Methods, devices, equipment and media for generating video scripts

Abstract

This invention relates to the field of artificial intelligence, and provides a method, apparatus, device, and medium for generating video scripts. The method includes: analyzing acquired initial data to obtain first script parameters; performing slot filling processing based on a preset template script and the first script parameters to obtain initial script; performing slot search processing using the initial script to obtain second script parameters; performing slot filling processing based on the initial script and the second script parameters to obtain intermediate script; and performing intelligent generation processing based on the intermediate script and a preset script model to obtain target script. This invention ensures processing timeliness and improves generation efficiency.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence, and in particular to a method, apparatus, device, and medium for generating video text. Background Technology

[0002] Currently, short videos have become a mainstream promotional tool. Traditional short video creation has a low barrier to entry, and videos can be easily shot and published on mainstream software. However, in terms of content, creating video scripts is more difficult and has become a major bottleneck. Creating video scripts places high demands on creators; they need to independently choose a theme and design the entire script. Furthermore, manual design is difficult to adapt to the demands of large-scale, high-efficiency creation and cannot meet the needs of the rapid development of modern society.

[0003] Therefore, existing video script generation methods suffer from low generation efficiency. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and medium for generating video text, aiming to solve the problem of low generation efficiency in existing video text generation methods.

[0005] In a first aspect, embodiments of the present invention provide a method for generating video text, the method comprising:

[0006] The first copy parameters are obtained by analyzing the acquired initial data;

[0007] The initial text is obtained by filling the slots according to the preset template text and the first text parameters;

[0008] The second copy parameters are obtained by performing a slot search process using the initial copy.

[0009] The intermediate text is obtained by filling slots based on the initial text and the second text parameters.

[0010] The target text is obtained through intelligent generation processing based on the intermediate text and the preset text model.

[0011] Secondly, embodiments of the present invention also provide a video script generation device, the device comprising:

[0012] The analysis unit is used to analyze the acquired initial data to obtain the first text parameters;

[0013] The first filling unit is used to fill slots according to the preset template text and the first text parameters to obtain the initial text.

[0014] The search unit is used to perform slot search processing using the initial copy to obtain the second copy parameters;

[0015] The second filling unit is used to perform slot filling processing based on the initial copy and the second copy parameters to obtain the intermediate copy;

[0016] The generation unit is used to intelligently generate the target text based on the intermediate text and the preset text model.

[0017] Thirdly, embodiments of the present invention also provide an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect above.

[0018] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, can implement the method described in the first aspect.

[0019] This invention provides a method, apparatus, device, and medium for generating video scripts. The method includes: analyzing acquired initial data to obtain first script parameters; performing slot filling processing based on a preset template script and the first script parameters to obtain initial script; performing slot search processing using the initial script to obtain second script parameters; performing slot filling processing based on the initial script and the second script parameters to obtain intermediate script; and performing intelligent generation processing based on the intermediate script and a preset script model to obtain target script. Embodiments of this invention can utilize the preset template script and the first script parameters to fill slots and obtain initial scripts, improving the efficiency of script generation. Embodiments of this invention can also perform generation processing based on the intermediate script and the preset script model to obtain target scripts, achieving standardized generation processing of target scripts, ensuring processing timeliness, and improving generation efficiency. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the video text generation method provided in an embodiment of the present invention;

[0022] Figure 2 This is a schematic block diagram of a video text generation device provided in an embodiment of the present invention;

[0023] Figure 3 A schematic block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0026] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0027] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. Embodiments of this invention provide a method, apparatus, device, and medium for generating video scripts. This video script generation method can be applied to a video script generation system, which can be used to generate promotional video scripts for various products, such as promotional video scripts for insurance products.

[0028] Figure 1 This is a flowchart illustrating the video text generation method provided in an embodiment of the present invention. Figure 1 As shown, the method includes the following steps S110-S150.

[0029] S110. Analyze the acquired initial data to obtain the first copy parameters.

[0030] In this embodiment, the initial data is user data obtained from the front end of the video script generation system, i.e., from the content input by the user. The video script generation system includes a front end and a back end. The front end is the user terminal, used for user interaction and interface display; the back end is the server terminal, used for data processing and logic, i.e., the video script generation method is applied to the back end.

[0031] In one embodiment, before step S110, i.e. before analyzing the acquired initial data to obtain the first text parameters, the method further includes:

[0032] Obtain user data from the user's end;

[0033] The user data is encapsulated to obtain the initial data.

[0034] In this embodiment, user data is obtained from the content of the user's input box. The user data includes topics, activity content, etc. For example, the topic might be "discussing concepts," "popular science," or "lifestyle topics." If "discussing concepts" is selected, the activity content might include: "insurance tips," "financial management tips," and "health topics." The user data is then encapsulated using key-value pairs to obtain the initial data. The initial data includes multiple keys and corresponding values.

[0035] The embodiments of the present invention can encapsulate the acquired user data to obtain initial data, thereby ensuring the reliability of data transmission, ensuring transmission efficiency, and improving generation efficiency.

[0036] The process of analyzing the acquired initial data to obtain the first text parameters includes:

[0037] The initial data is analyzed using a preset analysis strategy to obtain the first text parameters. The preset analysis strategy refers to rules determined based on the user input box, which can be set according to actual conditions. The first text parameters include two parameter arrays: a first key array and a first value array. The first key array may include "project," "content," etc., and the first value array may include "theme," "activity content," etc., and the positions of the first key array and the first value array correspond one-to-one. The preset template text can also be obtained by querying a database using the first value array of the first text parameters.

[0038] S120. The initial text is obtained by filling the slots according to the preset template text and the first text parameters.

[0039] In this embodiment, the preset template text is a text description that includes multiple slots and is stored in a database, including preset template texts for various scenarios.

[0040] In one embodiment, step S120, namely, obtaining the initial text by filling the slots according to the preset template text and the first text parameters, includes:

[0041] Multiple slots are obtained from the preset template text, and multiple first slots are obtained by analyzing the multiple slots using the preset first symbol;

[0042] The first text parameter is compared with each first slot to obtain the first comparison result;

[0043] Based on the first comparison result, the first copywriting parameters are used to fill each first slot to obtain the initial copywriting.

[0044] In this embodiment, the first symbol is a preset symbol pair, such as "()"; each first slot includes a first symbol and a corresponding first slot name, such as "(project)". Specifically, each parameter of the first key array in the first text parameters is compared with the first slot name in multiple first slots to obtain a first comparison result; if the first comparison result is the same, the parameter in the first value array at the corresponding position in the first text parameters is used to fill the first slot name, that is, the corresponding first slot name and the first symbol are replaced with the parameter in the first value array in the first text parameters; if the first comparison result is different, the remaining parameters of the first key array in the first text parameters are compared with the first slot name in each first slot to obtain a first comparison result, until all parameters in the first value array in the first text parameters have filled the first slot name and the first symbol in multiple first slots to obtain the initial text.

[0045] In this embodiment of the invention, the plurality of slots can be obtained by analyzing the plurality of slots using the first symbol, and the first comparison result of the first text parameter with each first slot is used to fill each first slot with the first text parameter to obtain the initial text. This achieves standardization of the first text parameter and the plurality of first slots, ensuring timely filling and improving generation efficiency.

[0046] S130. Use the initial copy to perform slot search processing to obtain the second copy parameters.

[0047] In this embodiment, the second text parameter includes two parameter arrays, namely a second key array and a second value array. The second key array may include template, canvas_title, etc., and the second value array may include example, title, etc., and the positions of the second key array and the second value array in the array correspond one-to-one.

[0048] In one embodiment, step S130, namely, obtaining the second copy parameters by performing slot search processing using the initial copy, includes:

[0049] Multiple second slots are obtained by analyzing the initial text using a preset second symbol;

[0050] The second text parameters are obtained by performing a search process using the multiple second slots according to a preset search rule.

[0051] In this embodiment, the second symbol is a preset symbol pair, such as "[]"; each second slot includes a second symbol and a corresponding second slot name, such as "[template]"; the preset search rules include a search method and a search platform, and the search method can be to extract the first result in the search results, extract the fourth result in the search results, etc.; that is, the search results are obtained by using the second slot name in the second slot on the search platform, and the second text parameter is obtained by extracting from the search results according to the search method.

[0052] This invention embodiment can analyze the initial text based on the second symbol to obtain multiple second slots. The design of the slots allows for convenient adjustment of parameters and dynamic configuration, enabling more diverse forms and content. Furthermore, the multiple second slots are used to perform search processing according to preset search rules to obtain the second text parameters, thereby standardizing the initial text and multiple second slots, ensuring timely analysis and search, and improving generation efficiency.

[0053] S140. Based on the initial copy and the second copy parameters, perform slot filling processing to obtain the intermediate copy.

[0054] In this embodiment, the second text parameter includes two parameter arrays, namely a second key array and a second value array.

[0055] In one embodiment, step S140, namely, obtaining intermediate text by performing slot filling processing based on the initial text and the second text parameters, further includes:

[0056] The second text parameter is compared with each second slot to obtain the second comparison result;

[0057] The intermediate text is obtained by filling each second slot based on the second comparison result and the second text parameters.

[0058] In this embodiment, each parameter of the second key array in the second copy parameters is compared with the second slot name in multiple second slots to obtain a second comparison result. If the second comparison result is the same, the parameter of the second value array at the corresponding position in the second copy parameters is filled with the corresponding second slot name, that is, the corresponding second slot name and second symbol are replaced with the parameter of the second value array in the second copy parameters. If the second comparison result is different, the remaining parameters of the second key array in the second copy parameters are compared with the second slot name in multiple second slots to obtain a first comparison result, until all parameters of the second key array in the second copy parameters are filled with the second slot name and second symbol in multiple first slots to obtain the intermediate copy.

[0059] The embodiments of the present invention can fill each second slot with the second copy parameters to obtain the intermediate copy based on the second comparison result of the second copy parameters and each second slot, thereby achieving the standardization of the second copy parameters and multiple second slots, ensuring timely filling and improving generation efficiency.

[0060] S150. The target text is obtained by intelligent generation processing based on the intermediate text and the preset text model.

[0061] In this embodiment, the preset copywriting model is a pre-trained copywriting output model, such as an AIGC model.

[0062] In one embodiment, step S150, i.e., the step of intelligently generating the target text based on the intermediate text and the preset text model, includes:

[0063] Obtain the preset copywriting model;

[0064] The intermediate text is input into the preset text model and intelligently generated to obtain the target text.

[0065] In this embodiment, the intermediate text is input into the acquired preset text model, and the preset text model performs intelligent generation processing based on the intermediate text to obtain the target text. This embodiment of the invention can achieve intelligent recognition and generation of intermediate text by inputting the intermediate text into the preset text model, thereby improving the accuracy and efficiency of text generation.

[0066] In one embodiment, after step S150, that is, after the intelligent generation process based on the intermediate copy and the preset copy model to obtain the target copy, the method further includes:

[0067] The target video is obtained by shooting and processing the video based on the generated target text.

[0068] In this embodiment, after the target text is generated, a third-party shooting platform is selected based on the target text and the user is redirected to the third-party shooting platform to perform fine-tuning and editing to obtain the processed target text. After clicking the start shooting button, subtitles are generated based on the processed target text to perform video shooting processing to obtain the target video. That is, the user only needs to read or express according to the subtitles during the video shooting process to complete the production of the target video, and can also publish and share it to the third-party shooting platform.

[0069] This invention provides an embodiment that allows for video shooting and processing based on the target text to obtain the target video, thereby meeting the needs of large-scale, high-efficiency creation, satisfying the rapid development of modern society, and improving generation efficiency. The entire lifecycle of video text generation, shooting, and sharing is integrated. The target text can be generated using the preset text model, and after shooting the video, it can be shared with one click to a third-party shooting platform to attract traffic.

[0070] In summary, the embodiments of the present invention can use the preset template text and the first text parameters to fill slots to obtain initial text, thereby improving the efficiency of text generation; the embodiments of the present invention can also perform intelligent generation processing based on the intermediate text and the preset text model to obtain target text, thereby realizing intelligent and standardized generation processing of target text, ensuring processing timeliness, and improving generation efficiency.

[0071] Figure 2 This is a schematic block diagram of a video text generation device provided in an embodiment of the present invention. Figure 2 As shown, corresponding to the above video script generation method, the present invention also provides a video script generation device. For details, please refer to... Figure 2 The video script generation device 700 includes:

[0072] Analysis unit 701 is used to analyze the acquired initial data to obtain the first text parameters;

[0073] The first filling unit 702 is used to fill slots according to the preset template text and the first text parameters to obtain the initial text.

[0074] Search unit 703 is used to perform slot search processing using the initial copy to obtain the second copy parameters;

[0075] The second filling unit 704 is used to perform slot filling processing based on the initial copy and the second copy parameters to obtain the intermediate copy;

[0076] The second filling unit 705 is used to intelligently generate the target text based on the intermediate text and the preset text model.

[0077] In some embodiments, when the first filling unit 702 performs the step of obtaining initial text by filling slots according to a preset template text and the first text parameters, it is specifically used for:

[0078] Multiple slots are obtained from the preset template text, and multiple first slots are obtained by analyzing the multiple slots using the preset first symbol;

[0079] The first text parameter is compared with each first slot to obtain the first comparison result;

[0080] Based on the first comparison result, the first copywriting parameters are used to fill each first slot to obtain the initial copywriting.

[0081] In some embodiments, when the search unit 703 performs the step of obtaining the second text parameter by performing slot search processing using the initial text, it is specifically used for:

[0082] Multiple second slots are obtained by analyzing the initial text using a preset second symbol;

[0083] The second text parameters are obtained by performing a search process using the multiple second slots according to a preset search rule.

[0084] In some embodiments, when the second filling unit 704 performs the step of obtaining intermediate text by filling slots based on the initial text and the second text parameters, it is specifically used for:

[0085] The second text parameter is compared with each second slot to obtain the second comparison result;

[0086] The intermediate text is obtained by filling each second slot based on the second comparison result and the second text parameters.

[0087] In some embodiments, when the generation unit 705 performs the step of intelligent generation processing based on the intermediate copy and the preset copy model to obtain the target copy, it is specifically used for:

[0088] Obtain the preset copywriting model;

[0089] The intermediate text is input into the preset text model and intelligently generated to obtain the target text.

[0090] In some embodiments, before performing the step of analyzing the acquired initial data to obtain the first textual parameters, the analysis unit 701 is further configured to:

[0091] Obtain user data from the user's end;

[0092] The user data is encapsulated to obtain the initial data.

[0093] In some embodiments, after performing the step of intelligent generation processing based on the intermediate copy and the preset copy model to obtain the target copy, the generation unit 705 is further configured to:

[0094] The target video is obtained by shooting and processing the video based on the generated target text.

[0095] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned video text generation device and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0096] The aforementioned video script generation device can be implemented as a computer program, which can, for example... Figure 3 It runs on the computer device shown.

[0097] Please see Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of the present invention. The computer device 800 can be a terminal or a server, wherein the terminal can be an electronic device with communication functions. The server can be a standalone server or a server cluster composed of multiple servers.

[0098] See Figure 3 The electronic device 800 includes a processor 802, a memory, and a network interface 805 connected via a system bus 801. The memory may include a non-volatile storage medium 803 and internal memory 804.

[0099] The non-volatile storage medium 803 may store an operating system 8031 ​​and a computer program 8032. The computer program 8032 includes program instructions that, when executed, cause the processor 802 to perform a video script generation method.

[0100] The processor 802 provides computing and control capabilities to support the operation of the entire electronic device 800.

[0101] The internal memory 804 provides an environment for the execution of the computer program 8032 in the non-volatile storage medium 803. When the computer program 8032 is executed by the processor 802, the processor 802 can execute a video script generation method.

[0102] This network interface 805 is used for network communication with other devices. Those skilled in the art will understand that... Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the electronic device 800 to which the present invention is applied. The specific electronic device 800 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0103] The processor 802 is used to run a computer program 8032 stored in the memory to perform the following steps:

[0104] The first copy parameters are obtained by analyzing the acquired initial data;

[0105] The initial text is obtained by filling the slots according to the preset template text and the first text parameters;

[0106] The second copy parameters are obtained by performing a slot search process using the initial copy.

[0107] The intermediate text is obtained by filling slots based on the initial text and the second text parameters.

[0108] The target text is obtained through intelligent generation processing based on the intermediate text and the preset text model.

[0109] In some embodiments, when the processor 802 performs the step of filling slots to obtain the initial text based on the preset template text and the first text parameters, it specifically implements the following steps:

[0110] Multiple slots are obtained from the preset template text, and multiple first slots are obtained by analyzing the multiple slots using the preset first symbol;

[0111] The first text parameter is compared with each first slot to obtain the first comparison result;

[0112] Based on the first comparison result, the first copywriting parameters are used to fill each first slot to obtain the initial copywriting.

[0113] In some embodiments, when the processor 802 performs the step of obtaining the second text parameter by performing slot search processing using the initial text, it specifically implements the following steps:

[0114] Multiple second slots are obtained by analyzing the initial text using a preset second symbol;

[0115] The second text parameters are obtained by performing a search process using the multiple second slots according to a preset search rule.

[0116] In some embodiments, when the processor 802 performs the step of obtaining intermediate text by slot filling based on the initial text and the second text parameters, it specifically implements the following steps:

[0117] The second text parameter is compared with each second slot to obtain the second comparison result;

[0118] The intermediate text is obtained by filling each second slot based on the second comparison result and the second text parameters.

[0119] In some embodiments, when the processor 802 performs the step of intelligently generating the target text based on the intermediate text and the preset text model to obtain the target text, it specifically implements the following steps:

[0120] Obtain the preset copywriting model;

[0121] The intermediate text is input into the preset text model and intelligently generated to obtain the target text.

[0122] In some embodiments, before implementing the step of analyzing the acquired initial data to obtain the first text parameters, the processor 802 also implements the following steps:

[0123] Obtain user data from the user's end;

[0124] The user data is encapsulated to obtain the initial data.

[0125] In some embodiments, after performing the step of intelligently generating the target text based on the intermediate text and the preset text model, the processor 802 further performs the following steps:

[0126] The target video is obtained by shooting and processing the video based on the generated target text.

[0127] It should be understood that, in this embodiment of the invention, the processor 802 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0128] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0129] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When executed by a processor, the program instructions cause the processor to perform the following steps:

[0130] The first copy parameters are obtained by analyzing the acquired initial data;

[0131] The initial text is obtained by filling the slots according to the preset template text and the first text parameters;

[0132] The second copy parameters are obtained by performing a slot search process using the initial copy.

[0133] The intermediate text is obtained by filling slots based on the initial text and the second text parameters.

[0134] The target text is obtained through intelligent generation processing based on the intermediate text and the preset text model.

[0135] In one embodiment, when the processor executes the program instructions to perform slot filling processing to obtain the initial text based on the preset template text and the first text parameters, the specific steps are as follows:

[0136] Multiple slots are obtained from the preset template text, and multiple first slots are obtained by analyzing the multiple slots using the preset first symbol;

[0137] The first text parameter is compared with each first slot to obtain the first comparison result;

[0138] Based on the first comparison result, the first copywriting parameters are used to fill each first slot to obtain the initial copywriting.

[0139] In one embodiment, when the processor executes the program instructions to perform slot search processing using the initial text to obtain the second text parameters, it specifically implements the following steps:

[0140] Multiple second slots are obtained by analyzing the initial text using a preset second symbol;

[0141] The second text parameters are obtained by performing a search process using the multiple second slots according to a preset search rule.

[0142] In one embodiment, when the processor executes the program instructions to perform slot filling processing based on the initial text and the second text parameters to obtain intermediate text, it specifically implements the following steps:

[0143] The second text parameter is compared with each second slot to obtain the second comparison result;

[0144] The intermediate text is obtained by filling each second slot based on the second comparison result and the second text parameters.

[0145] In one embodiment, when the processor executes the program instructions to perform intelligent generation processing based on the intermediate text and the preset text model to obtain the target text, the specific steps are as follows:

[0146] Obtain the preset copywriting model;

[0147] The intermediate text is input into the preset text model and intelligently generated to obtain the target text.

[0148] In one embodiment, before executing the program instructions to analyze the acquired initial data to obtain the first text parameters, the processor further implements the following steps:

[0149] Obtain user data from the user's end;

[0150] The user data is encapsulated to obtain the initial data.

[0151] In one embodiment, after executing the program instructions to achieve the step of intelligently generating the target text based on the intermediate text and the preset text model, the processor further performs the following steps:

[0152] The target video is obtained by shooting and processing the video based on the generated target text.

[0153] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0154] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0155] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0156] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0157] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0158] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims. Furthermore, any software tools or components not belonging to this company that appear in the embodiments of the present invention are merely illustrative examples and do not represent actual use.

Claims

1. A video script generation method, characterized by, The method includes: The first copy parameters are obtained by analyzing the acquired initial data; The initial text is obtained by filling the slots according to the preset template text and the first text parameters; The second copy parameters are obtained by performing a slot search process using the initial copy. The intermediate text is obtained by filling slots based on the initial text and the second text parameters. The target text is obtained by intelligent generation processing based on the intermediate text and the preset text model. The step of filling slots according to the preset template text and the first text parameters to obtain the initial text includes: Multiple slots are obtained from the preset template text, and multiple first slots are obtained by analyzing the multiple slots using a preset first symbol; the first text parameters are compared with each first slot to obtain a first comparison result; based on the first comparison result, the first text parameters are used to fill each first slot to obtain the initial text; The process of obtaining the second copy parameters by performing slot search using the initial copy includes: Multiple second slots are obtained by analyzing the initial text using a preset second symbol; the second text parameters are obtained by searching the multiple second slots according to a preset search rule; The preset search rules include search methods and search platforms; The step of using the plurality of second slots to perform search processing according to preset search rules to obtain the second text parameters includes: using the second slot name in the second slot to search on the search platform to obtain search results, and extracting the second text parameters from the search results according to the search method.

2. The video script generation method of claim 1, wherein, The process of obtaining intermediate text by filling slots based on the initial text and the second text parameters further includes: The second text parameter is compared with each second slot to obtain the second comparison result; The intermediate text is obtained by filling each second slot based on the second comparison result and the second text parameters.

3. The video script generation method according to claim 1, characterized in that, The intelligent generation process based on the intermediate copy and the preset copy model to obtain the target copy also includes: Obtain the preset copywriting model; The intermediate text is input into the preset text model and intelligently generated to obtain the target text.

4. The video script generation method according to claim 1, characterized in that, Before analyzing the acquired initial data to obtain the first text parameters, the process also includes: Obtain user data from the user's end; The user data is encapsulated to obtain the initial data.

5. The video script generation method according to claim 1, characterized in that, After obtaining the target text through intelligent generation processing based on the intermediate text and the preset text model, the process further includes: The target video is obtained by shooting and processing the video based on the generated target text.

6. A video script generation device, characterized in that, The device includes: The analysis unit is used to analyze the acquired initial data to obtain the first text parameters; The first filling unit is used to fill slots according to the preset template text and the first text parameters to obtain the initial text. The search unit is used to perform slot search processing using the initial copy to obtain the second copy parameters; The second filling unit is used to perform slot filling processing based on the initial copy and the second copy parameters to obtain the intermediate copy; The generation unit is used to intelligently generate the target text based on the intermediate text and the preset text model. The step of filling slots according to the preset template text and the first text parameters to obtain the initial text includes: Multiple slots are obtained from the preset template text, and multiple first slots are obtained by analyzing the multiple slots using a preset first symbol; the first text parameters are compared with each first slot to obtain a first comparison result; based on the first comparison result, the first text parameters are used to fill each first slot to obtain the initial text; The process of obtaining the second copy parameters by performing slot search using the initial copy includes: Multiple second slots are obtained by analyzing the initial text using a preset second symbol; the second text parameters are obtained by searching the multiple second slots according to a preset search rule; The preset search rules include search methods and search platforms; The step of using the plurality of second slots to perform search processing according to preset search rules to obtain the second text parameters includes: using the second slot name in the second slot to search on the search platform to obtain search results, and extracting the second text parameters from the search results according to the search method.

7. 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 video text generation method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which includes program instructions that, when executed by a processor, cause the processor to perform the video text generation method as described in any one of claims 1-5.

Images