Scenario analysis method and device, electronic equipment and storage medium

Abstract

The invention provides a script analysis method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a script text; determining at least one script analysis dimension corresponding to the script text; for each script analysis dimension, performing dimension analysis on the script text according to an analysis strategy corresponding to the script analysis dimension to obtain a dimension analysis result corresponding to the script analysis dimension; and according to dimension analysis results corresponding to all the script analysis dimensions, determining a script analysis result corresponding to the script text. According to the method and the device, the multi-dimensional intelligent analysis of the script text can be realized according to the preset analysis strategy of each script analysis dimension.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a script analysis method, device, electronic device and storage medium. Background Art

[0002] A script is a literary form that mainly consists of lines and stage directions, and is used to describe the plot and dialogue in a play, movie, animation, or other stage performance. It is the textual basis for the creation of dramatic art, and the basis for directors and actors to perform. Traditional script analysis mainly relies on manual reading and evaluation, which is inefficient and highly subjective. At the same time, the massive script data contains rich information such as narrative structure, character relationships, and emotional trends.

[0003] Therefore, how to achieve intelligent analysis of scripts has become an urgent problem to be solved. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a script analysis method, device, electronic device and storage medium to achieve intelligent analysis of the script. The specific technical solution is as follows:

[0005] In a first aspect, the present application provides a script analysis method, comprising:

[0006] Get the script text;

[0007] Determining at least one script analysis dimension corresponding to the script text;

[0008] For each script analysis dimension, perform dimension analysis on the script text according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension;

[0009] According to the dimensional analysis results corresponding to all the script analysis dimensions, the script analysis results corresponding to the script text are determined.

[0010] In a possible implementation, the script analysis dimension includes a plot rhythm analysis dimension, and the dimension analysis of the script text is performed according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension, including:

[0011] Extracting episode texts of all episodes from the script text;

[0012] For each episode, determining the episode story entropy corresponding to the episode according to the episode text corresponding to the episode;

[0013] Draw a story entropy curve according to the episode story entropies of all the episodes;

[0014] The script text is dimensionally analyzed according to the story entropy curve to obtain a dimension analysis result corresponding to the plot rhythm analysis dimension.

[0015] In a possible implementation manner, determining the episode story entropy corresponding to the episode according to the episode text corresponding to the episode includes:

[0016] Determine the number of story lines included in the script text as the number of story lines;

[0017] Determine the episode storyline ratio corresponding to the episode, wherein the episode storyline ratio is the ratio of the number of plot points contained in the episode text to the number of plot points contained in the script text;

[0018] Calculate the plot proportion of the episode according to the first formula to obtain the episode story entropy corresponding to the episode;

[0019] Among them, the first formula is:

[0020] in, is the story entropy of the kth episode, is the proportion of the episode storyline in the kth episode, and n is the number of story lines.

[0021] In a possible implementation, the script analysis dimension includes a plot structure analysis dimension, and the dimension analysis of the script text is performed according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension, including:

[0022] Extracting at least two story lines from the script text and the story line text and story line importance corresponding to each of the story lines;

[0023] For each story line, determine the story line plot ratio corresponding to the story line, wherein the story line plot ratio is the ratio of the number of plot points contained in the story line text corresponding to the story line to the number of plot points contained in the script text;

[0024] Determine the script structure story entropy corresponding to the script text according to the story line importance and the story line plot ratio corresponding to each story line;

[0025] The script text is dimensionally analyzed according to the script structure story entropy to obtain a dimension analysis result corresponding to the plot structure analysis dimension.

[0026] In a possible implementation, determining the script structure story entropy corresponding to the script text according to the story line importance and the story line plot ratio corresponding to each story line includes:

[0027] Divide every two story lines into a group of story line combinations, wherein the story line with a higher importance in the story line combination is the first story line, and the story line with a lower importance in the story line combination is the second story line;

[0028] For each story line combination, the story line plot ratio corresponding to the first story line and the story line plot ratio corresponding to the second story line are calculated according to a second formula to obtain a plot difference;

[0029] Among them, the second formula is:

[0030] Among them, r2 is the plot difference, p2 is the proportion of the story line corresponding to the first story line, and p3 is the proportion of the story line corresponding to the second story line;

[0031] Calculating the plot difference according to the third formula to obtain the combined structural story entropy corresponding to the story line combination;

[0032] Among them, the third formula is:

[0033] Among them, Stru entropy is the combined structural story entropy, is the experience value;

[0034] The combined structural story entropy corresponding to all story line combinations is determined as the script structural story entropy corresponding to the script text.

[0035] In a possible implementation, the script analysis dimension includes a plot theme analysis dimension, and the dimension analysis of the script text is performed according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension, including:

[0036] Determine the script theme corresponding to the script text;

[0037] Determine, from all the plot points included in the script text, the theme plot points that conform to the script theme and the non-theme plot points that do not conform to the script theme;

[0038] Determine the proportion of the theme plot corresponding to the theme plot node, wherein the theme plot proportion is the ratio of the number of the theme plot nodes to the number of plot nodes contained in the script text;

[0039] Determine the proportion of non-theme storylines corresponding to the non-theme plot nodes, wherein the proportion of non-theme storylines is the ratio of the number of non-theme plot nodes to the number of plot nodes contained in the script text;

[0040] Determining the theme story entropy corresponding to the script text according to the theme story plot ratio and the non-theme story plot ratio;

[0041] The script text is dimensionally analyzed according to the theme story entropy to obtain a dimension analysis result corresponding to the plot theme analysis dimension.

[0042] In a possible implementation, determining the theme story entropy corresponding to the script text according to the theme story plot ratio and the non-theme story plot ratio includes:

[0043] The proportion of the theme story plot is calculated according to the fourth formula to obtain the first story entropy, wherein the fourth formula is: The entropy1 is the first story entropy, p i The proportion of the main storyline;

[0044] The proportion of the non-theme story plot is calculated according to the fifth formula to obtain the second story entropy, where the fourth formula is: The entropy2 is the second story entropy, p j The proportion of non-thematic storylines;

[0045] Calculating the sum and average of the first story entropy and the second story entropy to obtain an average story entropy;

[0046] The first story entropy and the average story entropy are determined as the theme story entropy.

[0047] In a second aspect, the present application provides a script analysis device, comprising:

[0048] A text acquisition module is used to acquire the script text;

[0049] A dimension determination module, used to determine at least one script analysis dimension corresponding to the script text;

[0050] A dimension analysis module, for performing dimension analysis on the script text according to the analysis strategy corresponding to each script analysis dimension, and obtaining the dimension analysis result corresponding to the script analysis dimension;

[0051] The result determination module is used to determine the script analysis result corresponding to the script text according to the dimensional analysis results corresponding to all script analysis dimensions.

[0052] In a possible implementation, the script analysis dimension includes a plot rhythm analysis dimension, and the dimension analysis module is specifically used to:

[0053] Extracting episode texts of all episodes from the script text;

[0054] For each episode, determining the episode story entropy corresponding to the episode according to the episode text corresponding to the episode;

[0055] Draw a story entropy curve according to the episode story entropies of all the episodes;

[0056] The script text is dimensionally analyzed according to the story entropy curve to obtain a dimension analysis result corresponding to the plot rhythm analysis dimension.

[0057] In a possible implementation, the dimension analysis module is further used to:

[0058] Determine the number of story lines included in the script text as the number of story lines;

[0059] Determine the episode storyline ratio corresponding to the episode, wherein the episode storyline ratio is the ratio of the number of plot points contained in the episode text to the number of plot points contained in the script text;

[0060] Calculate the plot proportion of the episode according to the first formula to obtain the episode story entropy corresponding to the episode;

[0061] Among them, the first formula is:

[0062] in, is the story entropy of the kth episode, is the proportion of the episode storyline in the kth episode, and n is the number of story lines.

[0063] In a possible implementation, the script analysis dimension includes a plot structure analysis dimension, and the dimension analysis module is further used to:

[0064] Extracting at least two story lines from the script text and the story line text and story line importance corresponding to each of the story lines;

[0065] For each story line, determine the story line plot ratio corresponding to the story line, wherein the story line plot ratio is the ratio of the number of plot points contained in the story line text corresponding to the story line to the number of plot points contained in the script text;

[0066] Determine the script structure story entropy corresponding to the script text according to the story line importance and the story line plot ratio corresponding to each story line;

[0067] The script text is dimensionally analyzed according to the script structure story entropy to obtain a dimension analysis result corresponding to the plot structure analysis dimension.

[0068] In a possible implementation, the dimension analysis module is further used to:

[0069] Divide every two story lines into a group of story line combinations, wherein the story line with a higher importance in the story line combination is the first story line, and the story line with a lower importance in the story line combination is the second story line;

[0070] For each story line combination, the story line plot ratio corresponding to the first story line and the story line plot ratio corresponding to the second story line are calculated according to a second formula to obtain a plot difference;

[0071] Among them, the second formula is:

[0072] Among them, r2 is the plot difference, p2 is the proportion of the story line corresponding to the first story line, and p3 is the proportion of the story line corresponding to the second story line;

[0073] Calculating the plot difference according to the third formula to obtain the combined structural story entropy corresponding to the story line combination;

[0074] Among them, the third formula is:

[0075] Among them, Stru entropy is the combined structural story entropy, is the experience value;

[0076] The combined structural story entropy corresponding to all story line combinations is determined as the script structural story entropy corresponding to the script text.

[0077] In a possible implementation, the script analysis dimension includes a plot theme analysis dimension, and the dimension analysis module is further used to:

[0078] Determine the script theme corresponding to the script text;

[0079] Determine, from all the plot points included in the script text, the theme plot points that conform to the script theme and the non-theme plot points that do not conform to the script theme;

[0080] Determine the proportion of the theme plot corresponding to the theme plot node, wherein the theme plot proportion is the ratio of the number of the theme plot nodes to the number of plot nodes contained in the script text;

[0081] Determine the proportion of non-theme storylines corresponding to the non-theme plot nodes, wherein the proportion of non-theme storylines is the ratio of the number of non-theme plot nodes to the number of plot nodes contained in the script text;

[0082] Determining the theme story entropy corresponding to the script text according to the theme story plot ratio and the non-theme story plot ratio;

[0083] The script text is dimensionally analyzed according to the theme story entropy to obtain a dimension analysis result corresponding to the plot theme analysis dimension.

[0084] In a possible implementation, the dimension analysis module is further used to:

[0085] The proportion of the theme story plot is calculated according to the fourth formula to obtain the first story entropy, wherein the fourth formula is: The entropy1 is the first story entropy, p i The proportion of the main storyline;

[0086] The proportion of the non-theme story plot is calculated according to the fifth formula to obtain the second story entropy, where the fourth formula is: The entropy2 is the second story entropy, p j The proportion of non-thematic storylines;

[0087] Calculating the sum and average of the first story entropy and the second story entropy to obtain an average story entropy;

[0088] The first story entropy and the average story entropy are determined as the theme story entropy.

[0089] In a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0090] Memory, used to store computer programs;

[0091] The processor is used to implement any method step described in the first aspect when executing a program stored in the memory.

[0092] In a fourth aspect, a computer-readable storage medium is provided, characterized in that a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0093] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute any of the script analysis methods described above.

[0094] Beneficial effects of the embodiments of the present application:

[0095] The embodiments of the present application provide a script analysis method, device, electronic device, and storage medium. In the embodiments of the present application, first, a script text is obtained, and at least one script analysis dimension corresponding to the script text is determined. Then, for each script analysis dimension, the script text is dimensionally analyzed according to the analysis strategy corresponding to the script analysis dimension to obtain the dimensional analysis result corresponding to the script analysis dimension. Finally, the script analysis result corresponding to the script text is determined according to the dimensional analysis results corresponding to all script analysis dimensions. Through the present application, multi-dimensional intelligent analysis of the script text can be achieved according to the preset analysis strategies of each script analysis dimension.

[0096] Of course, implementing any product or method of the present application does not necessarily require achieving all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0098] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0099] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0100] Figure 1 A flowchart of a script analysis method provided in an embodiment of the present application;

[0101] Figure 2 A flowchart of another script analysis method provided in an embodiment of the present application;

[0102] Figure 3 A flowchart of another script analysis method provided in an embodiment of the present application;

[0103] Figure 4 A flowchart of another script analysis method provided in an embodiment of the present application;

[0104] Figure 5 A schematic diagram of the structure of a script analysis device provided in an embodiment of the present application;

[0105] Figure 6A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0106] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0107] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0108] Figure 1 A flowchart of a script analysis method provided for an embodiment of the present application. This method can be applied to one or more electronic devices such as smart phones, laptops, desktop computers, portable computers, servers, etc. In addition, the execution subject of this method can be hardware or software. When the above-mentioned execution subject is hardware, the execution subject can be one or more of the above-mentioned electronic devices. For example, a single electronic device can execute this method, or multiple electronic devices can cooperate with each other to execute this method. When the above-mentioned execution subject is software, this method can be implemented as multiple software or software modules, or it can be implemented as a single software or software module. No specific limitation is made here.

[0109] like Figure 1 As shown, the method specifically includes:

[0110] Step 101, obtain the script text.

[0111] Script text refers to text that describes a story or dramatic events in detail, such as movie scripts, TV drama scripts, etc.

[0112] In one embodiment, a complete script of a work (such as a movie, TV series, etc.) stored in the system or uploaded by a user can be used as the script text. In this way, the complete script can be analyzed as a whole later.

[0113] In another embodiment, a portion of the text of a work uploaded by a user or written by the user in real time can be used as the script text. In this way, the content written by the user can be analyzed in real time, thereby realizing analysis while creating, thereby assisting the user in better creation.

[0114] In actual applications, different screenwriters may use different ways to express scene headers, scene numbers, and other information. Some use line breaks or spaces, and some use different identification symbols, etc., and the format is relatively messy. Before the subsequent script analysis, the script format can be preprocessed. Specifically, regular matching can be used to identify the scene headers, scene numbers, dialogues, and character information of the script, remove special symbols that identify the scene headers and other information, and unify the scene header information, scene number, character dialogues, and other information of the script to express them in a unified structured manner for subsequent processing.

[0115] Step 102: Determine at least one script analysis dimension corresponding to the script text.

[0116] The script analysis dimension refers to the angle from which the script is analyzed, which helps to understand the structure, theme, characters, plot and other elements of the script. For example, the plot rhythm analysis dimension is used to analyze whether the plot rhythm is reasonable, the plot structure analysis dimension is used to analyze whether the plot structure is reasonable (that is, to analyze whether the main line and auxiliary line are clearly distinguished), and the plot theme analysis dimension is used to analyze whether the plot conforms to the theme.

[0117] In actual applications, multiple analysis dimensions and analysis strategies corresponding to each analysis dimension are pre-set in the system.

[0118] Based on this, in one embodiment, at least one analysis dimension selected by the user can be used as a script analysis dimension for subsequent analysis of the script text. In this way, the user can flexibly select the script analysis dimension according to actual needs.

[0119] In another embodiment, if the user does not select any analysis dimension within the specified time period, all analysis dimensions preset in the system can be used as script analysis dimensions. In this way, a comprehensive analysis of the script text can be achieved based on all analysis dimensions.

[0120] In addition, the script type corresponding to each analysis dimension can also be pre-set (for example, group portrait drama, female-dominated drama, male-dominated drama, etc.). Based on this, in another embodiment, the analysis dimension of the script type that conforms to the script text can be determined as the script analysis dimension, and subsequent script analysis is performed, so that the analysis result conforms to the script type of the script text.

[0121] For example, group portrait dramas generally need to be analyzed in the dimensions of plot rhythm analysis and plot theme analysis, while dramas with strong female and male protagonists generally need to be analyzed in the dimensions of plot rhythm analysis, plot theme analysis and plot structure analysis, and so on.

[0122] Step 103: for each script analysis dimension, perform dimension analysis on the script text according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension.

[0123] In one embodiment, the script text may be analyzed in dimension according to the analysis strategy corresponding to each script analysis dimension, thereby obtaining the dimension analysis result corresponding to each script analysis dimension. In this solution, the script text is analyzed by serial processing, which has low requirements on computer resources and is applicable to more scenarios.

[0124] In another embodiment, the script text may be dimensionally analyzed in parallel according to the analysis strategies corresponding to the various script analysis dimensions, thereby obtaining the dimension analysis results corresponding to each script analysis dimension. In this solution, the overall analysis time of the script text may be reduced by parallel processing, thereby improving processing efficiency.

[0125] Step 104: Determine the script analysis result corresponding to the script text based on the dimensional analysis results corresponding to all script analysis dimensions.

[0126] In one embodiment, the dimensional analysis results corresponding to all script analysis dimensions may be summarized to obtain multi-dimensional script analysis results corresponding to the script text.

[0127] In another embodiment, a cross-analysis may be performed based on the dimensional analysis results corresponding to each script analysis dimension to deeply explore the internal connections and complex structures of the script, thereby obtaining a script analysis result corresponding to the script text.

[0128] For example, the dimensions of script analysis include: Theme: identifying the core idea; Character: analyzing character motivation and development; Plot: sorting out the story structure; Dialogue: analyzing language style and subtext; Scene: analyzing environmental description; Conflict: identifying the main conflict and its role.

[0129] The following cross-analysis can be conducted: 1. Through themes and characters, analyze how characters reflect themes; 2. Through plots and conflicts, analyze how conflicts drive plots; 3. Through dialogues and characters, analyze how dialogues reveal personality; 4. Through scenes and themes, analyze how scenes set off themes; 5. Through themes and plots, analyze how plots express themes; 6. Through characters and conflicts, analyze how characters perform in conflicts; 7. Through dialogues and scenes, analyze how dialogues reflect the atmosphere of scenes. This approach can reveal the interactions between dimensions and fully understand the complex structure of the script.

[0130] In an embodiment of the present application, first, a script text is obtained, and at least one script analysis dimension corresponding to the script text is determined. Then, for each script analysis dimension, the script text is dimensionally analyzed according to the analysis strategy corresponding to the script analysis dimension to obtain the dimensional analysis result corresponding to the script analysis dimension. Finally, according to the dimensional analysis results corresponding to all script analysis dimensions, the script analysis result corresponding to the script text is determined. Through this application, multi-dimensional intelligent analysis of the script text can be achieved according to the preset analysis strategies of each script analysis dimension.

[0131] See also Figure 2 , is a flowchart of another script analysis method provided in the embodiment of the present application. Figure 2 The process shown in the above Figure 1 Based on the process shown in the figure, when the script analysis dimension is the plot rhythm analysis dimension, how to perform dimension analysis on the script text according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension. Figure 2 As shown, the process may include the following steps:

[0132] Step 201: extract the episode texts of all episodes from the script text.

[0133] The above-mentioned episode texts include all the texts in the corresponding episodes.

[0134] In practical applications, the script generally includes an identifier for determining the episode (such as "Episode X", "Episode X", etc.). Based on this, in the embodiment of the present application, the script text can be segmented by the identifier of the episode to obtain the episode text of each episode.

[0135] Step 202: For each episode, determine the episode story entropy corresponding to the episode according to the episode text corresponding to the episode.

[0136] Step 203: Draw a story entropy curve according to the episode story entropies of all the episodes.

[0137] Step 204: Perform dimensional analysis on the script text according to the story entropy curve to obtain a dimensional analysis result corresponding to the plot rhythm analysis dimension.

[0138] For ease of understanding, steps 202 to 204 are described in a unified manner as follows:

[0139] In the embodiment of the present application, the rhythm problems, tension and relaxation problems, information redundancy problems and abrupt turning problems that may exist in the plot can be identified according to the story entropy curve. Specifically, the fluctuation amplitude of the story entropy curve reflects the tension and rhythm changes of the plot. A larger fluctuation amplitude usually means that the plot is more ups and downs, and vice versa. The trend of the story entropy curve reflects the speed of the story rhythm. The rapidly rising curve indicates that the plot rhythm is accelerated, and the rapidly falling curve indicates that the rhythm is slowed down. The average value of the story entropy curve reflects the overall information content and complexity of the story. A higher average value usually means that the story is more complex and has more information; while a story entropy that is too low generally means that the plot is bland and lacks surprises.

[0140] Specifically, step 202 may include the following steps:

[0141] Step A1, determining the number of story lines contained in the script text as the number of story lines;

[0142] Step A2, determining the episode plot ratio corresponding to the episode, wherein the episode plot ratio is the ratio of the number of plot points contained in the episode text to the number of plot points contained in the script text;

[0143] Step A3, calculating the plot ratio of the episode according to the first formula to obtain the episode story entropy corresponding to the episode;

[0144] Among them, the first formula is: in, is the story entropy of the kth episode, is the proportion of the episode storyline in the kth episode, and n is the number of story lines.

[0145] The above storyline refers to the main line or thread of events in a narrative work, which runs through the entire story, promotes the development of the plot and connects various events. It is the core framework of the story and determines the direction and ending of the plot.

[0146] In the application, the large language model technology can be used to extract and analyze the main story lines in the script. In a specific example, the story lines can be extracted based on the relationships and goals of the characters (such as finding new clues, eliminating the other party's misunderstandings, etc.). If the relationships and goals of the characters are the same, it can be understood that different plot points form a coherent plot. By connecting these plot points with coherent plots in series, different story lines are formed. For example: the protagonist's growth line, love line, revenge line, etc. In another example, the story line can also be identified by analyzing the interactions and conflicts between the characters, and the impact of each plot point on different characters.

[0147] Among them, plot points refer to key information nodes such as scenes, characters, events, etc. in the script content, that is, the points where scenes change, characters transform, and events escalate.

[0148] In the application, the big model technology can be used to first extract the global structure of the script text and the main story line and main characters, etc., recorded as ɡ-Info. Then, plot points are extracted based on event changes, character emotional changes, etc. Among them, the process of extracting plot points based on event changes is: input the script content and ɡ-Info information to the big model, and the big model identifies the points of scene changes, character changes, and event escalation, that is, identifies the key events in the scene that cause major plot changes or change the fate of the characters, and marks them as plot points. For example, the death of a character, the establishment or breakdown of an important relationship, the change of the main goal, etc. The process of extracting plot points based on character emotional changes is: input the script content and ɡ-Info information to the big model, and the big model identifies the points of emotional changes of the main characters, that is, identifies the events in the scene that cause major changes in the characters' emotions, and marks them as plot points. For example: sudden joy, sadness, anger, fear, etc.

[0149] In addition, the large language model technology can be used to evaluate the dramatic function of plot points and confirm their importance and influence. Input the plot point content and ɡ-Info information into the large model, filter and merge the content of the plot points: remove redundant or unimportant plot points, and merge similar plot points. Among them, redundant plot points are mainly transitional scenes, such as empty scenes, and similar plot points are mainly similar in dramatic function content of plot points, that is, delete plot points that are too short, too fragmented, and have no actual plot content.

[0150] From the above description, it can be seen that in this solution, the proportion of episode storylines can be calculated according to the story entropy formula to obtain the corresponding episode story entropy.

[0151] pass Figure 2The process shown can analyze the script text from the dimension of plot rhythm analysis, that is, identify possible rhythm problems, tension problems, information redundancy problems, and abrupt transition problems in the plot based on the story entropy curve, thereby assisting the author to modify the script, or assisting the platform to efficiently screen high-quality scripts.

[0152] See also Figure 3 , is a flowchart of another script analysis method provided in the embodiment of the present application. Figure 3 The process shown in the above Figure 1 Based on the process shown in the figure, when the script analysis dimension is the plot structure analysis dimension, how to perform dimension analysis on the script text according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension. Figure 3 As shown, the process may include the following steps:

[0153] Step 301: extract at least two story lines from the script text and the story line text and story line importance corresponding to each story line.

[0154] Step 302: for each story line, determine the story line plot ratio corresponding to the story line, wherein the story line plot ratio is the ratio of the number of plot points contained in the story line text corresponding to the story line to the number of plot points contained in the script text.

[0155] Step 303: Determine the script structure story entropy corresponding to the script text according to the story line importance and story line plot ratio corresponding to each story line.

[0156] Step 304: Perform dimensional analysis on the script text according to the script structure story entropy to obtain dimensional analysis results corresponding to the plot structure analysis dimensions.

[0157] For ease of understanding, steps 301 to 304 are described in a unified manner as follows:

[0158] In an embodiment of the present application, first, the big model technology is used to extract the story lines in the script and the importance of each story line in the script. For example, the extraction result includes 3 story lines, among which the first is the most core story line, that is, the story line with the highest importance; the second is the auxiliary story line, that is, the story line with lower importance; the third is the secondary auxiliary story line, that is, the story line with the lowest importance.

[0159] Then, according to the importance of each story line and the proportion of the story line, the script structure entropy is determined, and the script text is analyzed in the dimension of plot structure analysis based on the script structure entropy. Among them, the larger the value of the structural story entropy, the more chaotic and scattered the plot is, and the more the branch plot occupies the plot. In the script evaluation, the structural story entropy of each track should be reasonably distributed within a range, generally less than 1. If the structural story entropy is relatively large, such as greater than 1, the probability that the main line and branch line structure of the story line have problems increases.

[0160] Specifically, step 303 may include the following steps:

[0161] Step B1, dividing every two story lines into a group of story line combinations, wherein the story line with a higher importance in the story line combination is the first story line, and the story line with a lower importance in the story line combination is the second story line;

[0162] Step B2: for each story line combination, the story line plot ratio corresponding to the first story line and the story line plot ratio corresponding to the second story line are calculated according to a second formula to obtain a plot difference;

[0163] Among them, the second formula is:

[0164] Among them, r2 is the plot difference, p2 is the proportion of the story line corresponding to the first story line, and p3 is the proportion of the story line corresponding to the second story line;

[0165] Step B3, calculating the plot difference according to the third formula to obtain the combined structural story entropy corresponding to the story line combination;

[0166] Among them, the third formula is: Among them, Stru entropy is the combined structural story entropy, is the experience value;

[0167] Step B4: Determine the combined structural story entropy corresponding to all story line combinations as the script structural story entropy corresponding to the script text.

[0168] Suppose that three story lines are extracted from the script text, the first is the core story line, the second is the story line, and the third is the secondary story line. In other words, from the perspective of the plot, the importance of the story is line 1, story line 2, and story line 3. In actual scripts, the shaping of the plot is also mainly carried out around these three lines. If the secondary plot occupies a larger amount of text space, this is unreasonable. For this reason, we propose the concept of structural story entropy to conduct script analysis.

[0169] Suppose that the plot difference between story line 3 and story line 2 is If r2>0, that is, the probability that the plot proportion of the least important story line 3 is greater than that of the more important story line 2, this means that the two auxiliary lines of the script are confused in terms of priority. The larger r2 is, the more water-filled the plot of branch line 3 is, and the more scattered and messy the story is.

[0170] The structural story entropy of the script in, The general value is 1.5, which is an empirical value. This hyperparameter is mainly used to normalize the value of structural story entropy within a reasonable range, such as [1.0, 2.0]. The larger the value of structural story entropy, the more chaotic and scattered the plot is, and the more side plots occupy the plot.

[0171] From the above description, it can be seen that in this solution, the plot difference corresponding to each group of story line combinations can be calculated according to the story entropy formula to obtain the corresponding structural story entropy.

[0172] pass Figure 3 The process shown can analyze the script text from the dimension of plot structure analysis to determine whether the plot is confusing and scattered, thereby assisting the author to modify the script, or assisting the platform to efficiently screen high-quality scripts.

[0173] See also Figure 4 , is a flowchart of another script analysis method provided in the embodiment of the present application. Figure 4 The process shown in the above Figure 1 Based on the process shown in the figure, when the script analysis dimension is the plot theme analysis dimension, how to perform dimension analysis on the script text according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension. Figure 4 As shown, the process may include the following steps:

[0174] Step 401: determine the script theme corresponding to the script text.

[0175] The theme of a script refers to the core idea or main idea that the script wants to express. It runs through the entire story and is reflected through elements such as plot, characters, and dialogue. It is the soul of the script and determines the direction and depth of the story.

[0176] In the embodiment of the present application, the big model technology can be used to analyze the script text to obtain the script theme.

[0177] Step 402: Determine, from all the plot nodes contained in the script text, the theme plot nodes that conform to the script theme and the non-theme plot nodes that do not conform to the script theme.

[0178] In an embodiment of the present application, the big model technology can be used to identify the theme plot nodes that match the theme of the script among all the plot nodes according to the theme of the script, and then determine the other plot nodes except the theme plot nodes as non-theme plot nodes.

[0179] Step 403: determine the proportion of the theme storyline corresponding to the theme plot node, wherein the theme storyline proportion is the ratio of the number of the theme plot nodes to the number of plot nodes contained in the script text.

[0180] Step 404: determine the proportion of non-theme storylines corresponding to the non-theme plot nodes, wherein the non-theme storyline proportion is the ratio of the number of the non-theme plot nodes to the number of plot nodes contained in the script text.

[0181] Step 405: Determine the theme story entropy corresponding to the script text according to the theme story plot ratio and the non-theme story plot ratio.

[0182] Step 406: Perform dimensional analysis on the script text according to the theme story entropy to obtain dimensional analysis results corresponding to the plot theme analysis dimension.

[0183] For ease of understanding, steps 403 to 406 are described in a unified manner as follows:

[0184] From the above description, it can be seen that in the embodiment of the present application, the theme story entropy corresponding to the script text is calculated based on the proportion of the theme story plot and the proportion of the non-theme story plot, and the script text is analyzed in the dimension of plot theme analysis based on the theme story entropy to obtain the corresponding dimensional analysis result.

[0185] Specifically, step 405 may include the following steps:

[0186] The proportion of the theme story plot is calculated according to the fourth formula to obtain the first story entropy, wherein the fourth formula is: The entropy1 is the first story entropy, p i The proportion of the main storyline;

[0187] The proportion of the non-theme story plot is calculated according to the fifth formula to obtain the second story entropy, where the fourth formula is: The entropy2 is the second story entropy, p j The proportion of non-thematic storylines;

[0188] Calculating the sum and average of the first story entropy and the second story entropy to obtain an average story entropy;

[0189] The first story entropy and the average story entropy are determined as the theme story entropy.

[0190] In the application, the larger the values ​​of the first story entropy and the average story entropy are, the closer the overall plot of the script is to the theme of the script.

[0191] From the above description, it can be seen that in this solution, the proportion of the theme story and the proportion of the non-theme story can be calculated according to the story entropy formula to obtain the corresponding theme story entropy.

[0192] pass Figure 4 The process shown can analyze the script text from the dimension of plot theme analysis to determine whether the plot is in line with the script theme, thereby assisting the author to modify the script, or assisting the platform to efficiently screen high-quality scripts.

[0193] Through the above scheme, this application can assist screenwriters in accurately locating the parts that need to be modified through the analysis of the story entropy curve and various story entropy indicators, and make targeted optimizations, such as adjusting the setting of plot points, strengthening the conflict between characters, and increasing the tension of the story.

[0194] In addition, the story entropy index can be used to quickly screen out scripts with good rhythm, reasonable structure, and rich information, thereby improving the efficiency of script screening. Moreover, by objectively evaluating the script, it can help decision makers to judge the value of the script more rationally, avoid the interference of subjective factors, and accurately identify potential risks, such as the lack of logical coherence of the plot, the lack of three-dimensional character creation, and the lack of appeal of the story, thereby reducing investment risks.

[0195] Based on the same technical concept, the present application embodiment also provides a script analysis device, such as Figure 5 As shown, the device comprises:

[0196] A text acquisition module 51 is used to acquire the script text;

[0197] A dimension determination module 52, used to determine at least one script analysis dimension corresponding to the script text;

[0198] A dimension analysis module 53 is used to perform dimension analysis on the script text according to the analysis strategy corresponding to each script analysis dimension, and obtain the dimension analysis result corresponding to the script analysis dimension;

[0199] The result determination module 54 is used to determine the script analysis result corresponding to the script text according to the dimension analysis results corresponding to all the script analysis dimensions.

[0200] In a possible implementation, the script analysis dimension includes a plot rhythm analysis dimension, and the dimension analysis module is specifically used to:

[0201] Extracting episode texts of all episodes from the script text;

[0202] For each episode, determining the episode story entropy corresponding to the episode according to the episode text corresponding to the episode;

[0203] Draw a story entropy curve according to the episode story entropies of all the episodes;

[0204] The script text is dimensionally analyzed according to the story entropy curve to obtain a dimension analysis result corresponding to the plot rhythm analysis dimension.

[0205] In a possible implementation, the dimension analysis module is further used to:

[0206] Determine the number of story lines included in the script text as the number of story lines;

[0207] Determine the episode storyline ratio corresponding to the episode, wherein the episode storyline ratio is the ratio of the number of plot points contained in the episode text to the number of plot points contained in the script text;

[0208] Calculate the plot proportion of the episode according to the first formula to obtain the episode story entropy corresponding to the episode;

[0209] Among them, the first formula is:

[0210] in, is the story entropy of the kth episode, is the proportion of the episode storyline in the kth episode, and n is the number of story lines.

[0211] In a possible implementation, the script analysis dimension includes a plot structure analysis dimension, and the dimension analysis module is further used to:

[0212] Extracting at least two story lines from the script text and the story line text and story line importance corresponding to each of the story lines;

[0213] For each story line, determine the story line plot ratio corresponding to the story line, wherein the story line plot ratio is the ratio of the number of plot points contained in the story line text corresponding to the story line to the number of plot points contained in the script text;

[0214] Determine the script structure story entropy corresponding to the script text according to the story line importance and the story line plot ratio corresponding to each story line;

[0215] The script text is dimensionally analyzed according to the script structure story entropy to obtain a dimension analysis result corresponding to the plot structure analysis dimension.

[0216] In a possible implementation, the dimension analysis module is further used to:

[0217] Divide every two story lines into a group of story line combinations, wherein the story line with a higher importance in the story line combination is the first story line, and the story line with a lower importance in the story line combination is the second story line;

[0218] For each story line combination, the story line plot ratio corresponding to the first story line and the story line plot ratio corresponding to the second story line are calculated according to a second formula to obtain a plot difference;

[0219] Among them, the second formula is:

[0220] Among them, r2 is the plot difference, p2 is the proportion of the story line corresponding to the first story line, and p3 is the proportion of the story line corresponding to the second story line;

[0221] Calculating the plot difference according to the third formula to obtain the combined structural story entropy corresponding to the story line combination;

[0222] Among them, the third formula is:

[0223] Among them, Stru entropy is the combined structural story entropy, is the experience value;

[0224] The combined structural story entropy corresponding to all story line combinations is determined as the script structural story entropy corresponding to the script text.

[0225] In a possible implementation, the script analysis dimension includes a plot theme analysis dimension, and the dimension analysis module is further used to:

[0226] Determine the script theme corresponding to the script text;

[0227] Determine, from all the plot points included in the script text, the theme plot points that conform to the script theme and the non-theme plot points that do not conform to the script theme;

[0228] Determine the proportion of the theme plot corresponding to the theme plot node, wherein the theme plot proportion is the ratio of the number of the theme plot nodes to the number of plot nodes contained in the script text;

[0229] Determine the proportion of non-theme storylines corresponding to the non-theme plot nodes, wherein the proportion of non-theme storylines is the ratio of the number of non-theme plot nodes to the number of plot nodes contained in the script text;

[0230] Determining the theme story entropy corresponding to the script text according to the theme story plot ratio and the non-theme story plot ratio;

[0231] The script text is dimensionally analyzed according to the theme story entropy to obtain a dimension analysis result corresponding to the plot theme analysis dimension.

[0232] In a possible implementation, the dimension analysis module is further used to:

[0233] The proportion of the theme story plot is calculated according to the fourth formula to obtain the first story entropy, wherein the fourth formula is: The entropy1 is the first story entropy, p i The proportion of the main storyline;

[0234] The proportion of the non-theme story plot is calculated according to the fifth formula to obtain the second story entropy, where the fourth formula is: The entropy2 is the second story entropy, p j The proportion of non-thematic storylines;

[0235] Calculating the sum and average of the first story entropy and the second story entropy to obtain an average story entropy;

[0236] The first story entropy and the average story entropy are determined as the theme story entropy.

[0237] In an embodiment of the present application, first, a script text is obtained, and at least one script analysis dimension corresponding to the script text is determined. Then, for each script analysis dimension, the script text is dimensionally analyzed according to the analysis strategy corresponding to the script analysis dimension to obtain the dimensional analysis result corresponding to the script analysis dimension. Finally, according to the dimensional analysis results corresponding to all script analysis dimensions, the script analysis result corresponding to the script text is determined. Through this application, multi-dimensional intelligent analysis of the script text can be achieved according to the preset analysis strategies of each script analysis dimension.

[0238] Based on the same technical concept, the embodiment of the present application also provides an electronic device, such as Figure 6 As shown, it includes a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0239] Memory 113, used for storing computer programs;

[0240] The processor 111 is used to execute the program stored in the memory 113 to implement the following steps:

[0241] Get the script text;

[0242] Determining at least one script analysis dimension corresponding to the script text;

[0243] For each script analysis dimension, perform dimension analysis on the script text according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension;

[0244] According to the dimensional analysis results corresponding to all the script analysis dimensions, the script analysis results corresponding to the script text are determined.

[0245] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0246] The communication interface is used for communication between the above electronic device and other devices.

[0247] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0248] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0249] In another embodiment provided in the present application, a computer-readable storage medium is also provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned script analysis methods are implemented.

[0250] In another embodiment provided in the present application, a computer program product comprising instructions is also provided, which, when executed on a computer, enables the computer to execute any script analysis method in the above embodiments.

[0251] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0252] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0253] It should be understood that the terms used in the text are only for the purpose of describing specific example embodiments, and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used in the text may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0254] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A script analysis method, characterized in that: The method comprises: Get the script text; Determining at least one script analysis dimension corresponding to the script text; For each script analysis dimension, perform dimension analysis on the script text according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension; According to the dimensional analysis results corresponding to all the script analysis dimensions, the script analysis results corresponding to the script text are determined.

2. The method according to claim 1, characterized in that The script analysis dimension includes a plot rhythm analysis dimension, and the dimension analysis of the script text is performed according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension, including: Extracting episode texts of all episodes from the script text; For each episode, determining the episode story entropy corresponding to the episode according to the episode text corresponding to the episode; Draw a story entropy curve according to the episode story entropies of all the episodes; The script text is dimensionally analyzed according to the story entropy curve to obtain a dimension analysis result corresponding to the plot rhythm analysis dimension.

3. The method according to claim 2, characterized in that The determining the episode story entropy corresponding to the episode according to the episode text corresponding to the episode includes: Determine the number of story lines included in the script text as the number of story lines; Determine the episode storyline ratio corresponding to the episode, wherein the episode storyline ratio is the ratio of the number of plot points contained in the episode text to the number of plot points contained in the script text; Calculate the plot proportion of the episode according to the first formula to obtain the episode story entropy corresponding to the episode; Among them, the first formula is: in, is the story entropy of the kth episode, is the proportion of the episode storyline in the kth episode, and n is the number of story lines.

4. The method according to claim 1, characterized in that The script analysis dimension includes a plot structure analysis dimension, and the dimension analysis of the script text is performed according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension, including: Extracting at least two story lines from the script text and the story line text and story line importance corresponding to each of the story lines; For each story line, determine the story line plot ratio corresponding to the story line, wherein the story line plot ratio is the ratio of the number of plot points contained in the story line text corresponding to the story line to the number of plot points contained in the script text; Determine the script structure story entropy corresponding to the script text according to the story line importance and the story line plot ratio corresponding to each story line; The script text is dimensionally analyzed according to the script structure story entropy to obtain a dimension analysis result corresponding to the plot structure analysis dimension.

5. The method according to claim 4, characterized in that Determining the script structure story entropy corresponding to the script text according to the story line importance and the story line plot proportion corresponding to each story line includes: Divide every two story lines into a group of story line combinations, wherein the story line with a higher importance in the story line combination is the first story line, and the story line with a lower importance in the story line combination is the second story line; For each story line combination, the story line plot ratio corresponding to the first story line and the story line plot ratio corresponding to the second story line are calculated according to a second formula to obtain a plot difference; Among them, the second formula is: Among them, r2 is the plot difference, p2 is the proportion of the story line corresponding to the first story line, and p3 is the proportion of the story line corresponding to the second story line; Calculating the plot difference according to the third formula to obtain the combined structural story entropy corresponding to the story line combination; Among them, the third formula is: Among them, Stru entropy is the combined structural story entropy, is the experience value; The combined structural story entropy corresponding to all story line combinations is determined as the script structural story entropy corresponding to the script text.

6. The method according to claim 1, characterized in that The script analysis dimension includes a plot theme analysis dimension, and the dimension analysis of the script text is performed according to the analysis strategy corresponding to the script analysis dimension to obtain the dimension analysis result corresponding to the script analysis dimension, including: Determine the script theme corresponding to the script text; Determine, from all the plot points included in the script text, the theme plot points that conform to the script theme and the non-theme plot points that do not conform to the script theme; Determine the proportion of the theme plot corresponding to the theme plot node, wherein the theme plot proportion is the ratio of the number of the theme plot nodes to the number of plot nodes contained in the script text; Determine the proportion of non-theme storylines corresponding to the non-theme plot nodes, wherein the proportion of non-theme storylines is the ratio of the number of non-theme plot nodes to the number of plot nodes contained in the script text; Determining the theme story entropy corresponding to the script text according to the theme story plot ratio and the non-theme story plot ratio; The script text is dimensionally analyzed according to the theme story entropy to obtain a dimension analysis result corresponding to the plot theme analysis dimension.

7. The method according to claim 6, characterized in that Determining the theme story entropy corresponding to the script text according to the theme story plot ratio and the non-theme story plot ratio includes: The proportion of the theme story plot is calculated according to the fourth formula to obtain the first story entropy, wherein the fourth formula is: The entropy1 is the first story entropy, p i The proportion of the main storyline; The proportion of the non-theme story plot is calculated according to the fifth formula to obtain the second story entropy, where the fourth formula is: The entropy2 is the second story entropy, p j The proportion of non-thematic storylines; Calculating the sum and average of the first story entropy and the second story entropy to obtain an average story entropy; The first story entropy and the average story entropy are determined as the theme story entropy.

8. A script analysis device, characterized in that: The device comprises: A text acquisition module is used to acquire the script text; A dimension determination module, used to determine at least one script analysis dimension corresponding to the script text; A dimension analysis module, for performing dimension analysis on the script text according to the analysis strategy corresponding to each script analysis dimension, and obtaining the dimension analysis result corresponding to the script analysis dimension; The result determination module is used to determine the script analysis result corresponding to the script text according to the dimensional analysis results corresponding to all script analysis dimensions.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the script analysis method described in any one of claims 1-7 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the script analysis method according to any one of claims 1 to 7 is implemented.

Images