Actor trial play evaluation method and device, electronic equipment and storage medium

By obtaining the test script, selecting the best test clips and evaluating the test video, using the large language model and scoring model, the problem of actors and roles in the film and television industry is solved, and the objective evaluation and performance effect of actor selection is achieved. Improvement.

CN118964953APending Publication Date: 2024-11-15BEIJING IQIYI TECH CO LTD

Patent Information

Application Number
CN202411213064.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The actor selection process in the film and television industry relies on the subjective conjectures of casting personnel, resulting in the incompatibility of actors and roles, affecting the performance effect and user experience.

Method used

By obtaining the test script, selecting the best test clips corresponding to the target character, obtaining the test video of the test actor, determining the test score based on the video, and determining the actor-character adaptability based on the score, using a large language model and pre-order The trained emotional, physical, facial expressions, and line scoring models were quantitatively evaluated.

Benefits of technology

It realizes an objective and accurate assessment of actors' auditions, helps casting personnel to select suitable actors, avoids the problem of actors and roles inappropriate due to subjective conjectures, and improves performance effect and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118964953A_ABST
    Figure CN118964953A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides an actor trial play evaluation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a trial play book; selecting an optimal trial play segment corresponding to a target role deduced by a trial play actor from the trial play book; obtaining a trial play video performed by the trial play actor according to the optimal trial play segment; determining a trial play score of the trial play actor based on the trial play video; and determining the adaptation degree of the trial play actor and the target role according to the trial play score. According to the technical scheme, the performance and expressive force of the trial play actor can be quantified through the trial play score determined by the trial play video, and the adaptation degree of the trial play actor and the target role can be evaluated more accurately and objectively, so that angle selection personnel are helped to accurately select proper actors; the problem that the actor and the role are not matched due to personal subjective assume of the corner selection personnel, and the performance effect is affected is effectively avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer data processing technology, and in particular to an actor audition evaluation method, device, electronic device and storage medium. Background Art

[0002] Currently, the film and television industry relies on the personal experience of directors and producers to select actors for TV series or movie roles. In the process of selecting actors, they only rely on the subjective conjecture of casting staff to evaluate the actors' audition process. This may cause problems such as the selected actors not being compatible with the roles, affecting the performance and greatly reducing the user's viewing experience. Summary of the invention

[0003] In view of this, in order to effectively avoid the problem of actors not being compatible with roles due to subjective and arbitrary evaluation of actors' auditions by casting personnel, an embodiment of the present invention provides an actor audition evaluation method, device, electronic device and storage medium.

[0004] In a first aspect, an embodiment of the present invention provides an actor audition evaluation method, the method comprising:

[0005] Get the pilot script;

[0006] Select the best audition clips corresponding to the target roles performed by the audition actors from the audition scripts;

[0007] Get audition videos of the audition actors performing based on the best audition clips;

[0008] Determine the audition score of the audition actor based on the audition video;

[0009] The suitability of the audition actor for the target role is determined based on the audition score.

[0010] In one possible implementation, selecting the best audition segment corresponding to the target role performed by the audition actor from the audition script includes:

[0011] Inputting the trial play script and the first prompt text into the large language model, the large language model outputting the character portraits of the characters included in the trial play script based on the first prompt text; wherein the first prompt text includes character portrait analysis content;

[0012] The second prompt text is input into the large language model, and the large language model outputs multiple audition clips of the target role; wherein the second prompt text includes the role name and role portrait corresponding to the target role;

[0013] The third prompt text is input into the large language model, and the large language model selects and outputs the best audition clip corresponding to the target role from multiple audition clips; wherein the third prompt text includes scene time constraint conditions.

[0014] In one possible implementation, determining an audition score of an audition actor based on an audition video includes:

[0015] Determine the emotional expression score, body language score, facial expression score and dialogue expression score of the audition actor based on the audition video;

[0016] The emotional expression score, body language score, facial expression score and dialogue expression score are linearly weighted and summed using preset weight coefficients to obtain the audition score of the audition actor.

[0017] In one possible implementation, determining the emotional expression score, body language score, facial expression score, and line expression score of the audition actor based on the audition video includes:

[0018] Transcribe the audio from the audition video into audio text;

[0019] Extract language features and non-language features from audio texts and audition videos; non-language features include facial expression features and body language features;

[0020] Inputting the language features and non-language features into a pre-trained first emotion expression model, and the first emotion expression model outputs the first emotion expression of the audition actor;

[0021] The audio text is input into a pre-trained second emotion expression model, and the second emotion expression model outputs the second emotion expression of the audition actor;

[0022] determining an emotional expression score of the audition actor based on the first emotional expression and the second emotional expression;

[0023] The body language features are input into a pre-trained body language scoring model, and the body language scoring model outputs the body language score of the audition actor;

[0024] The facial expression features are input into a pre-trained facial expression scoring model, and the facial expression scoring model outputs the facial expression score of the audition actor;

[0025] The language features are input into a pre-trained dialogue scoring model, and the dialogue scoring model outputs the dialogue expression score of the audition actor.

[0026] In a possible implementation, the first emotion expression includes a first emotion color and a first emotion intensity score, and the second emotion expression includes a second emotion color and a second emotion intensity score;

[0027] determining an emotional expression score of the audition actor based on the first emotional expression and the second emotional expression;

[0028] Determine whether the first emotional color is consistent with the second emotional color;

[0029] When the first emotional color is consistent with the second emotional color, the first emotional intensity score and the second emotional intensity score are linearly weighted summed by using a preset emotional intensity weight coefficient to obtain the emotional expression score of the audition actor;

[0030] In the case that the first emotional color is inconsistent with the second emotional color, the preset score is determined as the emotional expression score of the audition actor.

[0031] In a possible implementation, determining the suitability of the audition actor and the target role according to the audition score includes:

[0032] Get the casting staff's evaluation scores of the auditioning actors;

[0033] The review scores and audition scores are linearly weighted and summed using the preset score weight coefficients to obtain a comprehensive score.

[0034] Determine the suitability of the audition actor for the target role based on the comprehensive score.

[0035] In one possible implementation, determining the suitability of the audition actor and the target role based on the comprehensive score includes:

[0036] Querying an adaptation score range that matches the comprehensive score from the adaptation grade table; wherein the adaptation grade table stores a correspondence between the adaptation grade and the adaptation score range;

[0037] The fitness level corresponding to the fitness score range is determined as the fitness of the audition actor and the target role.

[0038] In a second aspect, an embodiment of the present invention provides an actor audition evaluation device, the device comprising:

[0039] The first acquisition module is used to acquire the trial play script;

[0040] A selection module is used to select the best audition clip corresponding to the target role performed by the audition actor from the audition script;

[0041] The second acquisition module is used to acquire the audition video of the audition actor performing according to the best audition clip;

[0042] A first determination module is used to determine the audition score of the audition actor based on the audition video;

[0043] The second determination module is used to determine the compatibility between the audition actor and the target role based on the audition score.

[0044] In a third aspect, an embodiment of the present invention provides an electronic device, which includes: a processor and a memory, the processor is used to execute the program for actor audition evaluation stored in the memory to implement the above-mentioned actor audition evaluation method.

[0045] In a fourth aspect, an embodiment of the present invention provides a storage medium, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned actor audition evaluation method.

[0046] The actor audition evaluation method, device, electronic device and storage medium provided by the embodiments of the present invention include obtaining an audition script; selecting the best audition clip corresponding to the target role performed by the audition actor from the audition script; obtaining an audition video of the audition actor performing according to the best audition clip; determining the audition score of the audition actor based on the audition video; and determining the compatibility between the audition actor and the target role based on the audition score. The above technical scheme can quantify the acting skills and expressiveness of the audition actor through the audition score determined by the audition video, and can more accurately and objectively evaluate the compatibility between the audition actor and the target role, thereby helping casting personnel to accurately select suitable actors, effectively avoiding the problem of actor-role mismatch caused by the personal subjective assumptions of casting personnel, and affecting the performance effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A flowchart of an embodiment of an actor audition evaluation method provided by an embodiment of the present invention;

[0048] Figure 2 A flowchart of another embodiment of an actor audition evaluation method provided by an embodiment of the present invention;

[0049] Figure 3 A block diagram of an embodiment of an actor audition evaluation device provided by an embodiment of the present invention;

[0050] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] To facilitate understanding of the embodiments of the present invention, specific embodiments will be further explained below in conjunction with the accompanying drawings. The embodiments do not constitute a limitation on the embodiments of the present invention.

[0053] The embodiment of the present invention provides an actor audition evaluation method, see Figure 1 , Figure 1 A flowchart of an embodiment of an actor audition evaluation method provided in an embodiment of the present invention. Figure 1 The process shown may include the following steps:

[0054] Step 101, obtaining a trial play script;

[0055] Among them, the trial script is a literary text that needs to select actors for a TV series or movie.

[0056] Step 102, selecting the best audition segment corresponding to the target role performed by the audition actor from the audition script;

[0057] The best audition clip is a clip that can show the expressiveness of the audition actor, among which clips with high emotional intensity in the audition script, clips of dialogues and actions that reflect the personality and emotions of the target role, clips of specific scenes including conflicts, climaxes, and turning points, or clips that reflect the multi-faceted nature of the target role can be regarded as clips that can show the expressiveness of the audition actor. The audition actor can fully demonstrate his acting skills by performing the above-mentioned best audition clips, so as to select the audition actor who matches the target role.

[0058] Step 103, obtaining an audition video of the audition actor performing according to the best audition clip;

[0059] Among them, the audition video can fully record the audition actor's performance of the best audition clip, including facial expressions, lines and body language.

[0060] Step 104, determining an audition score of the audition actor based on the audition video;

[0061] The above audition score is used to evaluate the acting skills and expressiveness of the audition actor. It can be understood that the higher the audition score, the better the acting skills and expressiveness of the audition actor, and vice versa. In this embodiment, by quantifying the acting skills and expressiveness of the audition actor, it effectively assists the casting staff to objectively evaluate the acting skills and expressiveness of the audition actor, rather than just objectively evaluating the audition actor based on the self-preference of the casting staff, and screening out the audition actor who is closer to the target role.

[0062] Step 105, determining the compatibility between the audition actor and the target role based on the audition score.

[0063] The degree of suitability can quantitatively represent the degree of suitability between the audition actor and the target role. The higher the degree of suitability, the closer the audition actor is to the target role. The performance of the target role by an audition actor with a high degree of suitability can make the performance better recognized by the public, thereby enhancing the user's viewing experience and effectively increasing the user's stickiness to the performance.

[0064] In addition, in the process of screening audition actors who are highly matched with the target roles, the casting personnel need to screen them layer by layer, which makes the screening process long and is not conducive to the timely release of the works. The actor audition evaluation method provided by this embodiment can effectively assist the casting personnel to speed up the actor screening process according to the degree of suitability, shorten the screening cycle, and enable the works to be released in time.

[0065] The actor audition evaluation method provided by the embodiment of the present invention includes: obtaining an audition script; selecting the best audition clip corresponding to the target role performed by the audition actor from the audition script; obtaining an audition video of the audition actor performing according to the best audition clip; determining the audition score of the audition actor based on the audition video; and determining the compatibility between the audition actor and the target role based on the audition score. The above technical scheme can quantify the acting skills and expressiveness of the audition actor through the audition score determined by the audition video, and can more accurately and objectively evaluate the compatibility between the audition actor and the target role, thereby helping casting personnel to accurately select suitable actors, effectively avoiding the problem of actor-role mismatch caused by the personal subjective assumptions of casting personnel, and affecting the performance effect.

[0066] exist Figure 1 Based on Figure 2 , Figure 2 A flow chart of another embodiment of an actor audition evaluation method provided by an embodiment of the present invention. Figure 2 The process shown may include the following steps:

[0067] Step 201, obtaining a trial play script;

[0068] Step 202, selecting the best audition clip corresponding to the target role performed by the audition actor from the audition script;

[0069] The above step 202 can be specifically implemented through steps A1 to A3:

[0070] Step A1, inputting the trial play script and the first prompt text into the large language model, and the large language model outputs the character portraits of each character included in the trial play script based on the first prompt text; wherein the first prompt text includes character portrait analysis content;

[0071] In the field of natural language processing and artificial intelligence, large language models are used to output corresponding responses based on the input content. Large Language Model: Large Language Model, referred to as LLM, refers to a computer model that can process and generate natural language. LLM can predict the next word or sentence by learning the statistical laws and semantic information of language data. As the input data set and parameter space continue to expand, the ability of LLM will also expand accordingly. It is used in a variety of application fields, such as machine learning, machine translation, speech recognition, image processing, etc., so it is called a multimodal large language model.

[0072] In this embodiment, the large language model can be GPT (Generative Pre-trained Transformer)-3, GPT-4, PaLM (Scaling Language Modeling with Pathways), LLaMA (Large Language Model Meta AI), etc., which are not limited here.

[0073] In this embodiment, the prompt method is applied to the large language model. The prompt method is a technique for guiding the large language model to generate text of a specific style or content by providing a text prompt (prompt text) to the large language model. For the large language model, the prompt method allows the user to guide the model to generate a reply or content that meets specific requirements in the form of text without complex fine-tuning or training. The flexibility and efficiency of this method make it very popular in practical applications.

[0074] Technically, the prompt method is implemented by concatenating the prompt text with the model input. The large language model accepts the prompt text as its input and generates corresponding replies or content based on the text. Based on the above principle, in this embodiment, the trial script and the first prompt text are used as inputs of the large language model, so that the large language model outputs the role portraits of each role in the trial script according to the prompt of the first prompt text.

[0075] The above character portrait analysis content includes but is not limited to the character's age, social background, personality traits, character fate, key turning points and emotional climax of the character in the entire trial script, etc.

[0076] In order to facilitate the understanding of the first prompt text, the specific content of the first prompt text is exemplified as follows: "You are a senior script analyst. Please output the character portraits of each character in the trial script. The content of the character portraits includes age, social background, personality traits, character destiny, key turning points and emotional climax of the character in the entire trial script."

[0077] Step A2, inputting the second prompt text into the large language model, and the large language model outputs multiple audition clips of the target role; wherein the second prompt text includes the role name and role portrait corresponding to the target role;

[0078] The specific content of the second prompt text is related to the audition clips to be selected. For example, if you choose audition clips with dialogues and actions that can reflect the personality and emotions of the target character, then the specific content of the second prompt text can be: "You are a senior script analyst. The character portrait of XX character is XXXXX. Please extract all dialogues and action clips that show the personality of XX character in the following script paragraphs."

[0079] Step A3, inputting the third prompt text into the large language model, and the large language model selects and outputs the best audition clip corresponding to the target role from multiple audition clips; wherein the third prompt text includes scene time constraint conditions.

[0080] The above-mentioned scene time constraints include at least one of the following: scene layout conditions, environmental factors, and performance duration. Based on the scene layout and environmental factors, select clips that are easy to reproduce in the audition environment, and based on the time limit of the audition, select clips with moderate duration and tight rhythm. Then the third prompt text can be: "Extract clips that meet the requirements of indoor performance and have a performance duration of 10 to 20 minutes from multiple audition clips that show the personality characteristics of xx role."

[0081] In this embodiment, through the understanding of the audition script by the large language model and the guidance of the prompt text, the most expressive and appropriate audition clip can be selected from the audition script, and the role portrait output by the large language model can further help the audition actor to quickly understand the target role, so that the audition actor can better interpret the target role.

[0082] Step 203, obtaining an audition video of the audition actor performing according to the best audition clip;

[0083] Step 204, determining the emotional expression score, body language score, facial expression score and dialogue expression score of the audition actor based on the audition video;

[0084] In this embodiment, the acting skills and expressiveness of the audition actor will be examined from four aspects: emotional expression, dialogue expression ability, body language and facial expressions. Among them, emotional expression can highlight whether the audition actor has consistency in emotion in language and non-verbal expression; dialogue expression ability is used to examine the audition actor's skills in pronunciation clarity, speaking speed, intonation and rhythm; body language is used to evaluate whether the audition actor's body movements are consistent with the role, whether the movements are natural and smooth, and whether they can effectively convey the role's inner world; facial expressions can observe whether the audition actor has rich facial expressions and whether he can accurately express the emotional changes of the target role.

[0085] The above step 204 can be specifically implemented through steps B1 to B8:

[0086] Step B1, transcribing the audio in the audition video into audio text;

[0087] Currently, this can be achieved using the general technology of converting audio to audio text, which will not be described in detail here.

[0088] Step B2, extracting language features and non-language features from the audio text and the audition video;

[0089] Among them, non-language features include facial expression features and body language features; in this embodiment, the above non-language features can be extracted from the audition video using existing image recognition technology. The above language features include pitch, volume, rhythm and speech speed, and the corresponding existing language feature extraction tools can be used to extract the above features, which will not be described in detail here.

[0090] Step B3, inputting the language features and non-language features into a pre-trained first emotion expression model, and the first emotion expression model outputs the first emotion expression of the audition actor;

[0091] The first emotional expression includes the first emotional color and the first emotional intensity score, wherein the first emotional color is used to specifically describe the emotional tendency, such as horror, joy, pain, sadness, etc., and the first emotional intensity score is used to indicate the intensity of the emotional color. The higher the first emotional intensity score, the stronger the emotional color, and vice versa. For example, if the first emotional color is joy, the first emotional intensity score is 90, indicating that the degree of joy performed by the audition actor is strong. If the first emotional intensity score is 40, it indicates that the degree of joy performed by the audition actor is poor.

[0092] The training process of the first emotion expression model can be obtained by the following steps:

[0093] S1, obtain the historical interpretation videos performed by each actor;

[0094] S2, performing the following processing for each historical interpretation video: transcribing the audio in the historical interpretation video into an audio text, extracting speech features from the audio text and non-language features from the historical interpretation video, and marking the emotional color and emotional intensity score for the historical interpretation video;

[0095] S3, inputting the language features and non-language features in each historical interpretation video into the neural network model to be trained, and the neural network model outputs the predicted emotional color and emotional intensity score;

[0096] S4, comparing the predicted emotional color and emotional intensity scores with the labeled emotional color and emotional intensity scores to determine whether the neural network model has converged;

[0097] S5: If the neural network model has not converged, adjust the model parameters of the neural network model and return to execute S2.

[0098] Based on the trained first emotion expression model, in step B3, the language features and non-language features extracted from the audition actor's audition video can be input into the pre-trained first emotion expression model to obtain the first emotion expression of the audition actor.

[0099] In actual application, the emotional expression of the audition actors can be presented in a visual way, such as emotional curves, expression change graphs, etc., to facilitate understanding and communication.

[0100] Step B4, inputting the audio text into a pre-trained second emotion expression model, and the second emotion expression model outputs the second emotion expression of the audition actor;

[0101] The second emotion expression includes a second emotion color and a second emotion intensity score. The second emotion expression has the same function as the first emotion expression and will not be elaborated here.

[0102] Among them, the second emotion expression model is obtained by training with training samples consisting of audio text and emotion expressions annotated on the audio text. The training process is the same as the training process of the first emotion expression model, except that the training samples used are different, which will not be elaborated here.

[0103] Step B5, determining the emotional expression score of the audition actor based on the first emotional expression and the second emotional expression;

[0104] The emotion expression score is used to assess whether the audition actor's emotions are consistent in terms of language and non-verbal characteristics. The higher the emotion expression score, the more consistent the audition actor's emotions are in terms of language and non-verbal characteristics, and vice versa.

[0105] The specific process of determining the emotional expression score of the audition actor is: judging whether the first emotional color is consistent with the second emotional color; when the first emotional color is consistent with the second emotional color, performing linear weighted summation of the first emotional intensity score and the second emotional intensity score respectively using a preset emotional intensity weight coefficient to obtain the emotional expression score of the audition actor; when the first emotional color is inconsistent with the second emotional color, determining the preset score as the emotional expression score of the audition actor.

[0106] The above emotional expression score can be expressed by the following formula:

[0107] W1=a1*R1+a2*R2; a1+a2=1; wherein a1 represents the preset emotion intensity weight coefficient corresponding to the first emotion expression, R1 represents the first emotion intensity score, a2 represents the preset emotion intensity weight coefficient corresponding to the second emotion expression, and R2 represents the second emotion intensity score.

[0108] If the first emotional color is inconsistent with the second emotional color, it means that the audition actor is highly inconsistent in verbal and non-verbal performance, and the emotional expression score is set to a preset score, such as 0, 5 or 10.

[0109] Step B6, inputting the body language features into a pre-trained body language scoring model, and the body language scoring model outputs the body language score of the audition actor;

[0110] The body language score is used to evaluate whether the audition actor's body movements are consistent with the target role, whether the movements are natural and smooth, and whether they can effectively convey the target role's inner world. The higher the body language score, the more consistent the audition actor's body movements are with the target role, the more natural and smooth the movements are, and the more effectively they can convey the target role's inner world.

[0111] Among them, the body language scoring model can be obtained by training with training samples consisting of body language features and body language scores annotated with body language features. The training process is the same as the training process of the first emotion expression model, except that the training samples used are different, which will not be elaborated here.

[0112] Step B7, inputting the facial expression features into a pre-trained facial expression scoring model, and the facial expression scoring model outputs the facial expression score of the audition actor;

[0113] The facial expression score is used to evaluate whether the audition actor's facial expressions are rich and whether he can accurately express the emotional changes of the target role. The higher the facial expression score, the richer the audition actor's facial expressions are and the more accurately he can express the emotional changes of the target role.

[0114] Among them, the facial expression scoring model can be obtained by training with training samples consisting of facial expression features and facial expression scores annotated with facial expression features. The training process is the same as the training process of the first emotion expression model, except that the training samples used are different, which will not be elaborated here.

[0115] Step B8, inputting the language features into a pre-trained dialogue scoring model, and the dialogue scoring model outputs the dialogue expression score of the audition actor.

[0116] The dialogue expression score is used to evaluate the language expression ability of the auditioning actor. The higher the dialogue expression score is, the better the auditioning actor can express himself in terms of pronunciation clarity, speaking speed, intonation and rhythm.

[0117] Among them, the dialogue scoring model can be obtained by training with training samples consisting of language features and dialogue expression scores annotated with language features. The training process is the same as the training process of the first emotion expression model, except that the training samples used are different, which will not be elaborated here.

[0118] Step 205, performing linear weighted summation of the emotion expression score, body language score, facial expression score, and dialogue expression score using preset weight coefficients to obtain the audition score of the audition actor;

[0119] The above audition score can be calculated by the following formula:

[0120] P1=b1*W1+b2*W2+b3*W3+b4*W4; b1+b2+b3+b4=1;

[0121] Among them, b1 represents the preset weight coefficient corresponding to the emotional expression score, W1 represents the emotional expression score, b2 represents the preset weight coefficient corresponding to the body language score, W2 represents the body language score, b3 represents the preset weight coefficient corresponding to the facial expression score, W3 represents the facial expression score, b4 represents the preset weight coefficient corresponding to the lines expression score, W4 represents the lines expression score.

[0122] Step 206, obtaining the evaluation scores of the auditioning actors by the casting staff;

[0123] Casting staff can score the best audition performances by the audition actors. The higher the score, the more confident the casting staff is in the audition actor's acting skills and expressiveness.

[0124] Step 207, performing linear weighted summation of the review scores and the audition scores using preset score weight coefficients to obtain a comprehensive score;

[0125] The above comprehensive score can be expressed by the following formula:

[0126] Ptotal=c1*P1+c2*P2; c1+c2=1; wherein c1 represents the preset scoring weight coefficient corresponding to the first audition score, P1 represents the audition score, c2 represents the preset scoring weight coefficient corresponding to the second review score, and P2 represents the review score.

[0127] Step 208, determining the compatibility between the audition actor and the target role based on the comprehensive score.

[0128] In one embodiment, the comprehensive score may be determined as the degree of suitability between the audition actor and the target role, wherein a higher comprehensive score indicates a higher degree of suitability between the audition actor and the target role.

[0129] In another embodiment, the process of determining the degree of adaptation is: querying the adaptation score range that matches the comprehensive score from the adaptation grade table; wherein the adaptation grade table stores the correspondence between the adaptation grade and the adaptation score range; and determining the adaptation grade corresponding to the adaptation score range as the degree of adaptation between the audition actor and the target role.

[0130] Specifically, the adaptation levels can be divided into level 1, level 2, level 3, level 4..., among which level 1 indicates that the audition actor is more compatible with the target role.

[0131] It is understandable that after determining the compatibility of each audition actor with the target role, the audition actors can be sorted in order of compatibility from high to low, so that casting personnel can select audition actors with higher compatibility to play the target role.

[0132] The degree of suitability provides casting staff with a basis for casting and guidance, while also providing auditioning actors with a reference for improving their performances.

[0133] See also Figure 3 , is a block diagram of an embodiment of an actor audition evaluation device provided by an embodiment of the present invention. Figure 3 As shown, the device comprises:

[0134] The first acquisition module 301 is used to acquire the trial play script;

[0135] A selection module 302 is used to select the best audition segment corresponding to the target role performed by the audition actor from the audition script;

[0136] The second acquisition module 303 is used to acquire an audition video of the audition actor performing according to the best audition clip;

[0137] A first determination module 304 is used to determine the audition score of the audition actor based on the audition video;

[0138] The second determination module 305 is used to determine the compatibility between the audition actor and the target role according to the audition score.

[0139] The actor audition evaluation device provided by the embodiment of the present invention includes the following steps: obtaining an audition script; selecting the best audition clip corresponding to the target role performed by the audition actor from the audition script; obtaining an audition video of the audition actor performing according to the best audition clip; determining the audition score of the audition actor based on the audition video; and determining the compatibility between the audition actor and the target role based on the audition score. The above technical solution can quantify the acting skills and expressiveness of the audition actor through the audition score determined by the audition video, and can more accurately and objectively evaluate the compatibility between the audition actor and the target role, thereby helping casting personnel to accurately select suitable actors, effectively avoiding the problem of actor-role mismatch caused by the personal subjective assumptions of casting personnel, and affecting the performance effect.

[0140] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, Figure 4 The electronic device 500 shown includes: at least one processor 501, a memory 502, at least one network interface 504 and other user interfaces 503. The various components in the electronic device 500 are coupled together via a bus system 505. It is understood that the bus system 505 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 505 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 505 is not shown in FIG. Figure 4 Various buses are labeled as bus system 505 .

[0141] The user interface 503 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touch pad, or a touch screen).

[0142] It can be understood that the memory 502 in the embodiment of the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct RAM bus random access memory (DRRAM). The memory 502 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0143] In some implementations, the memory 502 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 5021 and an application program 5022 .

[0144] The operating system 5021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 5022 includes various application programs, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present invention can be included in the application 5022.

[0145] In the embodiment of the present invention, by calling the program or instruction stored in the memory 502, specifically, the program or instruction stored in the application 5022, the processor 501 is used to execute the method steps provided by each method embodiment.

[0146] The method disclosed in the above embodiment of the present invention can be applied to the processor 501, or implemented by the processor 501. The processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 501 or the instruction in the form of software. The above processor 501 can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to execute, or the hardware and software units in the decoding processor can be executed. The software unit can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 502, and the processor 501 reads the information in the memory 502 and completes the steps of the above method in combination with its hardware.

[0147] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPDevice, DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in the present application, or a combination thereof.

[0148] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0149] The electronic device provided in this embodiment may be Figure 4 The electronic device shown in FIG. 1 may perform the following steps: Figure 1-2 All steps of the actor audition evaluation method in order to achieve Figure 1-2 The technical effect of the actor audition evaluation method shown is shown in the figure. Figure 1-2 For the sake of brevity, the relevant description is not repeated here.

[0150] The embodiment of the present invention also provides a storage medium (computer-readable storage medium). The storage medium here stores one or more programs. The storage medium may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid-state drive; the memory may also include a combination of the above-mentioned types of memory.

[0151] When one or more programs in the storage medium can be executed by one or more processors, the above-mentioned actor audition evaluation method can be implemented.

[0152] The processor is used to execute the actor audition evaluation program stored in the memory to implement the steps of the following actor audition evaluation method.

[0153] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0154] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0155] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for evaluating actor auditions. It is characterized in that The method comprises: Get the pilot script; Selecting the best audition segment corresponding to the target role performed by the audition actor from the audition script; Obtaining an audition video of the audition actor performing according to the best audition clip; Determining an audition score of the audition actor based on the audition video; The compatibility of the audition actor with the target role is determined based on the audition score.

2. The method according to claim 1, It is characterized in that The step of selecting the best audition segment corresponding to the target role performed by the audition actor from the audition script comprises: The trial play script and the first prompt text are input into a large language model, and the large language model outputs a character portrait of each character included in the trial play script based on the first prompt text; wherein the first prompt text includes character portrait analysis content; Inputting a second prompt text into the large language model, the large language model outputting a plurality of audition clips of the target role; wherein the second prompt text includes a role name corresponding to the target role and a role portrait; The third prompt text is input into the large language model, and the large language model selects and outputs the best audition clip corresponding to the target role from the multiple audition clips; wherein the third prompt text includes scene time constraint conditions.

3. The method according to claim 1, It is characterized in that The step of determining the audition score of the audition actor based on the audition video includes: Determine the emotional expression score, body language score, facial expression score, and dialogue expression score of the audition actor based on the audition video; The emotional expression score, the body language score, the facial expression score and the dialogue expression score are linearly weighted summed up by using preset weight coefficients to obtain the audition score of the audition actor.

4. The method according to claim 3, It is characterized in that The step of determining the emotional expression score, body language score, facial expression score, and dialogue expression score of the audition actor based on the audition video includes: transcribing the audio in the audition video into an audio text; Extracting language features and non-language features from the audio text and the audition video; wherein the non-language features include facial expression features and body language features; Inputting the language features and the non-language features into a pre-trained first emotion expression model, and the first emotion expression model outputs a first emotion expression of the audition actor; Inputting the audio text into a pre-trained second emotion expression model, and the second emotion expression model outputs the second emotion expression of the audition actor; Determining an emotional expression score of the audition actor based on the first emotional expression and the second emotional expression; Inputting the body language features into a pre-trained body language scoring model, the body language scoring model outputting the body language score of the audition actor; Inputting the facial expression features into a pre-trained facial expression scoring model, the facial expression scoring model outputting the facial expression score of the audition actor; The language features are input into a pre-trained dialogue scoring model, and the dialogue scoring model outputs the dialogue expression score of the audition actor.

5. The method according to claim 4, It is characterized in that The first emotion expression includes a first emotion color and a first emotion intensity score, and the second emotion expression includes a second emotion color and a second emotion intensity score; Determining an emotional expression score of the audition actor based on the first emotional expression and the second emotional expression; Determining whether the first emotional color is consistent with the second emotional color; When the first emotional color is consistent with the second emotional color, the first emotional intensity score and the second emotional intensity score are linearly weighted summed by using a preset emotional intensity weight coefficient to obtain an emotional expression score of the audition actor; In the case that the first emotional color is inconsistent with the second emotional color, a preset score is determined as the emotional expression score of the audition actor.

6. The method according to claim 1, It is characterized in that Determining the compatibility between the audition actor and the target role according to the audition score includes: Obtaining the evaluation scores of the auditioning actors by the casting staff; The review score and the audition score are linearly weighted and summed using a preset score weight coefficient to obtain a comprehensive score; The degree of compatibility between the audition actor and the target role is determined based on the comprehensive score.

7. The method according to claim 6, It is characterized in that Determining the compatibility between the audition actor and the target role based on the comprehensive score includes: Querying an adaptation score range that matches the comprehensive score from an adaptation grade table; wherein the adaptation grade table stores a correspondence between adaptation grades and adaptation score ranges; The adaptation level corresponding to the adaptation score range is determined as the degree of adaptation between the audition actor and the target role.

8. An actor audition evaluation device, It is characterized in that The device comprises: The first acquisition module is used to acquire the trial play script; A selection module is used to select the best audition segment corresponding to the target role performed by the audition actor from the audition script; A second acquisition module is used to acquire an audition video of the audition actor performing according to the best audition clip; A first determination module, configured to determine an audition score of the audition actor based on the audition video; The second determination module is used to determine the compatibility between the audition actor and the target role according to the audition score.

9. An electronic device, It is characterized in that include: A processor and a memory, wherein the processor is used to execute a program for actor audition evaluation stored in the memory to implement the actor audition evaluation method according to any one of claims 1 to 7.

10. A storage medium, It is characterized in that The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the actor audition evaluation method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Multimodal automatic scoring method for college English speech

    CN114187544A

  • Object evaluation method, system and equipment based on video and storage medium

    CN114330963A

  • Drama performance evaluation method, device and equipment and storage medium

    CN115526232A

  • Actor virtual performance system based on digital twinborn simulation and application method thereof

    CN118262588A

  • Evaluation of actor auditions

    US20200175457A1

Cited By

  • Neural network-based motion capture actor fitness evaluation method and system

    CN121170906A