Method, device, equipment and medium for generating film and television data based on large language model

Abstract

The present invention relates to the field of artificial intelligence technology, and provides a method, device, equipment and medium for generating film and television data based on a large language model, which can extract elements of a script to be processed to obtain script elements, so as to obtain effective content in the script; pre-process the script elements to obtain data to be processed, so as to further optimize the extracted script elements, so as to facilitate better recognition and processing by the model; use the large language model to perform script analysis on the processed data to obtain script analysis results, so as to obtain structured content of the script; generate prompt words according to the script analysis results and user questions, so as to improve the prompt words in combination with basic structured content, so that the model can respond to user questions more accurately; select a knowledge base based on the prompt words to provide a more reasonable knowledge base, further improve the accuracy of the model response, and thus provide users with effective film and television data in combination with artificial intelligence means to assist users in script creation.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for generating film and television data based on a large language model. Background Art

[0002] In the film and television industry, script writing and storyline design are core components of the quality of a work. Screenwriters usually need to deal with a large amount of information and complex plot arrangements during the creative process, and often encounter inspiration exhaustion and creative bottlenecks. In addition, screenwriters need to constantly adjust and optimize the outline, plot, and plot during the creative process, which is not only time-consuming, but may also lead to uneven creative quality due to subjective bias.

[0003] In addition, most existing script creation tools are based on text editing and simple auxiliary functions, lacking intelligent creative stimulation and personalized creative guidance, and are difficult to meet the diverse needs of screenwriters in the creative process. With the development of natural language processing (NLP) technology, text generation tools based on large language models have gradually been introduced into the creative field. However, these tools still have limitations in the specific scenarios of film and television creation, and cannot effectively combine the special needs of the film and television industry to provide intelligent and personalized creative guidance.

[0004] In summary, in the existing technology, there are still the following deficiencies in the generation of film and television data:

[0005] 1. Low creative efficiency: Existing script creation tools cannot effectively improve the creative efficiency of screenwriters, and cannot quickly generate and optimize script outlines and plots. Screenwriters often need to spend a lot of time repeatedly revising and adjusting, which seriously affects the progress and quality of creation.

[0006] 2. Insufficient inspiration: Screenwriters are prone to inspiration exhaustion during the creative process, and existing tools cannot provide effective inspiration and creative ideas. In this case, screenwriters may fall into a creative bottleneck and find it difficult to break through existing ideas, affecting the diversity and innovation of their creations.

[0007] 3. Insufficient script optimization: Existing tools are difficult to deeply analyze the script outline and plot, and provide targeted optimization suggestions and modification opinions. Lacking intelligent and personalized analysis tools, screenwriters can only rely on personal experience when optimizing script structure, character relationships and plot settings, and it is difficult to ensure the stability of creative quality.

[0008] 4. It is difficult to meet personalized needs: Existing tools cannot provide customized creative guidance based on the individual needs of screenwriters, and cannot meet the diverse needs of different screenwriters in the creative process. Each screenwriter has different creative styles and preferences. Existing tools lack flexibility and adaptability, making it difficult to provide screenwriters with personalized creative support.

[0009] 5. Lack of networking and knowledge base support: Existing tools cannot combine Internet and knowledge base resources to provide real-time reference information and materials, which limits the diversity and depth of creation. During the creative process, screenwriters often need to refer to a large amount of external materials and information. Existing tools cannot effectively integrate these resources, resulting in a cumbersome and inefficient creative process.

[0010] 6. The answers are not targeted and timely enough: During the creative process, screenwriters may need to conduct detailed discussions and analyses on a specific plot or chapter. The answers provided by existing tools are often not targeted enough to meet the specific needs of screenwriters. At the same time, the answers provided by existing tools are not timely enough to provide the latest reference information, which limits the real-time and cutting-edge nature of the creation.

[0011] 7. Poor user experience: Existing tools have deficiencies in user interface design and interaction methods, making it difficult to provide a good user experience. Screenwriters may encounter problems such as complex operations and slow responses during use, which affects the smoothness of the creative process and user satisfaction.

[0012] In view of the above problems, as the demand for original content in the film and television industry is growing, traditional script creation methods and tools can no longer meet current needs. Faced with complex creative tasks and a large amount of material requirements, it is urgent to develop a new technical solution to achieve efficient and intelligent analysis and optimization of script content, provide inspiration and creative support, so as to provide rich and in-depth original materials for film and television creation, and promote the innovation and diversified development of film and television works. Summary of the invention

[0013] In view of the above, it is necessary to provide a method, device, equipment and medium for generating film and television data based on a large language model, aiming to solve the problem of being unable to assist in generating effective film and television data when users are creating.

[0014] A method for generating film and television data based on a large language model, the method for generating film and television data based on a large language model comprising:

[0015] In response to the film and television data generation instruction, the film and television data generation instruction is parsed to obtain a script to be processed;

[0016] Extracting elements from the script to be processed to obtain script elements;

[0017] Preprocessing the script elements to obtain data to be processed;

[0018] Performing script analysis on the data to be processed using a large language model to obtain a script analysis result;

[0019] When receiving a user question triggered by the script analysis result, generating a prompt word according to the script analysis result and the user question;

[0020] Selecting a knowledge base based on the prompt word;

[0021] The large language model is used to respond to the user's question with the knowledge base to obtain a film and television data generation result.

[0022] According to a preferred embodiment of the present invention, extracting elements from the script to be processed to obtain script elements includes:

[0023] Identifying a plurality of structural elements included in the script to be processed;

[0024] Extract the script content of the script to be processed according to each structural element to obtain the elements corresponding to each structural element;

[0025] Integrate the elements corresponding to each structural element to obtain the script elements;

[0026] The structural elements include titles, characters, and plot paragraphs.

[0027] According to a preferred embodiment of the present invention, the preprocessing of the script elements to obtain the data to be processed includes:

[0028] Removing non-plot data from the script elements to obtain first data;

[0029] Performing standardization processing on the first data to obtain second data;

[0030] Perform word segmentation processing on the second data to obtain the data to be processed.

[0031] According to a preferred embodiment of the present invention, before using the large language model to perform script analysis on the data to be processed, the method further includes:

[0032] The large language model is multi-task trained by a multi-task learning algorithm, and the large language model is adaptively learned based on demand data in the film and television field.

[0033] According to a preferred embodiment of the present invention, the script analysis of the data to be processed using a large language model to obtain the script analysis result includes:

[0034] Based on the preset prompt words, the large language model is used to perform structural processing on the story plot in the data to be processed to obtain a plot structure diagram, and the large language model is used to extract the character relationship in the data to be processed to obtain a character relationship diagram;

[0035] Generate script optimization suggestions based on the plot structure diagram and the character relationship diagram;

[0036] The plot structure diagram, the character relationship diagram and the script optimization suggestions are integrated to obtain the script analysis result.

[0037] According to a preferred embodiment of the present invention, the selecting a knowledge base based on the prompt word comprises:

[0038] Determine whether there is a need for Internet access according to the prompt word;

[0039] When there is a need for Internet access, determining the external knowledge base used for Internet search as the knowledge base; or

[0040] When there is no need to connect to the Internet, an internal knowledge base that pre-stores a plurality of scripts is determined as the knowledge base.

[0041] According to a preferred embodiment of the present invention, the step of using the large language model to respond to the user's question with the knowledge base to obtain a film and television data generation result includes:

[0042] Performing a query in the knowledge base based on the user's question to obtain a query result;

[0043] Continuously optimizing the prompt words of the large language model based on the user's question and the query result until receiving a confirmation signal from the user regarding the output result of the large language model;

[0044] Obtaining a data source address in the knowledge base on which the output result of the large language model is based;

[0045] Establishing a hyperlink according to the data source address;

[0046] The hyperlink is added to the output result of the large language model to obtain the film and television data generation result.

[0047] A device for generating film and television data based on a large language model, the device for generating film and television data based on a large language model comprising:

[0048] A parsing unit, for responding to a film and television data generation instruction, parsing the film and television data generation instruction to obtain a script to be processed;

[0049] An extraction unit, used for extracting elements from the script to be processed to obtain script elements;

[0050] A preprocessing unit, used for preprocessing the script elements to obtain data to be processed;

[0051] An analysis unit, configured to perform script analysis on the data to be processed using a large language model to obtain a script analysis result;

[0052] A generating unit, configured to generate a prompt word according to the script analysis result and the user question when receiving a user question triggered by the script analysis result;

[0053] A selection unit, configured to select a knowledge base based on the prompt word;

[0054] The response unit is used to respond to the user's question using the large language model and the knowledge base to obtain a film and television data generation result.

[0055] A computer device, comprising:

[0056] a memory storing at least one instruction; and

[0057] A processor executes instructions stored in the memory to implement the method for generating film and television data based on a large language model.

[0058] A computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in a computer device to implement the method for generating film and television data based on a large language model.

[0059] It can be seen from the above technical solutions that the present invention can extract elements of the script to be processed to obtain script elements, so as to obtain effective content in the script; pre-process the script elements to obtain data to be processed, so as to further optimize the extracted script elements, so as to facilitate better recognition and processing by the model; use a large language model to perform script analysis on the processed data to obtain script analysis results, so as to obtain structured content of the script; generate prompt words according to the script analysis results and user questions, so as to improve the prompt words in combination with basic structured content, so that the model can respond to user questions more accurately; select a knowledge base based on the prompt words to provide a more reasonable knowledge base, further improve the accuracy of the model response, and thus provide users with effective film and television data in combination with artificial intelligence means to assist users in script creation. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of a preferred embodiment of the method for generating film and television data based on a large language model of the present invention.

[0061] Figure 2 It is a functional module diagram of a preferred embodiment of the film and television data generation device based on a large language model of the present invention.

[0062] Figure 3 It is a structural diagram of a computer device of a preferred embodiment of the present invention for implementing a method for generating film and television data based on a large language model. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0064] like Figure 1 FIG. 1 is a flowchart of a preferred embodiment of the method for generating film and television data based on a large language model of the present invention. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0065] The film and television data generation method based on the large language model is applied to one or more computer devices, and the computer device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0066] The computer device may be any electronic product that can perform human-computer interaction with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.

[0067] The computer device may also include a network device and / or a user device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.

[0068] The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0069] Among them, Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0070] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0071] The network where the computer device is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0072] S10, in response to the film and television data generation instruction, parsing the film and television data generation instruction to obtain a script to be processed.

[0073] In this embodiment, when it is detected that a script has been uploaded on the user interaction interface, it is determined that the film and television data generation instruction has been received.

[0074] Among them, through the user interaction interface, the operation and control process can be simplified, so that users can easily create and optimize scripts even without a deep technical background.

[0075] The script may be in the format of a text file, a Word document, or a PDF (Portable Document Format) file.

[0076] In this embodiment, the script to be processed can be located by parsing the film and television data generation instruction.

[0077] S11, extracting elements from the script to be processed to obtain script elements.

[0078] In this embodiment, extracting elements from the script to be processed to obtain script elements includes:

[0079] Identifying a plurality of structural elements included in the script to be processed;

[0080] Extract the script content of the script to be processed according to each structural element to obtain the elements corresponding to each structural element;

[0081] Integrate the elements corresponding to each structural element to obtain the script elements;

[0082] The structural elements include titles, characters, and plot paragraphs.

[0083] The title may include the main title of the script to be processed and the subtitles of each chapter.

[0084] The characters may include all the names of characters appearing in the script to be processed.

[0085] The plot paragraphs may include a detailed description of each plot or event in the script to be processed.

[0086] S12, pre-processing the script elements to obtain data to be processed.

[0087] In this embodiment, the preprocessing of the script elements to obtain the data to be processed includes:

[0088] Removing non-plot data from the script elements to obtain first data;

[0089] Performing standardization processing on the first data to obtain second data;

[0090] Perform word segmentation processing on the second data to obtain the data to be processed.

[0091] The non-plot data may include information that is irrelevant to the plot or is useless, such as headers, footers, advertisements, etc.

[0092] The script can be converted into a unified format through the standardization process to ensure that all text can be correctly recognized and processed by the model. For example, the standardization process can include standardizing punctuation marks, character case conversion, etc., such as standardizing all punctuation marks into English format and converting all uppercase letters to lowercase letters.

[0093] The word segmentation process can be used to segment a continuous text into individual words. The purpose of word segmentation is to allow the model to better understand each word in the text. For example, "script writing is a complex process" can be divided into "script", "creation", "is", "a", "complex", "of", and "process".

[0094] Through the above preprocessing operations, the noise in the script can be removed and the text content can be standardized to facilitate subsequent model recognition and processing.

[0095] S13, using a large language model to perform script analysis on the data to be processed to obtain a script analysis result.

[0096] In this embodiment, before using the large language model to perform script analysis on the data to be processed, the method further includes:

[0097] The large language model is multi-task trained by a multi-task learning algorithm, and the large language model is adaptively learned based on demand data in the film and television field.

[0098] In the above embodiment, the model uses a multi-task learning method to simultaneously perform training on multiple tasks, such as plot recognition, character relationship analysis, sentiment analysis, etc., which enables the model to comprehensively consider information from multiple dimensions when processing the script outline; the model performs adaptive learning based on the needs of specific fields. For example, in response to the needs of film and television script creation, the model can learn the writing styles and structural characteristics of a large number of film and television scripts to further optimize its analysis capabilities.

[0099] In this embodiment, the script analysis of the data to be processed using the large language model to obtain the script analysis results includes:

[0100] Based on the preset prompt words, the large language model is used to perform structural processing on the story plot in the data to be processed to obtain a plot structure diagram, and the large language model is used to extract the character relationship in the data to be processed to obtain a character relationship diagram;

[0101] Generate script optimization suggestions based on the plot structure diagram and the character relationship diagram;

[0102] The plot structure diagram, the character relationship diagram and the script optimization suggestions are integrated to obtain the script analysis result.

[0103] Among them, the preset prompt words can be used to instruct the large language model to parse the script content to obtain a structured plot structure diagram and character relationship diagram.

[0104] The preset prompt words can be configured according to user needs (such as screenwriter needs) to provide highly customized prompt words and creative guidance. Whether it is style, subject matter or creative preference, the system can be flexibly adjusted to meet the diverse needs of screenwriters in the creative process.

[0105] Through the above-mentioned embodiments, it is possible to preliminarily generate script optimization suggestions.

[0106] S14, when a user question triggered by the script analysis result is received, a prompt word is generated according to the script analysis result and the user question.

[0107] In this embodiment, the script analysis results are combined with user questions to generate prompt words that are easier for the large language model to understand, thereby guiding the large language model to respond to user questions more accurately in combination with the scripts uploaded by the user.

[0108] S15, selecting a knowledge base based on the prompt word.

[0109] In this embodiment, the selecting a knowledge base based on the prompt word includes:

[0110] Determine whether there is a need for Internet access according to the prompt word;

[0111] When there is a need for Internet access, determining the external knowledge base used for Internet search as the knowledge base; or

[0112] When there is no need to connect to the Internet, an internal knowledge base that pre-stores a plurality of scripts is determined as the knowledge base.

[0113] Specifically, if it is determined that the user's question requires the latest information or external reference materials, such as the latest film and television trends, current audience preferences, real cases of specific plots, etc., it is determined to conduct an online search. For example, if the user asks "What are the current audience's favorite plot twists?", it can be determined that this is a question that requires the latest information, and an advanced search engine can be used to conduct an online search to obtain relevant latest information and reference materials.

[0114] Specifically, if it is determined that the user's question involves an existing script or storyline, such as the development of a specific character, the plot design in a classic script, etc., it can be determined that a knowledge base query is performed. For example: if the user asks "What are the common plot settings in Shakespeare's plays?", it can be determined that this is a question involving an existing script, and the internal knowledge base is queried. The internal knowledge base can contain a large number of scripts, novels, and related documents, and provide rich creative materials and reference content.

[0115] By combining the Internet search function, the latest reference information and materials can be obtained in real time, providing authoritative external resource support. The online search mode ensures that screenwriters can use the latest information and resources to enrich their creative content.

[0116] The internal knowledge base can include a large amount of high-quality scripts and novels. Through knowledge base query, detailed plot references, creative ideas and optimization suggestions can be obtained, further enhancing the richness and depth of the script.

[0117] This embodiment intelligently integrates the results of online search and knowledge base query to provide a comprehensive, authoritative and targeted creative guidance to assist screenwriters in their creation with the support of rich materials and information.

[0118] S16, using the large language model to respond to the user's question with the knowledge base to obtain a film and television data generation result.

[0119] In this embodiment, the use of the large language model to respond to the user's question with the knowledge base to obtain the film and television data generation result includes:

[0120] Performing a query in the knowledge base based on the user's question to obtain a query result;

[0121] Continuously optimizing the prompt words of the large language model based on the user's question and the query result until receiving a confirmation signal from the user regarding the output result of the large language model;

[0122] Obtaining a data source address in the knowledge base on which the output result of the large language model is based;

[0123] Establishing a hyperlink according to the data source address;

[0124] The hyperlink is added to the output result of the large language model to obtain the film and television data generation result.

[0125] Among them, hyperlinks can facilitate the location of data sources, allowing users to obtain more effective data resources.

[0126] Among them, the film and television data generation results may include optimization suggestions for the script, creative direction, etc., which can be generated specifically based on user questions.

[0127] In the above embodiments, networking or querying the knowledge base are preparations for the final generation of results. The results found through networking or the knowledge base will be included in the underlying prompt words for training the large model. The content generated by the large model will be affected by the underlying prompt words to the greatest extent, thereby generating the answer that best suits the user's question.

[0128] This embodiment significantly improves the efficiency of script creation through automated data collection, preprocessing and plot analysis processes. Compared with traditional manual processing methods, it can process and analyze a large amount of script content in a short period of time, greatly shortening the creation cycle from the first draft of the script to the final version. At the same time, this embodiment can respond to the screenwriter's request in real time, provide quick analysis and suggestions, reduce the screenwriter's waiting time during the creative process, and thus improve the overall creative efficiency.

[0129] Through this embodiment, in combination with user questions, a variety of auxiliary creation functions can be provided, such as outline creation assistant, story inspiration assistant, plot segment setting assistant, etc. Each assistant can help screenwriters inspire inspiration and creativity from multiple angles according to specific creative needs; at the same time, using a large language model to generate intelligent prompts based on user questions and provide suggestions for creative ideas, it can help screenwriters break through creative bottlenecks and expand their thinking, thereby generating more creative and novel plots; in combination with user questions, the script outline can also be deeply analyzed to identify potential structural problems and optimization opportunities, and through the analysis of plot structure, character relationships, theme expression, etc., it can also provide refined optimization suggestions to help screenwriters rewrite and improve the script, thereby improving the overall quality of the script; in combination with user questions, detailed modification opinions and optimization ideas can be provided for specific chapters and segments of the script to help screenwriters further polish and improve the content of the script.

[0130] This embodiment reduces the use of paper materials through digital processing and analysis, which is helpful for environmental protection. At the same time, the optimized algorithm design and efficient computing resource management also reduce the energy consumption of the system.

[0131] This embodiment combines the interactivity of the large language model, not only excels in creative efficiency, inspiration, script optimization and personalized guidance, but also provides screenwriters with rich reference information and materials through networking and knowledge base support. At the same time, combined with a simple user interaction interface and operation, it comprehensively improves the quality and efficiency of script creation and promotes the innovation and diversified development of film and television works.

[0132] It can be seen from the above technical solutions that the present invention can extract elements of the script to be processed to obtain script elements, so as to obtain effective content in the script; pre-process the script elements to obtain data to be processed, so as to further optimize the extracted script elements, so as to facilitate better recognition and processing by the model; use a large language model to perform script analysis on the processed data to obtain script analysis results, so as to obtain structured content of the script; generate prompt words according to the script analysis results and user questions, so as to improve the prompt words in combination with basic structured content, so that the model can respond to user questions more accurately; select a knowledge base based on the prompt words to provide a more reasonable knowledge base, further improve the accuracy of the model response, and thus provide users with effective film and television data in combination with artificial intelligence means to assist users in script creation.

[0133] like Figure 2As shown, it is a functional module diagram of a preferred embodiment of the film and television data generation device based on a large language model of the present invention. The film and television data generation device 11 based on a large language model includes a parsing unit 110, an extraction unit 111, a preprocessing unit 112, an analysis unit 113, a generation unit 114, a selection unit 115, and a response unit 116. The module / unit referred to in the present invention refers to a series of computer program segments that can be executed by a processor and can perform fixed functions, which are stored in a memory. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0134] The parsing unit 110 is used to respond to the film and television data generation instruction and parse the film and television data generation instruction to obtain the script to be processed;

[0135] The extraction unit 111 is used to extract elements from the script to be processed to obtain script elements;

[0136] The preprocessing unit 112 is used to preprocess the script elements to obtain data to be processed;

[0137] The analysis unit 113 is used to perform script analysis on the data to be processed using a large language model to obtain a script analysis result;

[0138] The generating unit 114 is configured to generate a prompt word according to the script analysis result and the user question when receiving a user question triggered by the script analysis result;

[0139] The selection unit 115 is used to select a knowledge base based on the prompt word;

[0140] The response unit 116 is used to respond to the user's question using the large language model and the knowledge base to obtain a film and television data generation result.

[0141] It can be seen from the above technical solutions that the present invention can extract elements of the script to be processed to obtain script elements, so as to obtain effective content in the script; pre-process the script elements to obtain data to be processed, so as to further optimize the extracted script elements, so as to facilitate better recognition and processing by the model; use a large language model to perform script analysis on the processed data to obtain script analysis results, so as to obtain structured content of the script; generate prompt words according to the script analysis results and user questions, so as to improve the prompt words in combination with basic structured content, so that the model can respond to user questions more accurately; select a knowledge base based on the prompt words to provide a more reasonable knowledge base, further improve the accuracy of the model response, and thus provide users with effective film and television data in combination with artificial intelligence means to assist users in script creation.

[0142] like Figure 3The figure is a schematic diagram of the structure of a computer device of a preferred embodiment of the present invention for implementing the method for generating film and television data based on a large language model.

[0143] The computer device 1 may include a memory 12, a processor 13 and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a program for generating film and television data based on a large language model.

[0144] Those skilled in the art will appreciate that the schematic diagram is merely an example of the computer device 1 and does not constitute a limitation on the computer device 1. The computer device 1 may be a bus-type structure or a star-type structure. The computer device 1 may also include more or less other hardware or software than shown in the diagram, or a different arrangement of components. For example, the computer device 1 may also include input and output devices, network access devices, etc.

[0145] It should be noted that the computer device 1 is only an example, and other existing or future electronic products that are suitable for the present invention should also be included in the protection scope of the present invention and included here by reference.

[0146] Among them, the memory 12 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the computer device 1, such as a mobile hard disk of the computer device 1. In other embodiments, the memory 12 can also be an external storage device of the computer device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 1. Further, the memory 12 can also include both an internal storage unit of the computer device 1 and an external storage device. The memory 12 can not only be used to store application software and various types of data installed in the computer device 1, such as the code of the film and television data generation program based on the large language model, but also can be used to temporarily store data that has been output or is to be output.

[0147] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 13 is the control core (Control Unit) of the computer device 1, and uses various interfaces and lines to connect the various components of the entire computer device 1, and executes or executes programs or modules stored in the memory 12 (for example, executing a film and television data generation program based on a large language model, etc.), and calls the data stored in the memory 12 to execute various functions of the computer device 1 and process data.

[0148] The processor 13 executes the operating system of the computer device 1 and various installed applications. The processor 13 executes the applications to implement the steps in the above-mentioned embodiments of the method for generating film and television data based on a large language model, for example Figure 1 Steps shown.

[0149] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to implement the present invention. The one or more modules / units may be a series of computer-readable instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the computer device 1. For example, the computer program may be divided into a parsing unit 110, an extraction unit 111, a preprocessing unit 112, an analysis unit 113, a generation unit 114, a selection unit 115, and a response unit 116.

[0150] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, and includes a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to execute the part of the film and television data generation method based on a large language model described in various embodiments of the present invention.

[0151] If the module / unit integrated in the computer device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware devices through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of each of the above-mentioned method embodiments can be implemented.

[0152] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, etc.

[0153] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0154] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0155] The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The bus is represented by only one straight line, but it does not mean that there is only one bus or one type of bus. The bus is configured to realize the connection and communication between the memory 12 and at least one processor 13, etc.

[0156] Although not shown, the computer device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 13 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The computer device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0157] Furthermore, the computer device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the computer device 1 and other computer devices.

[0158] Optionally, the computer device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the computer device 1 and to display a visual user interface.

[0159] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0160] It can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the computer device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0161] Combination Figure 1 , the memory 12 in the computer device 1 stores a plurality of instructions to implement a method for generating film and television data based on a large language model, and the processor 13 can execute the plurality of instructions to implement:

[0162] In response to the film and television data generation instruction, the film and television data generation instruction is parsed to obtain a script to be processed;

[0163] Extracting elements from the script to be processed to obtain script elements;

[0164] Preprocessing the script elements to obtain data to be processed;

[0165] Performing script analysis on the data to be processed using a large language model to obtain a script analysis result;

[0166] When receiving a user question triggered by the script analysis result, generating a prompt word according to the script analysis result and the user question;

[0167] Selecting a knowledge base based on the prompt word;

[0168] The large language model is used to respond to the user's question with the knowledge base to obtain a film and television data generation result.

[0169] Specifically, the specific implementation method of the processor 13 for the above instructions can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0170] It should be noted that the data involved in this case were all obtained legally.

[0171] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0172] The present invention can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present invention can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0173] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0174] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0175] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0176] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0177] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the present invention can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for generating film and television data based on a large language model, characterized in that: The film and television data generation method based on the large language model includes: In response to the film and television data generation instruction, the film and television data generation instruction is parsed to obtain a script to be processed; Extracting elements from the script to be processed to obtain script elements; Preprocessing the script elements to obtain data to be processed; Performing script analysis on the data to be processed using a large language model to obtain a script analysis result; When receiving a user question triggered by the script analysis result, generating a prompt word according to the script analysis result and the user question; Selecting a knowledge base based on the prompt word; The large language model is used to respond to the user's question with the knowledge base to obtain a film and television data generation result.

2. The method for generating film and television data based on a large language model according to claim 1, characterized in that: The extracting of elements from the script to be processed to obtain the script elements includes: Identifying a plurality of structural elements included in the script to be processed; Extract the script content of the script to be processed according to each structural element to obtain the elements corresponding to each structural element; Integrate the elements corresponding to each structural element to obtain the script elements; The structural elements include titles, characters, and plot paragraphs.

3. The method for generating film and television data based on a large language model according to claim 1, characterized in that: The preprocessing of the script elements to obtain the data to be processed includes: Removing non-plot data from the script elements to obtain first data; Performing standardization processing on the first data to obtain second data; Perform word segmentation processing on the second data to obtain the data to be processed.

4. The method for generating film and television data based on a large language model according to claim 1, characterized in that: Before using the large language model to perform script analysis on the data to be processed, the method further includes: The large language model is multi-task trained by a multi-task learning algorithm, and the large language model is adaptively learned based on demand data in the film and television field.

5. The method for generating film and television data based on a large language model according to claim 1, characterized in that: The script analysis of the data to be processed using the large language model to obtain the script analysis results includes: Based on the preset prompt words, the large language model is used to perform structural processing on the story plot in the data to be processed to obtain a plot structure diagram, and the large language model is used to extract the character relationship in the data to be processed to obtain a character relationship diagram; Generate script optimization suggestions based on the plot structure diagram and the character relationship diagram; The plot structure diagram, the character relationship diagram and the script optimization suggestions are integrated to obtain the script analysis result.

6. The method for generating film and television data based on a large language model according to claim 1, characterized in that: The selecting of the knowledge base based on the prompt word comprises: Determine whether there is a need for Internet access according to the prompt word; When there is a need for Internet access, determining the external knowledge base used for Internet search as the knowledge base; or When there is no need to connect to the Internet, an internal knowledge base that pre-stores a plurality of scripts is determined as the knowledge base.

7. The method for generating film and television data based on a large language model according to claim 1, characterized in that: The step of using the large language model to respond to the user's question with the knowledge base to obtain a film and television data generation result includes: Performing a query in the knowledge base based on the user's question to obtain a query result; Continuously optimizing the prompt words of the large language model based on the user's question and the query result until receiving a confirmation signal from the user regarding the output result of the large language model; Obtaining a data source address in the knowledge base on which the output result of the large language model is based; Establishing a hyperlink according to the data source address; The hyperlink is added to the output result of the large language model to obtain the film and television data generation result.

8. A device for generating film and television data based on a large language model, characterized in that: The film and television data generation device based on the large language model includes: A parsing unit, for responding to a film and television data generation instruction, parsing the film and television data generation instruction to obtain a script to be processed; An extraction unit, used for extracting elements from the script to be processed to obtain script elements; A preprocessing unit, used for preprocessing the script elements to obtain data to be processed; An analysis unit, configured to perform script analysis on the data to be processed using a large language model to obtain a script analysis result; A generating unit, configured to generate a prompt word according to the script analysis result and the user question when receiving a user question triggered by the script analysis result; A selection unit, used for selecting a knowledge base based on the prompt word; The response unit is used to respond to the user's question using the large language model and the knowledge base to obtain a film and television data generation result.

9. A computer device, characterized in that: The computer device comprises: a memory storing at least one instruction; and A processor executes instructions stored in the memory to implement the method for generating film and television data based on a large language model as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in a computer device to implement the method for generating film and television data based on a large language model as described in any one of claims 1 to 7.

Images