CN117336539B - Video script production method and system for short video IP (Internet protocol) construction - Google Patents
Video script production method and system for short video IP (Internet protocol) construction Download PDFInfo
- Publication number
- CN117336539B CN117336539B CN202311273531.3A CN202311273531A CN117336539B CN 117336539 B CN117336539 B CN 117336539B CN 202311273531 A CN202311273531 A CN 202311273531A CN 117336539 B CN117336539 B CN 117336539B
- Authority
- CN
- China
- Prior art keywords
- user information
- sub
- information
- video
- video script
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013515 script Methods 0.000 title claims abstract description 162
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 51
- 238000010276 construction Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000012163 sequencing technique Methods 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 241000282414 Homo sapiens Species 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/232—Content retrieval operation locally within server, e.g. reading video streams from disk arrays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/235—Processing of additional data, e.g. scrambling of additional data or processing content descriptors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application belongs to the technical field of artificial intelligence content control, and particularly relates to a video script production method and system for short video IP (Internet protocol) construction. The method comprises the following steps: acquiring target positioning information and user information; extracting sub-user information with multiple dimensions from the user information, carrying out weight assignment on each sub-user information according to the importance of the information value pre-stored in a database, and sequencing the sub-user information with different dimensions from high to low according to the weight value to obtain a user information weight list; generating a video script outline according to the target positioning information and the user information weight list; generating a video script according to the video script outline, and merging the first N pieces of sub-user information in the user information weight list into the video script, wherein N is more than or equal to 1. The application breaks through the limitation of the traditional short video IP (Internet protocol) construction method, improves the efficiency of short video IP construction, ensures the video quality, saves human resources and reduces the production cost.
Description
Technical Field
The application belongs to the technical field of artificial intelligence content control, and particularly relates to a video script production method and system for short video IP (Internet protocol) construction.
Background
With the advent of short videos, more and more people began to build their own IP with short videos. The good short video IP can attract users to obtain a large amount of flow, so that the exposure degree is increased, and the brand awareness is improved.
In the current short video IP construction process, a technical algorithm for controlling content production by artificial intelligence is lacking, the whole short video IP construction process mainly adopts an artificial production mode, relies on subjective experience guidance, and has the problems of high cost, long time consumption and low efficiency. In addition, the existing short video IP (Internet protocol) construction method also lacks a scientific system, content production is planned through manual experience, randomness is high, video quality cannot be guaranteed, and copying is difficult.
It is therefore desirable to have a solution that overcomes or at least alleviates at least one of the above-mentioned drawbacks of the prior art.
Disclosure of Invention
The application aims to provide a video script production method and a system for short video IP (Internet protocol) construction, which are used for solving the problems that the existing short video IP construction mode is low in efficiency and cannot guarantee video quality.
The technical scheme of the application is as follows:
A first aspect of the present application provides a video script production method for short video IP creation, including:
step one, obtaining target positioning information and user information;
Extracting sub-user information with multiple dimensions from the user information, carrying out weight assignment on each sub-user information according to the importance of the information value pre-stored in a database, and sequencing the sub-user information with different dimensions from high to low according to the weight value to obtain a user information weight list;
generating a video script outline according to the target positioning information and the user information weight list;
And step four, generating a video script according to the video script outline, and merging the first N pieces of sub-user information in the user information weight list into the video script, wherein N is more than or equal to 1.
In at least one embodiment of the present application, in step one, the target location information includes IP person setting location information and IP style location information.
In at least one embodiment of the present application, in step one, the user information comprises personal user information or business user information, wherein,
The personal user information comprises personal basic information, learning experience, work experience, hobbies and interests and honor rewards, and the personal basic information comprises personal name, age and gender;
The enterprise user information comprises enterprise basic information, stakeholder information, team members and product information, wherein the enterprise basic information comprises enterprise names, establishment time and enterprise types.
In at least one embodiment of the present application, in the second step, the assigning weights to the information of each sub-user according to the importance of the information value pre-stored in the database includes:
searching and matching the sub-user information of each dimension in a corresponding database;
If the sub-user information is searched and matched, calculating the weight value of the sub-user information according to the corresponding weight assignment formula and the position of the sub-user information in the database;
If the sub-user information is not searched and matched, determining the weight value of the sub-user information according to a preset weight assignment rule.
In at least one embodiment of the application, when the child user information is graduation:
aiming at graduation schools, searching and matching are respectively carried out in a Chinese university database and a world university database;
If the sub-user information is searched and matched in the Chinese university database and the world university database, calculating the weight value of the sub-user information according to the corresponding weight assignment formula and the positions of the sub-user information in the Chinese university database and the world university database;
the weight assignment formula of the sub-user information is as follows:
Weight value of child user information= ((1-m/x) ×100+ (1-n/y) ×100)/2
Wherein m is the ranking of the child user information in the university database, x is the total number of universities contained in the university database, n is the ranking of the child user information in the university database, and y is the total number of universities contained in the university database;
If the sub-user information is not searched and matched in the Chinese university database, defining the ranking of the sub-user information in the Chinese university database as m=x;
If the sub-user information is not retrieved from the world university database, the ranking of the sub-user information in the world university database is defined as n=y.
In at least one embodiment of the present application, in step three, the generating a video script outline according to the target positioning information and the user information weight list includes:
S31, acquiring short video period number information;
S32, generating a video script outline of a preset period number according to the short video period number information, the target positioning information and the user information weight list.
In at least one embodiment of the present application, in S32, the generating a video script outline of a predetermined period number according to the short video period number information, the target positioning information, and the user information weight list includes:
generating a plurality of video script topics according to the target positioning information and the user information weight list;
Generating a plurality of video script episodes according to the target positioning information and the user information weight list;
generating a plurality of video script roles according to the target positioning information and the user information weight list;
Generating a plurality of video script scenes according to the target positioning information and the user information weight list;
And according to the short video period number information, fusing a plurality of video script topics, a plurality of video script episodes, a plurality of video script roles and a plurality of video script scenes to generate a video script outline with a preset period number.
In at least one embodiment of the present application, in step four, the generating a video script according to the video script outline, and merging the first N pieces of sub-user information in the user information weight list into the video script includes:
S41, generating a video script corresponding to a predetermined period number according to the video script outline of the predetermined period number;
s42, merging the first N pieces of sub-user information in the user information weight list into the video script, wherein each period of the video script comprises at least one piece of the first N pieces of sub-user information in the user information weight list.
In at least one embodiment of the present application, in S42, the first 3 pieces of sub-user information in the user information weight list are merged into the video script, and each period of the video script includes at least one of the first 3 pieces of sub-user information in the user information weight list.
A second aspect of the present application provides a video script production system for short video IP construction, comprising:
the information acquisition module is used for acquiring target positioning information and user information;
The weight assignment module is used for extracting sub-user information with multiple dimensions from the user information, carrying out weight assignment on each sub-user information according to the importance of the information value pre-stored in the database, and sequencing the sub-user information with different dimensions from high to low according to the weight value to obtain a user information weight list;
the video script outline production module is used for generating a video script outline according to the target positioning information and the user information weight list;
and the video script production module is used for generating a video script according to the video script outline, and integrating the first N pieces of sub-user information in the user information weight list into the video script, wherein N is more than or equal to 1.
The invention has at least the following beneficial technical effects:
The video script production method for short video IP construction breaks through the limitation of the traditional short video IP construction mode, improves the efficiency of short video IP construction, ensures the video quality, saves the manpower resources and reduces the production cost.
Drawings
FIG. 1 is a flow chart of a video script production method for short video IP creation according to one embodiment of the present application;
FIG. 2 is an information input interface of one embodiment of the present application;
FIG. 3 is a video script outline production interface of one embodiment of the present application;
FIG. 4 is a schematic diagram of a video script production system for short video IP creation in accordance with one embodiment of the present application;
fig. 5 is a schematic diagram of a computer device suitable for use in implementing an embodiment of the present application.
Wherein:
100-an information acquisition module; 200-a weight assignment module; 300-a video script outline production module; 400-a video script production module; 500-a computer device; 501-CPU;502-ROM;503-RAM; 504-bus; 505-I/O interface; 506-an input section; 507-an output section; 508-a storage portion; 509-a communication section; 510-a driver; 511-removable media.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application become more apparent, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the accompanying drawings in the embodiments of the present application. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are some, but not all, embodiments of the application. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. Embodiments of the present application will be described in detail below with reference to the accompanying drawings.
In the description of the present application, it should be understood that the terms "center," "longitudinal," "lateral," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, merely to facilitate describing the present application and simplify the description, and do not indicate or imply that the devices or elements being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the scope of the present application.
The application is described in further detail below with reference to fig. 1 to 5.
A first aspect of the present application provides a video script production method for short video IP creation, as shown in fig. 1, comprising the steps of:
S1, acquiring target positioning information and user information;
S2, extracting sub-user information with multiple dimensions from the user information, carrying out weight assignment on each sub-user information according to the importance of the information value pre-stored in a database, and sequencing the sub-user information with different dimensions from high to low according to the weight value to obtain a user information weight list;
S3, generating a video script outline according to the target positioning information and the user information weight list;
S4, generating a video script according to the video script outline, and merging the first N pieces of sub-user information in the user information weight list into the video script, wherein N is more than or equal to 1.
The application relates to a video script production method for short video IP construction, which comprises the steps of firstly acquiring information input by a user and extracting target positioning information and user information for short video IP construction from the information. In a preferred embodiment of the present application, the target location information includes IP person setting location information that the user wants to create, i.e., person setting that the user wants to create, and IP style location information that the user wants to create, when the user is an individual, the IP person setting location information may be a high-knowledge woman, insurance broker, financial consultant, house property broker, etc.; the IP style location information, i.e., what character style the user wants to create, may be a musician, professional expert, humour professor, successful business, grandma, juveniles, sister in mind, sister in imperial, etc. when the user is personal, as shown in fig. 2. The user information may be classified into personal user information and business user information according to user categories, wherein the personal user information includes personal basic information (e.g., name, age, sex of the personal user), learning experiences, work experiences, personal interests, honor rewards, etc.; the business user information includes business base information (e.g., business name, time of establishment, business type of business user), stakeholder investor information, team members, product information, etc.
The video script production method for short video IP construction of the application needs to extract N dimensions of sub-user information from the user information after obtaining the information input by the user, for example, extract graduation schools from learning experience information of personal user information, extract work units and positions acted by the personal from work experience information, etc. After obtaining a plurality of pieces of sub-user information with different dimensions, carrying out weight assignment on each piece of sub-user information according to the importance of the information value pre-stored in a database, and sorting according to the weight values to obtain a user information weight list.
In a preferred embodiment of the present application, the weight assignment for each piece of sub-user information according to the importance of the information value pre-stored in the database includes:
searching and matching the sub-user information of each dimension in a corresponding database;
If the sub-user information is searched and matched, calculating the weight value of the sub-user information according to the corresponding weight assignment formula and the position of the sub-user information in the database;
If the sub-user information is not searched and matched, determining the weight value of the sub-user information according to a preset weight assignment rule.
In one embodiment of the application, when the child user information is graduation:
aiming at graduation schools, searching and matching are respectively carried out in a Chinese university database and a world university database;
If the sub-user information is searched and matched in the Chinese university database and the world university database, calculating the weight value of the sub-user information according to the corresponding weight assignment formula and the positions of the sub-user information in the Chinese university database and the world university database;
the weight assignment formula of the sub-user information is as follows:
Weight value of child user information= ((1-m/x) ×100+ (1-n/y) ×100)/2
Wherein m is the ranking of the child user information in the university database, x is the total number of universities contained in the university database, n is the ranking of the child user information in the university database, and y is the total number of universities contained in the university database;
If the sub-user information is not searched and matched in the Chinese university database, defining the ranking of the sub-user information in the Chinese university database as m=x;
If the sub-user information is not retrieved from the world university database, the ranking of the sub-user information in the world university database is defined as n=y.
According to the weight assignment rule, if the sub-user information is searched and matched in the Chinese university database, but the sub-user information is not searched and matched in the world university database, the weight assignment formula of the sub-user information is as follows:
weight value of sub-user information= ((1-m/x) ×100)/2
If the sub-user information is not searched in the university of china database, but the sub-user information is searched in the university of the world database, the weight assignment formula of the sub-user information is:
weight value of sub-user information= ((1-n/y) ×100)/2
If the sub-user information is not searched and matched in the university of China database and the university of the world database, the weight value of the sub-user information is calculated to be 0 according to the weight assignment formula.
The method for producing the video script for short video IP construction has the advantage that the database containing each dimension information and the corresponding weight assignment formula is stored in the system in advance. After extracting the sub-user information of multiple dimensions from the user information, the sub-user information of each dimension needs to be searched and matched, and the weight value of the sub-user information is determined. For example, the Chinese university database contains 30 graduation school names and ranking materials, the world university database contains 100 graduation school names and ranking materials, the importance degree of the sub-user information is evaluated according to the retrieval matching result of the graduation schools (such as the Qinghai university) extracted from the user information and the two databases, and the weight value is given according to the corresponding weight assignment formula, and when the graduation schools of the sub-user information are ranked higher, the given weight value is higher.
It will be appreciated that when the sub-user information extracted from the individual's work experience is the unit of work, it is necessary to search and match with an enterprise database containing the names and ranking information of the strong enterprises in the world 500, and then calculate the weight values according to the corresponding weight assignment formulas and the locations in the database. When the sub-user information extracted from the work experience of the individual is the position that the individual takes, it is necessary to search and match with a position database containing names and ranking information of a plurality of positions such as CEO, CTO, advanced management, expert, etc., and then calculate the weight value of the position. Sub-user information of other dimensions, such as personal rewards, maximum achievement, etc., are retrieved and matched in a similar manner to obtain weight values.
According to the video script production method for short video IP construction, after the user information weight list is obtained, a video script outline required by short video IP construction is automatically constructed according to target positioning information and the user information weight list. Further, as shown in fig. 3, the method and the device can also generate the video script outline with the preset period number according to the requirement of the short video period number, for example, the video script outline with the 100 period is generated firstly when the video script with the 100 period is needed finally, so that the production efficiency of the video script is greatly improved. In a preferred embodiment of the present application, the video script outline generation process includes:
S31, acquiring short video period number information;
S32, generating a video script outline of a preset period number according to the short video period number information, the target positioning information and the user information weight list, wherein the video script outline is specifically as follows:
generating a plurality of video script topics according to the target positioning information and the user information weight list;
generating a plurality of video script episodes according to the target positioning information and the user information weight list;
Generating a plurality of video script roles according to the target positioning information and the user information weight list;
Generating a plurality of video script scenes according to the target positioning information and the user information weight list;
And merging the plurality of video script topics, the plurality of video script episodes, the plurality of video script roles and the plurality of video script scenes according to the short video period number information to generate a video script outline of a preset period number.
In a preferred embodiment of the present application, taking the theme as an example, Z themes are generated in the following manner:
First, the weight ratio of each piece of sub-user information in the user information weight list is calculated:
Q1＝q1/q1+q2+q3+…+qn
Q2＝q2/q1+q2+q3+…+qn
Q3＝q3/q1+q2+q3+…+qn
…
Qn＝qn/q1+q2+q3+…+qn
Wherein n is the number of sub-user information contained in the user information weight list, q 1 is the weight value of the 1 st sub-user information in the user information weight list, q 2 is the weight value of the 2 nd sub-user information in the user information weight list, q 3 is the weight value of the 3 rd sub-user information in the user information weight list, …, q n is the weight value of the n th sub-user information in the user information weight list; q 1、Q2、Q3、…、Qn is the weight ratio of the corresponding sub-user information respectively;
secondly, generating Z random numbers from 0 to 1 by adopting a random number generator;
Determining the number S1 of random numbers within the range of (0, Q 1) in the Z random numbers, and extracting S1 topics from a first topic database, wherein the topics in the first topic database are all topics matched with target positioning information and 1 st sub-user information;
determining the number S2 of random numbers within the range of (Q 1,Q1+Q2) in the Z random numbers, and extracting S2 topics from a second topic database, wherein the topics in the second topic database are topics matched with the target positioning information and the 2 nd sub-user information;
Determining the number S3 of random numbers within the range of (Q 1+Q2,Q1+Q2+Q3) in the Z random numbers, and extracting S3 topics from a third topic database, wherein the topics in the third topic database are all topics matched with the target positioning information and the 3 rd sub-user information;
…
And so on,
Determining the number Sn of random numbers within the range of (Q 1+Q2+Q3…+Qn-1,Q1+Q2+Q3…+Qn) in the Z random numbers, and extracting Sn topics from a third topic database, wherein the topics in an nth topic database are topics matched with the target positioning information and the nth sub-user information;
in this way, Z topics are obtained.
It will be appreciated that the generation of episodes, characters, scenes may be in a similar manner as the subject matter. And finally, randomly extracting and combining the obtained multiple topics, multiple episodes, multiple roles and multiple scenes to generate a video script outline with a preset period number.
In the process of generating the video script outline, the video script theme, the plot, the role and the scene can be converted into the video script outline described by natural language after fusion, and the video script outline with the corresponding term number can be generated according to the short video term number input by a user or the short video term number (for example, 30, 50 and 100 stages) customized by a system.
According to the video script production method for short video IP construction, after the video script outline is obtained, the video script is generated based on the video script outline, and the video script of how many periods is generated by the video script outline of how many periods. In a preferred embodiment of the present application, the video script generation process includes:
s41, generating a video script corresponding to the future number according to the video script outline of the predetermined future number;
s42, merging the first N pieces of sub-user information in the user information weight list into the video script, wherein each period of video script comprises at least one piece of the first N pieces of sub-user information in the user information weight list.
Advantageously, in this embodiment, the first 3 pieces of sub-user information with the highest weight value in the user information weight list are merged into the video script, and each period of video script includes at least one of the first 3 pieces of sub-user information in the user information weight list, so as to ensure that important sub-user information appears in the short video of each period.
It will be appreciated that the manner in which the child user information is incorporated into the video script is not limited to the embodiments described above, but may be any other suitable manner, for example, the university of bloom may be ranked highest in the user information weight list, and the university of bloom may be incorporated into each phase of video script, such that the IP high-knowledge of the university of bloom graduation may be enhanced differently within each phase of video script.
Based on the video script production method for short video IP construction, a second aspect of the present application provides a video script production system for short video IP construction, the system comprising: the system comprises an information acquisition module, a weight assignment module, a video script outline production module and a video script production module.
The information acquisition module is used for acquiring target positioning information and user information. The information acquisition module can be an online platform or an application program, and a user can input information of an IP (Internet protocol) created target and a person or enterprise into the system through the information acquisition module, and the information input by the user is collected and arranged for subsequent processing.
The weight assignment module is used for extracting sub-user information with multiple dimensions from the user information, carrying out weight assignment on each sub-user information according to the importance of the information value pre-stored in the database, and sequencing the sub-user information with different dimensions from high to low according to the weight value to obtain a user information weight list. The weight assignment module realizes a weight algorithm through an online platform or cloud service, and various modes can be adopted for designing the weight algorithm, such as a machine learning algorithm, a natural language processing technology, a rule engine and the like, and the system can quantize and sort the user information through the weight algorithm to obtain a user information weight list arranged according to importance.
The video script outline production module is used for generating a video script outline according to the target positioning information and the user information weight list. Setting position information and IP style positioning information of the IP person extracted from information input by a user, such as whether to sell insurance or sell automobiles, whether to build enterprise consultation management specialists or successful merchants, and inputting a user information weight list subjected to retrieval evaluation weight assignment into a pre-trained short video IP built model in a system, wherein the model can automatically output a specified number of video script outlines.
The video script production module is used for generating a video script according to the video script outline, and integrating the first N pieces of sub-user information in the user information weight list into the video script, wherein N is more than or equal to 1. The method comprises the steps of transmitting the first three sub-user information in the video script outline and the user information weight list as input information to a model created by short video IP to complete automatic production of specific content of the video script, and traversing the video script outline one by one to complete production of all video script content.
In a preferred embodiment of the present application, both the video script outline and the production of the video script use LLM large models. The LLM large model is a seq2seq language model built based on a transducer encoder-decoder structure, consisting mainly of transducer blocks stacked by encoder and decoder. Model parameters use very large scale parameter quantities, ranging from billions to billions, which make them possess very strong language expression and understanding capabilities. The model adopts sizer model expansion training technology, and parameters obtained through self-supervision learning are obtained from massive text data, IP construction scripts, video scripts and Internet large-scale language data through a training method of reinforcement learning. The LLM large model has generating capability, teaching capability and high safety, and can generate long language with logic self-consistency and semantic consistency; learning can be performed through examples, and the controllability is enhanced following the front guidance given by human beings; by deploying various security protection mechanisms, such as refusing to generate harmful content, the security is improved by avoiding remembering personal information and the like. The method is suitable for language understanding and generating application scenes, and can be widely applied to the fields of conversation robots, text generation, knowledge extraction and the like.
The video script production method and system for short video IP creation, provided by the application, are based on a computer system or a cloud service platform, and realize the automatic processes of collection, processing and script production of information input by a user. According to the application, the sub-user information with different dimensions is ordered according to the value importance degree through the weight algorithm, and the video script automatic production of the short video IP construction is realized by combining the weight value ordering of the sub-user information, so that the limitation of the traditional short video IP construction mode is broken, the efficiency, quality and replicability of the short video IP construction are effectively improved, the business value and replicability are higher, the manpower resources can be saved, the production cost is reduced, and important technological breakthroughs and progress are brought to the IP construction field.
In another aspect of the present application, a computer device is provided, including a processor, a memory, and a computer program stored on the memory and executable on the processor, the processor executing the computer program for implementing the video script production method for short video IP creation described above.
Referring now to FIG. 5, there is illustrated a schematic diagram of a computer device 500 suitable for use in implementing embodiments of the present application. The computer device shown in fig. 5 is only one example and should not be construed as limiting the functionality and scope of use of embodiments of the present application.
As shown in fig. 5, the computer device 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the device 500 are also stored. The CPU501, ROM502, and RAM503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output portion 507 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as needed so that a computer program read therefrom is mounted into the storage section 508 as needed.
In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 509, and/or installed from the removable medium 511. The above-described functions defined in the method of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 501. The computer storage medium of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules or units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware. The modules or units described may also be provided in a processor, the names of which do not in some cases constitute a limitation of the module or unit itself.
As another aspect, the present application also provides a computer-readable storage medium, which may be included in the apparatus described in the above embodiment; or may be present alone without being fitted into the device. The computer-readable storage medium carries one or more programs which, when executed by the apparatus, are in accordance with the video script production method for short video IP creation described above.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present application should be included in the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (3)
1. A video script production method for short video IP creation, comprising:
step one, obtaining target positioning information and user information;
Extracting sub-user information with multiple dimensions from the user information, carrying out weight assignment on each sub-user information according to the importance of the information value pre-stored in a database, and sequencing the sub-user information with different dimensions from high to low according to the weight value to obtain a user information weight list;
generating a video script outline according to the target positioning information and the user information weight list;
Generating a video script according to the video script outline, and merging the first N pieces of sub-user information in the user information weight list into the video script, wherein N is more than or equal to 1;
In the first step, the target positioning information comprises IP person setting position information and IP style positioning information;
in the second step, the step of performing weight assignment on each piece of sub-user information according to the importance degree of the information value pre-stored in the database comprises the following steps:
searching and matching the sub-user information of each dimension in a corresponding database;
If the sub-user information is searched and matched, calculating the weight value of the sub-user information according to the corresponding weight assignment formula and the position of the sub-user information in the database;
If the sub-user information is not searched and matched, determining a weight value of the sub-user information according to a preset weight assignment rule;
when the child user information is graduation,:
aiming at graduation schools, searching and matching are respectively carried out in a Chinese university database and a world university database;
If the sub-user information is searched and matched in the Chinese university database and the world university database, calculating the weight value of the sub-user information according to the corresponding weight assignment formula and the positions of the sub-user information in the Chinese university database and the world university database;
the weight assignment formula of the sub-user information is as follows:
Weight value of child user information= ((1-m/x) ×100+ (1-n/y) ×100)/2
Wherein m is the ranking of the child user information in the university database, x is the total number of universities contained in the university database, n is the ranking of the child user information in the university database, and y is the total number of universities contained in the university database;
If the sub-user information is not searched and matched in the Chinese university database, defining the ranking of the sub-user information in the Chinese university database as m=x;
if the sub-user information is not searched in the world university database, defining the ranking of the sub-user information in the world university database as n=y;
In the third step, the generating a video script outline according to the target positioning information and the user information weight list includes:
S31, acquiring short video period number information;
s32, generating a video script outline of a preset period number according to the short video period number information, the target positioning information and the user information weight list;
In S32, the generating a video script outline of a predetermined period number according to the short video period number information, the target positioning information and the user information weight list includes:
generating a plurality of video script topics according to the target positioning information and the user information weight list;
Generating a plurality of video script episodes according to the target positioning information and the user information weight list;
generating a plurality of video script roles according to the target positioning information and the user information weight list;
Generating a plurality of video script scenes according to the target positioning information and the user information weight list;
According to the short video period number information, fusing a plurality of video script topics, a plurality of video script episodes, a plurality of video script roles and a plurality of video script scenes to generate a video script outline with a preset period number;
the Z topics were generated in the following manner:
First, the weight ratio of each piece of sub-user information in the user information weight list is calculated:
Q1＝q1/q1+q2+q3+…+qn
Q2＝q2/q1+q2+q3+…+qn
Q3＝q3/q1+q2+q3+…+qn
…
Qn＝qn/q1+q2+q3+…+qn
Wherein n is the number of sub-user information contained in the user information weight list, q 1 is the weight value of the 1 st sub-user information in the user information weight list, q 2 is the weight value of the 2 nd sub-user information in the user information weight list, q 3 is the weight value of the 3 rd sub-user information in the user information weight list, …, q n is the weight value of the n th sub-user information in the user information weight list; q 1、Q2、Q3、…、Qn is the weight ratio of the corresponding sub-user information respectively;
secondly, generating Z random numbers from 0 to 1 by adopting a random number generator;
Determining the number S1 of random numbers within the range of (0, Q 1) in the Z random numbers, and extracting S1 topics from a first topic database, wherein the topics in the first topic database are all topics matched with target positioning information and 1 st sub-user information;
determining the number S2 of random numbers within the range of (Q 1,Q1+Q2) in the Z random numbers, and extracting S2 topics from a second topic database, wherein the topics in the second topic database are topics matched with the target positioning information and the 2 nd sub-user information;
Determining the number S3 of random numbers within the range of (Q 1+Q2,Q1+Q2+Q3) in the Z random numbers, and extracting S3 topics from a third topic database, wherein the topics in the third topic database are all topics matched with the target positioning information and the 3 rd sub-user information;
…
And so on,
Determining the number Sn of random numbers within the range of (Q 1+Q2+Q3…+Qn-1,Q1+Q2+Q3…+Qn) in the Z random numbers, and extracting Sn topics from a third topic database, wherein the topics in an nth topic database are topics matched with the target positioning information and the nth sub-user information;
Z subjects are obtained through the mode;
Generating plots, roles and scenes in a manner similar to the theme, and finally randomly extracting and combining a plurality of obtained themes, a plurality of plots, a plurality of roles and a plurality of scenes to generate a video script outline with a preset period number;
The method comprises the steps that IP person setting bit information and IP style positioning information extracted from information input by a user and a user information weight list subjected to retrieval evaluation weight assignment are input into a short video IP created model, and the model can automatically output a specified number of video script schemas;
in the fourth step, a video script is generated according to the video script outline, and the first N pieces of sub-user information in the user information weight list are merged into the video script, including:
S41, generating a video script corresponding to a predetermined period number according to the video script outline of the predetermined period number;
s42, merging the first N pieces of sub-user information in the user information weight list into the video script, wherein each period of the video script comprises at least one piece of the first N pieces of sub-user information in the user information weight list;
s42, merging the first 3 pieces of sub-user information in the user information weight list into the video script, wherein each period of the video script comprises at least one piece of the first 3 pieces of sub-user information in the user information weight list;
the method comprises the steps that the video script outline and sub-user information of the top three ranks in a user information weight list are used as input information to be transmitted to a model created by a short video IP to complete automatic production of specific content of the video script, and the video script outline is traversed one by one to complete production of all video script content;
the outline of the video script and the production of the video script all adopt LLM big models.
2. The method for producing video scripts for short video IP creation of claim 1 wherein in step one, the user information comprises personal user information or business user information, wherein,
The personal user information comprises personal basic information, learning experience, work experience, hobbies and interests and honor rewards, and the personal basic information comprises personal name, age and gender;
The enterprise user information comprises enterprise basic information, stakeholder information, team members and product information, wherein the enterprise basic information comprises enterprise names, establishment time and enterprise types.
3. A video script production system for short video IP construction, based on the video script production method for short video IP construction according to any one of claims 1 to 2, characterized by comprising:
the information acquisition module is used for acquiring target positioning information and user information;
The weight assignment module is used for extracting sub-user information with multiple dimensions from the user information, carrying out weight assignment on each sub-user information according to the importance of the information value pre-stored in the database, and sequencing the sub-user information with different dimensions from high to low according to the weight value to obtain a user information weight list;
the video script outline production module is used for generating a video script outline according to the target positioning information and the user information weight list;
and the video script production module is used for generating a video script according to the video script outline, and integrating the first N pieces of sub-user information in the user information weight list into the video script, wherein N is more than or equal to 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311273531.3A CN117336539B (en) | 2023-09-28 | 2023-09-28 | Video script production method and system for short video IP (Internet protocol) construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311273531.3A CN117336539B (en) | 2023-09-28 | 2023-09-28 | Video script production method and system for short video IP (Internet protocol) construction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117336539A CN117336539A (en) | 2024-01-02 |
| CN117336539B true CN117336539B (en) | 2024-05-14 |
Family
ID=89294683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311273531.3A Active CN117336539B (en) | 2023-09-28 | 2023-09-28 | Video script production method and system for short video IP (Internet protocol) construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117336539B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1503159A (en) * | 2002-11-25 | 2004-06-09 | ���µ�����ҵ��ʽ���� | Short film generation/reproduction apparatus and method thereof |
| CN103279581A (en) * | 2013-06-25 | 2013-09-04 | 中国科学院自动化研究所 | Method for performing video retrieval by compact video theme descriptors |
| CA2931623A1 (en) * | 2013-11-26 | 2015-06-04 | Taxconnections, Inc. | Systems and methods for searching for professionals within an online community |
| CN106354818A (en) * | 2016-08-30 | 2017-01-25 | 电子科技大学 | Dynamic user attribute extraction method based on social media |
| CN111048215A (en) * | 2019-12-13 | 2020-04-21 | 北京纵横无双科技有限公司 | CRM-based medical video production method and system |
| CN111629269A (en) * | 2020-05-25 | 2020-09-04 | 厦门大学 | Method for automatically shooting and generating mobile terminal short video advertisement based on mechanical arm |
| CN111970416A (en) * | 2020-08-29 | 2020-11-20 | 赣州圣享区块链技术有限公司 | Intelligent broadcast television program production and management method |
| CN113242445A (en) * | 2021-06-18 | 2021-08-10 | 秒影工场(北京)科技有限公司 | Method for pushing media material library in commercial short video production process |
| CN114788293A (en) * | 2019-06-11 | 2022-07-22 | 唯众挚美影视技术公司 | Production-as-a-service system for producing movies, television programs and multimedia content |
| CN114860995A (en) * | 2022-07-05 | 2022-08-05 | 北京百度网讯科技有限公司 | Video script generation method and device, electronic equipment and medium |
| CN115329206A (en) * | 2022-10-13 | 2022-11-11 | 深圳市人马互动科技有限公司 | Voice outbound processing method and related device |
| CN115374364A (en) * | 2022-09-08 | 2022-11-22 | 中国第一汽车股份有限公司 | Content recommendation method and device based on third-party video platform |
| CN115580758A (en) * | 2022-10-12 | 2023-01-06 | 中国平安人寿保险股份有限公司 | Video content generation method and device, electronic equipment and storage medium |
| CN115757756A (en) * | 2022-11-30 | 2023-03-07 | 北京有竹居网络技术有限公司 | Content retrieval method, device, medium and electronic equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060265730A1 (en) * | 2005-05-18 | 2006-11-23 | Podfitness, Inc | Mixing and producing individualized media files |
| US11989507B2 (en) * | 2021-08-24 | 2024-05-21 | Unlikely Artificial Intelligence Limited | Computer implemented methods for the automated analysis or use of data, including use of a large language model |
-
2023
- 2023-09-28 CN CN202311273531.3A patent/CN117336539B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1503159A (en) * | 2002-11-25 | 2004-06-09 | ���µ�����ҵ��ʽ���� | Short film generation/reproduction apparatus and method thereof |
| CN103279581A (en) * | 2013-06-25 | 2013-09-04 | 中国科学院自动化研究所 | Method for performing video retrieval by compact video theme descriptors |
| CA2931623A1 (en) * | 2013-11-26 | 2015-06-04 | Taxconnections, Inc. | Systems and methods for searching for professionals within an online community |
| CN106354818A (en) * | 2016-08-30 | 2017-01-25 | 电子科技大学 | Dynamic user attribute extraction method based on social media |
| CN114788293A (en) * | 2019-06-11 | 2022-07-22 | 唯众挚美影视技术公司 | Production-as-a-service system for producing movies, television programs and multimedia content |
| CN111048215A (en) * | 2019-12-13 | 2020-04-21 | 北京纵横无双科技有限公司 | CRM-based medical video production method and system |
| CN111629269A (en) * | 2020-05-25 | 2020-09-04 | 厦门大学 | Method for automatically shooting and generating mobile terminal short video advertisement based on mechanical arm |
| CN111970416A (en) * | 2020-08-29 | 2020-11-20 | 赣州圣享区块链技术有限公司 | Intelligent broadcast television program production and management method |
| CN113242445A (en) * | 2021-06-18 | 2021-08-10 | 秒影工场(北京)科技有限公司 | Method for pushing media material library in commercial short video production process |
| CN114860995A (en) * | 2022-07-05 | 2022-08-05 | 北京百度网讯科技有限公司 | Video script generation method and device, electronic equipment and medium |
| CN115374364A (en) * | 2022-09-08 | 2022-11-22 | 中国第一汽车股份有限公司 | Content recommendation method and device based on third-party video platform |
| CN115580758A (en) * | 2022-10-12 | 2023-01-06 | 中国平安人寿保险股份有限公司 | Video content generation method and device, electronic equipment and storage medium |
| CN115329206A (en) * | 2022-10-13 | 2022-11-11 | 深圳市人马互动科技有限公司 | Voice outbound processing method and related device |
| CN115757756A (en) * | 2022-11-30 | 2023-03-07 | 北京有竹居网络技术有限公司 | Content retrieval method, device, medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| Jingfeng Yang, Hongye Jin, Ruixiang Tang, Xiaotian Han, Qizhang Feng, Haoming Jiang, Bing Yin, Xia Hu.Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond.arXiv.org.2023,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117336539A (en) | 2024-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220215032A1 (en) | Ai-based recommendation method and apparatus, electronic device, and storage medium | |
| Qi et al. | Finding all you need: web APIs recommendation in web of things through keywords search | |
| CN110597981B (en) | Network news summary system for automatically generating summary by adopting multiple strategies | |
| CN109753635A (en) | Use high-quality exemplary document automation assistant | |
| CN111143684B (en) | Artificial intelligence-based generalized model training method and device | |
| CN108280218A (en) | A kind of flow system based on retrieval and production mixing question and answer | |
| CN113010702A (en) | Interactive processing method and device for multimedia information, electronic equipment and storage medium | |
| US20190295199A1 (en) | Intelligent legal simulator | |
| CN113392331A (en) | Text processing method and equipment | |
| CN110321483A (en) | A kind of online course content of platform recommended method, device, system and storage medium based on user's sequence sexual behaviour | |
| CN116956183A (en) | Multimedia resource recommendation method, model training method, device and storage medium | |
| CN117336539B (en) | Video script production method and system for short video IP (Internet protocol) construction | |
| CN116958738A (en) | Training method and device of picture recognition model, storage medium and electronic equipment | |
| CN116910201A (en) | Dialogue data generation method and related equipment thereof | |
| CN116662527A (en) | Method for generating learning resources and related products | |
| CN113254788A (en) | Big data based recommendation method and system and readable storage medium | |
| Qu et al. | The application of interactive methods under swarm computing and artificial intelligence in image retrieval and personalized analysis | |
| CN117633196B (en) | Question-answering model construction method and project question-answering method | |
| CN117633540B (en) | Sample data construction method and device | |
| CN117725191B (en) | Guide information generation method and device of large language model and electronic equipment | |
| CN115796405B (en) | Solution report generation method and computing device for optimization model | |
| CN116860952B (en) | RPA intelligent response processing method and system based on artificial intelligence | |
| CN112905884B (en) | Method, apparatus, medium and program product for generating sequence annotation model | |
| KR101951179B1 (en) | Ideation method for providing business support service | |
| CN117634434A (en) | Dialogue content generation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |