Intelligent script generation method, system and equipment based on large model

Abstract

The invention relates to the technical field of artificial intelligence, in particular to an intelligent script generation method, system and device based on a large model, and the method comprises the steps: obtaining the historical creation data of a user about a video script; learning the historical creation data by using a large model to generate figure portrait information of the user; and according to the figure portrait information and a set script generation rule, reasoning by using a large model and generating a video script. According to the method, the video script creation efficiency of the user can be improved, the problem that the script creation thinking of the user is exhausted is solved, and the user is helped to carry out continuous business innovation and creation.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, system and device for intelligently generating scripts based on a large model. Background Art

[0002] With the development of the Internet, the network economy is booming. The network economy presents a series of new features and trends, and contains huge potential for expanding domestic demand and increasing consumption. In today's era of booming short video marketing, promotional videos have become an important means for companies and individuals to showcase their products and services. And promotional videos often need to be produced based on video scripts. The video script is the blueprint for the creation of the entire promotional video, which determines the narrative logic, picture presentation and emotional communication of the video. However, at present, users usually need to spend a lot of time and energy on conception and creation to complete the video script, which is easy to exhaust their thinking and very inefficient. Summary of the invention

[0003] The present application provides a method, system and device for intelligent script generation based on a large model to solve the problem of low efficiency in current script creation.

[0004] In a first aspect, the present application provides a method for intelligently generating scripts based on a large model, comprising: Obtain the user's historical creation data on video scripts; Using a large model to learn the historical creation data, and generate character portrait information of the user; Based on the character portrait information and the set script generation rules, the big model is used to perform reasoning and generate the video script.

[0005] Furthermore, the historical creation data is video-based data, including narration subtitles, image information, and voice information.

[0006] Furthermore, the use of a large model to learn the historical creation data to generate the character portrait information of the user includes: Processing the historical creation data through multiple algorithms to construct multi-dimensional character features of the user; Generate character portrait information of the user based on the multi-dimensional character features.

[0007] Furthermore, the historical creation data is processed by multiple algorithms to construct the multi-dimensional character features of the user, including: Identifying the basic information of the user from the historical creation data through a text recognition algorithm; Acquire the user's life information and technical mastery information from the historical creation data through video segmentation, image feature recognition and deep learning algorithms; The user's psychological characteristics, behavioral characteristics and dynamic characteristics are obtained from the historical creation data through natural semantic processing, video image processing and deep learning algorithms.

[0008] Furthermore, the basic information of the person includes age, gender, geographical location, occupation, and educational background; The life information includes interests, hobbies, living habits, and values; the technical mastery information includes technical equipment, network behavior, and digital literacy; The psychological characteristics include personality traits and emotional tendencies, the behavioral characteristics include website behavior, application behavior, and task behavior, and the dynamic characteristics include time dimension, event triggering, and trend analysis.

[0009] Furthermore, the method of using a large model to perform reasoning and generate a video script based on the character portrait information and the set script generation rules includes: Based on the character portrait information, a large model is used for reasoning to generate a video script that conforms to the set script generation rules.

[0010] Furthermore, the script generation rules include current hot spot information, script creation rules, and business logic constraints.

[0011] On the second aspect, the present application provides a big model-based intelligent script generation system, including a historical data system, a general big model base, an intelligent learning system, a character knowledge system, a script generation rule system, a reasoning generation system and a script generation system; the big model-based intelligent script generation system is used to implement the big model-based intelligent script generation method as described above.

[0012] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for intelligent script generation based on a large model as described above is implemented.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the intelligent script generation method based on the big model as described above.

[0014] The above technical solution of the present application has the following advantages: The first aspect of the present application provides a big model-based intelligent script generation method, which obtains the user's historical creation data on video scripts, uses the big model to learn the historical creation data, generates the user's character portrait information, and uses the big model to reason and generate the video script based on the character portrait information and the set script generation rules. By utilizing the big model's intelligent learning and reasoning capabilities, it can improve the user's video script creation efficiency, solve the problem of user script creation thinking exhaustion, and help users to carry out continuous business innovation and creation.

[0015] It can be understood that the beneficial effects of the second, third and fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 A flowchart of the intelligent script generation method based on a large model provided for this application; Figure 2 A flowchart for generating character portrait information provided for this application; Figure 3 Generate a flowchart for the script provided for this application; Figure 4 The structural diagram of the script intelligent generation system based on the big model provided for this application; Figure 5 A schematic diagram of the structure of the electronic device provided in this application. DETAILED DESCRIPTION

[0018] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0019] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0020] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0021] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways. "Multiple" means "two or more".

[0022] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0023] like Figure 1 As shown, an embodiment of the present application provides a method for intelligent script generation based on a big model, which specifically includes the following steps: obtaining the user's historical creation data on video scripts; using the big model to learn the historical creation data to generate the user's character portrait information; and using the big model to perform reasoning and generate a video script based on the character portrait information and the set script generation rules.

[0024] In some embodiments, the historical creation data is video-based data, including narration subtitles, image information, and voice information.

[0025] In some embodiments, the use of a large model to learn the historical creation data to generate the user's character portrait information includes: processing the historical creation data through multiple algorithms to construct multi-dimensional character features of the user; and generating the user's character portrait information based on the multi-dimensional character features.

[0026] In some embodiments, the historical creation data is processed by multiple algorithms to construct the multi-dimensional character features of the user, including: identifying the basic character information of the user from the historical creation data through a text recognition algorithm; obtaining the user's life information and technical mastery information from the historical creation data through video segmentation, image feature recognition and deep learning algorithms; obtaining the user's psychological characteristics, behavioral characteristics and dynamic characteristics from the historical creation data through natural semantic processing, video image processing and deep learning algorithms.

[0027] In some embodiments, the basic information of the character includes age, gender, geographic location, occupation, and educational background; the life information includes interests, hobbies, living habits, and values; the technical mastery information includes technical equipment, network behavior, and digital literacy; the psychological characteristics include personality traits and emotional tendencies; the behavioral characteristics include website behavior, application behavior, and homework behavior; the dynamic characteristics include time dimension, event triggering, and trend analysis.

[0028] In some embodiments, the use of a large model to perform reasoning and generate a video script based on the character portrait information and set script generation rules includes: using a large model to perform reasoning based on the character portrait information to generate a video script that complies with the set script generation rules.

[0029] In some embodiments, the script generation rules include current hot spot information, script creation rules, and business logic constraints.

[0030] By obtaining the user's historical creation data on video scripts, training and intelligent learning of the historical creation data are performed to form the user's character portrait information, providing the user's basic characteristics for new script generation. The character portrait information generation process is as follows: Figure 2 As shown in the figure, historical creation data is mainly based on video data, which is composed of captions, image information, voice information, etc. The character portrait information is generated through the learning, reasoning and integration of historical texts, videos, images and other data by algorithms.

[0031] Explanation subtitles: Based on the OCR text recognition system, extract the self-introduction in the subtitles (such as age, gender, geographical features, occupation and educational background, etc.), the theme of this video explanation (such as food, scenery, etc.), and the video image mainly contains the gender, expression, action, hobbies, behavior and other content of the character, as well as the geographical background, mountains and rivers, buildings, life scenes and other image information of the display task. Based on the text recognition algorithm system, the basic attribute information of the character can be automatically identified, such as age, gender, geographical location, occupation and educational background. Among them, age: age range; gender: male, female; geographical location: city, region; occupation: industry, position; educational background: academic qualifications and professional fields.

[0032] Based on the study of video data, we can obtain the life information and technical mastery information of the characters, such as hobbies, living habits, values, technical equipment, network behavior, digital literacy, etc. Algorithms: video segmentation, image feature recognition, deep learning and reasoning algorithms, acquisition process: video data acquisition → video segmentation → image extraction → image feature recognition → deep learning → image reasoning, through the above technical flow to obtain the life information and technical mastery information of the characters. Life information includes hobbies: music, movies, sports, reading, travel, etc.; living habits: fitness habits, dietary preferences; values: attention to social events, comments and value orientation. Technical mastery information includes technical equipment: commonly used equipment (such as smart phones, tablets, computers); network behavior: browsing habits, acceptance of new technologies; digital literacy: familiarity with new technologies, such as whether familiar with artificial intelligence, the Internet of Things, etc.

[0033] Based on the fusion algorithms of NLP natural semantic processing, video image processing, deep learning, etc., we can obtain the psychological characteristics, behavioral data, dynamic characteristics such as personality characteristics and emotional orientation, website behavior, application behavior, work behavior and dynamic characteristics analysis that change over time and space. By extracting historical data, we establish a character theme library with characters as units, extract all the information of the characters into the character theme library for data fusion, elimination, cleaning and screening, and obtain high-precision character information. Psychological characteristics include personality characteristics: extroversion, introversion, caution, impulsiveness, etc.; emotional tendencies: optimism, pessimism, anxiety, calmness, etc. Behavioral data include website behavior: visit frequency, dwell time, click path, conversion rate; application behavior: usage frequency, function preference, retention rate; work behavior: historical creation video, facial expression, behavior action. Dynamic characteristics include time dimension: changes in the user's historical creation data over time; event triggering: changes in creation behavior with specific events; trend analysis: long-term trends in the development of the script and video data created.

[0034] Based on the user's character portrait information and the set script generation rules, a new video script is generated through reasoning and intelligence. The new video script generation process is as follows: Figure 3 As shown. Based on the intelligent learning function of the big model, through the graphics processing algorithm, video processing algorithm, OCR text recognition algorithm, NLP natural semantic understanding, reasoning algorithm and algorithm fusion, the basic information, life information, technical mastery, psychological characteristics, behavioral characteristics and dynamic characteristics of the character are obtained, and multi-dimensional character characteristics are constructed to form character portrait information. The character portrait information ensures that the created script meets the basic characteristics of the character. Search for the current hot traffic events, combine the duration / expression / emotion / language of the script generation, and the business logic rules between the scripts, put the above rule constraints into the big model reasoning system, and create a new video script that meets the script generation rules.

[0035] The script generation rules are as follows: 1. Obtain current traffic hotspot information (such as 315 anti-counterfeiting and food safety); 2. Learn based on historical data of characters (such as historical data of food bloggers); 3. Generate new food scripts based on the user's occupation, such as food blogger, and automatically generate text dialogues related to food safety and anti-counterfeiting in the dialogue link when creating the script; 4. Combine traffic hotspots and user's occupational attributes to realize the generation of new user-created scripts and scripts related to existing hot traffic in the script generation.

[0036] The big model-based intelligent script generation method provided in the embodiment of the present application obtains the user's historical creation data on video scripts, uses the big model to learn the historical creation data, generates the user's character portrait information, and uses the big model to reason and generate the video script based on the character portrait information and the set script generation rules. By utilizing the big model's intelligent learning and reasoning capabilities, it can improve the user's video script creation efficiency, solve the problem of user script creation thinking exhaustion, and help users to carry out continuous business innovation and creation.

[0037] Corresponding to the big model-based intelligent script generation method described in the above embodiment, Figure 4 As shown, an embodiment of the present application also provides a big model-based intelligent script generation system, including a historical data system, a general big model base, an intelligent learning system, a character knowledge system, a script generation rule system, a reasoning generation system and a script generation system; the big model-based intelligent script generation system is used to implement the big model-based intelligent script generation method as described above.

[0038] The historical data system mainly refers to the user's historical videos and excellent scripts. The historical data is stored in the form of a database, and the storage of the historical data system is realized by creating a specific file system. The general large model base is the core of the implementation of this application. By calling the API interface of open source large models such as deepseek, the access of the general large model capabilities is realized. The general large model mainly realizes the intelligent learning of historical data and the inference generation of scripts based on script generation rules. The intelligent learning system realizes the learning of historical data based on the general large model base.

[0039] The character knowledge system stores the user's character portrait information. The script generation rule system is the rules and constraints for the system to generate scripts, mainly including current network hot spots, script creation rules, business logic and other constraints. The creation of scripts is guided by re-emerging the generation rule system in the reasoning generation system. The reasoning generation system is based on the reasoning ability of the big model, combining the character portraits, emotions, and abilities in the generation rule system and the character knowledge system. By calling the intelligent reasoning ability of the big model, it generates scripts that meet the characteristics of the task and meet the traffic hot spots. The script generation system is used to store the generated scripts.

[0040] It should be noted that the information interaction, execution process, etc. between the above-mentioned modules / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0041] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0042] The present application also provides an electronic device, such as Figure 5 As shown, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the large model-based intelligent script generation method provided in the first aspect are implemented.

[0043] In applications, the electronic device may include, but is not limited to, a processor and a memory. Figure 5 This is only an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input and output devices, network access devices, etc. Input and output devices may include cameras, audio acquisition / playback devices, display screens, etc. Network access devices may include a network module for wirelessly communicating with external devices.

[0044] In applications, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0045] In applications, the memory may be an internal storage unit of an electronic device in some embodiments, such as a hard disk or memory of an electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SD) card, a flash card (Flash Card), etc. equipped on the electronic device. The memory may also include both an internal storage unit of an electronic device and an external storage device. The memory is used to store operating systems, applications, boot loaders (BootLoader), data, and other programs, such as program codes of computer programs, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0046] The embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0047] The present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0048] Those of ordinary skill in the art will appreciate that the devices and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0049] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices, which can be electrical, mechanical or other forms.

[0050] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for intelligent script generation based on a large model, characterized in that: include: Obtain the user's historical creation data on video scripts; Using a large model to learn the historical creation data, and generate character portrait information of the user; Based on the character portrait information and the set script generation rules, the big model is used to perform reasoning and generate the video script.

2. The method for intelligently generating a script based on a large model as claimed in claim 1, characterized in that: The historical creation data is video-based data, including narration subtitles, image information, and voice information.

3. The method for intelligently generating a script based on a large model as claimed in claim 1, characterized in that: The using of the big model to learn the historical creation data to generate the character portrait information of the user includes: Processing the historical creation data through multiple algorithms to construct multi-dimensional character features of the user; Generate character portrait information of the user based on the multi-dimensional character features.

4. The method for intelligently generating a script based on a large model as claimed in claim 3, characterized in that: The historical creation data is processed by multiple algorithms to construct the multi-dimensional character features of the user, including: Identifying the basic information of the user from the historical creation data through a text recognition algorithm; Acquire the user's life information and technical mastery information from the historical creation data through video segmentation, image feature recognition and deep learning algorithms; The user's psychological characteristics, behavioral characteristics and dynamic characteristics are obtained from the historical creation data through natural semantic processing, video image processing and deep learning algorithms.

5. The method for intelligently generating a script based on a large model as claimed in claim 4, characterized in that: The basic information of the person includes age, gender, geographical location, occupation, and educational background; The life information includes interests, hobbies, living habits, and values; the technical mastery information includes technical equipment, network behavior, and digital literacy; The psychological characteristics include personality traits and emotional tendencies, the behavioral characteristics include website behavior, application behavior, and task behavior, and the dynamic characteristics include time dimension, event triggering, and trend analysis.

6. The method for intelligently generating a script based on a large model as claimed in claim 1, characterized in that: The method of using a large model to perform reasoning and generate a video script based on the character portrait information and the set script generation rules includes: Based on the character portrait information, a large model is used for reasoning to generate a video script that conforms to the set script generation rules.

7. The method for intelligently generating a script based on a large model as claimed in claim 1, characterized in that: The script generation rules include current hot spot information, script creation rules, and business logic constraints.

8. A script intelligent generation system based on a large model, characterized in that: It includes a historical data system, a universal large model base, an intelligent learning system, a character knowledge system, a script generation rule system, a reasoning generation system and a script generation system; the large model-based intelligent script generation system is used to implement the large model-based intelligent script generation method as described in any one of claims 1 to 7.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the large model-based intelligent script generation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements the large model-based intelligent script generation method as described in any one of claims 1 to 7.

Images