CN114860995B

CN114860995B - Video script generation method and device, electronic equipment and medium

Info

Publication number: CN114860995B
Application number: CN202210781581.1A
Authority: CN
Inventors: 刘家辰; 肖欣延; 李伟; 佘俏俏; 吴甜; 吕雅娟
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-07-05
Filing date: 2022-07-05
Publication date: 2022-09-06
Anticipated expiration: 2042-07-05
Also published as: CN114860995A

Abstract

The present disclosure provides a video script generation method, device, electronic device and medium, which relate to the technical field of artificial intelligence such as computer vision, natural language processing, deep learning, and in particular to scenes such as human-computer interaction and intelligent creation. The implementation scheme is as follows: extracting a plurality of text units from the at least one original text in response to determining the at least one original text, wherein the text content in each text unit has coherent semantics; determining a structural framework of the video script based on a logical relationship among the text units, wherein the structural framework comprises a plurality of structural units with a time sequence relationship, and each structural unit corresponds to at least one text unit; and generating a video script based on the structural framework.

Description

Video script generation method and device, electronic equipment and medium

Technical Field

The present disclosure relates to the field of artificial intelligence technologies such as computer vision, natural language processing, deep learning, and the like, and in particular, to a method and an apparatus for generating a video script, an electronic device, a computer-readable storage medium, and a computer program product.

Background

Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge map technology and the like.

The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, unless otherwise indicated, the problems mentioned in this section should not be considered as having been acknowledged in any prior art.

Disclosure of Invention

The disclosure provides a method and a device for generating a video script, an electronic device, a computer readable storage medium and a computer program product.

According to an aspect of the present disclosure, there is provided a video script generation method, including: extracting a plurality of text units from the at least one original text in response to determining the at least one original text, wherein the text content in each text unit has coherent semantics; determining a structural framework of the video script based on a logical relationship among the text units, wherein the structural framework comprises a plurality of structural units with a time sequence relationship, and each structural unit corresponds to at least one text unit; and generating a video script based on the structural framework.

According to an aspect of the present disclosure, there is provided a video script generating apparatus including: an extraction module configured to extract a plurality of text units from the at least one original text in response to determining the at least one original text, wherein text content in each text unit has coherent semantics; a first determining module configured to determine a structural framework of the video script based on a logical relationship between a plurality of text units, wherein the structural framework comprises a plurality of structural units having a time-series relationship, and each structural unit corresponds to at least one text unit; and a generation module configured to generate a video script based on the structural framework.

According to an aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described above.

According to an aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the above-described method.

According to an aspect of the disclosure, a computer program product is provided, comprising a computer program, wherein the computer program realizes the above-mentioned method when executed by a processor.

According to one or more embodiments of the disclosure, a plurality of text units from original texts can be automatically organized together to obtain a final video script, automatic generation of the video script is realized, and large-scale and high-quality video production can be supported.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the embodiments and, together with the description, serve to explain the exemplary implementations of the embodiments. The illustrated embodiments are for purposes of illustration only and do not limit the scope of the claims. Throughout the drawings, identical reference numbers designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, according to an embodiment of the present disclosure;

FIG. 2 shows a flow diagram of a video script generation method according to an embodiment of the present disclosure;

FIG. 3 shows a schematic diagram of a method of determining at least one original text according to an embodiment of the present disclosure;

4A-4D illustrate schematic diagrams of a structural framework of a video script according to an embodiment of the present disclosure;

FIG. 5 shows a block diagram of a video script generation apparatus according to an embodiment of the present disclosure; and

FIG. 6 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, it will be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the present disclosure, unless otherwise specified, the use of the terms "first", "second", and the like to describe various elements is not intended to limit the positional relationship, the temporal relationship, or the importance relationship of the elements, and such terms are used only to distinguish one element from another. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, based on the context, they may also refer to different instances.

The terminology used in the description of the various examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element may be one or a plurality of. Furthermore, the term "and/or" as used in this disclosure is intended to encompass any and all possible combinations of the listed items.

Under the current internet environment, video content is the mainstream of content consumption of users, and particularly after the short video is started, the consumption of the video content occupies most of the time of content consumption of internet users. Therefore, how to improve the video generation efficiency while ensuring the video quality is a core difficulty of video creation.

In general, video production requires first generating a video script that functions in video production similar to a "script" of a movie. And (3) based on the video script, executing steps of visual material design, shooting, dubbing, video synthesis and the like, and finally generating the video.

In the current mainstream video production technology, video scripts mostly require the investors to complete the design by themselves. The mode can not release manpower, greatly restricts the efficiency of video production, and can not support large-scale high-efficiency video production.

Based on the above, the present disclosure provides a video script generation method, which determines a structural framework of a video script based on a logical relationship between a plurality of text units extracted from at least one original text, and generates the video script based on the structural framework. Therefore, a plurality of text units in the original text can be automatically organized together to generate a final video script, the automatic generation of the video script is realized, and large-scale and high-quality video production can be supported.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented in accordance with embodiments of the present disclosure. Referring to fig. 1, the system 100 includes one or

more client devices

101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120.

Client devices

101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

In embodiments of the present disclosure, the server 120 may run one or more services or software applications that enable the method of video script generation to be performed.

In some embodiments, the server 120 may also provide other services or software applications, which may include non-virtual environments and virtual environments. In certain embodiments, these services may be provided as web-based services or cloud services, for example, provided to users of

client devices

101, 102, 103, 104, 105, and/or 106 under a software as a service (SaaS) model.

In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof, which may be executed by one or more processors. A user operating a

client device

101, 102, 103, 104, 105, and/or 106 may, in turn, utilize one or more client applications to interact with the server 120 to take advantage of the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from system 100. Accordingly, fig. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

The user may use

client device

101, 102, 103, 104, 105, and/or 106 to obtain at least one original text. The client device may provide an interface that enables a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that any number of client devices may be supported by the present disclosure.

Client devices

101, 102, 103, 104, 105, and/or 106 may include various types of computer devices, such as portable handheld devices, general purpose computers (such as personal computers and laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, and so forth. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux, or Linux-like operating systems (e.g., GOOGLE Chrome OS); or include various Mobile operating systems such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular telephones, smart phones, tablets, Personal Digital Assistants (PDAs), and the like. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. The gaming system may include a variety of handheld gaming devices, internet-enabled gaming devices, and the like. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), Short Message Service (SMS) applications, and may use a variety of communication protocols.

Network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. By way of example only, one or more networks 110 may be a Local Area Network (LAN), an ethernet-based network, a token ring, a Wide Area Network (WAN), the internet, a virtual network, a Virtual Private Network (VPN), an intranet, an extranet, a blockchain network, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (e.g., bluetooth, WIFI), and/or any combination of these and/or other networks.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture involving virtualization (e.g., one or more flexible pools of logical storage that may be virtualized to maintain virtual storage for the server). In various embodiments, the server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above, as well as any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, and the like.

In some implementations, the server 120 may include one or more applications to analyze and consolidate data feeds and/or event updates received from users of the

client devices

101, 102, 103, 104, 105, and/or 106. Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of

client devices

101, 102, 103, 104, 105, and/or 106.

In some embodiments, the server 120 may be a server of a distributed system, or a server incorporating a blockchain. The server 120 may also be a cloud server, or a smart cloud computing server or a smart cloud host with artificial intelligence technology. The cloud Server is a host product in a cloud computing service system, and is used for solving the defects of high management difficulty and weak service expansibility in the traditional physical host and Virtual Private Server (VPS) service.

The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The database 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The database 130 may be of different types. In certain embodiments, the database used by the server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data to and from the database in response to the command.

In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key-value stores, object stores, or regular stores supported by a file system.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with this disclosure.

Fig. 2 shows a flowchart of a video script generation method according to an exemplary embodiment of the present disclosure, and as shown in fig. 2, the method 200 includes: step S201, in response to the fact that at least one original text is determined, a plurality of text units are extracted from the at least one original text, wherein text content in each text unit has coherent semantics; step S202, determining a structural framework of the video script based on a logical relationship among a plurality of text units, wherein the structural framework comprises a plurality of structural units with a time sequence relationship, and each structural unit corresponds to at least one text unit; and step S203, generating a video script based on the structural framework.

Therefore, a plurality of text units in the original text can be automatically organized together to obtain the final video script, the automatic generation of the video script is realized, and the large-scale and high-quality video production can be supported.

The video in the disclosure may be a relatively short video created by a user, a professional user, or a professional organization on an internet content consumption platform, the video script in the disclosure is a script specially used for generating the video, and the content in the video script may not only be limited to a text, but also include contents such as an image and a video.

The original text may be a sentence, a paragraph, or a text chapter. Each extracted text unit has coherent semantics and can be used as the minimum executable unit to execute the subsequent generation process of the video script, so that the content coherence of the video script is ensured.

According to some embodiments, the at least one original text is text content entered by the user for generating the video script.

According to further embodiments, the at least one original text is searched based on a video topic. Therefore, the requirement for the user to input the content can be reduced, and meanwhile, the content richness of the video script is improved.

For example, the video title determined based on user input is "first noon war". Based on the first noon war, a plurality of retrieval sentences can be constructed, such as the historical background of the first noon war, the process of the first noon war, the influence of the first noon war, the comment of the first noon war and the like. And searching in a preset material library by using the generated retrieval sentences to obtain at least one original text for generating the video script.

Whether the original text needs to be searched or not can be determined in advance or can be determined according to the input content of the user.

Fig. 3 is a schematic diagram illustrating a method for determining at least one original text according to an exemplary embodiment of the disclosure, which includes the following specific steps:

step S310, a user inputs text content 301 and setting parameters 302, wherein the setting parameters 302 comprise video duration requirements corresponding to the video scripts. It is determined whether content expansion needs to be performed on the basis of the text content 301 input by the user according to the setting parameter 302. For example, the text content 301 is a complete graphic text, and it is determined that content expansion is not necessary in anticipation of being able to generate a video script based on the text content 301. As another example, the text content 301 is not sufficient to support a video script that meets the video duration requirement of the setting parameter 302, and it is determined that content expansion is required. In case content expansion is needed, step S320 is further executed, and in case content expansion is not needed, the text content 301 is directly used as at least one original text 303 for generating a video script.

Step S320, constructing a plurality of search sentences based on the video topic determined by the text content 301 input by the user.

Step S330, searching in a material library respectively by using the plurality of constructed retrieval sentences to obtain at least one original text 303 for generating the video script. The material library is pre-established based on content expansion requirements in the video script generation process, and comprises various forms of encyclopedias, books, webpages and the like.

Therefore, under the condition that the text content 301 is insufficient, at least one original text 303 which is enough to support the generation of the video script can be obtained through searching in the material library, the requirement on the text content 301 input by a user is reduced, and meanwhile, the content richness of the video script is improved.

According to some embodiments, extracting a plurality of text units from at least one original text comprises: identifying redundant content in at least one original text; and extracting a plurality of text units from the text content of the at least one original text except the redundant content. Therefore, redundant contents which are not suitable for the video script can be filtered in advance, the data processing amount in the video script generating process is reduced, and the quality of the video script is improved.

Wherein the redundant content is content unsuitable for video scripts, for example, content that does not include valuable information, such as advertisements, concerns, and the like; repeating the contents of the table definition; the legend of the picture, etc.

Illustratively, the legend for the pictures contained in the original text may be, for example, "X month X number XX news reporter XXX was shot in XXX" and the legend text is not applicable in the video script. In one embodiment, the legends may be identified by a constructed rule (e.g., a sentence without punctuation, with a date, and with a "shoot" word eye); in another embodiment, the original text legend may also be identified by a trained model.

It is understood that other types of redundant content can be identified by methods similar to the two embodiments described above, and are not described in detail herein.

According to some embodiments, the logical relationship between the plurality of text units can be determined by any one of: for at least two text units from the same original text in a plurality of text units, determining a logical relationship between the at least two text units based on the corresponding sections of each of the at least two text units in the original text; and determining a logical relationship between the plurality of text units based on the pragmatic type corresponding to each of the plurality of text units. Thereby, the logical relationship between the plurality of text units can be automatically determined.

The original text has a semantic logical chapter structure. By identifying the title, the number and the like of each text unit in the original text, the corresponding chapter of the text unit in the original text can be determined, and the logical relationship between at least two text units can be determined by the logical property of the chapter structure of the original text.

For example, text element 1 and text element 2 are from the second chapter of the original text, and text element 3 is from the third chapter of the original text, whereby it can be inferred that text element 3 has a logical dependency on text element 1 and text element 2. In a video script, the content of text element 3 should appear after the content of text elements 1 and 2.

A pragmatic type is a higher level of abstraction than a semantic type for language understanding. In the video script generation process, the pragmatic type refers to the "role" each text unit plays in the video script.

The different pragmatic type classification modes are related to different video script types, for example, pragmatic types such as "event", "background", "comment", "quote", "data" and the like can be used for planning video scripts of event types, and pragmatic types such as "import", "content", "transition", "turn", "end" and the like can be used for planning video scripts of story types.

It is to be understood that the pragmatic type may be considered a type of label for a text unit. For example, of 5 original texts for a certain historical event, 2 original texts relate to the background of the historical event, and 3 original texts relate to comments on the historical event. According to the pragmatic type label of each text unit in the 5 original texts, the determination of which text unit of which original text relates to the background and which text unit of which original text relates to the comment can be conveniently determined, and therefore the determination of the structural framework of the subsequent video script is effectively supported.

According to some embodiments, for each of a plurality of text units, a pragmatic classification model is input to the text unit, and a pragmatic type corresponding to the text unit can be obtained, wherein the pragmatic classification model is obtained by training a text with pragmatic labels.

It can be understood that after the logical relationship among the text units is determined, the text units can be combined and sequenced according to the logical relationship to form a structural framework of the video script, so that the video script can sequentially present the text contents in the text units according to the logical relationship among the text units, and the situations of logic confusion, incoherence and the like of the automatically generated video script are avoided.

According to some embodiments, the structural frame comprises at least one of the following structural types: a parallel structure; a layered structure; or a progressive configuration.

4A-4D show schematic diagrams of a structural framework of a video script according to an exemplary embodiment of the present disclosure.

Fig. 4A shows a structural framework of a parallel structure, wherein a structural unit 411, a structural unit 412 and a structural unit 413 can be sequentially presented in a video script according to any time sequence relationship. For example, in the case where three text units having no logical dependency relationship are determined, the three text units may be made to correspond to the structural unit 411, the structural unit 412, and the structural unit 413, respectively. For example, the parallel structure may be used in a video script of a news broadcast type, in which each structural unit corresponds to a piece of news content.

Fig. 4B shows a structural framework of a hierarchical structure, wherein structural unit 421 is presented in the video script before structural unit 422 and structural unit 423. The text units corresponding to the

structure units

422 and 423 have logical dependency on the text unit corresponding to the structure unit 421. Illustratively, the hierarchy may be used in a video script of the overall hierarchy.

Fig. 4C shows a structural framework of a progressive structure, wherein in a video script, a structural unit 431, a structural unit 432 and a structural unit 433 are sequentially presented in the video script. The text unit corresponding to the structure unit 432 has a logical dependency on the text unit corresponding to the structure unit 431, and the text unit corresponding to the structure unit 433 has a logical dependency on the text unit corresponding to the structure unit 432. Illustratively, a progressive structure may be used in a narrative-like video script to express a layer-by-layer decreasing logical relationship.

FIG. 4D shows a structural framework that includes multiple structural types simultaneously, with

structural units

441 and 442 in a parallel configuration; the structure unit 441, the structure unit 443 and the structure unit 444 form a layered structure; the structure unit 443, the structure unit 445 and the structure unit 446 are in a progressive structure. By mixing structural frameworks of multiple structural types as shown in FIG. 4D, video scripts are enabled to express complex logical relationships.

In one embodiment, the logical relationship determined based on the sections corresponding to different text units in the same original text can be used for constructing a structural framework of a parallel structure and a hierarchical structure; the logical relationships determined based on the pragmatic types of the different text units may be used to build a structural framework of the progressive structure.

According to some embodiments, determining a structural framework of a video script based on logical relationships between a plurality of text units comprises: and in response to determining that the logical relationship among the text units can match the at least two structural frames, selecting the structural frame of the video script from the at least two structural frames according to the preset video duration. Therefore, the structural framework with better adaptability can be selected under the limit of the preset video duration, and the content balance and integrity of the video script are ensured.

For example, in the first structural framework shown in fig. 4D, since the preset video duration is limited, after the structural unit 441, the structural unit 443, the structural unit 445, the structural unit 446, and the structural unit 444 are sequentially presented, there is no time remaining to present the structural unit 442. In the second structural framework, the structural unit 443, the structural unit 445 and the structural unit 446 in fig. 4D may be merged into one structural unit (the other structural units in fig. 4D remain unchanged), and the text content of the text unit corresponding to the merged structural unit is simplified by means of abstract extraction, so that the content in each structural unit can be presented. Therefore, it can be determined that the second structural framework should be selected under the limitation of the preset video duration to ensure the balance and integrity of the video script content.

According to some embodiments, generating the video script comprises, based on the structural framework: extracting abstract information corresponding to the structural unit from the text content of at least one text unit corresponding to the structural unit aiming at each structural unit in the structural framework; and generating a video script based on the summary information corresponding to each structural unit in the structural framework.

There is often a user expectation for video length, especially given the current consumer trend of increasingly shorter, fragmented videos, even though the user-provided and system-enriched text units are sufficient to support longer videos, the user may specify shorter video lengths. In this case, it is necessary to refine the content of the video script and refine the core information so as to meet the user's needs.

In one embodiment, for each structural unit in the structural framework, one or more sentences are determined as summary information corresponding to the structural unit based on the importance, redundancy and coherence of each sentence in at least one text unit corresponding to the structural unit.

In another embodiment, for each structural unit in the structural framework, one or more text units are determined as the summary information corresponding to the structural unit based on the importance, redundancy and continuity of each text unit in at least one text unit corresponding to the structural unit.

In another embodiment, for each structural unit in the structural framework, at least one text unit corresponding to the structural unit is input into the abstract extraction model to obtain abstract information corresponding to the structural unit.

According to some embodiments, the video script comprises transition information, and wherein generating the video script based on the structural framework comprises: for any two structural units adjacent in time sequence in the structural framework, transition information is inserted between the two structural units. Therefore, when videos are manufactured according to the video scripts, transition setting among different structural units can be achieved according to transition information in the video scripts, and the continuity of the different structural units in video presentation is improved.

According to some embodiments, the transition information includes cue board information for indicating that a subtitle corresponding to a next structural unit is presented on a still picture in the video; and push information, wherein the push information is used for indicating the setting of adding the cut-out of the picture corresponding to the previous structural unit and the cut-in of the picture corresponding to the next structural unit in the video.

Illustratively, for the parallel structure and the layered structure, cue plate information may be employed as transition information; for progressive structures, marching information may be employed as transition information.

According to some embodiments, keywords suitable for transition can be extracted from at least one text unit corresponding to the next structural unit to generate transition lines, for example, "historical meaning" and "smith comment" for historical events, and a short transition line can be generated according to a template.

According to some embodiments, the video script comprises digital human information, and wherein generating the video script based on the structural framework comprises: and for any structural unit in the structural framework, determining the digital person information corresponding to the structural unit based on the text content in at least one text unit corresponding to the structural unit. Therefore, the expressive force of the video corresponding to the video script in the presentation process can be improved by arranging the digital person in the structural unit.

In automated, large-scale video production, there is no way to rely on human performances (e.g., news anchors, news reporters, presentation commentary, etc.) to promote affinity as in traditional video production. For this, a digital person may be used instead of a human presenter. Through carrying out relevant setting to the digital person in the video script, control digital person's performance for digital person can cooperate with the video script content, promotes the expressive force of video.

According to some embodiments, the digital personal information comprises at least one of: the lines of the digital person; a digital human action; a pose of the digital person; or a digital human expression.

The lines of the digital person may be text contents in at least one text unit corresponding to the structural unit. In other words, a role similar to "anchor" is realized by the digital human, and the content of the structural unit is vividly presented by dictating the text content to which the structural unit corresponds.

The actions of the digital person may further include natural narration, instructing the introduction (e.g., raising the arm to point to the video content), shifting the position, and the like. The digital person's gestures may include half-body, whole body, no mirror, etc. The expressions of the digital person may include serious, happy, excited, sad, etc.

In one embodiment, the actions, postures and expressions of the digital person can be determined by preset rules. For example, the posture of a digital person is assumed to be a whole body posture at the head, and a non-glasses type posture is adopted at a part with rich text content.

In another embodiment, the motion, pose, and expression of the digital person may be determined using a trained classification model. For example, the text content in at least one text unit corresponding to the structural unit is input into the classification model to obtain the expression of the digital person corresponding to the structural unit.

According to some embodiments, the video script comprises a video title, and wherein, based on the structural framework, generating the video script comprises: and inputting at least one text unit corresponding to each structural unit in the structural framework into a title extraction model to obtain a video title. Therefore, automatic extraction of the video titles can be conveniently realized.

Wherein, the title extraction model can be obtained by training a plurality of historical video scripts with video titles. Preferably, any one of the play amount, the review amount, the forwarding amount and the play-out rate of the video corresponding to the historical video script is greater than a preset threshold. Thus, the trained title extraction model can automatically determine a high-quality video title for the video script.

According to some embodiments, the video script comprises insertability information, and wherein generating the video script based on the structural framework comprises: identifying at least one insertion point in the structural frame; and determining insertability information corresponding to each of the at least one insertion point, wherein the insertability information is from at least one historical video script having a high degree of attention. Therefore, the content of the currently generated video script can be supplemented by the content in the history video script with high attention, so that the currently generated video script can have stronger user attraction.

Any one of the playing amount, the appraisal amount, the forwarding amount and the playing completion rate of the video corresponding to the historical video script with high attention is larger than a preset threshold value.

According to some embodiments, the insertability information comprises at least one of the following types: inserting language information; or special effect information. The insertion language information may further include stems, hindu languages, metaphors and the like, and the special effect information may further include audio, video, pictures and the like.

According to some embodiments, the video script may include non-textual elements, and wherein, based on the structural framework, generating the video script may include: and aiming at any structural unit in the structural framework, determining a non-text element corresponding to the structural unit based on the text content in at least one text unit corresponding to the structural unit. Therefore, by adding the non-text elements in the video script, the defects of the text in content expression can be compensated, the content richness of the video script is improved, and more abundant materials are provided for subsequent video production.

Wherein the non-text element may be determined together with the at least one original text as "material" for generating the video script. Similar to the at least one original text, the non-text elements may be entered by the user or may be obtained by searching in a corpus. After the structural framework of the video script is determined, the non-text elements corresponding to the structural units can be determined based on the text content in at least one text unit corresponding to each structural unit, and then the input non-text elements are incorporated into the video script, so that the text and the non-text elements in the same structural unit are unified in content.

According to some embodiments, the non-text element comprises at least one of an image, audio, or video.

According to some embodiments, the method further comprises: in response to determining to set the video script to the target language style, determining a conversion model corresponding to the target language style, wherein the conversion model is capable of converting the input text to text in the target language style; and inputting the video script into the conversion model to obtain the updated video script.

Wherein, the target language style can be serious, common, lively, grounded, etc.

In the process of generating the video script, a language style of at least one original text used for generating the video script may not be consistent with a set target language style, or a language style between at least one original text is not unified, so that the video script needs to be converted into a unified video script conforming to the target language style by using a conversion model according to content characteristics and user requirements.

According to some embodiments, the method further comprises: and aiming at any one updating sentence in the updated video script, responding to the fact that the semantics of the original sentence corresponding to the updating sentence in the video script before updating is inconsistent with the semantics of the updating sentence, and restoring the updating sentence into the original sentence.

In performing a video script update such as that described above, certain statements in the video script may be made to deviate from the original semantics during the update, resulting in errors in the content of the video script. By checking the semantic consistency between the updated sentence and the original sentence in the updated video script, the error rewriting can be corrected in time, and the ideographic accuracy of the video script is improved.

In one embodiment, a first semantic feature vector of an updated sentence and a second semantic feature vector of an original sentence are determined; and determining whether the semantics of the updated sentence are consistent with the semantics of the original sentence or not based on the similarity between the first semantic feature vector and the second semantic feature vector.

According to some embodiments, the method further comprises: and for any statement in the video script, responding to the sensitive information in the statement, and feeding back prompt information for the statement to a user.

Some sensitive and inappropriate contents can be introduced in the generation process of the video script, and the user can be prompted to check pertinently by feeding back prompting information aiming at the statement to the user, so that inappropriate text contents in the video script are avoided.

Fig. 5 shows a block diagram of a video script generation apparatus according to an exemplary embodiment of the present disclosure, where the apparatus 500 includes: an extracting module 501 configured to, in response to determining at least one original text, extract a plurality of text units from the at least one original text, wherein text content in each text unit has consecutive semantics; a first determining module 502 configured to determine a structural framework of the video script based on a logical relationship between a plurality of text units, wherein the structural framework includes a plurality of structural units having a time-series relationship, and each structural unit corresponds to at least one text unit; and a generation module 503 configured to generate a video script based on the structural framework.

According to some embodiments, the logical relationship between the plurality of text units can be determined by any one of the following: a second determining module configured to determine, for at least two text units from the same original text among the plurality of text units, a logical relationship between the at least two text units based on a section corresponding to each of the at least two text units in the original text; and a third determining module configured to determine a logical relationship between the plurality of text units based on the pragmatic type corresponding to each of the plurality of text units.

According to some embodiments, the structural frame comprises at least one of the following types of structures: a parallel structure; a layered structure; or a progressive structure.

According to some embodiments, the first determining module comprises: and the submodule is used for responding to the fact that the logic relation among the text units can be matched with the at least two structural frameworks, and selecting the structural framework of the video script from the at least two structural frameworks according to the preset video duration.

According to some embodiments, the generating module comprises: a sub-module for extracting summary information corresponding to the structural unit from the text content of at least one text unit corresponding to the structural unit for each structural unit in the structural frame; and the submodule is used for generating the video script based on the summary information corresponding to each structural unit in the structural framework.

According to some embodiments, the video script comprises transition information, and wherein the generating module comprises: and the submodule is used for inserting transition information between any two adjacent structural units in the structural framework in terms of time sequence.

According to some embodiments, the video script comprises digital human information, and wherein the generating module comprises: and the submodule is used for determining the digital person information corresponding to the structural unit according to the text content in at least one text unit corresponding to the structural unit aiming at any structural unit in the structural framework.

According to some embodiments, the video script comprises a video title, and wherein the generating module comprises: and the sub-module is used for inputting at least one text unit corresponding to each structural unit in the structural framework into the title extraction model to obtain the video title.

According to some embodiments, the video script comprises insertability information, and wherein the generating module comprises: a sub-module for identifying at least one insertion point in the structural frame; and a sub-module for determining insertability information corresponding to each of the at least one insertion point, wherein the insertability information is from at least one historical video script having a high degree of interest.

According to some embodiments, the insertability information comprises at least one of the following types: inserting language information; or special effect information.

According to some embodiments, the video script comprises non-text elements, and wherein the generating module comprises: and the sub-module is used for determining the non-text element corresponding to the structural unit according to the text content in at least one text unit corresponding to the structural unit aiming at any structural unit in the structural framework.

According to some embodiments, the at least one original text is searched based on a video topic.

According to some embodiments, the extraction module comprises: a sub-module for identifying redundant content in at least one original text; and a sub-module for extracting a plurality of text units from the text content of the at least one original text except the redundant content.

According to some embodiments, the apparatus further comprises: a fourth determination module configured to determine a conversion model corresponding to the target language style in response to determining to set the video script to the target language style, wherein the conversion model is capable of converting the input text to text in the target language style; and the acquisition module is configured for inputting the video script into the conversion model to obtain the updated video script.

According to some embodiments, the apparatus further comprises: and the restoring module is configured to restore the updated sentence into the original sentence aiming at any one of the updated sentences in the updated video script in response to the fact that the semantics of the original sentence corresponding to the updated sentence in the video script before the updated sentence is inconsistent with the semantics of the updated sentence.

According to an embodiment of the present disclosure, there is also provided an electronic apparatus including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform any one of the methods described above.

There is also provided, in accordance with an embodiment of the present disclosure, a non-transitory computer-readable storage medium having stored thereon computer instructions for causing a computer to perform any of the methods described above.

There is also provided, in accordance with an embodiment of the present disclosure, a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements any of the methods described above.

In the technical scheme of the disclosure, the processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the common customs of public order.

Referring to fig. 6, a block diagram of a structure of an electronic device 600, which may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Various components in the electronic device 600 are connected to the I/O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 may be any type of device capable of inputting information to the electronic device 600, and the input unit 606 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and/or a remote control. Output unit 607 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. The storage unit 608 may include, but is not limited to, a magnetic disk, an optical disk. The communication unit 609 allows the electronic device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and/or a chipset, such as a bluetooth (TM) device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and/or the like.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 601 performs the respective methods and processes described above, such as a video script generation method. For example, in some embodiments, the video script generation method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the video script generation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the video script generation method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, causes the functions/acts specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be performed in parallel, sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the above-described methods, systems and apparatus are merely exemplary embodiments or examples and that the scope of the present invention is not limited by these embodiments or examples, but only by the claims as issued and their equivalents. Various elements in the embodiments or examples may be omitted or may be replaced with equivalents thereof. Further, the steps may be performed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A method for generating a video script, the method comprising:

extracting a plurality of text units from at least one original text in response to determining the at least one original text, wherein the text content in each text unit has coherent semantics, and each text unit performs a subsequent generation process of a video script as a smallest executable unit;

determining a logical relationship between the plurality of text units by performing the following operations:

for at least two text units from the same original text in the plurality of text units, determining a logical relationship between the at least two text units based on the corresponding sections of each of the at least two text units in the original text; or

Determining a logical relationship between the plurality of text units based on a pragmatic type corresponding to each of the plurality of text units, wherein the pragmatic type is a label of the corresponding text unit;

in response to determining that the logical relationship between the text units can match at least two structural frameworks, selecting a structural framework of the video script from the at least two structural frameworks according to a preset video duration, wherein the structural framework comprises a plurality of structural units with a time sequence relationship, and each structural unit corresponds to at least one text unit; and

and generating the video script based on the structural framework.

2. The method of claim 1, wherein the structural framework comprises at least one of the following structural types:

a parallel structure;

a layered structure; or

And (5) a progressive structure.

3. The method of claim 1 or 2, wherein the generating the video script based on the structural framework comprises:

for each structural unit in the structural framework, extracting abstract information corresponding to the structural unit from the text content of at least one text unit corresponding to the structural unit; and

and generating the video script based on the summary information corresponding to each structural unit in the structural framework.

4. The method of claim 1 or 2, wherein the video script comprises transition information, and wherein the generating the video script based on the structural framework comprises:

for any two structural units adjacent in time sequence in the structural framework, transition information is inserted between the two structural units.

5. The method of claim 1 or 2, wherein the video script comprises digital human information, and wherein the generating the video script based on the structural framework comprises:

and for any structural unit in the structural framework, determining the digital person information corresponding to the structural unit based on the text content in at least one text unit corresponding to the structural unit.

6. The method of claim 5, wherein the digital personal information comprises at least one of:

the lines of the digital person;

a digital human action;

a pose of the digital person; or

The expression of the digital person.

7. The method of claim 1 or 2, wherein the video script comprises a video title, and wherein the generating the video script based on the structural framework comprises:

and inputting at least one text unit corresponding to each structural unit in the structural framework into a title extraction model to obtain the video title.

8. The method of claim 1 or 2, wherein the video script comprises insertability information, and wherein the generating the video script based on the structural framework comprises:

identifying at least one insertion point in the structural frame; and

determining insertability information corresponding to each of the at least one insertion points, wherein the insertability information is from at least one historical video script having a high degree of interest.

9. The method of claim 8, wherein the insertability information comprises at least one of the following types:

inserting language information; or

And (5) special effect information.

10. The method of claim 1 or 2, wherein the video script comprises non-text elements, and wherein the generating the video script based on the structural framework comprises:

and for any structural unit in the structural framework, determining a non-text element corresponding to the structural unit based on the text content in at least one text unit corresponding to the structural unit.

11. The method of claim 10, wherein the non-text element comprises at least one of an image, audio, or video.

12. The method of claim 1 or 2, wherein the at least one original text is searched based on a video topic.

13. The method according to claim 1 or 2, wherein said extracting a plurality of text elements from said at least one original text comprises:

identifying redundant content in the at least one original text; and

extracting the plurality of text units from text content of the at least one original text other than the redundant content.

14. The method of claim 1 or 2, further comprising:

in response to determining to set the video script to a target language style, determining a conversion model corresponding to the target language style, wherein the conversion model is capable of converting input text to the target language style text; and

and inputting the video script into the conversion model to obtain an updated video script.

15. The method of claim 14, further comprising:

and aiming at any one updating sentence in the updated video script, responding to the fact that the semantics of the original sentence corresponding to the updating sentence in the video script before updating is inconsistent with the semantics of the updating sentence, and restoring the updating sentence into the original sentence.

16. A video script generating apparatus, the apparatus comprising:

an extraction module configured to extract a plurality of text units from at least one original text in response to determining the at least one original text, wherein text content in each text unit has coherent semantics, and each text unit performs a subsequent generation process of a video script as a smallest executable unit;

a first determining module configured to determine a logical relationship between the plurality of text units by performing the following operations: for at least two text units from the same original text in the plurality of text units, determining a logical relationship between the at least two text units based on the corresponding sections of each of the at least two text units in the original text; or determining a logical relationship between the plurality of text units based on a pragmatic type corresponding to each of the plurality of text units, wherein the pragmatic type is a label of the corresponding text unit; in response to determining that the logical relationship between the text units can match at least two structural frameworks, selecting a structural framework of the video script from the at least two structural frameworks according to a preset video duration, wherein the structural framework comprises a plurality of structural units with a time sequence relationship, and each structural unit corresponds to at least one text unit; and

a generation module configured to generate the video script based on the structural framework.

17. The apparatus of claim 16, wherein the structural frame comprises at least one of the following structural types:

a parallel structure;

a layered structure; or

And (5) a progressive structure.

18. The apparatus of claim 16 or 17, wherein the generating module comprises:

a sub-module for extracting summary information corresponding to the structural unit from the text content of at least one text unit corresponding to the structural unit for each structural unit in the structural frame; and

and the submodule is used for generating the video script based on the summary information corresponding to each structural unit in the structural framework.

19. The apparatus of claim 16 or 17, wherein the video script comprises transition information, and wherein the generating module comprises:

and the submodule is used for inserting transition information between any two structural units adjacent in time sequence in the structural framework.

20. The apparatus of claim 16 or 17, wherein the video script comprises digital human information, and wherein the generating module comprises:

and the submodule is used for determining the digital person information corresponding to the structural unit according to the text content in at least one text unit corresponding to the structural unit aiming at any structural unit in the structural framework.

21. The apparatus of claim 20, wherein the digital personal information comprises at least one of:

the lines of the digital person;

a digital human action;

a pose of the digital person; or

The expression of a digital person.

22. The apparatus of claim 16 or 17, wherein the video script comprises a video title, and wherein the generating module comprises:

and the submodule is used for inputting at least one text unit corresponding to each structural unit in the structural framework into a title extraction model so as to obtain the video title.

23. The apparatus of claim 16 or 17, wherein the video script comprises interjectability information, and wherein the generating module comprises:

a sub-module for identifying at least one insertion point in the structural frame; and

a sub-module for determining insertability information corresponding to each of the at least one insertion points, wherein the insertability information is from at least one historical video script having a high degree of interest.

24. The apparatus of claim 23, wherein the insertability information comprises at least one of the following types:

inserting language information; or

And (5) special effect information.

25. The apparatus of claim 16 or 17, wherein the video script comprises non-text elements, and wherein the generating module comprises:

and the sub-module is used for determining the non-text element corresponding to the structural unit according to the text content in at least one text unit corresponding to the structural unit aiming at any structural unit in the structural framework.

26. The apparatus of claim 25, wherein the non-text element comprises at least one of an image, audio, or video.

27. The apparatus according to claim 16 or 17, wherein the at least one original text is searched based on a video topic.

28. The apparatus of claim 16 or 17, wherein the extraction module comprises:

a sub-module for identifying redundant content in the at least one original text; and

a sub-module for extracting the plurality of text units from text content in the at least one original text other than the redundant content.

29. The apparatus of claim 16 or 17, further comprising:

a fourth determination module configured to determine a conversion model corresponding to a target language style in response to determining to set the video script to the target language style, wherein the conversion model is capable of converting input text into text of the target language style; and

and the acquisition module is configured to input the video script into the conversion model to obtain an updated video script.

30. The apparatus of claim 29, further comprising:

and the restoring module is configured to respond to the fact that the semantics of the original sentence corresponding to the updated sentence in the video script before the updated sentence is not consistent with the semantics of the updated sentence aiming at any updated sentence in the updated video script, and restore the updated sentence into the original sentence.

31. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-15.

32. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-15.