Animation script automatic generation method and system, storage medium and program product

Abstract

The invention discloses an animation script automatic generation method and system, a storage medium and a program product, and the method comprises the steps: extracting a scene element set, a plot element set and a role element set in a static text; generating an element association graph containing weights; calculating the content matching degree of each element in the element association graph and each plot unit; selecting a core plot unit; calculating a semantic vector included angle cosine value between the core plot units as a semantic association degree, and constructing a plot unit association network by taking the semantic association degree as a connection weight; determining a plot development main line between the core plot units; determining an extended core plot unit; according to weight distribution of role elements in the element association graph, distributing corresponding roles for the extended core plot unit and generating role dialogue content to obtain a final core plot unit; and integrating the final core plot unit according to a preset animation script format to generate an animation script text. According to the method, the correlation between the generated script and the result required by the user is improved.

Description

Technical Field

[0001] The present application belongs to the field of animation game development, and in particular, relates to an animation script automatic generation method, system, storage medium and program product. Background Art

[0002] With the rapid development of the animation industry, the demand for animation script creation is growing. The traditional manual writing of animation scripts is not only time-consuming and labor-intensive, but also difficult to meet the needs of mass and personalized creation. Especially in the era of short videos, a large number of creators need to quickly generate animation content, and the manual script writing method has become a bottleneck restricting the improvement of animation creation efficiency.

[0003] In related technologies, multiple animation scene templates and character dialogue templates can be preset, and the corresponding templates can be matched according to the theme keywords input by the user, and the animation script can be automatically generated by rule replacement. This method improves the generation efficiency of animation scripts to a certain extent and reduces the creation threshold.

[0004] However, this generation method based on fixed templates relies too much on preset rules and is difficult to accurately understand and extend the user's creative intentions. In particular, when the creative materials or inspiration fragments provided by the user are relatively scattered and abstract, it is difficult to integrate these creative elements into a coherent and expressive animation plot, which reduces the relevance of the generated script to the results required by the user. Summary of the invention

[0005] The present application provides a method, system, storage medium and program product for automatically generating an animation script, which are used to improve the relevance of the generated script to the result required by the user.

[0006] In a first aspect, the present application provides a method for automatically generating an animation script, which performs semantic analysis on a static text description in a creative material input by a user, extracts a scene element set, a plot element set, and a character element set, wherein the creative material includes a static text description and a static keyword set; According to the semantic similarity between each keyword in the static keyword set and each element in the scene element set, the plot element set and the character element set, a weight is assigned to each element to obtain an element association graph including the weight; Divide the preset animation script structure template into several plot units, and calculate the content matching degree between each element in the element association diagram and each plot unit; According to the content matching degree, the plot units are sorted in descending order of importance, and the plot units ranked before a preset number in the descending order of importance are selected as the core plot units; The cosine value of the angle between the semantic vectors of the core plot units is calculated as the semantic association degree, and the semantic association degree is used as the connection weight to construct the plot unit association network; Execute the maximum weight path search algorithm in the plot unit association network to obtain the main plot development line between each core plot unit; Determine the sequential relationship of each core plot unit based on the main plot line, and supplement the scene description and expand the plot details of each core plot unit according to the preset narrative rule library to obtain an extended core plot unit; According to the weight distribution of the role elements in the element association graph, the corresponding roles are assigned to the extended core plot unit and the role dialogue content is generated to obtain the final core plot unit; Integrate the final core plot units according to the preset animation script format to generate the animation script text.

[0007] By adopting the above technical solution, the creative materials are semantically analyzed to extract key elements, and a weighted element association graph is constructed based on the semantic similarity between the elements and keywords, so that the creative intentions input by the user can be accurately quantified. The core plot units are screened using content matching as the evaluation index, and then the plot unit association network is constructed using semantic association and the maximum weight path search is performed, which not only ensures that the generated script content is highly consistent with the user's creativity, but also makes the plot development context clearer and more coherent. The scenes and plots are supplemented and expanded by the preset narrative rule library, and the dialogue content is distributed in combination with the role weights, so that the generated animation script has rich details and a complete dramatic structure while maintaining the creative core, reducing the problems of loose script structure, stiff plot connection, and thin character portrayal. It can fully restore the user's creative intentions, improve the artistry and integrity of the generated script, and improve the quality and practical value of the automatic generation of animation scripts.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, semantic analysis is performed on the static text description in the creative material input by the user to extract a scene element set, a plot element set, and a character element set, specifically including: Split the static text description into several text segments; Perform part-of-speech tagging and dependency syntax analysis on several text fragments to identify scene description sentences, plot description sentences, and character description sentences in each text fragment; Cluster the scene description sentences based on preset semantic feature indicators to obtain a set of scene elements; Classify the plot description sentences based on the preset plot type model to obtain a set of plot elements; Feature extraction is performed on the role description sentence based on the preset role feature dimension to obtain a role element set.

[0009] By adopting the above technical solution, the static text description is tagged with part of speech and analyzed by dependency syntax, and different types of description sentences are accurately identified. The scene, plot and character description sentences are analyzed in depth using the preset semantic feature indicators, plot type model and character feature dimensions, so that the various elements extracted from the creative materials have clear semantic attributes and structured expressions. The accuracy and completeness of element extraction are improved, providing a standardized data basis for subsequent weight calculation and plot unit generation, reducing semantic ambiguity and information loss problems, and improving the accuracy of creative material analysis.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, according to the semantic similarity between each keyword in the static keyword set and each element in the scene element set, the plot element set, and the character element set, a weight is assigned to each element to obtain an element association graph containing weights, specifically including: Constructing a keyword-element bipartite graph, wherein the nodes of the keyword-element bipartite graph include keyword nodes in the static keyword set and element nodes in each element set; Calculate the word vector cosine similarity between each keyword node and each feature node as the edge weight; Determine the importance score of each element node in the keyword element bipartite graph; The importance score is used as the weight value of each factor to construct the factor association graph.

[0011] By adopting the above technical solution and constructing a bipartite graph of keyword elements, an explicit association relationship between keywords and various elements is established, and the word vector cosine similarity is used as a quantitative evaluation indicator. The direct semantic association between keywords and elements is considered, and the core degree of elements in the overall creativity is reflected through the node importance score. The element association graph constructed in this way has a reasonable weight distribution, which accurately reflects the importance and mutual relationship of each element in creative expression. The problem of subjective and arbitrary weight allocation is reduced, so that the subsequent plot unit generation process can better grasp the creative focus and keep the primary and secondary content clear.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, before calculating the cosine value of the angle between the semantic vectors of the core plot units as the semantic association, the method further includes: Construct a multi-dimensional emotional feature space of the core plot unit, which includes tension, joy and sentimentality; Extract sentiment vectors based on the text content of the core plot unit and map the sentiment vectors into a multi-dimensional sentiment feature space; Calculate the emotional trajectory curve of each core plot unit in the multi-dimensional emotional feature space; Adjust the emotional trajectory curve according to the preset emotional fluctuation mode.

[0013] By adopting the above technical solution, a multi-dimensional emotional feature space is introduced to model the emotions of the core plot units. By extracting the emotional vector and calculating the emotional trajectory curve, the accurate description of the emotional changes in the plot is achieved. The emotional trajectory curve is adjusted based on the preset emotional fluctuation mode, so that the generated plot is more in line with artistic laws in terms of emotional expression. The logical coherence of the subsequent generated plot development main line is improved, and the rationality of the fluctuation changes at the emotional level is also improved.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, constructing a multidimensional emotional feature space of a core plot unit specifically includes: Obtain the emotion annotation data in the preset animation script corpus; Perform dimensionality reduction on the emotional annotation data to extract tension, happiness, and sadness; Calculate the independence coefficients between tension, euphoria, and sentimentality; A quantitative scoring standard was constructed based on the independence coefficients among tension, joviality, and sentimentality; Quantitative scoring criteria were applied to tension, cheerfulness, and sentimentality to construct a multidimensional emotional feature space.

[0015] By adopting the above technical solution, the emotional annotation data in the preset animation script corpus is obtained and dimensionality reduction processing is performed, the three basic dimensions of tension, cheerfulness and sentimentality are extracted, the independence coefficients between these three dimensions are calculated and a quantitative scoring standard is constructed accordingly, and finally a multidimensional emotional feature space is constructed. The uncertainty caused by subjective experience judgment is reduced. The orthogonality between the emotional dimensions is ensured by calculating the independence coefficient, so that each dimension can independently reflect the emotional characteristics of a certain aspect of the plot, reducing the information redundancy between dimensions. The quantitative scoring standard constructed based on large-scale corpus data has strong statistical reliability and universality, and can accurately capture the differences in emotional characteristics of different types of plot units, making the emotional analysis results comparable and repeatable, and improving the scientificity and accuracy of the emotional design of animation scripts.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after adjusting the emotion trajectory curve according to the preset emotion fluctuation mode, the method further includes: Based on the emotion trajectory curve, the significant feature points of emotion change are extracted, and the emotion span and duration between adjacent significant feature points are calculated to obtain the emotion fluctuation feature sequence; A neural oscillator network is constructed based on the characteristic sequence of emotional fluctuations. The frequency of each oscillator node in the neural oscillator network corresponds to the duration, and the amplitude corresponds to the emotional span. Model the emotional rhythm using a neural oscillator network to generate a rhythm feature vector; The rhythm change of the emotional trajectory curve is determined according to the golden ratio and rhythm feature vector.

[0017] By adopting the above technical solution and the method of modeling emotional rhythm using a neural oscillator network, the emotional span and duration between the significant feature points of emotional changes are mapped to the amplitude and frequency parameters of the oscillator nodes respectively, so that complex emotional fluctuations can be expressed and analyzed using a simple oscillation model. The neural oscillator network has good dynamic characteristics and can simulate the continuity and periodicity of emotional fluctuations, reducing the limitations of traditional discrete sampling methods in describing continuous emotional changes. By generating rhythm feature vectors through quantitative modeling of emotional rhythm, the control of emotional rhythm is made more precise and flexible, which improves the accuracy and fluency of animation scripts in controlling emotional rhythm.

[0018] In combination with some embodiments of the first aspect, in some embodiments, determining the rhythm change of the emotion trajectory curve according to the golden section ratio and the rhythm feature vector specifically includes: Divide the total duration of the emotional trajectory curve into multiple time segments according to the golden ratio; Calculate the energy distribution of the rhythm feature vector in each time segment, and construct a rhythm adjustment function based on the energy distribution, the rhythm adjustment function is used to amplify or suppress the intensity of emotional fluctuations in each time segment; The rhythm adjustment function is applied to the emotional trajectory curve to obtain the optimized emotional rhythm change.

[0019] By adopting the above technical solution, the total duration of the emotional trajectory curve is divided by the golden ratio, and the rhythm adjustment function is constructed based on the energy distribution of the rhythm feature vector, which realizes the precise control of the intensity of emotional fluctuations in each time segment. As a classic artistic composition rule, the golden ratio can create a natural and harmonious sense of rhythm in the time dimension. By analyzing the energy distribution of the rhythm feature vector in each time segment, the constructed rhythm adjustment function can specifically amplify or suppress the intensity of emotional fluctuations in different segments, making the overall emotional curve both in line with aesthetic laws and rich in changes, improving the artistry of the emotional rhythm, and enhancing the narrative tension and viewing experience of the animation script.

[0020] In a second aspect, an embodiment of the present application provides an animation script automatic generation system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a system, causes the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer program product, characterized in that when the computer program product runs on a system, the system executes the method described in any possible implementation manner in the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The present application provides a method for automatically generating animation scripts, which performs semantic analysis on creative materials to extract key elements, and constructs a weighted element association graph based on the semantic similarity between elements and keywords, so that the creative intentions input by users can be accurately quantified and expressed. The content matching degree is used as an evaluation index to screen the core plot units, and then the semantic association degree is used to construct a plot unit association network and perform a maximum weight path search, which not only ensures that the generated script content is highly consistent with the user's creativity, but also makes the plot development context clearer and more coherent. Through the preset narrative rule library to supplement and expand the scenes and plots, and combine the role weight distribution dialogue content, the generated animation script has rich details and a complete dramatic structure while maintaining the creative core, reducing the problems of loose script structure, stiff plot connection, and thin character portrayal. It can fully restore the user's creative intentions, improve the artistry and integrity of the generated script, and improve the quality and practical value of the automatic generation of animation scripts.

[0024] 2. This application provides a method for automatically generating animation scripts, which introduces a multi-dimensional emotional feature space to perform emotional modeling on the core plot unit, and achieves accurate depiction of emotional changes in the plot by extracting emotional vectors and calculating emotional trajectory curves. The emotional trajectory curve is adjusted based on a preset emotional fluctuation mode, so that the generated plot is more in line with artistic laws in terms of emotional expression. The logical coherence of the main plot development line generated subsequently is improved, and the rationality of the fluctuations formed at the emotional level is also improved.

[0025] 3. The present application provides a method for automatically generating animation scripts, which uses a neural oscillator network to model emotional rhythm, and maps the emotional span and duration between the significant feature points of emotional changes to the amplitude and frequency parameters of the oscillator nodes, respectively, so that complex emotional fluctuations can be expressed and analyzed using a simple oscillation model. The neural oscillator network has good dynamic characteristics and can simulate the continuity and periodicity of emotional fluctuations, reducing the limitations of traditional discrete sampling methods in describing continuous emotional changes. By generating rhythm feature vectors through quantitative modeling of emotional rhythms, the control of emotional rhythms is made more precise and flexible, which improves the accuracy and fluency of animation scripts in controlling emotional rhythms. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of a method for automatically generating an animation script in an embodiment of the present application.

[0027] Figure 2 This is another flowchart of a method for automatically generating an animation script in an embodiment of the present application.

[0028] Figure 3 It is a schematic diagram of the physical device structure of an animation script automatic generation system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0030] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0031] The following uses an embodiment and combines Figure 1 , a method for automatically generating an animation script in an embodiment of the present application is described: See also Figure 1 , which is a flow chart of a method for automatically generating an animation script in an embodiment of the present application.

[0032] S101, performing semantic analysis on the static text description in the creative material input by the user, and extracting a scene element set, a plot element set, and a character element set; The system performs semantic analysis on the static text description in the creative material input by the user, extracting a set of scene elements, a set of plot elements and a set of character elements. The creative material includes a static text description and a set of static keywords. Specifically: the static text description is divided into several text segments; Perform part-of-speech tagging and dependency syntax analysis on several text fragments to identify scene description sentences, plot description sentences, and character description sentences in each text fragment; Cluster the scene description sentences based on preset semantic feature indicators to obtain a set of scene elements; Classify the plot description sentences based on the preset plot type model to obtain a set of plot elements; Feature extraction is performed on the role description sentence based on the preset role feature dimension to obtain a role element set.

[0033] In this step, the system processes and analyzes the creative materials input by the user. The creative materials include static text descriptions and static keyword sets. The system mainly performs semantic analysis on static text descriptions, with the aim of extracting key information related to the animation script from the text, namely, the scene element set, the plot element set, and the character element set. These three element sets provide basic data for the subsequent generation of animation scripts.

[0034] Specifically, the system can implement this step by adopting the following technical solutions: First, the static text description is divided into several text segments to facilitate subsequent semantic analysis. Then, each text segment is subjected to part-of-speech tagging and dependency syntax analysis to identify the scene description sentences, plot description sentences, and character description sentences. Next, the system can cluster the scene description sentences based on the preset semantic feature indicators to obtain a set of scene elements; classify the plot description sentences based on the preset plot type model to obtain a set of plot elements; and extract features from the character description sentences based on the preset character feature dimensions to obtain a set of character elements.

[0035] S102, assigning weights to the elements according to the semantic similarity between each keyword in the static keyword set and each element in the scene element set, the plot element set, and the character element set, to obtain an element association graph including weights; The system assigns weights to each element according to the semantic similarity between each keyword in the static keyword set and each element in the scene element set, plot element set and character element set, and obtains an element association graph containing weights. Specifically: a keyword element bipartite graph is constructed, and the nodes of the keyword element bipartite graph include keyword nodes in the static keyword set and element nodes in each element set; Calculate the word vector cosine similarity between each keyword node and each feature node as the edge weight; Determine the importance score of each element node in the keyword element bipartite graph; The importance score is used as the weight value of each factor to construct the factor association graph.

[0036] In this step, the system uses a static keyword set to evaluate the importance of the extracted scene elements, plot elements, and character elements, and constructs an element association graph. The static keyword set reflects the user's focus and emphasis on the content of the animation script. By calculating the semantic similarity between the keyword and each element, the importance of the element can be quantitatively evaluated.

[0037] Specifically, the system can use the following technical solutions to implement this step: First, construct a keyword-element bipartite graph, in which the nodes include keyword nodes in the static keyword set and element nodes in each element set, and the weight of the edge is the cosine similarity of the word vector between the keyword node and the element node. Then, calculate the importance score of each element node in the bipartite graph as the weight value of the element. Finally, construct an element association graph based on the element weight value to reflect the importance relationship between the elements.

[0038] In practical applications, evaluating the importance of elements based solely on word vector similarity may have limitations and cannot fully consider the role and influence of elements in the entire storyline. To solve this problem, the system can introduce story structuring and element relationship reasoning technology, construct a storyline graph through structured analysis of text descriptions, and perform element relationship reasoning on the plot graph to obtain a more comprehensive and accurate element importance evaluation result. For example, the system can associate the core plot nodes and key plot trends in the plot graph with the element nodes, and calculate the importance of the element nodes in the plot advancement; by analyzing the causal and logical relationships between the element nodes in the plot graph, the importance of the element nodes in the story causal chain can be inferred. In this way, the system can make full use of the story structure and plot logic on the basis of static keyword matching to obtain a more reasonable and accurate element weight distribution, providing a more reliable basis for the generation of subsequent animation scripts.

[0039] S103, dividing the preset animation script structure template into a number of plot units, and calculating the content matching degree between each element in the element association diagram and each plot unit; In this step, the system uses the preset animation script structure template to divide and arrange the overall structure of the animation script. The animation script structure template defines the basic components and story paths of a typical animation story, such as opening, development, climax, and ending. The system divides the structure template into several plot units, each of which corresponds to a paragraph or scene in the animation script. Then, the system calculates the degree of matching between the scene elements, plot elements, and character elements in the element association diagram and the content of each plot unit, providing a basis for the subsequent selection of core plot units.

[0040] Specifically, the system can use the following technical solutions to implement this step: First, the preset animation script structure template is divided according to fixed rules and formats to obtain several plot units. Each plot unit contains a certain storyline and scene content, and is consistent with the development context of the entire story. Then, the system uses the semantic features of each element in the element association graph to calculate the similarity with the content of each plot unit to obtain the content matching degree of each element with each plot unit. The higher the content matching degree, the stronger the correlation between the element and the plot unit, and the greater the possibility of appearing in the plot unit.

[0041] S104, sorting the plot units in descending order of importance according to the content matching degree, and selecting the plot units ranked before a preset number in the descending order of importance as the core plot units; In this step, the system evaluates and ranks the importance of all plot units based on the content matching calculated in the previous step. The higher the content matching degree of a plot unit, the higher its importance and the more critical its role in the animation script. The system sorts the plot units in descending order of importance according to the content matching degree, and then selects a preset number of plot units with high rankings as the core plot units of the animation script. These core plot units constitute the main line of the animation script and play a decisive role in the development and advancement of the storyline.

[0042] Specifically, the system can implement this step using the following technical solution: First, the comprehensive importance score of each plot unit is calculated based on the content matching degree of each plot unit and each element in the element association diagram. The importance score can be a weighted average of the content matching degrees of all relevant elements, and the weight can be determined based on the importance of the element in the element association diagram. Then, the system sorts all plot units in descending order according to the importance score to obtain an importance ranking list. Finally, the system selects a preset number (e.g., the top 10) of plot units from the ranking list as core plot units.

[0043] S105, calculating the cosine value of the semantic vector angle between the core plot units as the semantic association degree, and using the semantic association degree as the connection weight to construct a plot unit association network; In this step, the system uses the core plot units selected in the previous step to analyze the semantic associations between them and construct a plot unit association network. The semantic associations between plot units reflect the coherence of the previous and subsequent plots and the causality of the plots, which is crucial to ensuring the logical rationality of the animation script and the fluency of the story. The system calculates the semantic association between the core plot units and uses it as the weight of the connection between the plot units to construct a weighted plot unit association network.

[0044] Specifically, the system can use the following technical solutions to implement this step: First, for each core plot unit, extract the semantic feature vector of its text content. The semantic feature vector can be obtained using natural language processing technologies such as word vectors and sentence vectors, reflecting the position and direction of the plot unit in the semantic space. Then, for each pair of core plot units, calculate the cosine value of the angle between their semantic feature vectors as the semantic association between the two plot units. The larger the cosine value, the more semantically similar the two plot units are, and the stronger the plot association between them. Finally, the system constructs a plot unit association network with the core plot units as nodes and the semantic association as the weight of the edges.

[0045] S106, executing a maximum weight path search algorithm in the plot unit association network to obtain the main plot development line between the core plot units; In this step, the system uses the plot unit association network constructed in the previous step and uses the maximum weight path search algorithm to find a path that connects all core plot units and has the largest weight sum as the main plot development line of the animation script. The main plot development line determines the plot direction and story context of the animation script, and is the skeleton and outline of the entire animation story. Along the main plot development line, the core plot units are unfolded in a certain order, forming a complete and coherent animation narrative structure.

[0046] Specifically, the system can use the following technical solutions to implement this step: First, the plot unit association network is regarded as a weighted directed graph, in which the nodes represent the core plot units and the weights of the edges represent the degree of association between adjacent plot units. Then, the system executes a maximum weight path search algorithm on the graph, such as the Dijkstra algorithm or the Bellman-Ford algorithm, to find an optimal path from the starting node (usually the plot unit at the beginning of the story) to the ending node (usually the plot unit at the end of the story) with the maximum weight on the path. This optimal path is the main plot development line of the animation script, which reflects the best arrangement and combination of the core plot units in the advancement of the plot.

[0047] S107, determining the sequential relationship of each core plot unit based on the main plot development line, and supplementing the scene description and expanding the plot details of each core plot unit according to the preset narrative rule library to obtain an expanded core plot unit; In this step, the system clarifies the temporal and logical order of the core plot units based on the main plot development line obtained in the previous step, and enriches the content and improves the details of each core plot unit to obtain a more complete and vivid extended core plot unit. The extended core plot unit not only contains the original core plot content, but also adds more scene descriptions and plot details, making the animation script more full, three-dimensional and attractive.

[0048] Specifically, the system can implement this step by adopting the following technical solutions: First, according to the arrangement order of the core plot units in the main line of plot development, determine their sequential temporal relationship in the animation script to form an orderly sequence of plot units. Then, for each core plot unit, the system matches the corresponding scene description template and plot detail template from the preset narrative rule library to expand the content of the core plot unit. The narrative rule library contains a large amount of scene description materials and plot detail materials, covering various common animation narrative scenes and segments. The system can retrieve the most relevant description templates and detail templates based on the semantic features and keywords of the core plot unit, and merge them with the core plot unit to generate an extended core plot unit with richer content, more specific descriptions, and more vivid details.

[0049] In practical applications, the content expansion method based on fixed templates may be difficult to generate innovative and diverse animation script content, and it is easy to produce homogeneity and routine problems. In order to improve the originality and attractiveness of animation scripts, the system can introduce natural language generation technology based on deep learning, and learn the language style and creative ideas of animation narrative by training a large-scale animation script corpus, so as to achieve flexible, diverse and creative plot unit expansion. For example, the system can use a sequence-to-sequence neural network model, take the key information of the core plot unit as input, and automatically generate matching scene descriptions and plot details; for animation scripts of different types and styles, the system can train multiple specialized generation models to capture the narrative characteristics and creative techniques of different genres and themes; in addition, the system can also use reinforcement learning algorithms to continuously optimize and adjust the parameters of the generation model according to user feedback and evaluation, so that it can generate animation script content that is closer to user needs and aesthetic preferences. In this way, the system can break through the traditional template expansion method, and create extended core plot units with rich content, diverse forms, creativity and attractiveness through intelligent natural language generation technology, so as to provide users with better quality and personalized animation script creation services.

[0050] S108, assigning corresponding roles to the extended core plot unit and generating role dialogue content according to the weight distribution of the role elements in the element association graph, to obtain the final core plot unit; In this step, the system assigns appropriate roles to each extended core plot unit based on the role element information in the element association graph, and generates corresponding dialogue content for these roles, and finally obtains a complete and full core plot unit. Roles are one of the core elements in an animation story. The setting and dialogue of roles are key means to shape the image of characters and promote the development of the plot. By reasonably assigning roles to plot units and generating role dialogues, the animation script can be made more readable, immersive, and artistically appealing.

[0051] Specifically, the system can implement this step by adopting the following technical solutions: First, according to the weight value of each character element node in the element association graph, determine the importance and appearance frequency of each character in the animation story. The higher the weight value of the character, the more important the role and function in the animation script. Then, the system traverses each extended core plot unit, matches the most relevant characters according to its plot content and scene description, and distributes them in order from high to low according to the character weight. For each character that appears, the system automatically generates dialogue content that meets the character identity and plot requirements based on its character attributes, emotional state, situation and other factors, combined with preset dialogue generation rules and templates. The character dialogue includes not only the text content of the lines, but also performance instructions such as tone, emotion, and action. Finally, the system integrates the generated character dialogue information with the extended core plot unit to obtain a final core plot unit containing a complete plot description and character interaction.

[0052] S109, integrating the final core plot units according to a preset animation script format to generate an animation script text.

[0053] In this step, the system arranges all the final core plot units obtained in the previous step in chronological order, integrates and standardizes them according to the preset animation script format, and finally outputs a complete and standardized animation script text file. The animation script format is a set of text organization and expression standards recognized in the field of animation creation. The use of a unified animation script format can make the script text more professional and standardized, and is also conducive to the subsequent storyboard design, animation production and other links.

[0054] Specifically, the system can implement this step by adopting the following technical solutions: First, all the final core plot units are arranged in sequence according to the chronological order determined by the main line of plot development to form a complete animation storyline sequence. Then, the system structures the content of each plot unit and marks it in rich text according to the preset animation script format template. For example, in the script format, each scene usually includes multiple elements such as scene title, scene number, scene description, character dialogue, narration, and storyboard instructions. The system needs to identify and extract these elements from the text content of the plot unit and arrange them in a standardized format. At the same time, the system also needs to perform grammar checking, word polishing, typesetting and formatting on the script text to ensure that the language quality and expression of the script meet professional standards. Finally, the integrated animation script content is output as a structured text file to complete the automatic generation task of the animation script.

[0055] In the above embodiment, the creative material is semantically analyzed to extract key elements, and a weighted element association graph is constructed based on the semantic similarity between the elements and the keywords, so that the creative intentions input by the user can be accurately quantified. The core plot units are screened using content matching as an evaluation index, and then the plot unit association network is constructed using semantic association and the maximum weight path search is performed, which not only ensures that the generated script content is highly consistent with the user's creativity, but also makes the plot development context clearer and more coherent. The scenes and plots are supplemented and expanded by the preset narrative rule library, and the dialogue content is distributed in combination with the role weights, so that the generated animation script has rich details and a complete dramatic structure while maintaining the creative core, reducing the problems of loose script structure, stiff plot connection, and thin character portrayal. It can fully restore the user's creative intentions, improve the artistry and integrity of the generated script, and improve the quality and practical value of the automatic generation of animation scripts.

[0056] In order to further optimize the emotional expression effect of the generated script and solve the problems of monotonous emotional rhythm and abrupt emotional transition in the traditional automatic generation method, this application also realizes the precise modeling and optimized regulation of the emotional changes of the script by constructing a multi-dimensional emotional feature space and applying a neural oscillator network. Figure 2 , another method for automatically generating an animation script in an embodiment of the present application is described: See also Figure 2 , is another flow chart of a method for automatically generating an animation script in an embodiment of the present application.

[0057] S201, constructing a multi-dimensional emotional feature space of the core plot unit, the multi-dimensional emotional feature space including tension, joy and sentimentality; The system constructs a multi-dimensional emotional feature space of the core plot unit, which includes tension, joy and sentimentality. Specifically: obtain the emotional annotation data in the preset animation script corpus; Perform dimensionality reduction on the emotional annotation data to extract tension, happiness, and sadness; Calculate the independence coefficients between tension, euphoria, and sentimentality; A quantitative scoring standard was constructed based on the independence coefficients among tension, joviality, and sentimentality; Quantitative scoring criteria were applied to tension, cheerfulness, and sentimentality to construct a multidimensional emotional feature space.

[0058] In this step, the system constructs a multidimensional emotional feature space by analyzing and processing the emotional annotation data in the preset animation script corpus. This feature space contains three dimensions: tension, joy, and sentimentality, which are used to quantify and describe the emotional changes in the core plot unit. By extracting the key features in the emotional annotation data and performing dimensionality reduction processing, the system can effectively capture and represent the differences and associations between different emotional states.

[0059] In order to construct a multidimensional emotional feature space, the system first obtains the emotional annotation data in the preset animation script corpus, and performs preprocessing and feature extraction on it. Then, the extracted features are reduced in dimension by applying a dimensionality reduction algorithm (such as principal component analysis or independent component analysis) to obtain three key emotional dimensions: tension, cheerfulness, and sentimentality. Next, the system calculates the independence coefficient between these three dimensions to measure their correlation and independence. Based on the independence coefficient, the system constructs a quantitative scoring standard to map tension, cheerfulness, and sentimentality into a normalized numerical range, forming a multidimensional emotional feature space.

[0060] In the process of constructing a multidimensional emotional feature space, the system may face technical challenges in the selection of emotional dimensions and the design of quantitative scoring criteria. To solve these problems, the system can introduce more emotional dimensions, such as surprise and disgust, to capture richer and more delicate emotional changes. At the same time, the system can use machine learning algorithms, such as support vector machines or neural networks, to automatically learn and optimize quantitative scoring criteria to improve the representation ability and accuracy of the emotional feature space. Through continuous iteration and optimization, the system can construct a more complete and effective multidimensional emotional feature space, providing a solid foundation for subsequent emotional analysis and script generation.

[0061] S202, extracting emotion vectors based on the text content of the core plot unit, and mapping the emotion vectors to a multi-dimensional emotion feature space; The system extracts emotion vectors based on the text content of the core plot unit and maps the emotion vectors into a multi-dimensional emotion feature space.

[0062] In this step, the system analyzes the text content of the core plot unit, extracts the sentiment vector that can characterize the sentiment characteristics of the unit, and maps it to the multidimensional sentiment feature space constructed previously. Sentiment vector is a mathematical representation used to quantify and describe the sentiment information contained in the text. By mapping the sentiment vector to the multidimensional sentiment feature space, the system can establish a direct connection between the text content and the corresponding emotional state, which facilitates subsequent sentiment analysis and optimization.

[0063] In order to extract sentiment vectors, the system can use various natural language processing techniques, such as sentiment lexicon, sentiment dependency analysis, deep learning, etc. First, the system can build a sentiment lexicon containing rich sentiment vocabulary and use the lexicon to sentimentally annotate the text content. Then, through sentiment dependency analysis, the system can identify sentiment keywords and their dependencies in the text, thereby inferring the sentiment tendency of the entire text. In addition, the system can also apply deep learning models, such as recurrent neural networks or attention mechanisms, to automatically learn the sentiment representation of the text and capture the contextual information and semantic associations therein. Finally, the system maps the extracted sentiment vector to a multidimensional sentiment feature space to obtain a quantitative representation of the text in terms of tension, cheerfulness, and sentimentality.

[0064] In the process of extracting and mapping sentiment vectors, the system may face the problems of sentiment ambiguity and context dependence. To solve these problems, the system can introduce sentiment disambiguation technology to analyze the sentiment tendency of words in different contexts, eliminate sentiment ambiguity, and improve the accuracy of sentiment vectors. At the same time, the system can adopt context-aware sentiment analysis methods, consider the semantic information before and after the text, and capture the dynamic changes of sentiment. In addition, the system can also use transfer learning and domain adaptation technology to apply the sentiment analysis model trained in other fields to the sentiment analysis of animation scripts, so as to improve the generalization ability and robustness of sentiment vector extraction.

[0065] S203, calculating the emotion trajectory curve of each core plot unit in the multi-dimensional emotion feature space; In this step, the system calculates the emotional trajectory curves of the core plot units based on their mapping positions in the multidimensional emotional feature space. The emotional trajectory curve is a mathematical representation of the emotional change process, which reflects the dynamic change trend of the plot unit in terms of tension, joy, and sentimentality. By analyzing the emotional trajectory curve, the system can grasp the emotional trend of the entire story and provide a basis for subsequent emotional optimization and rhythm adjustment.

[0066] In order to calculate the emotion trajectory curve, the system first needs to determine the position coordinates of the core plot unit in the multidimensional emotion feature space. This can be achieved by mapping the emotion vector of each plot unit to the corresponding coordinate point. Then, the system connects these coordinate points according to the order of the plot units to form a continuous curve, which is the emotion trajectory curve. The system can use curve fitting algorithms, such as spline interpolation or Bezier curves, to smooth and optimize the emotion trajectory curve to make it more natural and coherent.

[0067] S204: Adjust the emotion trajectory curve according to a preset emotion fluctuation mode.

[0068] In this step, the system adjusts and optimizes the previously calculated emotion trajectory curve according to the preset emotion fluctuation pattern. The emotion fluctuation pattern is a template that describes the law of ideal emotion change, which reflects the general law and rhythm arrangement of the emotional development of the story. By matching and adjusting the emotion trajectory curve with the preset emotion fluctuation pattern, the system can make the generated animation script more reasonable, vivid and fascinating in emotional expression.

[0069] In order to adjust the emotion trajectory curve, the system first needs to build a preset emotion fluctuation pattern library, which contains various typical emotion change patterns, such as gradual rise, fluctuation, climax, etc. Then, the system matches the emotion trajectory curve with the patterns in the pattern library to find the most similar pattern. Next, the system deforms and adjusts the emotion trajectory curve according to the matched pattern to make it more consistent with the ideal emotion fluctuation law. The adjustment process can be achieved through various mathematical transformations and optimization algorithms, such as scaling, translation, rotation, etc.

[0070] In the process of adjusting the emotional trajectory curve, the system may face the problems of inaccurate pattern matching and unreasonable adjustment range. In order to solve these problems, the system can adopt a multi-scale pattern matching strategy to match at different time scales to capture the local and global characteristics of emotional changes. At the same time, the system can introduce an adaptive adjustment strategy to dynamically adjust the adjustment range and method according to the characteristics of the emotional trajectory curve and the needs of the plot to avoid excessive changes in the original emotional trend. In addition, the system can also use reinforcement learning algorithms to learn and optimize the adjustment strategy of the emotional trajectory curve through continuous trials and feedback, so that the generated animation script is more natural, smooth and contagious in emotional expression.

[0071] After that, the system extracts the significant feature points of emotional changes based on the emotional trajectory curve, and calculates the emotional span and duration between adjacent significant feature points to obtain the emotional fluctuation feature sequence; A neural oscillator network is constructed based on the characteristic sequence of emotional fluctuations. The frequency of each oscillator node in the neural oscillator network corresponds to the duration, and the amplitude corresponds to the emotional span. Model the emotional rhythm using a neural oscillator network to generate a rhythm feature vector; The rhythm change of the emotion trajectory curve is determined according to the golden ratio and the rhythm feature vector. Specifically, the total duration of the emotion trajectory curve is divided into multiple time segments according to the golden ratio; Calculate the energy distribution of the rhythm feature vector in each time segment, and construct a rhythm adjustment function based on the energy distribution, the rhythm adjustment function is used to amplify or suppress the intensity of emotional fluctuations in each time segment; The rhythm adjustment function is applied to the emotional trajectory curve to obtain the optimized emotional rhythm change.

[0072] In the above embodiment, a multi-dimensional emotional feature space is introduced to perform emotional modeling on the core plot unit, and an accurate depiction of the emotional changes in the plot is achieved by extracting the emotional vector and calculating the emotional trajectory curve. The emotional trajectory curve is adjusted based on the preset emotional fluctuation mode, so that the generated plot is more in line with artistic laws in terms of emotional expression. The logical coherence of the main plot development line generated subsequently is improved, and the rationality of the fluctuation changes formed at the emotional level is also improved.

[0073] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of an animation script automatic generation system provided in an embodiment of the present application.

[0074] It should be noted that Figure 3 The structure of the system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0075] like Figure 3 As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through a bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0076] The following components are connected to the I / O interface 305: an input section 306 including a camera, an infrared sensor, etc.; an output section 307 including a liquid crystal display (LCD) and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0077] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0078] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.

[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0080] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiment; or may exist independently without being assembled into the system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of a system, the system implements the method provided in the above embodiment.

[0081] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0082] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0083] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0084] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for automatically generating an animation script, characterized in that: include: Performing semantic analysis on the static text description in the creative material input by the user to extract a scene element set, a plot element set and a character element set, wherein the creative material includes the static text description and the static keyword set; According to the semantic similarity between each keyword in the static keyword set and each element in the scene element set, the plot element set and the character element set, weights are assigned to each element to obtain an element association graph containing weights; Divide the preset animation script structure template into a number of plot units, and calculate the content matching degree between each element in the element association diagram and each plot unit; Sorting the plot units in descending order of importance according to the content matching degree, and selecting the plot units ranked before a preset number in the descending order of importance as core plot units; Calculating the cosine value of the semantic vector angle between the core plot units as the semantic association degree, and using the semantic association degree as the connection weight to construct a plot unit association network; Executing a maximum weight path search algorithm in the plot unit association network to obtain the main plot development line between the core plot units; Determine the sequential relationship of each core plot unit based on the main plot development line, and supplement the scene description and expand the plot details of each core plot unit according to a preset narrative rule library to obtain an extended core plot unit; According to the weight distribution of the role elements in the element association graph, the corresponding roles are assigned to the extended core plot unit and the role dialogue content is generated to obtain the final core plot unit; The final core plot units are integrated according to a preset animation script format to generate an animation script text.

2. The method according to claim 1, characterized in that The semantic analysis of the static text description in the creative material input by the user to extract the scene element set, the plot element set and the character element set specifically includes: Segmenting the static text description into a plurality of text segments; Performing part-of-speech tagging and dependency syntax analysis on the plurality of text segments, and identifying scene description sentences, plot description sentences, and character description sentences in each of the text segments; Clustering the scene description sentences based on preset semantic feature indicators to obtain a scene element set; Classifying the plot description sentences based on a preset plot type model to obtain a plot element set; Feature extraction is performed on the role description sentence based on preset role feature dimensions to obtain a role element set.

3. The method according to claim 1, characterized in that The step of assigning weights to the elements according to the semantic similarity between each keyword in the static keyword set and each element in the scene element set, the plot element set, and the character element set to obtain an element association graph containing weights specifically includes: Constructing a keyword-element bipartite graph, wherein the nodes of the keyword-element bipartite graph include keyword nodes in the static keyword set and element nodes in each element set; Calculate the word vector cosine similarity between each of the keyword nodes and each of the element nodes as the edge weight; Determine the importance score of each of the element nodes in the keyword element bipartite graph; The importance score is used as the weight value of each element to construct an element association graph.

4. The method according to claim 1, characterized in that: Before calculating the cosine value of the semantic vector angle between the core plot units as the semantic association, the method further includes: Constructing a multi-dimensional emotional feature space of the core plot unit, wherein the multi-dimensional emotional feature space includes tension, joy and sentimentality; Extracting emotion vectors based on the text content of the core plot unit, and mapping the emotion vectors to the multidimensional emotion feature space; Calculating the emotion trajectory curve of each of the core plot units in the multi-dimensional emotion feature space; The emotion trajectory curve is adjusted according to a preset emotion fluctuation mode.

5. The method according to claim 4, characterized in that The multi-dimensional emotional feature space of the core plot unit is constructed as follows: Obtain the emotion annotation data in the preset animation script corpus; Performing dimensionality reduction processing on the emotion annotation data to extract tension, happiness and sadness; calculating the independence coefficients among the tension, the jollity and the sadness; Constructing a quantitative scoring standard based on the independence coefficients among the tension, the euphoria and the sentimentality; The quantitative scoring standard is applied to the tension, the cheerfulness and the sadness to construct a multi-dimensional emotional feature space.

6. The method according to claim 4, characterized in that After adjusting the emotion trajectory curve according to the preset emotion fluctuation mode, the method further includes: Extracting significant feature points of emotion changes based on the emotion trajectory curve, and calculating the emotion span and duration between adjacent significant feature points to obtain an emotion fluctuation feature sequence; Building a neural oscillator network based on the emotional fluctuation characteristic sequence, wherein the frequency of each oscillator node in the neural oscillator network corresponds to the duration, and the amplitude corresponds to the emotional span; Modeling the emotional rhythm using the neural oscillator network to generate a rhythm feature vector; The rhythm change of the emotion trajectory curve is determined according to the golden section ratio and the rhythm feature vector.

7. The method according to claim 6, characterized in that The step of determining the rhythm change of the emotion trajectory curve according to the golden section ratio and the rhythm feature vector specifically includes: Dividing the total duration of the emotion trajectory curve into multiple time segments according to the golden ratio; Calculating the energy distribution of the rhythm feature vector in each of the time segments, and constructing a rhythm adjustment function based on the energy distribution, wherein the rhythm adjustment function is used to amplify or suppress the intensity of the emotional fluctuation in each of the time segments; The rhythm adjustment function is applied to the emotion trajectory curve to obtain an optimized emotion rhythm change.

8. An animation script automatic generation system, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to execute the method according to any one of claims 1 to 7.

Images