Method and system for determining drama conflict frequency based on drama

Abstract

The invention discloses a drama conflict frequency determining method and system based on a script, and the method comprises the steps: obtaining a character paragraph from the script, and enabling the character paragraph to describe at least one role and the performance information corresponding to the role; determining the emotion of the role according to the performance information corresponding to the role; acquiring a time axis corresponding to the performance information, and arranging the emotions of the roles on a two-dimensional coordinate system according to a time sequence on the time axis; the two-dimensional coordinate system is displayed, the displayed two-dimensional coordinate system is used as a shooting outline, and the emotion on the two-dimensional coordinate system is used as a basis for determining the drama conflict in the scene. According to the method and the device, the problem of subjective script evaluation caused by the fact that conflicts in a script cannot be objectively displayed in related technologies is solved, so that emotion changes in the script can be objectively displayed, and objective data is provided for evaluating highlighting in the script.

Description

Technical Field

[0001] The present application relates to the field of software, and in particular, to a method and system for determining the frequency of dramatic conflicts based on a script. Background Art

[0002] The script is mainly composed of lines and stage instructions. It is the textual basis of theatrical art creation and the basis for the director and actors to perform. Words similar to scripts include scripts, plays, etc. It is a literary style that mainly expresses the plot in a representative manner. Scripts are mainly divided into literary scripts and photographic scripts. Literary scripts are scripts that highlight literary qualities and have a low sense of photography. They include drama scripts (or drama scripts), novel scripts (or drama novels), sketch scripts, crosstalk scripts, etc.; photographic scripts are scripts that highlight the sense of shooting. The literary and artistic quality can be high or low (determined by the film subject, market, investment funds, etc.), including scene scripts, storyboard scripts (storyboard scripts or movie scripts), scripts, etc. The script is one of the necessary tools for stage performances or filming. It is the reference language for the characters in the play to have dialogues. It is an art style that serves stage performances, which is different from drama and other literary styles.

[0003] The quality of a movie depends largely on whether the story is attractive, which requires sufficient conflicts in the movie script. Currently, the evaluation of the amount of conflict in a movie script mainly relies on people's subjective reading. This depends on people's subjective factors and cannot objectively measure the script. That is, there is no solution in the relevant technology that can objectively display the amount of conflict. Summary of the invention

[0004] The embodiments of the present application provide a method and system for determining the frequency of dramatic conflicts based on a script, so as to at least solve the problem of subjective script evaluation caused by the inability to objectively display the conflicts in the script in the related art.

[0005] According to one aspect of the present application, a method for determining the frequency of dramatic conflict based on a script is provided, which is applied to software, and the software is used to execute the method, and the method includes the following steps: obtaining a text paragraph from a script, wherein the text paragraph is a text paragraph under the same shooting scene, and the text paragraph describes at least one role and the performance information corresponding to the role, wherein the performance information includes at least one of the following: language, action, expression; determining the emotion of a role according to the performance information corresponding to the role, wherein the emotion is determined according to the text description in the performance information, and the emotion is several preset emotions; obtaining a timeline corresponding to the performance information, and arranging the emotions of the role in a two-dimensional coordinate system according to the time sequence on the timeline; wherein the horizontal axis of the two-dimensional coordinate system is the timeline, and the vertical axis of the two-dimensional coordinate system is the emotion, and different emotions have different positions on the vertical axis; displaying the two-dimensional coordinate system, wherein the displayed two-dimensional coordinate system is used as a shooting outline, and the emotions on the two-dimensional coordinate system are used as the basis for determining the dramatic conflict in the scene.

[0006] Furthermore, obtaining the text paragraph from the script includes: dividing the script into different chapters according to the text in the script used to identify chapters; for each chapter, obtaining the corresponding scene in the chapter, wherein the scene is a shooting scene; and using the text in the same scene as the text paragraph.

[0007] Furthermore, it also includes: generating a corresponding two-dimensional coordinate system for each scene in all chapters of the script; arranging all the generated two-dimensional coordinate systems in chronological order according to the scenes corresponding to the two-dimensional coordinate systems in the chapter; displaying the arranged two-dimensional coordinate systems in the chapter; arranging all chapters in chronological order, and displaying the two-dimensional coordinate systems corresponding to all the arranged chapters.

[0008] Furthermore, determining the emotion of a character based on the performance information corresponding to a character includes: obtaining words in the performance information used to describe the character's actions and / or expressions, or obtaining the language of the character in the performance information, and obtaining words from the language used to indicate the character's emotions; dividing the words into positive words, neutral words and negative words, wherein the positive words correspond to a first emotion, the neutral words correspond to a second emotion, and the negative words correspond to a third emotion, and the first emotion, the second emotion and the third emotion are different emotions; determining the emotion of the character based on the words.

[0009] According to another aspect of the present application, there is also provided a system for determining the frequency of dramatic conflicts based on a script, which is applied to software, and the software includes the following modules: an acquisition module, used to acquire text paragraphs from a script, wherein the text paragraphs are text paragraphs under the same shooting scene, and the text paragraphs describe at least one role and performance information corresponding to the role, wherein the performance information includes at least one of the following: language, action, expression; a determination module, used to determine the emotion of a role according to the performance information corresponding to the role, wherein the emotion is determined according to the text description in the performance information, and the emotion is several preset emotions; an arrangement module, used to acquire the timeline corresponding to the performance information, and arrange the emotions of the role in a two-dimensional coordinate system according to the time order on the timeline; wherein the horizontal axis of the two-dimensional coordinate system is the timeline, and the vertical axis of the two-dimensional coordinate system is the emotion, and different emotions have different positions on the vertical axis; a display module, used to display the two-dimensional coordinate system, wherein the displayed two-dimensional coordinate system is used as a shooting outline.

[0010] Furthermore, the acquisition module is used to: divide the script into different chapters according to the text in the script used to identify chapters; obtain the corresponding scene in each chapter, wherein the scene is a shooting scene; and use the text in the same scene as the text paragraph.

[0011] Furthermore, the display module is also used to: generate a corresponding two-dimensional coordinate system for each scene in all chapters of the script; arrange all the generated two-dimensional coordinate systems in chronological order according to the scenes corresponding to the two-dimensional coordinate systems in the chapter; display the arranged two-dimensional coordinate systems in the chapter; arrange all chapters in chronological order, and display the two-dimensional coordinate systems corresponding to all the arranged chapters.

[0012] Furthermore, the determination module is used to: obtain words from the performance information for describing the character's actions and / or expressions, or obtain the language of the character in the performance information, and obtain words from the language for indicating the character's emotions; divide the words into positive words, neutral words, and negative words, wherein the positive words correspond to a first emotion, the neutral words correspond to a second emotion, and the negative words correspond to a third emotion, and the first emotion, the second emotion, and the third emotion are different emotions; determine the character's emotions based on the words.

[0013] According to another aspect of the present application, an electronic device is also provided, comprising a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the above-mentioned method steps.

[0014] According to another aspect of the present application, a readable storage medium is provided, on which computer instructions are stored, wherein the computer instructions implement the above method steps when executed by a processor.

[0015] In the embodiment of the present application, a text paragraph is obtained from the script, wherein the text paragraph is a text paragraph under the same shooting scene, and the text paragraph describes at least one role and the performance information corresponding to the role, wherein the performance information includes at least one of the following: language, action, expression; the emotion of the role is determined according to the performance information corresponding to a role, wherein the emotion is determined according to the text description in the performance information, and the emotion is a preset emotion; the time axis corresponding to the performance information is obtained, and the emotions of the role are arranged on a two-dimensional coordinate system according to the time sequence on the time axis; wherein the horizontal axis of the two-dimensional coordinate system is the time axis, and the vertical axis of the two-dimensional coordinate system is the emotion, and different emotions have different positions on the vertical axis; the two-dimensional coordinate system is displayed, wherein the displayed two-dimensional coordinate system is used as a shooting outline, and the emotions on the two-dimensional coordinate system are used as the basis for determining the dramatic conflict in the scene. This application solves the problem of subjective script evaluation caused by the inability to objectively display the conflict in the script in the related art, so that the emotional changes in the script can be objectively displayed, providing objective data for evaluating the prominence in the script. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 is a flow chart of a method for determining the frequency of dramatic conflict based on a script according to an embodiment of the present application;

[0018] Figure 2 is a schematic diagram of two-dimensional coordinates of emotional points according to an embodiment of the present application; and,

[0019] Figure 3 It is a schematic diagram of the two-dimensional coordinates of the emotion points of character A related to the event according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0022] Scripts, especially those used for filming TV dramas, need to be presented to the audience in the form of images. The conflicts felt by the audience are basically expressed through the actors' performances of their roles. Therefore, the following implementation methods objectively present the emotional changes of the characters in the script, so that film and television workers can clearly and objectively evaluate whether the conflict in a certain scene in a script is sufficient, providing an objective basis for script modification and even subsequent filming.

[0023] In the following implementation, a method for determining the frequency of dramatic conflict based on a script is provided, which is applied to software, and the software is used to execute the method. Figure 1 is a flow chart of a method for determining the frequency of dramatic conflict based on a script according to an embodiment of the present application. Figure 1 As shown, the steps included in the method are described below.

[0024] Step S102, obtaining a text paragraph from the script, wherein the text paragraph is a text paragraph under the same shooting scene, and the text paragraph describes at least one role and performance information corresponding to the role, wherein the performance information includes at least one of the following: language, action, and expression.

[0025] Step S104, determining the emotion of a character according to the performance information corresponding to the character, wherein the emotion is determined according to the text description in the performance information, and the emotion is several preset emotions.

[0026] Step S106, obtaining the timeline corresponding to the performance information, and arranging the emotions of the character on a two-dimensional coordinate system according to the time sequence on the timeline; wherein the horizontal axis of the two-dimensional coordinate system is the timeline, and the vertical axis of the two-dimensional coordinate system is the emotion, and different emotions have different positions on the vertical axis.

[0027] Step S108, displaying the two-dimensional coordinate system, wherein the displayed two-dimensional coordinate system is used as a shooting outline, and the emotions on the two-dimensional coordinate system serve as the basis for determining the dramatic conflict in the scene, and each emotion in the two-dimensional coordinate system is mapped to a value on the vertical axis, and the closer the position on the vertical axis is to the origin of the coordinate system, the lower the emotion corresponding to the value on the vertical axis, and the farther away from the origin of the coordinate system, the higher the emotion corresponding to the value on the vertical axis, and each emotion corresponds to a point on the two-dimensional coordinate system.

[0028] In an additional implementation, the points corresponding to the emotions displayed in the two-dimensional coordinate system can be connected to form a curve, which can be called an emotion curve; the curve is compared with a pre-configured curve, and if the similarity between the curve and the pre-configured curve exceeds a threshold, it is determined that the scene corresponding to the curve meets the requirements. The pre-configured curve can be generated based on the emotions in the scene in the script selected by the expert; the script selected by the expert can be some classic and excellent scripts.

[0029] Through the above steps, the problem of subjective script evaluation caused by the inability to objectively display the conflicts in the script in the related technology is solved, so that the emotional changes in the script can be objectively displayed, providing objective data for evaluating the prominence in the script.

[0030] Usually a script may also include different chapters. In order to distinguish chapters, in an optional implementation, obtaining the text paragraphs from the script may include the following steps: dividing the script into different chapters according to the text in the script used to identify chapters; for each chapter, respectively obtaining the corresponding scene in the chapter, wherein the scene is a shooting scene; and using the text in the same scene as the text paragraph.

[0031] Corresponding to each chapter, in an optional implementation, a corresponding two-dimensional coordinate system is generated for each scene in all chapters of the script; all generated two-dimensional coordinate systems are arranged in chronological order according to the scenes corresponding to the two-dimensional coordinate systems in the chapter; the arranged two-dimensional coordinate systems are displayed in the chapter; all chapters are arranged in chronological order, and the two-dimensional coordinate systems corresponding to all arranged chapters are displayed.

[0032] There are many methods for determining emotions. For example, the following method for extracting emotions from microblogs can also be applied to this embodiment. The method is described in detail below.

[0033] Step 1: Collect original Weibo comment text data for training capsule network, and preprocess the original Weibo comment text data to obtain a Weibo text dataset, wherein the Weibo text dataset includes a training set and a test set.

[0034] Step 2: Pre-train the Weibo texts in the Weibo text dataset and convert the Weibo texts in the Weibo text dataset into word2vec feature word vectors.

[0035] Step 3: Using the emotion dictionary, select sentences containing emotions from the pre-trained microblog texts to be classified in the training set as local emotion features.

[0036] Step 4: Use the capsule network trained with the training set and the test set to extract the overall emotional features of the microblog text to be classified.

[0037] Step 5: The overall emotion features and local emotion features of the microblog texts to be classified in the microblog text data set are integrated to obtain the emotion classification results of the microblog texts to be classified, wherein the emotion classification results include positive emotion probability and negative emotion probability.

[0038] Step 6: Sum and average the emotion classification results of all the to-be-classified microblog texts of a microblog user in the microblog text data set, and determine the emotional tendency of the microblog user based on the average value.

[0039] Specifically, in this embodiment, the microblog comment sentiment classification method utilizes local and overall sentiment features and classifies the sentiment of microblog comments based on the trained capsule network. The detailed operation steps are as follows. In step 1, the original microblog comment text data for training capsule network model parameters is collected, and the original microblog comment text data is normalized and preprocessed to generate a preprocessed microblog text data set, which is divided into a training set and a test set.

[0040] The microblog comment data on a microblog user's microblog platform is crawled as the original microblog comment text data, and the collected original microblog comment text data is preprocessed. Specifically, first, the original microblog comment text data is collected by a web crawler, and the data is filtered to remove comments containing pictures, special symbols and expressions; then, the filtered comment data is emotionally annotated by manual annotation to obtain the corresponding microblog text labels. Emotions are divided into two categories, namely positive emotions and negative emotions. For example, the preprocessed sentences - "Updated, posted photos, handsome!" Such sentences with positive emotions are marked as 1; "I'm sleepy at this point, can I do anything else?" Such sentences with negative emotions are marked as 0, which are used as microblog text data sets; finally, the preprocessed microblog text data sets are divided into training data sets and test data sets according to a certain ratio, for example, the ratio is 4:1. In step 2, the single microblog text in the training data set is segmented as a whole using Chinese punctuation marks, and then the emotion dictionary is used to select sentences containing emotions, and the sentences are used as local emotion features. In this embodiment, the emotional dictionary is used to mark sentences with emotional tendencies so that the sentences can be automatically recognized by the capsule network model, and the sentences are obtained by segmenting punctuation marks, such as commas, periods, semicolons, exclamation marks, question marks, etc. The sentence in the capsule network model represents the local content in a microblog text. The capsule network model can learn the emotional characteristics of the local content and obtain the corresponding emotional classification probability. If a microblog text can extract k sentences, that is, it has k parts, the microblog text is input as a whole during training, and the capsule network model will automatically identify sentences with emotional tendencies through the emotional dictionary and learn the probability of its emotional classification. After that, the probability is selected according to the size and retained to participate in the calculation of the final emotional classification prediction result. In step three, a vocabulary is constructed, and the microblog text data set is pre-trained to obtain the corresponding Word2vec feature word vector. In this embodiment, a Chinese word segmentation tool, such as the word segmentation tool jieba, is used to segment the microblog text, and the word2vec tool is used to train on the microblog text data set to convert the sentence into a corresponding word vector matrix. For example, if a microblog text s consists of n words, it can be represented as: s = (w1, w2, w3, ... wn) after word segmentation, and each word w is represented as a k-dimensional real vector, then each sentence is finally represented as an n × k matrix. In step 4, the overall emotional features of the microblog text to be classified are extracted: the capsule network (CapsuleNetwok) is used to extract the overall emotional features of the microblog text.In this embodiment, a single microblog text is taken as an input and input into the capsule network for learning to obtain a binary classification result expressed as probability. The designed deep learning model can also learn the characteristics of sentences containing emotions. The output result is the same as the microblog text form, and the output form is {y1, y2}, where y1 is positive emotion and y2 is negative emotion.

[0041] The specific method for extracting the overall emotional features of microblog texts includes the following steps: A: Constructing a capsule network. In order to extract the local and overall emotional features of microblog texts, the technical solution of the present invention constructs a capsule network, which includes an input layer, a convolution layer, a basic capsule layer, a convolution capsule layer, a fully connected capsule layer, a capsule average pooling layer, and an output layer. Three types of convolution kernels are used in the convolution layer, namely 3*300, 4*300, and 5*300. The three types of convolution kernels are used so that the model can better learn the characteristic information between microblog text sentences. B: Training the capsule network. The microblog text data set of microblog comments is split into a training set and a test set in a ratio of 4:1, and the capsule network is trained on the training set. In order to prevent overfitting during the training process, the Dropout rate is set to 0.5, that is, a part of the training parameters are randomly abandoned in each iteration. The brain capsule network uses the Adam algorithm to update the parameters of each layer of the network, and the number of iterations is 100 times. After the capsule network model reaches a certain accuracy, the model is tested using a test set to check the prediction accuracy of the model. C: The emotional features of microblog texts are extracted using the trained capsule network model. The microblog text represented by m n*k dimensional matrices is input into the trained capsule network. After extraction by the convolution layer, the learned local emotional features are not extracted by the pooling layer, but directly stored in the capsule layer, so that the positional features between words can be better preserved. After that, the capsule network uses a dynamic routing algorithm to learn features. At the same time, the capsule network model of the embodiment of the present invention will retain the features of the previously marked emotional sentences. Finally, the features learned by the three convolution kernels are all mapped to the capsule average pooling layer. In step five, the overall emotional features of a single microblog text have the same word vector representation as the local emotional features of the sentence. Combining the learned overall and local emotional features, three methods can be used to obtain the final emotional classification prediction results of a single microblog text to be classified.

[0042] In another example, a method for emotion recognition of question and answer text is provided, which can also be applied to the present embodiment. The method comprises: processing the target question and answer text to extract multiple question and answer text pairs corresponding to all preset topics, each question and answer text pair comprising a question text and a corresponding answer text. In this step, a diagnostic text or audio recording can be obtained through the diagnostic process of the medical interview or depression rating scale, and then converted into multiple rounds of question and answer text. A round of question and answer text is a question and answer text pair (Qi, Ai), including a question text Qi and an answer text Ai, where i∈[0,l], l is the number of question and answer text pairs. Many question and answer pairs will be generated in the process of evaluating depression, and these question and answer pairs do not all play a positive role in the identification of depression. Question and answer pairs that are less relevant or irrelevant to the identification of depression may become interference information, affecting the accuracy and efficiency of depression identification. Therefore, after obtaining the question and answer text, the question and answer pairs must be screened first. Inspired by the scales used by doctors to screen depression and related literature research, the preset topics here include: argue, proud, sleep, study, emotion, depression, PTSD (post-traumatic stress disorder). For example, the corresponding questions can be "What / when was the last quarrel", "Is there anything to be proud of", "How is your sleep", "How is your learning ability", "How is your emotional control ability", "Have you been diagnosed with depression", and "Have you been diagnosed with post-traumatic stress disorder", etc. Specifically, the target question-answer text can be processed in the following way: determine all question-answer text pairs in the target question-answer text. For each question-answer text pair, based on the similarity of text emotions, determine whether the topic expressed by the question-answer text pair is one of the preset topics. If so, the question-answer text pair is used as a question-answer text pair corresponding to the preset topic. Here, the question-answer text pairs corresponding to the preset topic can be screened by using the MPNet (Masked and Permuted Pretraining for Language Understanding) model to calculate the sentence similarity, or by matching by manually constructing regular expressions. For each preset topic, before converting all the question-answer text pairs corresponding to the preset topic into feature vectors, the step also includes: normalizing the question text and answer text in each question-answer text pair by at least one of the following methods: restoring abbreviations in the question text and answer text; restoring the parts of speech in the question text and answer text; removing stop words in the question text and answer text; removing punctuation marks in the question text and answer text. The screened question-answer text pairs also need to be preprocessed to normalize the text for easy input into the deep learning model.Here, all methods can be used to process each question-answer text pair in turn according to the above order. For each preset topic, all question-answer text pairs corresponding to the preset topic are converted into feature vectors, and a question text vector sequence and an answer text vector sequence corresponding to the preset topic are formed. In this step, for each preset topic, a question text vector sequence and an answer text vector sequence corresponding to the preset topic are formed in the following manner: all question-answer text pairs corresponding to the preset topic are input into a pre-trained BERT model for vector conversion to output a question text vector sequence and an answer text vector sequence.

[0043] In this embodiment, an optional method is also provided, which determines the emotion of a character according to the performance information corresponding to the character, including: obtaining words used to describe the character's actions and / or expressions in the performance information, or obtaining the language of the character in the performance information, and obtaining words used to indicate the character's emotions from the language; dividing the words into positive words, neutral words and negative words, wherein the positive words correspond to a first emotion, the neutral words correspond to a second emotion, and the negative words correspond to a third emotion, and the first emotion, the second emotion and the third emotion are different emotions; and determining the emotion of the character according to the words.

[0044] All emotion allocations may include the above three emotions. Of course, in addition to the above three emotions, multiple emotions may also be included. The classification of emotion types may be set as needed, but no matter how it is set, it should include the above three emotions, namely the first emotion, the second emotion and the third emotion.

[0045] Figure 2 is a schematic diagram of two-dimensional coordinates of emotional points according to an embodiment of the present application, such as Figure 2 As shown in the figure, there can be four values ​​on the vertical axis, and the time on the horizontal axis is in units of 30 seconds. The points on the two-dimensional coordinates can be connected to form an emotion curve. An emotion curve can be generated for each character. The current event read from the script can also be marked on the points on the emotion curve of a character, so that the reason for the change of the emotion curve can be more clearly shown. Figure 3 is a schematic diagram of two-dimensional coordinates of emotional points of character A related to events according to an embodiment of the present application, such as Figure 3 As shown, the emotional changes of character A are written out from the script. After being drawn into a two-dimensional coordinate system, events related to the emotional changes of character A are read out from the script and displayed on the two-dimensional coordinate system, thereby making the two-dimensional coordinate system more intuitive.

[0046] In an optional implementation, a complete shooting outline may be generated according to the above steps. This method may be referred to as a method for automatically generating a shooting outline based on a script. The method may include the following steps:

[0047] Obtaining a script, and dividing the script into different chapters according to words used to indicate chapters in the script;

[0048] For each chapter, obtain text paragraphs of different scenes in the chapter, where the scene is a shooting scene;

[0049] Obtaining a character in a text paragraph in a shooting scene and performance information of the character; wherein the performance information includes at least one of the following: language, action, expression;

[0050] determining the emotion of the character according to the performance information;

[0051] Acquire lens position information in the shooting scene, wherein the lens position information is used to indicate a relative position relationship between a camera or a virtual camera and the person when shooting the person, and the camera or the virtual camera may be one or more;

[0052] Displaying the character, the performance information, the emotion and the camera position information under the shooting scene;

[0053] Arranging all the shooting scenes in the script that display the thoughts, the performance information, the emotions, and the camera position information according to a timeline;

[0054] Generate a table of the arranged shooting scenes, wherein the columns of the table are different shooting scenes, and the multiple rows under the columns are the characters in the shooting scene, the performance information of the characters, the emotions of the characters and the camera position information.

[0055] The shooting script can be automatically generated through the above steps, which avoids the time required for the shooting personnel to read and understand the script, and to a certain extent provides a script basis for improving the shooting efficiency.

[0056] The generated shooting script may be in a table format, and the header content of the table may be as follows:

[0057]

[0058]

[0059] As an additional implementation method, the frequency of emotion changes can also be determined to determine whether the dramatic conflict in the scene is sufficient. That is, the implementation method can also include the following steps: obtaining a two-dimensional coordinate system in a scene; obtaining all emotions in the two-dimensional coordinate system, and determining the number of times the emotion changes on the time axis, wherein the change is the change between the first emotion, the second emotion, and the third emotion; obtaining the duration of the scene when it is filmed into a video; determining the frequency of emotion changes based on the duration and the number; and displaying the two-dimensional coordinate system using different colors, wherein different change frequencies correspond to different colors.

[0060] As another implementation that can be added, when the frequency of change of the emotion is lower than a first threshold or the frequency of change of the emotion is higher than a second threshold, a prompt message is displayed, wherein the prompt message is used to indicate that the frequency of change of the emotion is too slow or too fast.

[0061] The above implementation solves the problem of subjective script evaluation caused by the inability to objectively display the conflicts in the script in the related art, thereby being able to objectively display the emotional changes in the script and providing objective data for evaluating the highlights in the script.

[0062] In this embodiment, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and the processor is configured to run the computer program to execute the method in the above embodiment.

[0063] The above program can be run in the processor, or it can also be stored in the memory (or computer-readable medium), which includes permanent and non-permanent, removable and non-removable media. Information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0064] These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more blocks can be implemented by different modules corresponding to different steps.

[0065] Such a device or system is provided in this embodiment. The system is called a system for determining the frequency of dramatic conflicts based on a script, and is applied to software, wherein the software includes the following modules: an acquisition module, used to acquire a text paragraph from a script, wherein the text paragraph is a text paragraph under the same shooting scene, and the text paragraph describes at least one role and the performance information corresponding to the role, wherein the performance information includes at least one of the following: language, action, expression; a determination module, used to determine the emotion of a role according to the performance information corresponding to the role, wherein the emotion is determined according to the text description in the performance information, and the emotion is a preset several emotions; an arrangement module, used to acquire the time axis corresponding to the performance information, and arrange the emotions of the role in a two-dimensional coordinate system according to the time order on the time axis; wherein the horizontal axis of the two-dimensional coordinate system is the time axis, and the vertical axis of the two-dimensional coordinate system is the emotion, and different emotions have different positions on the vertical axis; a display module, used to display the two-dimensional coordinate system, wherein the displayed two-dimensional coordinate system is used as a shooting outline.

[0066] The system or device is used to implement the functions of the method in the above-mentioned embodiment. Each module in the system or device corresponds to each step in the method, which has been explained in the method and will not be repeated here.

[0067] Optionally, the acquisition module is used to: divide the script into different chapters according to the text in the script used to identify chapters; for each chapter, respectively acquire the corresponding scene in the chapter, wherein the scene is a shooting scene; and use the text in the same scene as the text paragraph.

[0068] Optionally, the display module is also used to: generate a corresponding two-dimensional coordinate system for each scene in all chapters of the script; arrange all the generated two-dimensional coordinate systems in chronological order according to the scenes corresponding to the two-dimensional coordinate systems in the chapter; display the arranged two-dimensional coordinate systems in the chapter; arrange all chapters in chronological order, and display the two-dimensional coordinate systems corresponding to all the arranged chapters.

[0069] Optionally, the determination module is used to: obtain words from the performance information for describing the character's actions and / or expressions, or obtain the language of the character in the performance information, and obtain words from the language for indicating the character's emotions; divide the words into positive words, neutral words, and negative words, wherein the positive words correspond to a first emotion, the neutral words correspond to a second emotion, and the negative words correspond to a third emotion, and the first emotion, the second emotion, and the third emotion are different emotions; determine the character's emotions based on the words.

[0070] Optionally, the determination module is also used to: obtain a two-dimensional coordinate system in a scene; obtain all emotions in the two-dimensional coordinate system, and determine the number of times the emotion changes on the timeline, wherein the change is the change between the first emotion, the second emotion and the third emotion; obtain the duration of the scene when it is captured as a video; determine the frequency of change of the emotion based on the duration and the number of times; and display the two-dimensional coordinate system using different colors, wherein different change frequencies correspond to different colors.

[0071] As another implementation that can be added, the display module is also used to: when the frequency of change of the emotion is lower than a first threshold or the frequency of change of the emotion is higher than a second threshold, display a prompt message, wherein the prompt message is used to indicate that the frequency of change of the emotion is too slow or too fast.

[0072] Through the above implementation, the problem of subjective script evaluation caused by the inability to objectively display the conflicts in the script in the related art is solved, so that the emotional changes in the script can be objectively displayed, providing objective data for evaluating the highlights in the script.

[0073] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining the frequency of dramatic conflict based on a script, applied to software, the software being used to execute the method, characterized in that: The method comprises the following steps: Obtaining a text paragraph from a script, wherein the text paragraph is a text paragraph under the same shooting scene, and the text paragraph describes at least one role and performance information corresponding to the role, wherein the performance information includes at least one of the following: language, action, and expression; Determining an emotion of a character according to performance information corresponding to the character, wherein the emotion is determined according to a text description in the performance information, and the emotion is one of several preset emotions; Obtaining a time axis corresponding to the performance information, and arranging the emotions of the character on a two-dimensional coordinate system according to the time sequence on the time axis; wherein the horizontal axis of the two-dimensional coordinate system is the time axis, the vertical axis of the two-dimensional coordinate system is the emotion, and different emotions have different positions on the vertical axis; The two-dimensional coordinate system is displayed, wherein the displayed two-dimensional coordinate system is used as a shooting outline, and the emotions on the two-dimensional coordinate system serve as a basis for determining dramatic conflicts in the scene.

2. The method according to claim 1, characterized in that Obtaining the text paragraph from the script includes: Dividing the script into different chapters according to the characters used to identify the chapters in the script; For each chapter, respectively obtain a corresponding scene in the chapter, wherein the scene is a shooting scene; The text in the same scene is regarded as the text paragraph.

3. The method according to claim 2, characterized in that Also includes: Generate a corresponding two-dimensional coordinate system for each scene in all chapters of the script; Arrange all generated two-dimensional coordinate systems in chronological order according to the scenes corresponding to the two-dimensional coordinate systems in the chapter; The arranged two-dimensional coordinate system is displayed in this section; Arrange all chapters in chronological order, and display the two-dimensional coordinate system corresponding to all the arranged chapters.

4. The method according to any one of claims 1 to 3, characterized in that Determining the emotion of a character according to performance information corresponding to the character includes: Acquire words used to describe the action and / or expression of the character in the performance information, or acquire the language of the character in the performance information, and acquire words used to indicate the emotion of the character from the language; Classifying the words into positive words, neutral words and negative words, wherein the positive words correspond to a first emotion, the neutral words correspond to a second word, and the negative words correspond to a third emotion, and the first emotion, the second emotion and the third emotion are different emotions; An emotion of the character is determined based on the words.

5. A system for determining the frequency of dramatic conflict based on a script, applied in software, characterized in that: The software includes the following modules: An acquisition module is used to acquire a text paragraph from a script, wherein the text paragraph is a text paragraph under the same shooting scene, and the text paragraph describes at least one role and performance information corresponding to the role, wherein the performance information includes at least one of the following: language, action, and expression; A determination module, used to determine the emotion of a character according to the performance information corresponding to the character, wherein the emotion is determined according to the text description in the performance information, and the emotion is several preset emotions; An arrangement module, used for obtaining a time axis corresponding to the performance information, and arranging the emotions of the characters on a two-dimensional coordinate system according to the time sequence on the time axis; wherein the horizontal axis of the two-dimensional coordinate system is the time axis, the vertical axis of the two-dimensional coordinate system is the emotions, and different emotions have different positions on the vertical axis; The display module is used to display the two-dimensional coordinate system, wherein the displayed two-dimensional coordinate system is used as a shooting outline.

6. The system according to claim 5, characterized in that The acquisition module is used for: Dividing the script into different chapters according to the characters used to identify the chapters in the script; For each chapter, respectively obtain a corresponding scene in the chapter, wherein the scene is a shooting scene; The text in the same scene is regarded as the text paragraph.

7. The system according to claim 6, characterized in that The display module is also used for: Generate a corresponding two-dimensional coordinate system for each scene in all chapters of the script; Arrange all generated two-dimensional coordinate systems in chronological order according to the scenes corresponding to the two-dimensional coordinate systems in the chapter; The arranged two-dimensional coordinate system is displayed in this section; Arrange all chapters in chronological order, and display the two-dimensional coordinate system corresponding to all the arranged chapters.

8. The system according to any one of claims 5 to 7, characterized in that The determination module is used for: Acquire words used to describe the action and / or expression of the character in the performance information, or acquire the language of the character in the performance information, and acquire words used to indicate the emotion of the character from the language; Classifying the words into positive words, neutral words and negative words, wherein the positive words correspond to a first emotion, the neutral words correspond to a second word, and the negative words correspond to a third emotion, and the first emotion, the second emotion and the third emotion are different emotions; An emotion of the character is determined based on the words.

9. An electronic device comprising a memory and a processor; wherein: The memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method steps described in any one of claims 1 to 4.

10. A readable storage medium having computer instructions stored thereon, wherein: When the computer instructions are executed by a processor, the method steps described in any one of claims 1 to 4 are implemented.

Images