animation picture information, animation text information, animation theme information and a plurality of animation template information;

extracting picture characteristic information of the animation picture information and text characteristic information of the animation text information, and determining picture style information of the animation and picture content information of the animation based on the picture characteristic information and the text characteristic information;

And screening target animation template information corresponding to the picture style information in the animation main body information from the animation template information based on the picture style information and the animation topic information, and inputting the animation picture information, the animation text information, the picture content information and the target animation template information into an animation generation model to obtain target animation information.

Optionally, the extracting the picture feature information of the animation picture information and the text feature information of the animation text information includes:

extracting initial picture feature information of the animation picture information through a picture feature extraction network aiming at each animation picture information, carrying out vectorization processing on the initial picture feature information to obtain feature vectors of the initial picture features, and taking the initial picture feature information and the feature vectors as picture feature information of the animation picture information;

extracting initial text feature information of the animation text information through a text feature extraction network aiming at each animation text information, and identifying semantic features of each text feature information to obtain the text feature information containing the initial text feature information and the semantic features of the initial text feature information.

Optionally, the determining picture style information of the animation and picture content information of the animation based on the picture feature information and the text feature information includes:

based on the feature vector of each piece of picture feature information, establishing a picture feature vector matrix of the animation, calculating the feature value of the picture feature vector matrix, and screening picture style information corresponding to a feature range to which the feature value belongs from each piece of picture style information to serve as picture style information of the animation;

identifying picture characteristics of each initial picture characteristic information of the picture characteristic information, and establishing association relations between each text characteristic information and each picture characteristic information based on semantic characteristics of each text characteristic information and picture characteristics of each picture characteristic information;

and taking the association relation, the text characteristic information and the picture characteristic information as picture content information of the animation.

Optionally, the establishing the association relationship between each piece of text feature information and each piece of picture feature information based on the semantic feature of each piece of text feature information and the picture feature of each piece of picture feature information includes:

Acquiring a plurality of sample semantic features containing association relations and sample picture features, and respectively calculating a first similarity between each semantic feature and each sample semantic feature and a second similarity between each picture feature and each sample picture feature;

and aiming at each pair of sample semantic features and sample picture features, taking the association relationship between the sample semantic features and the sample picture features as the association relationship between the semantic features with the first similarity of the sample semantic features being larger than a first similarity threshold value and the picture features with the second similarity of the sample picture features being larger than a second similarity threshold value, and obtaining the association relationship of each piece of text feature information and each piece of picture feature information.

Optionally, the selecting, based on the picture style information and the animation topic information, target animation template information corresponding to the picture style information in the animation main body information from the animation template information includes:

calculating the association degree between the animation topic information and the template topic information of each animation template information, and screening the animation topic information corresponding to the template topic information with the association degree larger than the preset association degree as initial target animation template information;

And identifying the template characteristic range of the style information of each piece of initial target animation template information, and screening the initial target animation template information corresponding to the style information with the highest similarity between the template characteristic range and the characteristic range of the picture style information, wherein the initial target animation template information is used as target animation template information.

Optionally, the inputting the animation picture information, the animation text information, the picture content information and the target animation template information into an animation generation model to obtain target animation information includes:

based on the association relationship between the text characteristic information and the picture characteristic information in the picture content information, establishing a corresponding relationship between the animation text information and the animation picture information;

inputting the corresponding relation, the animation text information and the animation picture information into an animation generation model, and generating target animation information in the target animation template information.

Optionally, before inputting the animation picture information, the animation text information, the picture content information and the target animation template information into an animation generation model to obtain target animation information, the method further includes:

Acquiring sample animation picture information, sample animation text information, sample correspondence between the sample animation picture information and the sample animation text information, sample animation template information and sample animation effects of the sample animation information;

inputting the sample correspondence, the sample animation text information and the sample animation picture information into an initial animation generation model, generating animation information in the sample animation template information, and identifying an animation effect of the animation information;

and when the deviation value of the sample animation effect and the animation effect is larger than a deviation threshold value, returning to execute the steps of inputting the sample corresponding relation, the sample animation text information and the sample animation picture information into an initial animation generation model, and generating the animation information in the sample animation template information until the deviation value is not larger than the deviation threshold value, and taking the initial animation generation model corresponding to the deviation value which is not larger than the deviation threshold value as an animation generation model.

In order to solve the above problems, the present invention also provides an animation generation device including:

the acquisition module is used for acquiring the animation picture information, the animation text information, the animation theme information and a plurality of animation template information;

The extraction module is used for extracting picture characteristic information of the animation picture information and text characteristic information of the animation text information, and determining picture style information and picture content information of the animation based on the picture characteristic information and the text characteristic information;

and the generation module is used for screening target animation template information corresponding to the picture style information in the animation main body information from the animation template information based on the picture style information and the animation theme information, and inputting the animation picture information, the animation text information, the picture content information and the target animation template information into an animation generation model to obtain target animation information.

In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:

a memory storing at least one computer program; a kind of electronic device with high-pressure air-conditioning system

And a processor executing the computer program stored in the memory to implement the animation generation method.

In order to solve the above-described problems, the present invention also provides a computer-readable storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the above-described animation generation method.

The invention obtains the animation picture information, the animation text information, the animation theme information and a plurality of animation template information; extracting picture characteristic information of the animation picture information and text characteristic information of the animation text information, and determining picture style information of the animation and picture content information of the animation based on the picture characteristic information and the text characteristic information; and screening target animation template information corresponding to the picture style information in the animation main body information from the animation template information based on the picture style information and the animation topic information, and inputting the animation picture information, the animation text information, the picture content information and the target animation template information into an animation generation model to obtain target animation information. The method comprises the steps of determining picture style information of an animation and picture content information of the animation based on animation picture information and animation text information, screening target animation template information according to the picture content information of the animation and animation subject information, and finally generating a model based on the target template information by generating the animation, so that the process of manually drawing the animation is avoided, and the efficiency of drawing the MG animation of the medical technology is improved.

Drawings

FIG. 1 is a flowchart of an animation generation method according to an embodiment of the present invention;

FIG. 2 is a functional block diagram of an animation generating device according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device implementing the animation generation method according to an embodiment of the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The embodiment of the invention provides an animation generation method. The execution subject of the animation generation method includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the invention. In other words, the animation generation method may be performed by software or hardware installed at a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (ContentDelivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

Referring to fig. 1, a flowchart of an animation generation method according to an embodiment of the invention is shown.

In this embodiment, the animation generation method includes the following steps S101 to S103:

step S101, obtaining animation picture information, animation text information, animation theme information, and a plurality of animation template information.

In this embodiment, the terminal obtains the animation picture information, the animation text information, and the animation theme information uploaded by the user in response to the animation generation operation with the user. Then, the terminal screens a plurality of template information related to the medical technology in the animation template database as animation template information. The animation picture information comprises picture content, picture color, picture size, picture resolution, picture color richness and picture basic content information. The picture basic content information includes the number of persons in the picture, the duty ratio of the main content, distribution information of the main content, and the like. The animated text information includes text content, number of text words, text language, main text content, and the like. The animation topic information is the purpose information of the animation characterization, such as the usage of medical products, emergency rescue methods, popularization of medical common knowledge, introduction of conventional medical technology and the like.

Step S102, extracting the picture characteristic information of the animation picture information and the text characteristic information of the animation text information, and determining the picture style information of the animation and the picture content information of the animation based on the picture characteristic information and the text characteristic information.

In this embodiment, the terminal extracts, through the image feature extraction network, image feature information of animation image information related to usage of medical products, emergency rescue methods, medical common sense, and the like, and extracts, through the text feature extraction network, text feature information related to medical treatment of the animation text information. The image feature extraction network may be, but is not limited to, an edge image detection network, a neural network corresponding to an LBP (Local Binary Patterns, local binary pattern) algorithm, and the like. The text diagnosis extraction network is any feature extraction neural network capable of extracting text semantic features and text features of the text. And the terminal analyzes the picture style information of the animation through the picture feature information and the text feature information, establishes the association relationship between the picture feature information and the text feature information, and obtains the picture content information of the animation. The specific extraction process, analysis process, and setup process will be described in detail later.

And step S103, based on the picture style information and the animation topic information, screening target animation template information corresponding to the picture style information in the animation main body information from the animation template information, and inputting the animation picture information, the animation text information, the picture content information and the target animation template information into an animation generation model to obtain target animation information.

In this embodiment, the terminal screens the target animation template information corresponding to the picture style information in the animation main body information from the animation template information based on the picture style information and the animation topic information. Then, the terminal inputs the animation picture information, the animation text information, and the picture content information into the animation generation model, and generates target animation information in the target animation template information. The animation generation model can be, but is not limited to, a ChatGPT intelligent generation model, and an artificial intelligent model corresponding to a reinforced learning neural network based on a reward function.

Based on the scheme, taking an emergency rescue method in the medical field as an example, by determining the picture style information of the animation and the picture content information of the animation based on the animation picture information and the animation text information related to the emergency rescue method, screening target animation template information based on the picture content information of the animation and the animation subject information during emergency rescue, and finally generating the animation picture information and the target animation information corresponding to the animation text information based on the type of target template information by generating a model through the animation, the process of manually drawing the animation is avoided, and the efficiency of drawing the MG animation of the medical technology is improved.

Optionally, extracting the picture feature information of the animation picture information and the text feature information of the animation text information includes: extracting initial picture feature information of the animation picture information through a picture feature extraction network aiming at each animation picture information, carrying out vectorization processing on the initial picture feature information to obtain feature vectors of initial picture features, and taking the initial picture feature information and the feature vectors as picture feature information of the animation picture information; for each piece of animation text information, extracting initial text feature information of the animation text information through a text feature extraction network, and identifying semantic features of each piece of text feature information to obtain text feature information containing the initial text feature information and the semantic features of the initial text feature information.

In this embodiment, the terminal extracts initial picture feature information of the animation picture information through the picture feature extraction network for each animation picture information corresponding to an emergency rescue and medical product use method in the medical field. Wherein the initial picture feature information includes feature information corresponding to picture content of the above-described type of moving picture information. And then, the terminal carries out vectorization processing on the initial picture feature information to obtain feature vectors of the initial picture features. The vectorization processing mode is to perform feature vectorization on the initial picture features through feature hash transformation, and the obtained feature vectors corresponding to the initial picture features. Finally, the terminal uses the initial picture feature information and the feature vector as the picture feature information of the animation picture information, and it is to be noted that the feature type in the medical field selected in advance can promote the rapid extraction and identification of the feature information corresponding to the picture information.

The terminal extracts initial text feature information of each animation text message through a text feature extraction network. The initial text characteristic information is text information corresponding to characteristic text in the animation text information. Then, the terminal identifies the semantic feature of each text feature information based on the distribution information of each initial text feature information in the animation text information, and obtains the text feature information containing the initial text feature information and the semantic feature of the initial text feature information.

Based on the scheme, the initial picture characteristic information is extracted, vectorization processing is carried out on the initial picture characteristic information, the picture style information corresponding to the picture characteristic information is conveniently identified in a data mode, the identification efficiency of the picture style information is improved, and secondly, the semantic characteristics of each text characteristic information are identified by extracting the initial text characteristic information, so that the accuracy of establishing the association relation between each text characteristic information and each picture characteristic information is improved.

Optionally, determining the picture style information of the animation and the picture content information of the animation based on the picture feature information and the text feature information includes: based on the feature vector of each picture feature information, establishing a picture feature vector matrix of the animation, calculating the feature value of the picture feature vector matrix, and screening picture style information corresponding to a feature range to which the feature value belongs from each picture style information as picture style information of the animation; identifying picture characteristics of each initial picture characteristic information of the picture characteristic information, and establishing association relations between each text characteristic information and each picture characteristic information based on semantic characteristics of each text characteristic information and picture characteristics of each picture characteristic information; the association relationship, each text feature information, and each picture feature information are used as the picture content information of the animation.

In this embodiment, the terminal establishes a picture feature vector matrix of the animation based on feature vectors of feature information of each picture, and then calculates feature values of the picture feature vector matrix by using a feature vector algorithm. The terminal presets the corresponding characteristic value range of each picture style information, and screens picture style information corresponding to the characteristic range to which the characteristic value belongs in each picture style information as picture style information of the animation. The terminal extracts the picture characteristics in each piece of initial picture characteristic information in the picture characteristic information again through a picture characteristic extraction network, and then establishes association relations between each piece of text characteristic information and each piece of picture characteristic information based on semantic characteristics of each piece of text characteristic information and picture characteristics of each piece of picture characteristic information. The specific setup procedure will be described in detail later. Finally, the terminal uses the association relationship, each text characteristic information and each picture characteristic information as the picture content information of the animation.

Based on the scheme, the characteristic value of the characteristic vector matrix of the picture is calculated through a characteristic vector algorithm in a data mode, the picture style information corresponding to the characteristic information of each picture is screened, and the accuracy of the screened picture style information is improved. And secondly, the terminal establishes association relations between each piece of text feature information and each piece of picture feature information through the picture features and the semantic features of the text feature information, so that the accuracy of establishing the association relations is improved.

Optionally, establishing the association relationship between each text feature information and each picture feature information based on the semantic feature of each text feature information and the picture feature of each picture feature information includes: acquiring a plurality of sample semantic features containing association relations and sample picture features, and respectively calculating first similarity between each semantic feature and each sample semantic feature and second similarity between each picture feature and each sample picture feature; aiming at each pair of sample semantic features and sample picture features, the association relationship between the sample semantic features and the sample picture features is used as the association relationship between the semantic features with the first similarity larger than a first similarity threshold value and the picture features with the second similarity larger than a second similarity threshold value, so as to obtain the association relationship of each text feature information and each picture feature information.

In this embodiment, the terminal obtains a plurality of sample semantic features including association relationships, and sample picture features. Then, the terminal calculates first similarity between each semantic feature and each sample semantic feature by a feature similarity algorithm. Similarly, through the scheme, the terminal calculates the first similarity between each semantic feature and each sample semantic feature. And then the terminal calculates the second similarity between the picture feature and each sample picture feature according to each picture feature through a feature similarity algorithm. Likewise, through the scheme, the terminal calculates the second similarity between each picture feature and each sample picture feature. Then, the terminal presets a first similarity threshold and a second similarity threshold, and for each pair of sample semantic features and sample picture features, semantic features, of which the first similarity with the sample semantic features is larger than the preset first similarity threshold, are screened from the semantic features to serve as target semantic features, and picture features, of which the second similarity with the sample picture features is larger than the preset second similarity threshold, are screened from the picture features to serve as target picture features. Under the condition that the target semantic features and the target picture features are unique, the terminal takes the association relationship between the sample semantic features and the sample picture features as the association relationship between the target semantic features and the target picture features. And under the condition that the target semantic features and the target picture features are not unique, the terminal judges whether the target picture features are unique, and under the condition that the target picture features are unique, the terminal takes the association relationship between the sample semantic features and the sample picture features as the association relationship between the target picture features and the target semantic features. And under the condition that the object picture feature is unique, the terminal determines that the association does not accord with each semantic feature and each picture feature, deletes the sample semantic feature and the sample picture feature, returns to execute the association between the sample semantic feature and the sample picture feature aiming at each pair of sample semantic feature and sample picture feature, and stops the iterative operation under the condition that the association between all the semantic features and all the picture features exists as the semantic feature with the first similarity greater than the first similarity threshold value and the association between the picture feature with the second similarity greater than the second similarity threshold value.

Based on the scheme, the association relation between each semantic feature and the picture feature is determined by calculating the semantic feature, the picture feature, a plurality of sample semantic features containing the association relation and the similarity between the sample picture features, so that the accuracy of the association relation between each semantic feature and the picture feature is improved.

Optionally, based on the picture style information and the animation topic information, selecting the target animation template information corresponding to the picture style information in the animation main body information from the animation template information, including: calculating the association degree between the animation theme information and the template theme information of each animation template information, and screening the animation theme information corresponding to the template main body information with the association degree larger than the preset association degree as initial target animation template information; and identifying the template characteristic range of the style information of each initial target animation template information, and screening the initial target animation template information corresponding to the style information with the highest similarity between the template characteristic range and the characteristic range of the picture style information, wherein the initial target animation template information is used as the target animation template information.

In this embodiment, the terminal calculates, by using a text information association algorithm, association between the animation theme information and the template theme information of each animation template information. Then, the terminal screens the animation theme information corresponding to the template main body information with the association degree larger than the preset association degree as initial target animation template information. The terminal presets the template characteristic range of the style information of each animation template information, and then the terminal identifies the template characteristic range of the style information of the initial target animation template information related to each medical technology. The terminal calculates the range overlapping degree between the template characteristic range and the characteristic range of the picture style information, takes the overlapping degree as the similarity between the template characteristic range and the picture style information, and then screens initial target animation template information corresponding to style information with highest similarity between the template characteristic range and the characteristic range of the picture style information as target animation template information. The text information relevance algorithm is a feature similarity algorithm based on the combination of a cosine similarity algorithm and a Euclidean distance algorithm.

Based on the scheme, the terminal screens the target animation template information in each animation template information through the animation theme information and the picture style information, so that the accuracy of the screened target animation template information is improved.

Optionally, inputting the animation picture information, the animation text information, the picture content information and the target animation template information into the animation generation model to obtain target animation information, including: based on the association relation between the text characteristic information and the picture characteristic information in the picture content information, establishing a corresponding relation between the animation text information and the animation picture information; the correspondence, the animation text information, and the animation picture information are input into an animation generation model, and target animation template information is used to generate target animation information.

In this embodiment, the terminal first establishes a correspondence between each piece of animation text information acquired in step S101 and each piece of animation picture information based on the association between the text feature information and the picture feature information in the picture content information. Wherein the correspondence may be, but is not limited to, one-to-one, and one-to-many. The terminal inputs the correspondence, the animation text information, and the animation picture information into an animation generation model, and generates target animation information based on the target animation template information.

With the scheme, the corresponding relation between the animation text information and the animation picture information is established through the association relation between the text feature information and the picture feature information in the picture content information, a data base is provided for an animation generation model, the target animation information is generated through the animation generation model, the process of manually drawing the animation is avoided, and the efficiency of drawing the MG animation of the medical technology is improved.

Optionally, inputting the animation picture information, the animation text information, the picture content information and the target animation template information into the animation generation model, and before obtaining the target animation information, further including: acquiring sample animation picture information, sample animation text information, sample correspondence between the sample animation picture information and the sample animation text information, sample animation template information and sample animation effects of the sample animation information; inputting the sample corresponding relation, sample animation text information and sample animation picture information into an initial animation generation model, generating animation information in sample animation template information, and identifying the animation effect of the animation information; and when the deviation value of the sample animation effect and the animation effect is larger than the deviation threshold value, returning to execute the steps of inputting the sample corresponding relation, the sample animation text information and the sample animation picture information into the initial animation generation model, and generating the animation information in the sample animation template information until the deviation value is not larger than the deviation threshold value, and taking the initial animation generation model corresponding to the deviation value which is not larger than the deviation threshold value as the animation generation model.

In this embodiment, the terminal acquires sample animation picture information, sample animation text information, a sample correspondence between the sample animation picture information and the sample animation text information, and sample animation template information. And then the terminal evaluates the sample picture evaluation values of each frame of picture in the sample animation information through a picture evaluation network respectively, and takes the evaluation values of all pictures as the sample animation effect of the sample animation information. Then, the terminal inputs the sample correspondence, sample animation text information, and sample animation picture information into the initial animation generation model, and generates animation information in the sample animation template information. And the terminal evaluates the picture evaluation value of each frame of picture in the animation information through a picture evaluation network to obtain the animation effect of the animation information. And finally, the terminal respectively compares the sample picture evaluation value of the sample animation information under the same frame number with the sub-deviation value between the picture evaluation value of the animation information, and then carries out average summation on all the sub-deviation values to obtain the deviation value between the sample animation effect and the animation effect. And presetting a deviation threshold by the terminal, and judging whether the deviation value of the sample animation effect and the animation effect is larger than the deviation threshold. When the deviation value between the sample animation effect and the animation effect is larger than the deviation threshold value, the terminal takes the initial animation generation model corresponding to the deviation value as the animation generation model. And when the deviation value of the sample animation effect and the animation effect is larger than the deviation threshold value, the terminal returns to execute the steps of inputting the sample corresponding relation, the sample animation text information and the sample animation picture information into the initial animation generation model, and generating the animation information in the sample animation template information until the deviation value is not larger than the deviation threshold value, and the terminal takes the initial animation generation model corresponding to the deviation value which is not larger than the deviation threshold value as the animation generation model. The image evaluation network is an image quality evaluation neural network based on deep learning.

Based on the scheme, the terminal trains the initial animation generation model and evaluates the initial animation generation model through the picture evaluation network, so that the initial animation generation model is adjusted, the animation generation model is obtained, and the accuracy of animation information generated by the animation generation model is improved.

Fig. 2 is a functional block diagram of an animation generating device according to an embodiment of the present invention.

The animation generating apparatus 200 of the present invention may be installed in an electronic device. The animation generating device 200 includes an acquisition module 210, an extraction module 220, and a generation module 230 according to the implemented functions. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.

In the present embodiment, the functions concerning the respective modules/units are as follows:

an obtaining module 210, configured to obtain animation picture information, animation text information, animation theme information, and a plurality of animation template information;

an extracting module 220, configured to extract picture feature information of the animation picture information and text feature information of the animation text information, and determine picture style information and picture content information of an animation based on the picture feature information and the text feature information;

The generating module 230 is configured to screen, based on the picture style information and the animation topic information, target animation template information corresponding to the picture style information in the animation main body information from the animation template information, and input the animation picture information, the animation text information, the picture content information and the target animation template information into an animation generating model to obtain target animation information.

Optionally, the extraction model 220 is specifically configured to:

Optionally, the generating model 230 is specifically configured to:

Optionally, the apparatus further includes:

the sample acquisition module is used for acquiring sample animation picture information, sample animation text information, sample correspondence between the sample animation picture information and the sample animation text information, sample animation template information and sample animation effects of the sample animation information;

the simulation module is used for inputting the sample corresponding relation, the sample animation text information and the sample animation picture information into an initial animation generation model, generating animation information in the sample animation template information and identifying an animation effect of the animation information;

and the iteration module is used for returning to input the sample corresponding relation, the sample animation text information and the sample animation picture information into an initial animation generation model when the deviation value of the sample animation effect and the animation effect is larger than a deviation threshold value, and generating animation information in the sample animation template information until the initial animation generation model corresponding to the deviation value which is not larger than the deviation threshold value is used as the animation generation model when the deviation value is not larger than the deviation threshold value.

The respective modules in the above-described animation generation apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

The electronic device may comprise a processor 10, a memory 11, a communication interface 12 and a bus 13, and may further comprise a computer program, such as an animation generation program, stored in the memory 11 and executable on the processor 10.

The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only for storing application software installed in an electronic device and various types of data, such as codes of an animation generation program, but also for temporarily storing data that has been output or is to be output.

The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing Unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, and executes various functions of the electronic device and processes data by running or executing programs or modules (e.g., animation generation programs, etc.) stored in the memory 11, and calling data stored in the memory 11.

The communication interface 12 is used for communication between the electronic device and other devices, including network interfaces and user interfaces. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.

The bus 13 may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus 13 may be classified into an address bus, a data bus, a control bus, and the like. The bus 13 is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.

Fig. 3 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 is not limiting of the electronic device and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.

For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.

Further, the electronic device may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices.

Optionally, the electronic device may further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.

It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.

The animation generation program stored in the memory 11 of the electronic device is a combination of instructions that, when executed in the processor 10, may implement:

In particular, the specific implementation method of the above instructions by the processor 10 may refer to the description of the relevant steps in the corresponding embodiment of the drawings, which is not repeated herein.

Further, the electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).

The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:

In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.

The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The embodiment of the invention can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.

Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method of animation generation, the method comprising:

2. The method according to claim 1, wherein the extracting the picture feature information of the moving picture information and the text feature information of the moving text information includes:

3. The method of claim 2, wherein the determining picture style information of an animation, and picture content information of the animation, based on the picture feature information and the text feature information, comprises:

4. The method according to claim 3, wherein the establishing the association between each piece of text feature information and each piece of picture feature information based on the semantic feature of each piece of text feature information and the picture feature of each piece of picture feature information includes:

5. The method according to claim 2, wherein the selecting, from each of the animation template information, target animation template information corresponding to the picture style information in the animation body information based on the picture style information and the animation topic information, comprises:

6. The method of claim 3, wherein inputting the animated picture information, the animated text information, the picture content information, and the target animated template information into an animation generation model to obtain target animated information comprises:

7. The method of claim 6, wherein the inputting the animated picture information, the animated text information, the picture content information, and the target animated template information into an animation generation model, prior to obtaining target animated information, further comprises:

8. An animation generation device, the device comprising:

9. An electronic device, the electronic device comprising:

at least one processor; the method comprises the steps of,

a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the animation generation method of any of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the animation generation method according to any one of claims 1 to 7.