WO2019169979A1

WO2019169979A1 - Film and television works production method, apparatus, and device

Info

Publication number: WO2019169979A1
Application number: PCT/CN2019/073407
Authority: WO
Inventors: 邵帅
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2018-03-09
Filing date: 2019-01-28
Publication date: 2019-09-12
Also published as: CN108549655A; TWI713965B; TW201939322A

Abstract

Disclosed are a film and television works production method, apparatus, and device. The method comprises: analyzing, by means of a pre-trained analysis model, film and television elements input by a user to determine feature attributes corresponding to the film and television elements; then, filtering, from pre-collected video materials, video materials matching the determined feature attributes corresponding to the film and television elements; and further editing the filtered video materials by means of a pre-trained production model and the determined feature attributes corresponding to the film and television elements, thereby obtaining film and television works.

Description

Method, device and device for making film and television works

Cross-reference to related applications

The present application claims priority to Chinese Patent Application No. 201101192606.8, entitled "A Method for Making a Film and Television Work, Apparatus and Apparatus", filed on March 9, 2018, the entire disclosure of which is incorporated by reference. The manner is incorporated herein.

Technical field

The present specification relates to the field of computer technology, and in particular, to a method, device and device for making a film and television work.

Background technique

At present, the development of the film and television industry is very rapid, and a large number of domestic and foreign film and television masterpieces have been played in cinemas and TV stations across the country, thus bringing people a rich and diverse viewing experience.

In practical applications, the production process of a film and television work is more complicated, from scriptwriting, actor selection, shooting to post-production, usually takes a long time to complete. Moreover, the film and television style, performance style, and costume characteristics of a film and television work are often determined by the director, screenwriter, and actor who filmed the film and television work, and because the directors and actors of different users are different, A film and television work is often only favored by some users.

Based on the existing technology, more effective production methods of film and television works are needed.

Summary of the invention

The present specification provides a method for producing a film and television work, which solves the problem that the production method of the prior art film and television works is costly and inefficient, and cannot meet the needs of the user.

This specification provides a method for producing a film and television work, including:

The pre-trained analysis model is used to analyze the film and television elements input by the user, and determine the feature attributes corresponding to the film and television elements;

Filtering video material matching the feature attribute from each of the pre-collected video materials;

The screened video material is arranged by the pre-trained production model and the feature attributes to obtain a movie and television work.

The present specification provides a device for making a film and television work, which solves the problem that the production method of the prior art film and television works is costly and inefficient, and cannot meet the needs of the user.

This specification provides a device for making a film and television work, including:

The analysis module analyzes the film and television elements input by the user through the pre-trained analysis model to determine the feature attributes corresponding to the film and television elements;

a screening module, for filtering video materials matching the feature attributes from each of the pre-collected video materials;

The programming module, through the pre-trained production model and the feature attributes, arranges the selected video material to obtain a film and television work.

The present specification provides a production device for a film and television work, which solves the problem that the production method of the prior art film and television works is costly and inefficient, and cannot meet the needs of the user.

The present specification provides a production apparatus for a movie and television production comprising one or more memories and a processor, the memory storing a program, and configured to perform the following steps by the one or more processors:

Through the pre-trained production model and the feature attributes, the selected video material is arranged to obtain a film and television work.

The above at least one technical solution adopted in the present specification can achieve the following beneficial effects:

In one or more embodiments of the present specification, the video elements input by the user may be analyzed by a pre-trained analysis model to determine the feature attributes corresponding to the video elements, and then filtered out from the pre-collected video materials. The video material matching the characteristic attribute corresponding to the determined film and television element, and then the selected video material is arranged through the pre-trained production model and the determined feature attribute corresponding to the film element to obtain the film and television work.

It can be seen from the above methods that the user can complete the production of the film and television works through the pre-trained analysis model and the production model through the self-selected film and television elements, which not only greatly reduces the production cost of the film and television works, but also improves the film and television production. The production efficiency of the works, at the same time, the film and television works used for the production are based on the user-selected film and television elements. Therefore, the film and television works produced can meet the needs of users well, thus improving the users to a certain extent. Video experience.

DRAWINGS

The drawings described herein are provided to provide a further understanding of the specification, and are intended to be a part of this specification. In the drawing:

FIG. 1 is a schematic diagram of making a film and television work in combination with the determined characteristic attributes provided by the present specification;

2 is a schematic diagram of a process of making a film and television work provided by the present specification;

FIG. 3 is a schematic diagram of adjusting a video image of each actor by a server provided by the present specification; FIG.

4 is a schematic diagram of a device for making a film and television work provided by the present specification;

FIG. 5 is a schematic diagram of a production device of a movie and television work provided by the present specification.

Detailed ways

In this specification, the user can create a desired movie and television work based on his own preferences and needs, as shown in FIG.

FIG. 1 is a schematic diagram of making a film and television work in combination with the determined characteristic attributes provided by the present specification.

As can be seen from Figure 1, the pre-trained analysis model can be used to determine the director's shooting style (such as the black humor, violent aesthetics shown in Figure 1), the actors' facial expressions, body movements and other characteristic attributes, And the feature attributes such as the type of the script and the background of the era, and then the determined feature attributes can be aggregated through the pre-trained production model to produce a film and television work that can reflect these characteristic attributes for the user to watch. .

The execution body for executing the above-mentioned film and television production method may be a terminal such as a computer, or a server, and the user may input a film and television element required for making a film and television work in a terminal such as a mobile phone or a tablet computer, and send it to the terminal through the terminal. server. The server can use the pre-trained analysis model and the production model to produce the film and television works through the film and television elements sent by the terminal. In order to facilitate the subsequent description, the method for producing the movie and television works provided in this specification will be described below only with the server as the execution subject.

In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present specification, in the following one or more embodiments of the present specification, in one or more embodiments of the present specification, The technical solutions are described clearly and completely, and it is obvious that the described embodiments are only a part of the embodiments of the specification, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without departing from the scope of the invention shall fall within the scope of the present disclosure.

FIG. 2 is a schematic diagram of a process for producing a movie and television work provided by the present specification, which specifically includes the following steps:

S200: analyzing, by using a pre-trained analysis model, a video element input by the user, and determining a feature attribute corresponding to the movie element.

In this specification, the user can input the film and television elements in the terminal held by the user, and the terminal can send the film and television elements to the server, so that the server can create the movie and television works of the user through the user-entered elements. Among them, the terminal mentioned here may refer to devices such as a mobile phone, a tablet computer, a desktop computer, and the like.

The terminal can determine the film and television element filled in by the user in the terminal interface as the film and television element input by the user, and can also determine the film and television element selected by the user in the terminal interface as the film and television element input by the user. In practical applications, it is usually necessary to play a script, a director of a film and television production, and an actor to shoot a film and television work. Therefore, the film and television elements mentioned here may include a script selected by the user and a film and television candidate selected by the user. The movie candidate mentioned here may be the director selected by the user, and the user selects at least one actor, wherein the actor mentioned here may refer to the real actor or the virtual actor selected by the user (such as a character in an animation). character).

In practical applications, because the directors that users like are different, and the favorite actors are different, so for the same script, the server can make different users and different users according to different directors and actors selected by the user. The film and television works of appetite, to a certain extent, greatly satisfy the user's viewing requirements, and realize the tailor-made film and television works for the needs of users.

In this specification, the server can include two analysis models, one of which can be used to analyze the script, which can be called the first analysis model, and is used to analyze the feature attributes of the film and television candidates. The model can be called the second analysis model.

Based on this, after the server determines the script selected by the user, the text content of the script can be analyzed through a pre-trained analysis model to determine the feature attribute of the script. The terminal may send the name of the script input by the user to the server, and the server may obtain the text content of the script from the network by using the name of the script. Of course, the terminal may also send the text file of the script uploaded by the user to the server. The server may analyze the text content included in the text file of the script through the first analysis model to determine the feature attribute of the script.

The characteristic attributes of the script mentioned here may include the background of the script, the environment, the type of the work, the relationship of the characters, the characteristics of the characters, and the status of the characters (the so-called role status refers to which characters are the protagonists and which are the supporting roles in the script). The atmosphere of the plot, etc. The server can subsequently filter the video material through the determined feature attributes to make the film and television production.

Similarly, in the present specification, the server may analyze the director selected by the user through the second analysis model to determine the feature attribute corresponding to the director. Specifically, after the server determines the director selected by the user, the director can obtain the film and television work of the director from the network. Then, the server can analyze the film and television work of the director through the second analysis model to determine the feature attribute corresponding to the director. The feature attributes corresponding to the director mentioned herein may include: a shooting style, a narrative means, and the like.

It should be noted that in practical applications, the filming styles and the narrative methods used by a film and television film produced by a director may be different. Therefore, the server can analyze the various film and television works of the director through the second analysis model to determine the narrative means used by the director to shoot each film and television work and the shooting style reflected. Then, the server can count the number of film and television works corresponding to different shooting styles, and the number of film and television works taken by different narrative methods, and then determine the most commonly used narrative means of the director and the most obvious shooting style of the director.

In the present specification, after determining the at least one actor selected by the user, the server may determine the feature attribute corresponding to each actor through the second analysis model. Specifically, the server determines, according to each actor selected by the user, the movie and television works of the actor from the network for each actor, and then inputs the film and television works into the second analysis model to determine that the actor corresponds to Feature attribute.

Wherein, the feature attributes corresponding to the actor mentioned herein include: a limb feature, a character type, a voiceprint feature, a facial expression parameter (the facial expression parameter is used to represent an actor's facial features under different expressions), and the like.

It should be noted that, in this specification, the server needs to train the analysis model before using the above analysis model (including the first analysis model and the second analysis model). Specifically, the staff training the analysis model can pre-collect some film and television elements (including various scripts, directors, actors, etc.) as sample film and television elements, and manually mark the characteristic attributes corresponding to the sample film and television elements. Then, the sample film and television elements can be input into the analysis model to be trained included in the server, and the analysis model is trained by combining the feature attributes corresponding to the marked sample film and television elements.

S202: Filter video material that matches the feature attribute from each of the pre-collected video materials.

In the present specification, the server includes a large amount of video material collected in advance, and based on this, after determining the feature attribute corresponding to the video element selected by the user, the server may collect the video material according to the determined feature attribute from the pre-collected video material. In the process, the video material matching the determined feature attribute is filtered, and in the subsequent process, the video material is produced through the selected video material.

Among them, for a film and television work, its various backgrounds, environments, etc. should be closely related to the script itself. Therefore, the server can determine each video material that matches the feature attributes (such as the background of the era, the environment, and the plot atmosphere) of the script from the pre-collected plurality of video materials based on the determined feature attributes of the script.

Of course, in the present specification, the server may also filter the video material matching the feature attribute corresponding to the actor from a plurality of pre-collected video materials according to the determined feature attribute corresponding to the actor, so as to be determined in the subsequent process. The video images of the actors contained in these video materials are produced to produce film and television works.

S204: The screened video material is arranged through a pre-trained production model and the feature attribute to obtain a movie and television work.

The server can arrange the selected video materials according to the determined feature attributes corresponding to the respective movie elements through the pre-trained production model to produce the film and television works. Specifically, for a script, because of the different narrative methods and shooting styles of different directors, the final sequence of the film and television works in the narrative script will also differ in the order of the plots.

Based on this, in the present specification, the content layout model of the script can be determined by the production model, the determined feature attribute corresponding to the script, and the feature attribute corresponding to the director, and then according to the determined content layout mode of the script. , the selected video material is arranged to obtain the first film and television work.

In other words, the server can determine in which form the script development order, content focus, and the like should be presented by the server through the production model, combined with the feature attributes corresponding to the script and the feature attributes corresponding to the director. The sequence of the story development and the content focus of the script mentioned here are the content arrangement mode of the script mentioned here.

After the server determines the first movie and television work, the video image of the determined at least one actor may be further added to the first film and television work according to the content arrangement mode of the script to obtain a second film and television work. The video image of the at least one actor may be selected by the server from a plurality of pre-collected video materials according to the determined feature attributes corresponding to each actor.

The roles of a film and television work will appear at different moments in the film and television work along with the sequence of development of the film and television work. Since a script is filmed into a film and television work by the director, the sequence of the story development, the content focus, etc. will change with respect to the original story development order and content focus of the script. Accordingly, each character in the script is in the script. The moments that appear in it will also change.

Therefore, the server can determine, at each role in the script, the moments at which the character appears in the script through the first analysis model described above. Then, the server may determine, according to the determined feature attribute of each character in the script, the determined attribute of each actor selected by the user and each character in the script, and determine the corresponding relationship by using the production model. Each actor selected by the user should be at each moment in the script in the content arrangement mode.

The corresponding relationship between each actor selected by the user and the roles in the script may be determined by the server according to the correspondence between each actor selected by the user and each character in the script. After analyzing the script through the first analysis model, the server may display the characters in the script, the relationship between the characters, and the role status of each character (such as a protagonist, a supporting role, etc.) through the terminal. The user can input the actors corresponding to the roles in the terminal based on the role status of each role displayed by the server to the user through the terminal, so that the server determines the correspondence between the actors selected by the user and the roles in the script.

The server may add a video image corresponding to each actor to the first film and television work according to each moment that appears in the script in the content arrangement mode by each actor selected by the user to obtain the second film and television work. That is, on the basis of obtaining the first film and television work, the server may add, for each actor, the video image of the actor to the character corresponding to the actor corresponding to the actor according to the scenario development sequence of the script. At the moment.

Of course, in the present specification, the server may further determine a new script in the content arrangement mode after determining the content arrangement mode of the script, and input the new script into the first analysis model to determine The moments of the roles in the new script, and then determine the first film and television work corresponding to each actor in the new script (because the new script and the first film and television work are based on the content layout mode, Therefore, each moment that appears in the first film and television work corresponds to the new script.

For a film and television work, the actors' physical movements, facial expressions, etc. will be different in the different plot atmospheres of the film and television works. Therefore, in the present specification, the server may, for each actor, according to the determined role of the actor in the script, the character corresponding to the role of the actor in the script in the content arrangement mode, and the The character corresponding to the actor appears in the state of appearance at each moment in the script, and determines the appearance state of the actor at each moment in the film and television work. Among them, the topography state mentioned here is used to represent what kind of physical movements, facial expressions, etc. the actor should be in at a moment in the film and television work. The server can analyze the script through the first analysis model, and determine the appearance state of each character in the script at each moment as the feature attribute of the script.

For example, if it is determined that in the section of the second film and television work, the atmosphere of the plot is in a state of tension, it can be determined that the character corresponding to the character corresponding to the character in the paragraph should be in a state of nervous expression and dignity. .

After the server determines the appearance state of each actor in each moment of the second film and television work, the server can adjust the shape of the video image of each actor according to the determined feature attributes corresponding to each actor.

Wherein, before the server, the second analysis model can determine the facial expression parameters of the actors under different emotions, and then, according to the production model, according to the determined facial expression parameters of the actors under different emotions, Each actor adjusts the face when appearing in the second film and television work to adapt to the plot atmosphere. In the same way, the physical movements of the actors in different plot atmospheres in the second film and television works can also be adjusted based on the determined physical characteristics of the actors, as shown in FIG.

FIG. 3 is a schematic diagram of adjusting the video image of each actor by the server provided in the present specification.

Assuming that the server determines that the character A corresponding to the actor A appears at the time A in the second film and television production, one frame of the video image of the actor A can be added to the time A of the second film and television work. After that, the server can determine, according to the determined plot atmosphere of the script and the sequence of the plot development, that the actor A should be in a state of anger and striding forward at the time A, and then based on the determined actor A. The facial expression parameter, the limb feature, and the like, the actor A adjusts the frame video image at time A to obtain the adjusted video image of the actor A.

After adjusting the appearance state of each actor in the second film and television works at each moment, the server may perform processing such as soundtrack and subtitles on the adjusted second film and television work, thereby obtaining the final film and television work, and returning to the film and television works. The user is watching.

The server may translate the text content of the script into the text corresponding to the language selected by the user through the first analysis model, and determine the lines corresponding to the roles. Then, according to each moment that each character appears in the second film and television work (or the first film and television work), the moments corresponding to the characters corresponding to the characters in the second film and television work (or the first film and television work) may be determined. And converting each word into a subtitle, and adding it to each corresponding moment of the second film and television work (or the first film and television work).

The server may determine, according to the determined plot atmospheres included in the script, the soundtrack materials that match the plot atmospheres from the pre-collected music materials, and then, in accordance with each plot atmosphere, the second film and television works. The moments appearing in the moment are added to the second film and television work.

It should be noted that the production model mentioned above may be a staff member who trains the production model, and pre-selects the sample feature attributes corresponding to the sampled film and television elements of the mark and the standard film and television works corresponding to the collected sample film and television elements. Train the production model. For example, suppose that the production model worker trains the feature attributes corresponding to director A, actor B, C, and D by manual means, and the actors B, C, and D are photographed by the director A found in the network. The film and television works are performed as standard film and television works. The staff can train the production model based on the determined characteristic attributes and the standard film and television work.

Since the script may involve a large number of characters, such as the army, the people in the downtown, etc., the server may select some character materials according to the feature attributes of the script from the pre-collected character materials, and then correspondingly the character materials. The video image is added to the appropriate moments in the second film and television production (or the first film and television production).

The above is a method for making a movie and television work provided by one or more embodiments of the present specification. Based on the same idea, the present specification also provides a corresponding device for making a film and television work, as shown in FIG. 4 .

4 is a schematic diagram of a device for making a movie and television work provided by the present specification, which specifically includes:

The analyzing module 401 analyzes the film and television elements input by the user through the pre-trained analysis model, and determines the feature attributes corresponding to the film and television elements;

The screening module 402 is configured to filter video materials that match the feature attributes from each of the pre-collected video materials;

The programming module 403, through the pre-trained production model and the feature attributes, arranges the selected video material to obtain a movie and television work.

The device also includes:

The first training module 404 trains the analysis model by using the pre-collected sample film elements and the marked feature attributes corresponding to the sample film elements.

The film and television element input by the user includes: a script selected by the user and a film and television candidate selected by the user; the film and television candidate includes: at least one of a director selected by the user and at least one selected by the user;

The analysis model includes: a first analysis model and a second analysis model.

The analyzing module 401, when the movie element is a script selected by the user, analyzing the script by using the first analysis model to determine a feature attribute corresponding to the script; When the element is the director selected by the user, determining the film and television work of the director, analyzing the film and television work of the director through the second analysis model to determine a feature attribute corresponding to the director; When the element is at least one actor selected by the user, the actor's movie and television work is determined for each actor selected by the user, and the actor's film and television work is analyzed by the second analysis model to determine the The feature attribute corresponding to the actor.

The orchestration module 403 determines a content arrangement mode of the script by using the production model, a feature attribute corresponding to the script, and a feature attribute corresponding to the director; and filtering the content according to the content arrangement mode of the script The video material is arranged to obtain a first film and television work; according to the content arrangement mode of the script, the determined video image of the at least one actor is added to the first film and television work to obtain a second film and television work; a video image of each actor in the second film and television work, adjusting the video image of the actor according to the content arrangement mode of the script and the determined feature attribute corresponding to the actor, and adjusting the second film and television work As a production of film and television works.

The feature attributes corresponding to the script include: each moment in which each character appears in the script;

The orchestration module 403, for each actor, determines a role corresponding to the actor in the script according to the determined correspondence between the at least one actor selected by the user and each character in the script; Each time of each character appearing in the script, and the corresponding characters of the at least one actor in the script, determining, by the production model, a script of the at least one actor in the content arrangement mode Each moment occurring in the scene; adding, according to the determined moments of the at least one actor in the script in the content arrangement mode, the video image of the at least one actor in the first film and television work , get the second film and television works.

The feature attribute corresponding to the script further includes: a state of appearance of each character in the script at each moment;

The orchestration module 403, for each actor, according to the determined role of the actor in the script, the moments of the characters in the script in the script in the content arrangement mode, and the Depicting the state of appearance of each character in the script at each moment, determining the appearance state of the actor at each moment in the second film and television work; according to the determined shape of the actor in each moment of the second film and television work The appearance state, and the feature attribute corresponding to the actor, the topographical adjustment of the actor's video image.

The device also includes:

The second training module 405 trains the production model by pre-marking each sample feature attribute corresponding to each sample film element and the collected standard film and television works corresponding to the sample film and television elements.

The first training module 404 and the second training module 405 may also be a module for training the model to be trained, including the analysis model and the production model.

Based on the above-described method for producing a film and television work, the present specification also provides a device for making a film and television work, as shown in FIG. The device includes one or more memories and a processor that stores the program and is configured to perform the following steps by the one or more processors:

In one or more embodiments of the present specification, the video elements input by the user may be analyzed by a pre-trained analysis model to determine the feature attributes corresponding to the video elements, and then filtered from the pre-collected video materials. The video material matching the characteristic attribute corresponding to the determined film and television element is outputted, and the selected video material is arranged through the pre-trained production model and the determined feature attribute corresponding to the film and television element to obtain the film and television work.

In the 1990s, improvements to a technology could clearly distinguish between hardware improvements (eg, improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (for process flow improvements). However, as technology advances, many of today's method flow improvements can be seen as direct improvements in hardware circuit architecture. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented by hardware entity modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic function is determined by the user programming the device. Designers program themselves to "integrate" a digital system on a single PLD without having to ask the chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, today, instead of manually making integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in programming development, but before compiling The original code has to be written in a specific programming language. This is called the Hardware Description Language (HDL). HDL is not the only one, but there are many kinds, such as ABEL (Advanced Boolean Expression Language). AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should also be apparent to those skilled in the art that the hardware flow for implementing the logic method flow can be easily obtained by simply programming the method flow into the integrated circuit with a few hardware description languages.

The controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor. In the form of logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic. Those skilled in the art will also appreciate that in addition to implementing the controller in purely computer readable program code, the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding. The form of a microcontroller or the like to achieve the same function. Such a controller can therefore be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component. Or even a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.

The system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.

For the convenience of description, the above devices are described separately by function into various units. Of course, the functions of the various units may be implemented in one or more software and/or hardware in the implementation of the present specification.

Those skilled in the art will appreciate that embodiments of the present specification can be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware. Moreover, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

This description is described with reference to flowchart illustrations and/or block diagrams of a method, a device (system), and a computer program product according to one or more embodiments of the present specification. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory. Memory is an example of a computer readable medium.

Computer readable media includes both permanent and non-persistent, removable and non-removable media. Information storage can be implemented by any method or technology. The information can be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.

It is also to be understood that the terms "comprises" or "comprising" or "comprising" or any other variations are intended to encompass a non-exclusive inclusion, such that a process, method, article, Other elements not explicitly listed, or elements that are inherent to such a process, method, commodity, or equipment. An element defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device including the element.

This description can be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including storage devices.

The various embodiments in the specification are described in a progressive manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

The foregoing description of the specific embodiments of the specification has been described. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than the embodiments and still achieve the desired results. In addition, the processes depicted in the figures are not necessarily in a particular order or in a sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The above description is only one or more embodiments of the present specification, and is not intended to limit the present specification. One or more embodiments of the present disclosure can be variously changed and changed by those skilled in the art. Any modifications, equivalents, improvements, etc. made within the spirit and scope of the present invention are intended to be included within the scope of the appended claims.

Claims

A method for making a film and television work, comprising:

The pre-trained analysis model is used to analyze the film and television elements input by the user, and determine the feature attributes corresponding to the film and television elements;

Filtering video material matching the feature attribute from each of the pre-collected video materials;

Through the pre-trained production model and the feature attributes, the selected video material is arranged to obtain a film and television work.
The method of claim 1, training the analysis model, specifically comprising:

The analysis model is trained by pre-collecting each sample film element and the marked feature attributes corresponding to the sample film elements.
The method of claim 1, wherein the user-entered film and television element comprises: a user-selected script and a user-selected film and television candidate; the film and television candidate comprises: at least one of a user-selected director and at least one actor selected by the user. Species

The analysis model includes: a first analysis model and a second analysis model.
The method of claim 3, wherein the user-entered video and television elements are analyzed by a pre-trained analysis model to determine feature attributes corresponding to the video elements, including:

When the movie element is a script selected by the user, the script is analyzed by the first analysis model to determine a feature attribute corresponding to the script;

When the movie element is the director selected by the user, determining the film and television work of the director, analyzing the film and television work of the director through the second analysis model to determine a feature attribute corresponding to the director;

When the movie element is at least one actor selected by the user, determining, for each actor selected by the user, a movie and television work of the actor, and analyzing the actor's film and television work through the second analysis model To determine the feature attribute corresponding to the actor.
The method of claim 4, the screened video material is arranged by the pre-trained production model and the feature attribute, and the film and television work is obtained, which specifically includes:

Determining a content arrangement mode of the script by using the production model, a feature attribute corresponding to the script, and a feature attribute corresponding to the director;

According to the content arrangement mode of the script, the selected video material is arranged to obtain the first film and television work;

Adding, according to the content arrangement mode of the script, the determined video image of the at least one actor in the first film and television work to obtain a second film and television work;

And for the video image of each actor in the second movie and television work, adjusting the video image of the actor according to the content arrangement mode of the script and the determined feature attribute corresponding to the actor, and adjusting the second image Film and television works as production of film and television works.
The method according to claim 5, wherein the feature attribute corresponding to the script comprises: each moment in which each character in the script appears;

And adding, according to the content arrangement mode of the script, the determined video image of the at least one actor in the first film and television work to obtain the second film and television work, specifically comprising:

Determining, by each actor, a role corresponding to the actor in the script according to the determined correspondence between the at least one actor selected by the user and each character in the script;

Determining, by the production model, the at least one actor in the content arrangement mode according to the determined moments of occurrence of each character in the script, and the respective roles of the at least one actor in the script The moments that appear in the script;

And adding, according to the determined moments of the at least one actor in the script in the content arrangement mode, the video image of the at least one actor in the first film and television work to obtain a second film and television work.
The method according to claim 6, wherein the feature attribute corresponding to the script further comprises: a state of appearance of each character in the script at each moment;

For the video image of each of the actors in the second film and television work, the video image of the actor is adjusted according to the content arrangement mode of the script and the determined feature attribute corresponding to the actor, and specifically includes:

For each actor, according to the determined role of the actor in the script, the moments in which the characters in the script appear in the script in the content arrangement mode, and the roles in the script The state of appearance at each moment determines the appearance state of the actor at each moment in the second film and television work;

The morphological adjustment of the video image of the actor is performed according to the determined appearance state of the actor at each moment in the second film and television work and the feature attribute corresponding to the actor.
The method of claim 1, training the production model, specifically comprising:

The production model is trained by pre-marking each sample feature attribute corresponding to each sample film element and the collected standard film and television work corresponding to each sample film element.
A production device for a film and television work, comprising:

The analysis module analyzes the film and television elements input by the user through the pre-trained analysis model to determine the feature attributes corresponding to the film and television elements;

a screening module, for filtering video materials matching the feature attributes from each of the pre-collected video materials;

The programming module, through the pre-trained production model and the feature attributes, arranges the selected video material to obtain a film and television work.
The device of claim 9 further comprising:

The first training module trains the analysis model by pre-collecting each sample film element and the marked feature attributes corresponding to the sample film elements.
The device of claim 9, wherein the user-entered film and television element comprises: a user-selected script and a user-selected film and television candidate; and the film and television candidate comprises: at least one of a user-selected director and at least one actor selected by the user. Species

The analysis model includes: a first analysis model and a second analysis model.
The apparatus according to claim 11, wherein the analysis module, when the movie element is a script selected by the user, analyzes the script by the first analysis model to determine that the script corresponds to a feature attribute; when the movie element is a director selected by the user, determining the film and television work of the director, analyzing the film and television work of the director through the second analysis model to determine that the director corresponds to a feature attribute; when the movie element is at least one actor selected by the user, determining, for each actor selected by the user, a movie and television work of the actor, and using the second analysis model, the actor's The film and television work is analyzed to determine the feature attributes corresponding to the actor.
The apparatus according to claim 12, wherein the orchestration module determines a content arrangement mode of the script by the production model, a feature attribute corresponding to the script, and a feature attribute corresponding to the director; a content arrangement mode, the selected video material is arranged to obtain a first film and television work; and the determined video image of the at least one actor is added to the first film and television work according to the content arrangement mode of the script, Obtaining a second film and television work; for the video image of each of the actors in the second film and television work, adjusting the video image of the actor according to the content arrangement mode of the script and the determined feature attribute corresponding to the actor, and The adjusted second film and television work will be used as the film and television production.
The apparatus according to claim 13, wherein the feature attribute corresponding to the script comprises: each moment in which each character in the script appears;

The orchestration module determines, according to the determined correspondence between the at least one actor selected by the user and each character in the script, for each actor, according to the determined role of the actor in the script; Each moment in which the characters appear in the script, and the respective characters of the at least one actor in the script, determine, by the production model, the at least one actor in the script in the content arrangement mode Each moment of occurrence; adding, according to the determined moments of the at least one actor in the script in the content arrangement mode, the video image of the at least one actor in the first film and television work, Get the second film and television production.
The device according to claim 14, wherein the feature attribute corresponding to the script further comprises: a state of appearance of each character in the script at each moment;

The orchestration module, for each actor, according to the determined role of the actor in the script, the moments in which the characters in the script appear in the script in the content arrangement mode, and the a state of appearance of each character in the script at each moment, determining a state of appearance of the actor at each moment in the second film and television work; according to the determined appearance of the actor in each moment of the second film and television work The state, and the feature attribute corresponding to the actor, adjusts the shape of the actor's video image.
The device of claim 9 further comprising:

The second training module trains the production model by pre-marking each sample feature attribute corresponding to each sample film element and the collected standard film and television works corresponding to the sample film and television elements.
A production device for a movie and television production, the device comprising one or more memories and a processor, the memory storing the program and configured to perform the following steps by the one or more processors:

The pre-trained analysis model is used to analyze the film and television elements input by the user, and determine the feature attributes corresponding to the film and television elements;

Filtering video material matching the feature attribute from each of the pre-collected video materials;

Through the pre-trained production model and the feature attributes, the selected video material is arranged to obtain a film and television work.