Script generation method, electronic device, storage medium and product

Abstract

The present disclosure relates to a script generation method, an electronic device, a storage medium and a product, and relates to the technical field of computers. The script generation method comprises: generating meta-information of a novel based on a text of the novel; generating an abstract of one or more script units corresponding to the novel according to the meta-information, the abstract matching the meta-information; for each script unit, generating content of one or more script elements based on the meta-information and the abstract of the script unit; and generating a script according to the content of the script elements of the one or more script units.

Description

Script generation methods, electronic devices, storage media, and products Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method for generating a script, an electronic device, a storage medium, and a product. Background Technology

[0002] In industries such as film, animation, and games, the participation of professionals from multiple disciplines, including literature and fine arts, is required. A script is fundamental to the creation of such audiovisual works. Currently, scripts are often written by screenwriters, and some large-scale productions even require a team of multiple screenwriters. Therefore, scriptwriting demands significant time and manpower and is highly dependent on the screenwriter's experience.

[0003] Summary of the Invention

[0004] According to some embodiments of this disclosure, a method for generating a script is provided, comprising: generating meta-information of a novel based on the text of the novel; generating a summary of one or more script units corresponding to the novel based on the meta-information, wherein the summary matches the meta-information; for each script unit, generating content of one or more script elements based on the meta-information and the summary of the script unit; and generating a script based on the content of the script elements of the one or more script units.

[0005] According to some embodiments of the present disclosure, an electronic device is provided, including: a memory; and a processor coupled to the memory, the processor being configured to execute a script generation method of any embodiment of the present disclosure based on instructions stored in the memory.

[0006] According to some embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs a script generation method of any embodiment described in the present disclosure.

[0007] According to some embodiments of the present disclosure, a computer program product is provided that, when the computer program product is run on a computer, causes the computer to implement the script generation method of any embodiment of the present disclosure.

[0008] Other features, aspects, and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0009] Embodiments of this disclosure are described below with reference to the accompanying drawings. It should be understood that the drawings described below are merely illustrative of some embodiments of this disclosure and are not intended to limit the scope of this disclosure.

[0010] Figure 1 shows a schematic flowchart of a script generation method according to some embodiments of the present disclosure.

[0011] Figure 2 shows a flowchart illustrating a method for generating metadata according to some embodiments of the present disclosure.

[0012] Figure 3 shows a schematic flowchart of a summary generation method according to some embodiments of the present disclosure.

[0013] Figure 4 shows a flowchart illustrating a method for generating script elements according to some embodiments of the present disclosure.

[0014] Figure 5 shows a schematic flowchart of a script generation method according to some embodiments of the present disclosure.

[0015] Figure 6 illustrates a schematic diagram of the processing flow of an intelligent agent according to some embodiments of the present disclosure.

[0016] Figure 7 shows a schematic diagram of the structure of a script generation apparatus according to some embodiments of the present disclosure.

[0017] Figure 8 shows a block diagram of an electronic device according to some embodiments of the present disclosure.

[0018] Figure 9 shows a block diagram of an electronic device according to some other embodiments of the present disclosure. Detailed Implementation

[0019] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. It should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0020] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. Unless otherwise specifically stated, the numerical values ​​set forth in these embodiments should be interpreted as merely exemplary and do not limit the scope of this disclosure.

[0021] As used in this disclosure, the term "comprising" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". The term "based on" means "at least partially based on".

[0022] It should be noted that the concepts of "first," "second," etc., used in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described herein must be in a given temporal, spatial, rank, or any other given order.

[0023] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0024] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0025] The embodiments of this disclosure are described in detail below with reference to the accompanying drawings; however, this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Furthermore, in one or more embodiments, specific features, structures, or characteristics can be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0026] Scriptwriting by hand is time-consuming and therefore increases both time and labor costs. In an era of booming multimedia content, higher creative efficiency is needed to improve the output of multimedia content and enhance user experience.

[0027] With the development of artificial intelligence technology, users can utilize generative models to generate various types of information. Generative models are machine learning models, such as foundation models or large language models (LLMs). After a user inputs a description of the content to be generated, the model can generate prompts based on that description. The generative model can process these prompts and, based on its training results and a knowledge base, generate the information. For example, it can generate text or images based on the user's description.

[0028] The emergence of generative models has met many user needs and improved the efficiency of information acquisition. For example, in intelligent dialogue scenarios, users can ask questions, and an intelligent agent based on a generative model can respond to the user's questions.

[0029] As for screenplays adapted from novels, since the novel text already exists, it seems that the novel text and the instructions to adapt the novel text into a screenplay can be directly input into the generative model, and the screenplay will be fed back by the generative model.

[0030] However, in practice, when the information the model needs to process is very complex, directly inputting the information into the model and expecting to get the generated result immediately often fails to produce the desired outcome. The above-mentioned method of generating scripts may result in users not obtaining satisfactory scripts, thus leading to relatively low generation efficiency.

[0031] This disclosure provides a method, electronic device, storage medium, and product for generating a script. First, key information and summaries are extracted from the novel, and based on this information, elements that can be adapted to the script are generated so that the generated script can meet the creative needs in terms of content, theme, and key information, thereby improving the efficiency of script generation.

[0032] Figure 1 shows a schematic flowchart of a script generation method according to some embodiments of the present disclosure. As shown in Figure 1, the generation method of this embodiment includes steps S102 to S108. The method of this embodiment can be executed by an electronic device, such as a computer, terminal device, etc.

[0033] In step S102, the meta-information of the novel is generated based on the novel's text.

[0034] Meta-information in a novel refers to its key information, such as characters and crucial plot points. It can be extracted directly from the novel or summarized from the original text. Meta-information reflects key passages or dimensions of the novel. In other words, meta-information can be understood as fragmented information that matches the original text of the novel.

[0035] The process of generating metadata for a novel can be implemented using machine learning models. If the metadata includes multiple categories, different categories of metadata can be obtained through a single machine learning model, or through a machine learning model corresponding to each category. Alternatively, it can be obtained through an agent of the machine learning model (or a client, agent, etc. of the machine learning model), or through an agent corresponding to each category.

[0036] In step S104, a summary of one or more script units corresponding to the novel is generated based on the meta-information, and the summary matches the meta-information.

[0037] Novels typically consist of multiple chapters. Similarly, screenplays can consist of multiple screenplay units, each of which may be an episode or an act. Since novel chapters and screenplay units often do not correspond one-to-one, it is necessary to determine which screenplay units the adapted novel will have, as well as a summary of each unit.

[0038] A summary can be generated by aggregating the meta-information related to each script unit. That is, the meta-information is fragmented, but the summary is relatively complete. A summary can be viewed as a plot synopsis for each script unit.

[0039] Screenplays and novels differ in their forms of expression. Screenplays tend to describe visual content more concisely, with a more tightly woven plot. Novels, on the other hand, bear the author's stylistic influences and have a slower pace compared to screenplays. However, for screenplays adapted from novels, both the novel and the screenplay describe the same story. Even though they are expressed in different ways, the core content of the story remains consistent. By extracting summaries from the novel's meta-information, the core content of the novel can be accurately determined, thus constraining the subsequent screenplay generation process.

[0040] Machine learning models can also be used to process metadata during the generation of summaries to produce script summaries.

[0041] In step S106, for each script unit, content of one or more script elements is generated based on the metadata and the script unit's summary.

[0042] After determining the summary for each script unit, a script in script format needs to be generated based on that summary. A script typically requires script elements such as time, place, characters, and dialogue. This content can be extracted from metadata or generated based on metadata. In addition to metadata, script elements can also be obtained from the novel's text.

[0043] In some embodiments, the summaries of script units can be expanded according to the requirements of the script, and the expanded results can be matched with the metadata. This process can be achieved using a machine learning model. For example, the metadata and the summaries of script units can be input into a machine learning model to obtain the content of one or more script elements output by the model.

[0044] In step S108, a script is generated based on the content of script elements of one or more script units.

[0045] For example, these script elements can be rearranged and combined according to the script format to generate a script. A script can be generated by text concatenation, or the script elements can be input into a machine learning model for concatenation. The model can also be fine-tuned during processing.

[0046] The above embodiments sequentially generate the novel's meta-information, generate summaries for each script unit, and generate script elements, thus breaking down the script generation process. In this way, information is generated in stages during script generation. Meta-information represents key content from the novel's perspective, while script elements represent key content from the script's perspective. The conversion between the two is accomplished through summaries, ensuring that the generated script elements do not deviate from the original novel's theme. Therefore, novels can be adapted into scripts more efficiently and accurately.

[0047] Since visualizations adapted from novels rely heavily on stories centered around characters, the extraction of metadata allows us to identify the characters and related information within the novel. Meta-information is then generated based on this information.

[0048] Some novels feature numerous characters, each potentially described in detail. However, visual works differ from novels, often exhibiting more concentrated plot conflicts and a clearer storyline. Therefore, films and television series typically unfold around the stories of the main characters. Especially in recent years, with the rise of user-generated content and the popularity of multimedia content platforms, many short dramas with tighter plots have emerged. Each episode of a short drama is shorter than a preset duration, perhaps only a few minutes long. Therefore, in some implementations, metadata can be generated around the main characters and associated tags to more clearly reflect the core plot of the novel.

[0049] Figure 2 shows a flowchart illustrating a method for generating metadata according to some embodiments of the present disclosure. As shown in Figure 2, the generation method of this embodiment includes steps S202 to S206.

[0050] In step S202, information about one or more characters, including the protagonist, is extracted from the text of the novel.

[0051] Whether a character is the protagonist can be determined based on the novel's attributes. For example, some novels introduce the protagonist through a synopsis or preface, while others include a list of protagonists. Alternatively, the protagonist can be identified from the novel's text itself, such as by the character's frequency of appearance, the number of chapters covered by the character, and the amount of content related to the character, thus distinguishing the protagonist from multiple characters.

[0052] The information about a character can be a description of the character's basic attributes, such as name, gender, age, occupation, personality traits, physical characteristics, and major events involved.

[0053] The character information extracted from the novel text can be considered the character's primary information. This primary information mainly comes from the content of the novel's original text. The process of extracting this primary information can be implemented using machine learning models.

[0054] In step S204, tags for one or more dimensions associated with the protagonist are extracted.

[0055] One or more dimensions of tags, such as character behavior (facial expressions, actions, etc.), plot points involving the character, interactions between characters, conflicts between characters, and so on. This information can be obtained relatively directly from the novel's text.

[0056] When extracting these tags, this information can be obtained from text paragraphs containing the characters through text matching, and then categorized to determine the corresponding tags. Alternatively, a text processing model can be used to perform semantic understanding of the novel text, allowing the model to output information related to these characters within the novel text.

[0057] Since the protagonist is involved in most of the novel's plot, extracting tags from multiple dimensions based on the protagonist's information can comprehensively cover the key information points in the novel.

[0058] In step S206, the novel's meta-information is generated based on information about one or more characters and tags of one or more dimensions.

[0059] Meta-information in a novel is the result of fusing tags from one or more dimensions with character information. Meta-information includes, for example, the novel's world-building, character information, setting information, plot conflicts, background story, and so on.

[0060] In meta-information, a character's information can be referred to as the character's secondary information. Compared to the character's primary information, secondary information is more comprehensive and complete, providing a more three-dimensional description of the character. For example, the original primary information of a character extracted from a novel text consists of fragmented descriptions, while in the generated meta-information, the character's secondary information can connect the character's background, personality, and experiences, forming a character biography.

[0061] The above embodiments, from the perspective of the characters, extract tags associated with the main characters and generate original information. This allows for efficient and accurate extraction of key information from the novel, and provides a relatively comprehensive coverage of the novel's key content, facilitating the subsequent generation of a coherent plot summary. Therefore, it improves the efficiency of script generation.

[0062] The process of generating metadata can be implemented using machine learning models. Metadata can include multiple categories of information. To avoid interference between different types of metadata during generation, in some embodiments, generating metadata for a novel's text involves processing the text using an agent corresponding to each of the multiple categories to generate metadata for each category. For example, extracted character information and tags can be processed separately using agents corresponding to each category to generate metadata. By leveraging the different agents' focus on different important information, more accurate generation of metadata for specific categories can be achieved.

[0063] The summary for each script unit describes the main plot of that script unit. Therefore, the summary can be generated primarily based on the conflict plot in the metadata. Figure 3 shows a flowchart illustrating a summary generation method according to some embodiments of the present disclosure. As shown in Figure 3, the summary generation method of this embodiment includes steps S302 to S306.

[0064] In step S302, based on the character information, scene, and conflict plot in the metadata, the character and scene associated with each of the multiple conflict plots are determined.

[0065] The conflict scenario briefly describes the content of the conflict; for example, the conflict scenario could be "Character A's company is facing a crisis." Through the descriptions of characters and scenes in the metadata, the content of other metadata related to this conflict scenario can be clearly identified. For example, the relevant information in the metadata includes a description of character A: "Holds a management position in Company X"; scene information includes: "Company X's cash flow has dried up, the company's directors are very anxious, and the phone keeps ringing..."

[0066] In step S304, one or more script units are generated based on multiple conflict scenarios.

[0067] For example, a script unit may include one or more conflict scenarios. Each script unit revolves around its corresponding conflict scenario. The script units generated in this step only include basic information such as the identifier and the corresponding conflict scenario. The content of the script units needs to be filled in after the script elements are generated later.

[0068] In step S306, a summary of each script unit is generated based on the conflict plot of each script unit and the characters and scenes associated with the conflict plot. The summary matches the world view.

[0069] First, the conflict plot can be expanded using characters and scenes associated with it, generating detailed descriptions of the script units. Then, this detailed description can be abbreviated to extract a summary. For example, the conflict plot, along with its associated characters and scenes, can be input into a machine learning model, instructing the model to expand the conflict plot based on these characters and scenes. Then, the descriptions and world-building can be input into the machine learning model, instructing the model to extract a summary based on this world-building.

[0070] Taking the conflict scenario described after step S302, "Character A's company is facing a crisis," as an example, the generated summary could be, "Character A's company is facing a business crisis, its project has been stolen, and its cash flow is in trouble."

[0071] The above embodiments divide the plot into units based on conflict, aggregate meta-information related to the conflict, and extract summaries. Thus, the extracted summaries can revolve around the plot conflict, making the rewritten content suitable for the script's expressive requirements.

[0072] After determining the summary of each script unit, content matching the summary can be searched again from the meta-information and the text of the novel as script elements. Figure 4 shows a flowchart illustrating a method for generating script elements according to some embodiments of the present disclosure. As shown in Figure 4, the method for generating script elements in this embodiment includes steps S402 to S404.

[0073] In step S402, content matching the summary of the script unit is extracted from the metadata and the text of the novel.

[0074] For metadata, text fragments matching the summary can be identified. For the text of a novel, the content of chapters related to the summary can be identified, allowing for the extraction of script elements from this content.

[0075] Since there may be a lot of content matching the summary, content related to important characters can be prioritized. In some embodiments, based on the character's priority, the content of one or more script elements for generating script units using content matching the summary is determined, wherein the amount of content involved in each character is positively correlated with the character's priority. The character's priority can be divided according to protagonist, main supporting character, supporting character, etc. This classification method can be determined from the novel's synopsis or character list. Alternatively, the novel's text can be input into a text processing model to obtain the amount of content corresponding to each character in the novel, and the character's priority can be determined based on the amount of content in the novel. Correspondingly, in the script, the character's priority can also be positively correlated with the amount of content the character has in the script. By determining the amount of content on which the generated script elements are based based on the character's priority, redundant script content can be avoided.

[0076] In step S404, content for one or more script elements of a script unit is generated using content that matches the summary.

[0077] One or more script elements, such as time, place, scene description, character actions, character dialogue, and descriptive information of characters appearing for the first time.

[0078] In some embodiments, content matching the summary and script elements can be input into a machine learning model, and the machine learning model can be instructed to extract content matching the script elements from the content matching the summary. For example, instructing the machine learning model to extract scene descriptions can extract descriptive information about the scene of the current script unit from this content.

[0079] The above embodiments first determine the basis for generating the script based on the summary, that is, the content that matches the summary, and then extract the script elements from this content. Thus, script content that meets the script format can be generated, and irrelevant information can be removed, improving the efficiency of script generation.

[0080] After determining the script elements, the main plot content of the script is determined. In addition, some plot points, while not the main focus, can serve as transitional elements between different script units. The script can also generate the beginning or ending of each script unit based on these plot points. Figure 5 shows a flowchart illustrating a script generation method according to some embodiments of this disclosure. As shown in Figure 5, the generation method of this embodiment includes steps S502 to S504.

[0081] In step S502, for each script unit, at least one of the start plot and end plot of the script unit is determined based on the content and summary of the script elements of the script unit and the summary of the adjacent script units of the script unit. The start plot is used to connect to the previous adjacent script unit, and the end plot is used to trigger the next adjacent script unit.

[0082] The ending of a script unit and the beginning of the next script unit can belong to the first and second halves of the same story, respectively. Thus, the ending and beginning of the story can serve as a link between adjacent script units.

[0083] In some embodiments, for each script unit, a plot turning point between the script unit and the next adjacent script unit is determined based on the content and summary of one or more script elements of the script unit and the summary of the next adjacent script unit; the ending plot of the script unit is determined based on the plot turning point. For example, the relevant content (script elements, summaries, etc.) of two adjacent script units can be input into a machine learning model, and the model can be instructed to generate a plot turning point between the two script units.

[0084] For example, the i-th script unit tells the story of a company facing a crisis, and the (i+1)-th script unit tells the story of a company turning around. The plot turning point could be receiving a phone call from character B, who can help the company overcome its difficulties. The ending of the i-th script unit could be that the company's manager receives an important phone call, and the beginning of the (i+1)-th script unit could be the revelation that the call was made by character B.

[0085] In step S504, a script is generated based on at least one of the start plot and end plot of one or more script units, as well as the content of script elements.

[0086] In some embodiments, a machine learning model can be instructed to splice together the start plot, script elements, and end plot of each script unit to generate the script for each script unit, and then integrate the scripts of each script unit to generate a complete script.

[0087] The above embodiments generate transitional storylines, i.e., beginning or ending storylines, between script units. This allows for a smooth transition between generated script units, improving the usability of the script.

[0088] Figure 6 illustrates a schematic diagram of the processing flow of an intelligent agent according to some embodiments of the present disclosure. As shown in Figure 6, after obtaining the novel text, a novel plot analysis intelligent agent is used to extract multiple tags from the novel text. In Figure 6, these are exemplarily illustrated as character tags, plot tags, behavior tags, conflict tags, and interaction tags. The plot analysis intelligent agent may include one or more, and in the case of multiple agents, each agent may be responsible for extracting one type of tag.

[0089] After obtaining these tags, one or more script generation agents can continue processing. For example, first, separate agents for world-building, character generation, story background generation, and conflict plot generation can be used to generate meta-information including world-building, character information, story background, conflict plot, etc. Then, a story outline generation agent processes this meta-information to generate a story outline, including summaries of each script unit. Finally, the script generation agent processes the generated summaries to generate script elements, and ultimately, the script itself.

[0090] This embodiment allows for the use of multiple agents to complete the script generation process step-by-step. Thus, the script generation process can be completed through the collaborative operation of multiple agents. Each agent, after receiving input data, can invoke a machine learning model to process the data according to preset instructions or instructions contained in the input data, and then return the machine learning model's output. The agent can either directly return the machine learning model's output or perform preset processing on the output before returning it.

[0091] To enhance user engagement with visual content, key plot points can be placed at the beginning of the script. In some embodiments, key plot points of the novel are generated based on summaries of one or more script units; the script is then generated based on these key plot points and the content of script elements from one or more script units, with the key plot points positioned at the beginning of the script. This allows for the extraction of the conflicting plot points that run throughout the text, creating the opening scene that increases the appeal of the series to the user and improves the usability of the script.

[0092] The following is a simple example to describe the process of automatically adapting a novel text into a screenplay.

[0093] Suppose a passage from a novel reads as follows: "A arrived at the office before even having breakfast. He saw colleagues B and C whispering to each other, while his boss D rushed around. This was a crucial period for negotiations on a project he was leading, a project that would determine the company's development for the next few years. Could there be a problem with the project? Just then, A's phone rang; it was his boss D calling. A had a bad feeling. Returning from the boss's office, A looked distressed, not even noticing his coffee had gone cold..." The novel includes other content, which is omitted here.

[0094] Based on the novel's text, some meta-information can be extracted. Through text processing, the following information about character A is obtained: "A is a beautiful and independent woman holding a mid-level management position in a well-known company. She is straightforward, with her own opinions and pursuits. She dresses fashionably and appropriately, is decisive in the workplace, and desires a warm and harmonious atmosphere at home." The obtained worldview is "modern, workplace." The obtained conflict information is "problems arise in the project." The obtained scene information is "colleagues B and C whispering to each other in the company, while boss D is rushing around." Using this meta-information, the summary "A's company is facing a business crisis; the project has been stolen and the cash flow is in trouble."

[0095] By summarizing and utilizing the descriptions in the original text, a corresponding script excerpt can be generated, as shown in the following example.

[0096] Act M: The Company's Dilemma

[0097] Time: Morning

[0098] Location: Company A

[0099] Description: A is looking worried at the company. The company has encountered a major business crisis. An important cooperation project has been snatched away by a competitor, and the cash flow has also run into problems.

[0100] dialogue:

[0101] D: (Seriously) A, our competitor has snatched the project away. You were in charge of this project, so you need to think about what to do next.

[0102] A: (Sitting wearily in the office) What should we do? If we can't get this project back, the company might not survive.

[0103] By utilizing the script automatic generation process of the embodiments of this disclosure, a script adapted to a visual work can be obtained, thereby efficiently adapting a novel into a corresponding script.

[0104] The methods of embodiments of this disclosure have been described above. Apparatus for performing the methods of the above embodiments is described below.

[0105] Figure 7 shows a schematic diagram of the structure of a script generation apparatus according to some embodiments of the present disclosure. As shown in Figure 7, the generation apparatus 70 of this embodiment includes: a first generation module 701, configured to generate meta-information of a novel based on the text of the novel; a second generation module 702, configured to generate a summary of one or more script units corresponding to the novel based on the meta-information, wherein the summary matches the meta-information; a third generation module 703, configured to generate content of one or more script elements for each script unit based on the meta-information and the summary of the script unit; and a fourth generation module 704, configured to generate a script based on the content of the script elements of one or more script units.

[0106] In some embodiments, the first generation module 701 is further configured to extract information about one or more characters from the text of the novel, including the protagonist; extract one or more dimensional tags associated with the protagonist; and generate meta-information of the novel based on the information about the one or more characters and the tags of one or more dimensions.

[0107] In some embodiments, the first generation module 701 is further configured to process the text of the novel using an agent corresponding to each of the plurality of categories to generate meta-information for each category.

[0108] In some embodiments, the meta-information of the novel includes worldview, character information, scenes, and conflict plots. The second generation module 702 is further configured to: determine the characters and scenes associated with each of the multiple conflict plots based on the character information, scenes, and conflict plots; generate one or more script units based on the multiple conflict plots; and generate a summary of each script unit based on the conflict plot of each script unit and the characters and scenes associated with the conflict plots, wherein the summary matches the worldview.

[0109] In some embodiments, the third generation module 703 is further configured to: extract content matching the summary of the script unit from the metadata and the text of the novel; and generate content of one or more script elements of the script unit using the content matching the summary.

[0110] In some embodiments, the third generation module 703 is further configured to: determine, based on the priority of the role, generate content for one or more script elements of the script unit using content that matches the summary, wherein the amount of content involved in each role is positively correlated with the priority of the role.

[0111] In some embodiments, one or more script elements include at least one of time, place, scene description, character actions, character dialogue, and descriptive information of characters appearing for the first time.

[0112] In some embodiments, the fourth generation module 704 is further configured to: for each script unit, determine at least one of the start plot and end plot of the script unit based on the content and summary of the script elements of the script unit and the summary of the adjacent script units of the script unit, wherein the start plot is used to continue from the previous adjacent script unit and the end plot is used to trigger the next adjacent script unit; and generate a script based on at least one of the start plot and end plot of one or more script units and the content of the script elements.

[0113] In some embodiments, the fourth generation module 704 is further configured to: for each script unit, determine the plot turning point between the script unit and the next adjacent script unit based on the content and summary of one or more script elements of the script unit and the summary of the next adjacent script unit of the script unit; and determine the ending plot of the script unit based on the plot turning point.

[0114] In some embodiments, the fourth generation module 704 is further configured to: generate key plot points of the novel based on summaries of one or more script units; and generate a script based on the key plot points and the content of script elements of one or more script units, wherein the key plot points are located at the beginning of the script.

[0115] Figure 8 shows a block diagram of an electronic device according to some embodiments of the present disclosure.

[0116] Memory 81 is used to store one or more computer-readable instructions. Memory 81 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Memory 81 may, for example, store operating systems, application programs, boot loaders, databases, and other programs, as well as various application programs and various data.

[0117] The processor 82 is configured to execute computer-readable instructions to implement the method described in any of the foregoing embodiments. Specific implementations of each step of the method can be found in the above embodiments; repeated details will not be elaborated upon here.

[0118] The processor 82 can be configured to perform the steps of the above embodiments. The processor 82 can be embodied in various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The central processing unit (CPU) can be an x86 or ARM architecture, etc.

[0119] The processor 82 and the memory 81 can communicate with each other directly or indirectly. For example, the processor 82 and the memory 81 can communicate via a network. The network can include wireless networks, wired networks, and / or any combination of wireless and wired networks. The processor 82 and the memory 81 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0120] It should be noted that the components of the electronic device 8 shown in Figure 8 are exemplary and not limiting. The electronic device 8 may have other components depending on the specific application requirements. The processor 82 can control other components in the electronic device 8 to perform the desired functions.

[0121] Electronic device 8 can be implemented by software, firmware and / or hardware, and can be integrated into a device with the relevant application installed.

[0122] Figure 9 shows a block diagram of an electronic device according to some other embodiments of the present disclosure.

[0123] The electronic device 9 shown in Figure 9 can be a computer system with a dedicated hardware structure, capable of performing corresponding functions when relevant applications are installed.

[0124] Electronic devices include, but are not limited to, mobile terminals such as smartphones, laptops, personal digital assistants (PDAs), tablet computers (PCs), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), wearable devices, and fixed terminals such as digital televisions and desktop computers.

[0125] As shown in Figure 9, the Central Processing Unit (CPU) 91 executes various processes based on programs stored in Read-Only Memory (ROM) 92 or programs loaded from Storage Section 98 into Random Access Memory (RAM) 93. RAM 93 stores data required as needed when the CPU 91 executes various processes. The CPU is merely exemplary and can also be other types of processors, such as the various processors described above. ROM 92, RAM 93, and Storage Section 98 can be various forms of computer-readable storage media. It should be noted that although ROM 92, RAM 93, and Storage Section 98 are shown separately in Figure 9, one or more of them can be combined or located in the same or different memories or storage modules.

[0126] CPU 91, ROM 92 and RAM 93 are interconnected via bus 94. Input / output interface 95 is also connected to bus 94.

[0127] The following components are connected to the input / output interface 95: input section 96, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 97, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 98, including hard disk, magnetic tape, etc.; and communication section 99, including network interface cards such as LAN cards, modems, etc. The communication section 99 allows communication processing to be performed via a network such as the Internet. It is readily understood that although some parts of the electronic device 9 shown in Figure 9 communicate via bus 94, they can also communicate via a network or other means, wherein the network can include wireless networks, wired networks, and / or any combination of wireless and wired networks.

[0128] As needed, drive 910 is also connected to input / output interface 95. Removable media 911, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 910 as needed, so that computer programs read from them can be installed into storage section 98 as needed.

[0129] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or a storage medium such as a removable medium 911.

[0130] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product that, when run on a computer, causes the computer to perform the methods described in any of the foregoing embodiments. The computer program product includes computer instructions carried on a computer-readable medium, containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer instructions can be downloaded and installed from a network via communication section 99, or installed from storage section 98, or installed from ROM 92. When the computer program is executed by CPU 91, the methods of embodiments of this disclosure are performed.

[0131] It should be noted that, in the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0132] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.

[0133] Computer-readable storage media include, but are not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Computer instructions are stored on the computer-readable storage medium that, when executed by a processor, implement the methods described in any of the foregoing embodiments.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0135] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0136] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the methods described in any of the foregoing embodiments. For example, the instructions may be embodied in computer program code.

[0137] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0138] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0139] The functions described above can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0140] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for generating a script, comprising: Based on the text of the novel, generate the novel's meta-information; Based on the metadata, a summary of one or more script units corresponding to the novel is generated, and the summary is matched with the metadata; For each script unit, based on the metadata and the script unit's summary, the content of one or more script elements is generated; A script is generated based on the content of the script elements of one or more script units.

2. The generation method according to claim 1, wherein, The generation of meta-information of the novel based on its text includes: Extract information about one or more characters from the text of the novel, including the protagonist; Extract tags for one or more dimensions associated with the protagonist; Based on the information of the one or more characters and the tags of the one or more dimensions, the meta-information of the novel is generated.

3. The generation method according to claim 1 or 2, wherein, The metadata includes multiple types of information. The generation of the metadata for the novel based on its text includes: The text of the novel is processed using an agent corresponding to each of the multiple categories to generate metadata for each category.

4. The generation method according to any one of claims 1 to 3, wherein, The novel's meta-information includes its world-building, character information, settings, and plot conflicts. Generating a summary of one or more script units corresponding to the novel based on this meta-information includes: Based on the character information, the scene, and the conflict plot, determine the character and scene associated with each of the multiple conflict plots; Based on the multiple conflict scenarios, generate one or more script units; Based on the conflict plot of each script unit, as well as the characters and scenes associated with the conflict plot, a summary of each script unit is generated, and the summary matches the world view.

5. The generation method according to any one of claims 1 to 4, wherein, The process of generating one or more script elements based on the metadata and the script unit summary includes: Extract content that matches the summary of the script unit from the metadata and the text of the novel; Using the content that matches the summary, generate content for one or more script elements of the script unit.

6. The generation method according to claim 5, wherein, The step of generating one or more script elements of the script unit using content matching the summary includes: Based on the priority of the roles, a script unit is generated using content that matches the summary. The content of one or more script elements, wherein the amount of content involved in each character is positively correlated with the priority of the character.

7. The generation method according to any one of claims 1 to 6, wherein, The one or more script elements include at least one of the following: time, place, scene description, character actions, character dialogue, and descriptive information of characters appearing for the first time.

8. The generation method according to any one of claims 1 to 7, wherein, The process of generating a script based on the content of script elements from one or more script units includes: For each script unit, based on the content and summary of the script elements of the script unit and the summaries of the adjacent script units, at least one of the start plot and the end plot of the script unit is determined, wherein the start plot is used to connect to the previous adjacent script unit, and the end plot is used to trigger the next adjacent script unit. A script is generated based on at least one of the start and end plots of the one or more script units, as well as the content of the script elements.

9. The generation method according to claim 8, wherein, For each script unit, based on the content and summary of the script elements of that script unit, and the summaries of the adjacent script units, the ending plot of that script unit is determined to include: For each script unit, the plot turning point between the script unit and the next adjacent script unit is determined based on the content and summary of one or more script elements of the script unit and the summary of the next adjacent script unit. Based on the aforementioned plot turning point, determine the ending plot of the script unit.

10. The generation method according to any one of claims 1 to 9, wherein, The process of generating a script based on the content of script elements from one or more script units includes: Based on the summaries of one or more script units, generate the key plot points of the novel; A script is generated based on the key plot points and the content of script elements from one or more script units, wherein the key plot points are located at the beginning of the script.

11. An electronic device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the script generation method as described in any one of claims 1 to 10 based on instructions stored in the memory.

12. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for generating a script according to any one of claims 1 to 10.

13. A computer program product, when run on a computer, causes the computer to implement the script generation method of any one of claims 1 to 10.

Images