Film and television work playing effect estimation method and device, electronic equipment and storage medium

By analyzing the character scene structure and calculating the contribution degree of film and television works, and combining the role playback effect scores, the problem of low accuracy of the viewing effect of film and television works in the existing technology is solved, and a higher accuracy of prediction is achieved.

CN119621796APending Publication Date: 2025-03-14BEIJING IQIYI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411592358.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-08
Publication Date
2025-03-14

AI Technical Summary

Technical Problem

In the prior art, the playback effect of film and television works is evaluated based on the historical works data of the two main actors with the most scenes, resulting in low estimate accuracy.

Method used

By analyzing the character scene structure of the estimated film and television works, the contribution of each character in the film and television works is determined, and the role playback effect score is obtained. Finally, the target playback effect score of the film and television works is calculated based on these data.

Benefits of technology

The accuracy of the estimate of the playback effect of film and television works is improved, the impact of more characters on the playback effect of film and television works is considered, and the role structure type of film and television works is considered when determining the contribution degree of each character.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119621796A_ABST
    Figure CN119621796A_ABST
Patent Text Reader

Abstract

The invention provides a film and television work playing effect estimation method and device, electronic equipment and a storage medium. The method comprises the following steps: performing character play structure analysis on a to-be-estimated film and television work to obtain a plurality of roles included in the to-be-estimated film and television work and first play structure types corresponding to the plurality of roles; based on the first play structure type, determining a first contribution degree corresponding to each role in the to-be-estimated film and television work; for each role, obtaining a role playing effect score corresponding to the role; and based on the first contribution degrees and the role playing effect scores corresponding to all the roles, determining a target playing effect score corresponding to the to-be-estimated film and television work. Compared with the prior art, when the playing effect (such as the playing amount, the playing income, the word-of-mouth score and the like) of the film and television work is estimated, the influence of more roles on the playing effect of the film and television work is considered, so that the estimation accuracy is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a method, device, electronic device and storage medium for estimating the playback effect of a film or television work. Background Art

[0002] Film and television works are a general term for completed works of art that are recorded on film by a camera and projected through a player. Film and television works are also a kind of art work. They are a combination of photography and sound, integrating visual and auditory art. They are the product of the combination of modern science and technology and art. Common film and television works include TV series, movies, etc.

[0003] Before selecting a film or TV work to be broadcast, the video platform usually estimates the broadcast effect of the film or TV work (such as broadcast volume, broadcast revenue, word-of-mouth rating, etc.). The broadcast effect of a film or TV work is related to the economic interests of film and TV investors, advertising investors, and every audience watching the film or TV work, so it has attracted much attention from industry practitioners. At present, the broadcast effect of a film or TV work is usually evaluated based on the historical work data of the two main actors with the most roles.

[0004] However, when evaluating the playback effect of film and television works in this way, the accuracy of the estimate is relatively low due to the small amount of data. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method, device, electronic device and storage medium for estimating the playback effect of a film or television work, so as to solve the problem that the playback effect of a film or television work is currently evaluated based on the historical work data of the two main actors with the most roles, and the accuracy is relatively low. The specific technical solution is as follows:

[0006] In a first aspect, the present application provides a method for estimating the playback effect of a film or television work, comprising:

[0007] Performing character role structure analysis on the film and television work to be estimated, obtaining a plurality of characters included in the film and television work to be estimated and a first role structure type corresponding to the plurality of characters;

[0008] Based on the first role structure type, determining a first contribution degree corresponding to each of the characters in the film and television work to be estimated;

[0009] For each role, obtaining a role playing effect score corresponding to the role;

[0010] Based on the first contribution degrees and the role playback effect scores corresponding to all the roles, a target playback effect score corresponding to the film and television work to be estimated is determined.

[0011] In a possible implementation, the performing of character role structure analysis on the film and television work to be estimated to obtain a plurality of characters included in the film and television work to be estimated and a first role structure type corresponding to the plurality of characters includes:

[0012] Obtaining the script corresponding to the film and television work to be estimated;

[0013] Performing role analysis on the script of the work to obtain multiple roles and the role ratio of each role in the film and television work to be estimated;

[0014] The first role structure type is determined based on the proportion of each character's role in the film and television work to be estimated.

[0015] In a possible implementation, the performing of character role structure analysis on the film and television work to be estimated to obtain a plurality of characters included in the film and television work to be estimated and a first role structure type corresponding to the plurality of characters includes:

[0016] Obtaining the script corresponding to the film and television work to be estimated;

[0017] Obtaining model prompt words, wherein the model prompt words are used to describe definitions of various types of play structure;

[0018] The script of the work and the model prompt words are input into the large language model, so that the large language model outputs multiple characters included in the film and television work to be estimated and the first scene structure types corresponding to the multiple characters.

[0019] In a possible implementation, determining the first contribution of each character in the film and television work to be estimated based on the first role structure type includes:

[0020] Acquire contribution weight distribution data corresponding to the first role structure type, wherein the contribution weight distribution data includes a ranking weight corresponding to each ranking;

[0021] For each role, determining the role ranking corresponding to the role in the film and television work to be estimated based on the first role structure type;

[0022] The role ranking weight corresponding to the role ranking is searched in the contribution weight distribution data, and the role ranking weight is determined as the first contribution corresponding to the role.

[0023] In a possible implementation manner, obtaining the role playing effect score corresponding to the role includes:

[0024] Obtain the historical film and television works corresponding to the role and the historical playback effect scores corresponding to the historical film and television works;

[0025] Performing character role structure analysis on the historical film and television work to obtain a second role structure type corresponding to the historical film and television work;

[0026] Based on the second role structure type, determining a second contribution degree corresponding to the character in the historical film or television work;

[0027] The product of the historical playback effect score and the second contribution degree is determined as the role playback effect score.

[0028] In a possible implementation, the performing character role structure analysis on the historical film or television work to obtain the second role structure type corresponding to the historical film or television work includes:

[0029] Obtaining work introduction data and work evaluation data corresponding to the historical film and television works;

[0030] Obtaining model prompt words, wherein the model prompt words are used to describe definitions of various types of play structure;

[0031] The work introduction data, the work evaluation data and the model prompt words are input into the large language model so that the large language model outputs the second scene structure type corresponding to the historical film and television work.

[0032] In a possible implementation manner, determining the target playback effect score corresponding to the to-be-estimated film and television work based on the first contribution degrees and the role playback effect scores corresponding to all the roles includes:

[0033] Substituting the first contribution degrees and the role playback effect scores corresponding to all the roles into Formula 1, to obtain the target playback effect score corresponding to the film and television work to be estimated;

[0034]

[0035] Among them, actors all is the target playback effect score, actor i is the role playing effect score corresponding to role i, w i1 is the first contribution corresponding to character i, and n is the number of all characters.

[0036] In a second aspect, the present application provides a device for estimating the playback effect of a film or television work, comprising:

[0037] A structure analysis module, used for performing character role structure analysis on the film and television work to be estimated, and obtaining a plurality of roles included in the film and television work to be estimated and a first role structure type corresponding to the plurality of roles;

[0038] A contribution determination module, configured to determine, based on the first role structure type, a first contribution corresponding to each of the roles in the film and television work to be estimated;

[0039] A score acquisition module, used for acquiring, for each role, a role playing effect score corresponding to the role;

[0040] The score determination module is used to determine the target playback effect score corresponding to the film and television work to be estimated based on the first contribution degrees and the role playback effect scores corresponding to all the roles.

[0041] In a possible implementation, the structural analysis module is specifically used to:

[0042] Obtaining the script corresponding to the film and television work to be estimated;

[0043] Performing role analysis on the script of the work to obtain multiple roles and the role ratio of each role in the film and television work to be estimated;

[0044] The first role structure type is determined based on the proportion of each character's role in the film and television work to be estimated.

[0045] In a possible implementation, the structural analysis module is further used to:

[0046] Obtaining the script corresponding to the film and television work to be estimated;

[0047] Obtaining model prompt words, wherein the model prompt words are used to describe definitions of various types of play structure;

[0048] The script of the work and the model prompt words are input into the large language model, so that the large language model outputs multiple characters included in the film and television work to be estimated and the first scene structure types corresponding to the multiple characters.

[0049] In a possible implementation manner, the contribution determination module is specifically configured to:

[0050] Acquire contribution weight distribution data corresponding to the first role structure type, wherein the contribution weight distribution data includes a ranking weight corresponding to each ranking;

[0051] For each role, determining the role ranking corresponding to the role in the film and television work to be estimated based on the first role structure type;

[0052] The role ranking weight corresponding to the role ranking is searched in the contribution weight distribution data, and the role ranking weight is determined as the first contribution corresponding to the role.

[0053] In a possible implementation manner, the score acquisition module is specifically configured to:

[0054] Obtain the historical film and television works corresponding to the role and the historical playback effect scores corresponding to the historical film and television works;

[0055] Performing character role structure analysis on the historical film and television work to obtain a second role structure type corresponding to the historical film and television work;

[0056] Based on the second role structure type, determining a second contribution degree corresponding to the character in the historical film or television work;

[0057] The product of the historical playback effect score and the second contribution degree is determined as the role playback effect score.

[0058] In a possible implementation manner, the score acquisition module is further used to:

[0059] Obtaining work introduction data and work evaluation data corresponding to the historical film and television works;

[0060] Obtaining model prompt words, wherein the model prompt words are used to describe definitions of various types of play structure;

[0061] The work introduction data, the work evaluation data and the model prompt words are input into the large language model so that the large language model outputs the second scene structure type corresponding to the historical film and television work.

[0062] In a possible implementation, the score determination module is specifically configured to:

[0063] Substituting the first contribution degrees and the role playback effect scores corresponding to all the roles into Formula 1, to obtain the target playback effect score corresponding to the film and television work to be estimated;

[0064]

[0065] Among them, actors all is the target playback effect score, actor i is the role playing effect score corresponding to role i, w i1 is the first contribution corresponding to character i, and n is the number of all characters.

[0066] 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;

[0067] Memory, used to store computer programs;

[0068] The processor is used to implement any method step described in the first aspect when executing a program stored in the memory.

[0069] 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.

[0070] 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 above-mentioned methods for estimating the playback effect of a film or television work.

[0071] Beneficial effects of the embodiments of the present application:

[0072] The embodiment of the present application provides a method, device, electronic device and storage medium for estimating the playback effect of a film and television work. In the present application, first, the character role structure analysis is performed on the film and television work to be estimated, and multiple characters contained in the film and television work to be estimated and the first role structure type corresponding to the multiple characters are obtained. Then, based on the first role structure type, the first contribution degree corresponding to each character in the film and television work to be estimated is determined, and the role playback effect score corresponding to each character is obtained. Finally, based on the first contribution degree and role playback effect score corresponding to all the characters, the target playback effect score corresponding to the film and television work to be estimated is determined. Compared with the prior art, when estimating the playback effect (such as playback volume, playback income, word-of-mouth rating, etc.) of the film and television work, the present application considers the influence of more characters on the playback effect of the film and television work, thereby improving the accuracy of the estimation, and when determining the contribution of each character to the film and television work, the role structure type of the film and television work is considered, so that the accuracy of determining the influence of each character on the playback effect of the film and television work can be improved, thereby further improving the accuracy of the estimation.

[0073] 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

[0074] 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.

[0075] 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.

[0076] 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.

[0077] Figure 1 A flowchart of a method for estimating the playback effect of a film or television work provided in an embodiment of the present application;

[0078] Figure 2 A flowchart of another method for estimating the playback effect of a film or television work provided in an embodiment of the present application;

[0079] Figure 3 This is an example of determining the first role structure type by role proportion;

[0080] Figure 4 Another example of determining the first role structure type by role proportion;

[0081] Figure 5 A flowchart of another method for estimating the playback effect of a film or television work provided in an embodiment of the present application;

[0082] Figure 6 A schematic diagram of the structure of a device for estimating the playback effect of a film or television work provided in an embodiment of the present application;

[0083] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0084] 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.

[0085] 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.

[0086] Figure 1A flow chart of a method for estimating the playback effect of a film and television work provided in 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 as a single software or software module. No specific limitation is made here.

[0087] like Figure 1 As shown, the method specifically includes:

[0088] S101, analyzing the role structure of characters in the film and television work to be estimated, and obtaining a plurality of roles included in the film and television work to be estimated and a first role structure type corresponding to the plurality of roles.

[0089] The film and television works to be estimated are generally those that have not yet been released, such as unreleased movies, unreleased TV series, etc.

[0090] Character structure analysis refers to the analysis of the characters included in the estimated film and television works, the importance of each character, and the relationship between each character.

[0091] The first role structure type is used to characterize the type of the protagonist setting of the film or TV work to be estimated. The protagonist setting type is used to describe the importance of each role in the film or TV work to be estimated and the relationship between the roles. For example, the main female lead type, the main male lead type, the double female lead type, the double male lead type, the male and female lead type, the triangle play type, and the group play type.

[0092] In the embodiment of the present application, by analyzing the character role structure of the film and television work to be estimated, multiple characters included in the film and television work to be estimated and the first role structure type corresponding to the multiple characters can be obtained. In the application, all the characters included in the film and television work to be estimated can be used as multiple characters for evaluating the playback effect, or a preset number of characters can be selected as multiple characters for evaluating the playback effect. It should be noted that the preset number is generally not less than 3.

[0093] As for how to conduct character role structure analysis on estimated film and television works, it will be explained in detail through the examples below and will not be described in detail here.

[0094] S102: Based on the first role structure type, determine a first contribution degree corresponding to each of the characters in the film or television work to be estimated.

[0095] The first contribution is used to represent the importance of the corresponding role in the film and television work to be estimated.

[0096] In the embodiment of the present application, based on the first role structure type, the specific implementation of determining the first contribution degree corresponding to each of the characters in the film and television work to be estimated may include:

[0097] Step A1, obtaining contribution weight distribution data corresponding to the first role structure type, wherein the contribution weight distribution data includes a ranking weight corresponding to each ranking;

[0098] Step A2, for each role, determining the role ranking corresponding to the role in the film and television work to be estimated based on the first role structure type;

[0099] Step A3, searching the contribution weight distribution data for the role ranking weight corresponding to the role ranking, and determining the role ranking weight as the first contribution corresponding to the role.

[0100] The following is a unified description of steps A1 to A3:

[0101] In the application, the correspondence between each role structure type and contribution weight distribution data is pre-set as shown in Table 1. This correspondence is generally derived by staff based on experience and historical data. For example, when the role structure type is "Male Lead / Female Lead", the contribution weight of the role corresponding to the No. 1 ranking is 100%, the contribution weight of the role corresponding to the No. 2 ranking is 40%, the contribution weight of the role corresponding to the No. 11-16 ranking is 2%, and so on.

[0102] Table 1

[0103]

[0104] Based on this, in this solution, the contribution weight distribution data corresponding to the first role structure type can be obtained, so as to obtain the ranking weight corresponding to each ranking when the film and television work to be estimated is of the first role structure type.

[0105] In addition, the role ranking of each role in the film and television work to be estimated can be determined according to the importance of each role described by the first role structure type, that is, the higher the importance of the role, the higher the corresponding role ranking. In other words, the role ranking of the first role is No. 1, the role ranking of the second role is No. 2, the role ranking of the third role is No. 3, and so on, to obtain the role ranking of each role in the film and television work to be estimated.

[0106] In this way, the role ranking weight corresponding to each role ranking can be found in the contribution weight distribution data corresponding to the first role structure type, and the role ranking weight can be determined as the first contribution corresponding to the role.

[0107] S103: For each role, obtain a role play effect score corresponding to the role.

[0108] The role playback effect score is used to represent the corresponding role's ability to resist drama in the film and television works in which it has historically participated, that is, the influence of the role on the playback effect of the film and television works in which it has historically participated.

[0109] Specifically, the implementation of obtaining the role playing effect score corresponding to the role may include:

[0110] Step B1, obtaining the historical film and television works corresponding to the role and the historical playback effect scores corresponding to the historical film and television works;

[0111] Step B2, analyzing the character role structure of the historical film or television work to obtain a second role structure type corresponding to the historical film or television work;

[0112] Step B3, determining a second contribution degree corresponding to the character in the historical film or television work based on the second role structure type;

[0113] Step B4: multiplying the historical playback effect score by the second contribution degree to determine the role playback effect score.

[0114] The following is a unified description of steps B1 to B3:

[0115] Historical film and television works refer to the film and television works in which the corresponding characters have participated in history. The number of historical film and television works can be one or more.

[0116] The historical playback effect score is used to characterize the playback effect of the corresponding historical film and television works, such as playback volume, playback revenue, word-of-mouth rating, etc. The higher the score, the better the corresponding playback effect.

[0117] The second role structure type is used to characterize the protagonist setting type of historical film and television works. The protagonist setting type is used to describe the importance of each role in historical film and television works and the relationship between each role.

[0118] The second contribution is used to represent the importance of the corresponding role in historical film and television works.

[0119] In this solution, firstly, the character role structure of the historical film and television works is analyzed to obtain the second role structure type corresponding to the historical film and television works.

[0120] Specifically, performing character role structure analysis on the historical film or television work to obtain the second role structure type corresponding to the historical film or television work may include the following steps:

[0121] Obtain work introduction data and work evaluation data corresponding to the historical film or television work, obtain model prompt words, wherein the model prompt words are used to describe the definitions of various types of role structures, input the work introduction data, the work evaluation data and the model prompt words into a large language model, so that the large language model outputs a second role structure type corresponding to the historical film or television work.

[0122] Work introduction data refers to data used to introduce historical film and television works, such as script content, plot summary, character relationship diagram, poster image, concept map, etc.

[0123] Work evaluation data refers to data on users' evaluations of historical film and television works, such as film reviews, user movie-watching comments, etc.

[0124] Model prompt words are used to describe the definitions of various types of scene structures, and to prompt GPT (Generative Pre-Trained Transformer, large language model) to analyze the scene structure types of film and television works.

[0125] Based on this, the large language model can analyze the second role structure type corresponding to historical film and television works based on the input work introduction data and work evaluation data.

[0126] Then, according to the second role structure type, the second contribution degree corresponding to the character in the historical film and television works is determined. The process of determining the second contribution degree is similar to the process of determining the first contribution degree, and will not be described in detail here.

[0127] Finally, the product of the historical playback effect score of the historical film and television work and the second contribution degree is determined as the role playback effect score of the corresponding role. That is, the role playback effect score is calculated by the following formula:

[0128] actor i =album j *w i2

[0129] Among them, actor i is the role playing effect score corresponding to role i, album j is the historical playback effect score, w i2 is the second contribution corresponding to character i.

[0130] Thus, the role playing effect score of each role is obtained.

[0131] S104: Determine a target playback effect score corresponding to the film or television work to be estimated based on the first contribution degrees and the playback effect scores of the characters corresponding to all the characters.

[0132] The target playback effect score is used to represent the playback effect of the film or television work to be estimated.

[0133] Specifically, based on the first contribution degrees and the role playback effect scores corresponding to all the roles, determining the target playback effect score corresponding to the to-be-estimated film and television work may include:

[0134] Substituting the first contribution degrees and the role playback effect scores corresponding to all the roles into Formula 1, to obtain the target playback effect score corresponding to the film and television work to be estimated;

[0135]

[0136] Among them, actors all is the target playback effect score, actor i is the role playing effect score corresponding to role i, w i1 is the first contribution corresponding to character i, and n is the number of all characters.

[0137] In an embodiment of the present application, first, the character role structure of the film and television work to be estimated is analyzed to obtain multiple characters contained in the film and television work to be estimated and the first role structure type corresponding to the multiple characters. Then, based on the first role structure type, the first contribution degree corresponding to each character in the film and television work to be estimated is determined, and the role playback effect score corresponding to each character is obtained. Finally, based on the first contribution degree and the role playback effect score corresponding to all the characters, the target playback effect score corresponding to the film and television work to be estimated is determined. Compared with the prior art, when estimating the playback effect of the film and television work (such as playback volume, playback income, word-of-mouth rating, etc.), the present application considers the influence of more characters on the playback effect of the film and television work, thereby improving the accuracy of the estimation. Moreover, when determining the contribution of each character to the film and television work, the role structure type of the film and television work is considered. In this way, the accuracy of determining the influence of each character on the playback effect of the film and television work can be improved, thereby further improving the accuracy of the estimation.

[0138] See also Figure 2 , is a flow chart of another method for estimating the playback effect of a film or television work provided in an embodiment of the present application. Figure 2 The process shown in the above Figure 1 Based on the process shown, it is described how to analyze the character role structure of the estimated film and television works to obtain multiple characters included in the estimated film and television works and the first role structure types corresponding to the multiple characters. Figure 2As shown, the process may include the following steps:

[0139] S201, obtaining the script corresponding to the film and television work to be estimated;

[0140] S202, performing role analysis on the script of the work to obtain a plurality of roles and a role ratio of each role in the film and television work to be estimated;

[0141] S203, determining the first role structure type based on the role proportion of each character in the film and television work to be estimated.

[0142] The following is a unified description of S201-S203:

[0143] In an embodiment of the present application, the script (script outline or complete script) corresponding to the film and television work to be estimated can be interpreted by a script disassembly tool to obtain the proportion of each character in the film and television work to be estimated, and then, based on the proportion of each character, the first role structure type corresponding to the film and television work to be estimated is determined.

[0144] As an example, Figure 3 As shown, this is the proportion of each character in the TV series "Police Story". The proportion of each character is not much different. Therefore, the first role structure type corresponding to the TV series is group drama.

[0145] As another example, Figure 4 As shown, this is the proportion of each character in the TV series "Wind Blows in Half Summer". Among them, the heroine's proportion of scenes is much higher than that of other characters. Therefore, the first role structure type corresponding to the TV series is the heroine.

[0146] Through this solution, the first role structure type corresponding to the film and television work to be estimated can be determined according to the role proportion of each character in the film and television work to be estimated as determined by the script of the work. The calculation amount is small and the determination efficiency is relatively high.

[0147] See also Figure 5 , is a flow chart of another method for estimating the playback effect of a film or television work provided in an embodiment of the present application. Figure 5 The process shown in the above Figure 1 Based on the process shown, it is described how to analyze the character role structure of the estimated film and television works to obtain multiple characters included in the estimated film and television works and the first role structure types corresponding to the multiple characters. Figure 5 As shown, the process may include the following steps:

[0148] S501, obtaining the script corresponding to the film and television work to be estimated;

[0149] S502, obtaining model prompt words, wherein the model prompt words are used to describe the definitions of various types of play structure;

[0150] S503, inputting the work script and the model prompt words into the large language model, so that the large language model outputs multiple characters included in the film and television work to be estimated and the first role structure types corresponding to the multiple characters.

[0151] The following is a unified description of S501-S503:

[0152] Model prompts, i.e., prompts in GPT, are used to describe the definitions of various types of scene structures. In applications, the definitions of various types of scene structures can prompt the large language model to consider the importance of the characters, their dynamic relationships, character development, and how they drive the plot forward when analyzing.

[0153] As an example, the prompt is: You are a senior script analyst. The character structure usually refers to the importance of each character in the script and the relationship between them. Based on the given script, please determine the character structure of the script and which of the following protagonist settings it belongs to: a female protagonist, a male protagonist, two female protagonists, two male protagonists, a male and female protagonist, a triangle drama, and an ensemble drama.

[0154] The following are definitions of different play structures:

[0155] Heroine: The script is centered around a female character whose storyline and emotional development dominate the plot, and other characters usually revolve around her.

[0156] Male protagonist: In contrast to the female protagonist, the script is centered on a male character, and his story and emotional development dominate the plot.

[0157] Dual Heroines: There are two female characters in the script. Their story lines and emotional development are very important. The plot usually unfolds between them, forming a complementary or antagonistic relationship.

[0158] Dual Male Protagonists: Similar to dual female protagonists, there are two male characters in the script. Their story lines and emotional development are very important, and the plot usually revolves around them.

[0159] Male and female protagonists: There is a male protagonist and a female protagonist in the script, and their story lines and emotional development are very important and usually form the main line of the plot.

[0160] Triangle play: There are three protagonists in the script, usually involving a love or friendship triangle, and the plot revolves around the emotional entanglements and conflicts among these three characters.

[0161] Group drama: There are four or more important characters in the script, and the plot is interwoven through the interaction and story lines of these characters, showing the multifaceted nature of a group or society.

[0162] In the embodiment of the present application, the script (script outline or complete script) and model prompt words are input into the large language model, so that the large language model outputs multiple characters contained in the film and television works to be estimated and the first play structure type corresponding to the multiple characters. Thereby, intelligent analysis of the play structure type of the film and television works to be estimated is realized, and because the large language model analyzes the play structure type, in addition to considering the importance of the characters, it also considers the dynamic relationship between them, the development of the characters, and how they promote the development of the plot, which can make the output result more accurate, thereby improving the accuracy of the subsequent estimated playback effect.

[0163] Based on the same technical concept, the embodiment of the present application also provides a device for predicting the playback effect of a film or television work, such as Figure 6 As shown, the device comprises:

[0164] The structure analysis module 601 is used to perform character role structure analysis on the film and television work to be estimated, and obtain a plurality of roles included in the film and television work to be estimated and a first role structure type corresponding to the plurality of roles;

[0165] A contribution determination module 602 is used to determine a first contribution corresponding to each of the roles in the film and television work to be estimated based on the first role structure type;

[0166] The score acquisition module 603 is used to acquire, for each role, a role playing effect score corresponding to the role;

[0167] The score determination module 604 is used to determine the target playback effect score corresponding to the film and television work to be estimated based on the first contribution degrees and the role playback effect scores corresponding to all the roles.

[0168] In a possible implementation, the structural analysis module is specifically used to:

[0169] Obtaining the script corresponding to the film and television work to be estimated;

[0170] Performing role analysis on the script of the work to obtain multiple roles and the role ratio of each role in the film and television work to be estimated;

[0171] The first role structure type is determined based on the proportion of each character's role in the film and television work to be estimated.

[0172] In a possible implementation, the structural analysis module is further used to:

[0173] Obtaining the script corresponding to the film and television work to be estimated;

[0174] Obtaining model prompt words, wherein the model prompt words are used to describe definitions of various types of play structure;

[0175] The script of the work and the model prompt words are input into the large language model, so that the large language model outputs multiple characters included in the film and television work to be estimated and the first scene structure types corresponding to the multiple characters.

[0176] In a possible implementation manner, the contribution determination module is specifically configured to:

[0177] Acquire contribution weight distribution data corresponding to the first role structure type, wherein the contribution weight distribution data includes a ranking weight corresponding to each ranking;

[0178] For each role, determining the role ranking corresponding to the role in the film and television work to be estimated based on the first role structure type;

[0179] The role ranking weight corresponding to the role ranking is searched in the contribution weight distribution data, and the role ranking weight is determined as the first contribution corresponding to the role.

[0180] In a possible implementation manner, the score acquisition module is specifically configured to:

[0181] Obtain the historical film and television works corresponding to the role and the historical playback effect scores corresponding to the historical film and television works;

[0182] Performing character role structure analysis on the historical film and television work to obtain a second role structure type corresponding to the historical film and television work;

[0183] Based on the second role structure type, determining a second contribution degree corresponding to the character in the historical film or television work;

[0184] The product of the historical playback effect score and the second contribution degree is determined as the role playback effect score.

[0185] In a possible implementation manner, the score acquisition module is further used to:

[0186] Obtaining work introduction data and work evaluation data corresponding to the historical film and television works;

[0187] Obtaining model prompt words, wherein the model prompt words are used to describe definitions of various types of play structure;

[0188] The work introduction data, the work evaluation data and the model prompt words are input into the large language model so that the large language model outputs the second scene structure type corresponding to the historical film and television work.

[0189] In a possible implementation, the score determination module is specifically configured to:

[0190] Substituting the first contribution degrees and the role playback effect scores corresponding to all the roles into Formula 1, to obtain the target playback effect score corresponding to the film and television work to be estimated;

[0191]

[0192] Among them, actors all is the target playback effect score, actor i is the role playing effect score corresponding to role i, w i1 The first contribution corresponding to character i, n is the number of all characters.

[0193] In an embodiment of the present application, first, the character role structure of the film and television work to be estimated is analyzed to obtain multiple characters contained in the film and television work to be estimated and the first role structure type corresponding to the multiple characters. Then, based on the first role structure type, the first contribution degree corresponding to each character in the film and television work to be estimated is determined, and the role playback effect score corresponding to each character is obtained. Finally, based on the first contribution degree and the role playback effect score corresponding to all the characters, the target playback effect score corresponding to the film and television work to be estimated is determined. Compared with the prior art, when estimating the playback effect of the film and television work (such as playback volume, playback income, word-of-mouth rating, etc.), the present application considers the influence of more characters on the playback effect of the film and television work, thereby improving the accuracy of the estimation. Moreover, when determining the contribution of each character to the film and television work, the role structure type of the film and television work is considered. In this way, the accuracy of determining the influence of each character on the playback effect of the film and television work can be improved, thereby further improving the accuracy of the estimation.

[0194] Based on the same technical concept, the embodiment of the present application also provides an electronic device, such as Figure 7 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.

[0195] Memory 113, used for storing computer programs;

[0196] The processor 111 is used to execute the program stored in the memory 113 to implement the following steps:

[0197] Performing character role structure analysis on the film and television work to be estimated, obtaining a plurality of characters included in the film and television work to be estimated and a first role structure type corresponding to the plurality of characters;

[0198] Based on the first role structure type, determining a first contribution degree corresponding to each of the characters in the film and television work to be estimated;

[0199] For each role, obtaining a role playing effect score corresponding to the role;

[0200] Based on the first contribution degrees and the role playback effect scores corresponding to all the roles, a target playback effect score corresponding to the film and television work to be estimated is determined.

[0201] 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.

[0202] The communication interface is used for communication between the above electronic device and other devices.

[0203] 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.

[0204] 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.

[0205] In another embodiment provided in the present application, a computer-readable storage medium is 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 methods for estimating the playback effect of a film or television work are implemented.

[0206] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any of the methods for estimating the playback effect of a film or television work in the above-mentioned embodiments.

[0207] 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.

[0208] 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.

[0209] It should be understood that the terms used herein 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 herein 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.

[0210] 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 method for estimating the playback effect of a film or TV work, characterized in that: The method comprises: Performing character role structure analysis on the film and television work to be estimated, obtaining a plurality of characters included in the film and television work to be estimated and a first role structure type corresponding to the plurality of characters; Based on the first role structure type, determining a first contribution degree corresponding to each of the characters in the film and television work to be estimated; For each role, obtaining a role playing effect score corresponding to the role; Based on the first contribution degrees and the role playback effect scores corresponding to all the roles, a target playback effect score corresponding to the film and television work to be estimated is determined.

2. The method according to claim 1, characterized in that The step of performing character role structure analysis on the film and television work to be estimated to obtain a plurality of characters included in the film and television work to be estimated and a first role structure type corresponding to the plurality of characters includes: Obtaining the script corresponding to the film and television work to be estimated; Performing role analysis on the script of the work to obtain multiple roles and the role ratio of each role in the film and television work to be estimated; The first role structure type is determined based on the proportion of each character's role in the film and television work to be estimated.

3. The method according to claim 1, characterized in that: The step of performing character role structure analysis on the film and television work to be estimated to obtain a plurality of characters included in the film and television work to be estimated and a first role structure type corresponding to the plurality of characters includes: Obtaining the script corresponding to the film and television work to be estimated; Obtaining model prompt words, wherein the model prompt words are used to describe definitions of various types of play structure; The script of the work and the model prompt words are input into the large language model, so that the large language model outputs multiple characters included in the film and television work to be estimated and the first scene structure types corresponding to the multiple characters.

4. The method according to claim 1, characterized in that The determining, based on the first role structure type, a first contribution degree corresponding to each of the characters in the film and television work to be estimated includes: Acquire contribution weight distribution data corresponding to the first role structure type, wherein the contribution weight distribution data includes a ranking weight corresponding to each ranking; For each role, determining the role ranking corresponding to the role in the film and television work to be estimated based on the first role structure type; The role ranking weight corresponding to the role ranking is searched in the contribution weight distribution data, and the role ranking weight is determined as the first contribution corresponding to the role.

5. The method according to claim 1, characterized in that: The obtaining of the role playing effect score corresponding to the role includes: Obtain the historical film and television works corresponding to the role and the historical playback effect scores corresponding to the historical film and television works; Performing character role structure analysis on the historical film and television work to obtain a second role structure type corresponding to the historical film and television work; Based on the second role structure type, determining a second contribution degree corresponding to the character in the historical film or television work; The product of the historical playback effect score and the second contribution degree is determined as the role playback effect score.

6. The method according to claim 5, characterized in that The performing character role structure analysis on the historical film and television work to obtain a second role structure type corresponding to the historical film and television work includes: Obtaining work introduction data and work evaluation data corresponding to the historical film and television works; Obtaining model prompt words, wherein the model prompt words are used to describe definitions of various types of play structure; The work introduction data, the work evaluation data and the model prompt words are input into the large language model so that the large language model outputs the second scene structure type corresponding to the historical film and television work.

7. The method according to claim 1, characterized in that The step of determining a target playback effect score corresponding to the film and television work to be estimated based on the first contribution degrees and the role playback effect scores corresponding to all the roles includes: Substituting the first contribution degrees and the role playback effect scores corresponding to all the roles into Formula 1, to obtain the target playback effect score corresponding to the film and television work to be estimated; Among them, actors all is the target playback effect score, actor i is the role playing effect score corresponding to role i, w i1 The first contribution corresponding to character i, n is the number of all characters.

8. A device for predicting the playing effect of a film or TV work, characterized in that: The device comprises: A structure analysis module, used for performing character role structure analysis on the film and television work to be estimated, and obtaining a plurality of roles included in the film and television work to be estimated and a first role structure type corresponding to the plurality of roles; A contribution determination module, configured to determine, based on the first role structure type, a first contribution corresponding to each of the roles in the film and television work to be estimated; A score acquisition module, used for acquiring, for each role, a role playing effect score corresponding to the role; The score determination module is used to determine the target playback effect score corresponding to the film and television work to be estimated based on the first contribution degrees and the role playback effect scores corresponding to all the roles.

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; The processor is used to implement the method for predicting the playback effect of a film or television work as described in any one of claims 1 to 7 when executing the program stored in the 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 method for predicting the playback effect of a film or television work according to any one of claims 1 to 7 is implemented.