CN114639051B - Advertisement short video quality evaluation method, system and storage medium based on big data analysis - Google Patents
Advertisement short video quality evaluation method, system and storage medium based on big data analysis Download PDFInfo
- Publication number
- CN114639051B CN114639051B CN202210287821.2A CN202210287821A CN114639051B CN 114639051 B CN114639051 B CN 114639051B CN 202210287821 A CN202210287821 A CN 202210287821A CN 114639051 B CN114639051 B CN 114639051B
- Authority
- CN
- China
- Prior art keywords
- video
- evaluated
- advertisement
- advertisement short
- short
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
Abstract
The invention discloses an advertisement short video quality evaluation method, system and storage medium based on big data analysis, which are characterized in that according to the video line information of the line head in each advertisement short video to be evaluated, the coincidence theme coefficient of the line head video line information in each advertisement short video to be evaluated is analyzed, meanwhile, the relevant parameters and video time points of each video frame image in each advertisement short video to be evaluated are obtained, the video content playing influence coefficient of each advertisement short video to be evaluated is analyzed, the matching number of video frame images in each advertisement short video to be evaluated is combined, the comprehensive manufacturing quality coefficient of each advertisement short video to be evaluated is evaluated, and the corresponding processing is carried out after the comparison and analysis, so that the comprehensive evaluation according to the multidimensional quality influence factor of the advertisement short video is realized, the problem that the existing method has a certain limitation is broken, and the reliability and the accuracy of the advertisement short video manufacturing quality evaluation result are effectively ensured.
Description
Technical Field
The invention relates to the technical field of advertisement short video quality evaluation, in particular to an advertisement short video quality evaluation method, system and storage medium based on big data analysis.
Background
Advertising is an important way to promote corporate products and improve brand awareness. Due to the popularity of media such as televisions, networks and the like, the advertising short video audience is very wide, and is an important advertising form. In the current society, commercial competition is increasingly strong, and enterprises are urgent to know the production quality and the delivery effect of advertisement short videos.
At present, the existing advertisement short video production quality evaluation method mainly considers the conformity between the whole content of the advertisement short video and the planned theme, and does not consider the theme conformity of the video of the head of the advertisement short video, so that the problem of insufficient expressive force of the theme of the video of the head of the advertisement short video exists, and the interested content of the user cannot be represented rapidly, and further the user cannot be attracted to continue watching the advertisement short video, so that the contradiction psychology of the user to the advertisement short video is enhanced to a great extent, the watching experience and satisfaction of the user are reduced, and the whole production quality of the advertisement short video is further influenced.
The conventional method for evaluating the production quality of the advertisement short video mainly concentrates on evaluating the planning theme of the advertisement short video in terms of conformity, and cannot realize comprehensive evaluation according to the multidimensional quality influence factors of the advertisement short video, so that the conventional method has certain limitations, cannot effectively ensure the reliability and the accuracy of the evaluation result of the production quality of the advertisement short video, further influences the expected delivery effect of the advertisement short video in the later stage, and further influences the economic cost, the delivery economic cost and the time cost of the advertisement short video production of enterprises.
In order to solve the problems, an advertisement short video quality evaluation method, an advertisement short video quality evaluation system and a storage medium based on big data analysis are designed.
Disclosure of Invention
The invention aims to provide an advertisement short video quality evaluation method, system and storage medium based on big data analysis, which solve the problems in the background technology.
The technical scheme adopted for solving the technical problems is as follows:
in a first aspect, the present invention provides a method for evaluating advertisement short video quality based on big data analysis, comprising the steps of:
s1, acquiring advertisement short video film head video: acquiring a video of a film head in each advertisement short video to be evaluated according to the playing time of each advertisement short video to be evaluated;
s2, comparing and analyzing the video speech information of the film head: extracting the video line information of the head of each advertisement short video to be evaluated, comparing the video line information with the preset planning subject information of each advertisement short video to be evaluated, and analyzing the coincidence subject coefficient of the video line information of the head of each advertisement short video to be evaluated;
s3, processing relevant parameters of the video frame image: dividing each advertisement short video to be evaluated into each video frame image, obtaining relevant parameters of each video frame image in each advertisement short video to be evaluated, and processing to obtain parameter influence weight indexes of each video frame image in each advertisement short video to be evaluated;
s4, video frame image clipping fluency analysis: acquiring video time points corresponding to video frame images in the advertisement short videos to be evaluated, and comparing and analyzing clipping fluency weight indexes of the video frame images in the advertisement short videos to be evaluated;
s5, analyzing the video content playing influence coefficient: analyzing video content playing influence coefficients of the advertisement short videos to be evaluated according to parameter influence weight indexes and editing fluency weight indexes of video frame images in the advertisement short videos to be evaluated;
s6, video frame image contrast processing: extracting preset product display images corresponding to the advertisement short videos to be evaluated, comparing and screening the matching number of video frame images in the advertisement short videos to be evaluated, and analyzing the product display image matching coefficients of the advertisement short videos to be evaluated;
s7, evaluating the production quality of the advertisement short video: and evaluating the comprehensive production quality coefficient of each advertisement short video to be evaluated, comparing the comprehensive production quality coefficient with a preset advertisement short video production quality coefficient threshold value, and carrying out corresponding processing according to a comparison result.
Further, the detailed steps corresponding to the step S1 are as follows:
sequentially numbering the advertisement short videos to be evaluated according to the production time sequence, wherein the numbers of the advertisement short videos to be evaluated are 1,2, i, n;
acquiring the playing time length of each advertisement short video to be evaluated, and analyzing the time length of the head of each advertisement short video to be evaluated based on the preset time length of the head of each advertisement short video;
obtaining the video of the head of each short video to be evaluated according to the time length of the head of each short video to be evaluated, and marking the video of the head of each short video to be evaluated as a i I=1, 2..n, i represents the i-th ad short video to be rated.
Further, in the step S2, the analyzing the topic factors of the video line information of the film head in each advertisement short video to be evaluated specifically includes:
extracting the line information of the head video in each short advertisement video to be evaluated, extracting the preset planning subject information of each short advertisement video to be evaluated in an advertisement short video planning database, comparing the line information of the head video in each short advertisement video to be evaluated with the preset planning subject information of the corresponding short advertisement video to be evaluated, obtaining the coincidence degree of the line information of the head video in each short advertisement video to be evaluated and the corresponding preset planning subject information, and marking the coincidence degree of the line information of the head video in each short advertisement video to be evaluated and the corresponding preset planning subject information as thetaa i ;
Analyzing the topic coefficient of the video line information of the film head in each advertisement short video to be evaluatedWherein mu θ Expressed as an impact index corresponding to a preset compliance, θ Standard of And the standard coincidence degree threshold value of the preset short video line information and the planning subject information is expressed.
Further, the specific detailed steps corresponding to the step S3 include:
dividing each advertisement short video to be evaluated into each video frame image in sequence according to the video playing sequence, obtaining related parameters of each video frame image in each advertisement short video to be evaluated, wherein the related parameters comprise resolution, frame rate, pixels and definition, and respectively marking the resolution, frame rate, pixels and definition of each video frame image in each advertisement short video to be evaluated as w 1 b ij 、w 2 b ij 、w 3 b ij 、w 4 b ij J=1, 2,..m, j is denoted as the j-th video frame image;
analyzing parameter influence weight index of each video frame image in each advertisement short video to be evaluatedWherein lambda is 1 、λ 2 、λ 3 、λ 4 Respectively expressed as preset imagesResolution, image frame rate, image pixels, weight impact factor corresponding to image sharpness, and λ 1 +λ 2 +λ 3 +λ 4 =1,w 1 b Label (C) 、w 2 b Label (C) 、w 3 b Label (C) 、w 4 b Label (C) Respectively representing the standard resolution, the standard frame rate, the standard pixel and the standard definition corresponding to the preset video frame image.
Further, in the step S4, the clipping fluency weight index of each video frame image in each advertisement short video to be evaluated is compared and analyzed, and the specific analysis mode is as follows:
acquiring video time points corresponding to video frame images in the advertisement short videos to be evaluated, and marking the video time points corresponding to the video frame images in the advertisement short videos to be evaluated as t i b j ;
Substituting video time points corresponding to video frame images in the advertisement short videos to be evaluated into a formulaObtaining the editing fluency weight index ++ ++of each video frame image in each advertisement short video to be evaluated>η 1 、η 2 Respectively expressed as preset clip fluency influencing factors, t i b j+1 The video time point, t, corresponding to the (j+1) th video frame image in the ith advertisement short video to be evaluated is represented as i b j-1 The video time point corresponding to the j-1 th video frame image in the ith advertisement short video to be evaluated is shown as delta t Allow for Represented as a preset allowable point-in-time error value between video frame images.
Further, the specific detailed steps corresponding to the step S5 include:
the parameter influence weight index epsilon b 'of each video frame image in each advertisement short video to be evaluated' ij And clipping fluency weight index of each video frame image in each advertisement short video to be evaluatedSubstitution formulaObtaining video content playing influence coefficients xi of each advertisement short video to be evaluated 2 a i Where m is expressed as the number of divided video frame images, β 1 、β 2 Respectively expressed as preset video content playing influence factors, and beta 1 +β 2 =1。
Further, in the step S6, the matching coefficients of the product display images of the advertisement short videos to be evaluated are analyzed, and the specific analysis mode is as follows:
comparing each video frame image in each short advertisement video to be evaluated with a preset product display image corresponding to the short advertisement video to be evaluated, if the preset product display image corresponding to the short advertisement video to be evaluated appears in a certain video frame image in a certain short advertisement video to be evaluated, matching the video frame image in the short advertisement video to be evaluated with the corresponding preset product display image, counting the matching number of the video frame images in each short advertisement video to be evaluated, and marking the matching number of the video frame images in each short advertisement video to be evaluated as za i ;
Analyzing product display image matching coefficients of advertisement short videos to be evaluatedWherein delta is expressed as a preset product display image matching influence factor, z Presetting Expressed as a preset video frame image matching number threshold, e is expressed as a constant.
Further, in the step S7, evaluating the comprehensive production quality coefficient of each advertisement short video to be evaluated includes:
the method comprises the steps of conforming a theme coefficient xi of the video line information of the film head in each advertisement short video to be evaluated 1 a i Video content playing influence coefficient xi of each advertisement short video to be evaluated 2 a i And product display image matching coefficients xi of each advertisement short video to be evaluated 3 a i Substituting advertisement short video production quality evaluation formula psi i =γ 1 *ξ 1 a i +γ 2 *ξ 2 a i +γ 3 *ξ 3 a i Obtaining the comprehensive production quality coefficient psi of each advertisement short video to be evaluated i Wherein gamma is 1 、γ 2 、γ 3 Respectively expressed as preset advertisement short video production quality influencing factors, and gamma 1 +γ 2 +γ 3 =1。
In a second aspect, the present invention also provides a short video analysis processing system, including:
the advertisement short video film head video acquisition module: the method comprises the steps of obtaining a video of a film head in each advertisement short video to be evaluated according to the playing time of each advertisement short video to be evaluated;
the film head video speech information comparison and analysis module: the method comprises the steps of extracting the video line information of the head of each advertisement short video to be evaluated, comparing the video line information with the preset planning subject information of each advertisement short video to be evaluated, and analyzing the coincidence subject coefficient of the video line information of the head of each advertisement short video to be evaluated;
advertisement short video plan database: the method comprises the steps of storing preset planning subject information and preset product display images of advertisement short videos to be evaluated;
the video frame image related parameter processing module: the method comprises the steps of dividing each advertisement short video to be evaluated into each video frame image, obtaining relevant parameters of each video frame image in each advertisement short video to be evaluated, and processing to obtain parameter influence weight indexes of each video frame image in each advertisement short video to be evaluated;
and the video frame image clipping fluency analysis module is used for: the method comprises the steps of obtaining video time points corresponding to video frame images in each advertisement short video to be evaluated, and comparing and analyzing clipping fluency weight indexes of the video frame images in each advertisement short video to be evaluated;
video content playing influence coefficient analysis module: the method comprises the steps of analyzing video content playing influence coefficients of advertisement short videos to be evaluated according to parameter influence weight indexes and editing fluency weight indexes of video frame images in the advertisement short videos to be evaluated;
the video frame image contrast processing module: the method comprises the steps of extracting preset product display images corresponding to advertisement short videos to be evaluated, comparing and screening the matching quantity of video frame images in the advertisement short videos to be evaluated, and analyzing the product display image matching coefficient of the advertisement short videos to be evaluated;
the advertisement short video production quality evaluation module: the method is used for evaluating the comprehensive production quality coefficient of each advertisement short video to be evaluated, comparing the comprehensive production quality coefficient with a preset advertisement short video production quality coefficient threshold value, and carrying out corresponding processing according to a comparison result.
In a third aspect, the present invention further provides a storage medium, where the storage medium is burned with a computer program, and the computer program implements the advertisement short video quality evaluation method based on big data analysis according to the present invention when running in a memory of a server.
Compared with the prior art, the advertisement short video quality evaluation method, the advertisement short video quality evaluation system and the storage medium based on big data analysis have the following beneficial effects:
according to the advertisement short video quality evaluation method, system and storage medium based on big data analysis, the head video in each advertisement short video to be evaluated is obtained, and the head video line information in each advertisement short video to be evaluated is analyzed according to the head video line information in each advertisement short video to be evaluated, so that the problem of insufficient expressive force of the head video subject in the advertisement short video is effectively avoided, the content of interest of a user is ensured to be rapidly reflected, the user is further attracted to continuously watch the advertisement short video, the contradiction psychology of the user to the advertisement short video is further eliminated, the watching experience and satisfaction of the user are improved, and the whole manufacturing quality of the advertisement short video is ensured to a great extent.
According to the advertisement short video quality evaluation method, system and storage medium based on big data analysis, relevant parameters and video time points of video frame images in the advertisement short videos to be evaluated are obtained, video content playing influence coefficients of the advertisement short videos to be evaluated are analyzed, the matching number of the video frame images in the advertisement short videos to be evaluated is combined, comprehensive manufacturing quality coefficients of the advertisement short videos to be evaluated are obtained through evaluation, and corresponding processing is carried out after comparison and analysis, so that comprehensive evaluation according to multi-dimensional quality influence factors of the advertisement short videos is achieved, the problem that the existing method has certain limitation is broken, reliability and accuracy of advertisement short video manufacturing quality evaluation results are effectively guaranteed, the expected effect of the advertisement short videos in the later period is guaranteed, and meanwhile economic cost, economic cost and time cost loss of enterprise advertisement short video manufacturing can be avoided to a certain extent.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of the method of the present invention;
fig. 2 is a system module connection diagram of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a first aspect of the present invention provides a short video analysis processing method, which includes the following steps:
s1, acquiring advertisement short video film head video: and acquiring the video of the title in each advertisement short video to be evaluated according to the playing time of each advertisement short video to be evaluated.
In this embodiment, the detailed steps corresponding to the step S1 are as follows:
sequentially numbering the advertisement short videos to be evaluated according to the production time sequence, wherein the numbers of the advertisement short videos to be evaluated are 1,2, i, n;
acquiring the playing time length of each advertisement short video to be evaluated, and analyzing the time length of the head of each advertisement short video to be evaluated based on the preset time length of the head of each advertisement short video;
obtaining the video of the head of each short video to be evaluated according to the time length of the head of each short video to be evaluated, and marking the video of the head of each short video to be evaluated as a i I=1, 2..n, i represents the i-th ad short video to be rated.
In one possible design, the analysis formula of the duration of the head of each advertisement short video to be evaluated is T i ′=k Pre-preparation *T i ,T i ' the duration, k, of the title denoted as the ith short video of advertisement to be evaluated Pre-preparation The preset advertisement short video film head duration ratio is represented as T i And the playing time length of the ith advertisement short video to be evaluated is represented.
S2, comparing and analyzing the video speech information of the film head: extracting the video line-of-sight video information in each advertisement short video to be evaluated, comparing the video line-of-sight information with preset planning subject information of each advertisement short video to be evaluated, and analyzing the coincidence subject coefficient of the video line-of-sight information in each advertisement short video to be evaluated.
In this embodiment, in the step S2, the analyzing the topic factors of the video line information of the film head in each advertisement short video to be evaluated specifically includes:
extracting the line information of the head video in each short advertisement video to be evaluated, extracting the preset planning subject information of each short advertisement video to be evaluated in an advertisement short video planning database, comparing the line information of the head video in each short advertisement video to be evaluated with the preset planning subject information of the corresponding short advertisement video to be evaluated, obtaining the coincidence degree of the line information of the head video in each short advertisement video to be evaluated and the corresponding preset planning subject information, and comparing the line information of the head video in each short advertisement video to be evaluated with the line information of the head video in each short advertisement video to be evaluatedThe coincidence degree of the information and the corresponding preset planning subject information is marked as theta a i ;
Analyzing the topic coefficient of the video line information of the film head in each advertisement short video to be evaluatedWherein mu θ Expressed as an impact index corresponding to a preset compliance, θ Standard of And the standard coincidence degree threshold value of the preset short video line information and the planning subject information is expressed.
In one possible design, the above-mentioned method obtains the coincidence degree of the speech information of the video of the title in each advertisement short video to be evaluated and the corresponding preset planning subject information, and the specific obtaining mode is as follows:
word segmentation processing is carried out on the word segmentation information of the video of the head in each advertisement short video to be evaluated, so that each effective word in the word segmentation information of the video of the head in each advertisement short video to be evaluated is obtained;
comparing each effective word in the video line information of the head of each advertisement short video to be evaluated with each preset effective word in the preset planning subject information of the corresponding advertisement short video to be evaluated, counting the matching quantity of the video line information of the head of each advertisement short video to be evaluated and the effective word corresponding to the preset planning subject information, and marking the matching quantity of the video line information of the head of each advertisement short video to be evaluated and the effective word corresponding to the preset planning subject information as x i ;
Extracting keywords from the speech information of the video of the title in each advertisement short video to be evaluated to obtain keywords in the speech information of the video of the title in each advertisement short video to be evaluated;
extracting each near-meaning keyword corresponding to a keyword in preset planning subject information of each advertisement short video to be evaluated in an advertisement short video planning database, comparing each keyword in the head video line information of each advertisement short video to be evaluated with each near-meaning keyword in the preset planning subject information of the corresponding advertisement short video to be evaluated, and counting the matching quantity of the head video line information of each advertisement short video to be evaluated and the near-meaning keywords corresponding to the preset planning subject informationMarking the matching number of the video line information of the head of each advertisement short video to be evaluated and the near-meaning keywords corresponding to the preset planning subject information as y i ;
Analyzing the coincidence degree of the line information of the video of the head of each advertisement short video to be evaluated and the corresponding preset planning subject informationWherein alpha is 1 、α 2 Respectively expressed as a preset coincidence degree influence factor, x Pre-preparation The number of valid word matches expressed as preset short video speech information and planning subject information, y Pre-preparation The matching number of the short video speech information and the near-meaning keywords of the planning subject information is shown as the preset matching number.
It is to be noted that, the invention analyzes the subject-conforming coefficient of the video line information of the head in each advertisement short video to be evaluated according to the line information of the head in each advertisement short video to be evaluated, thereby effectively avoiding the problem of insufficient subject expressive force of the head in the advertisement short video, ensuring that the interested content of the user can be quickly reflected, further attracting the user to continue watching the advertisement short video, further eliminating the contradiction psychology of the user to the advertisement short video, improving the watching experience and satisfaction of the user, and ensuring the whole manufacturing quality of the advertisement short video to a great extent.
S3, processing relevant parameters of the video frame image: dividing each advertisement short video to be evaluated into each video frame image, acquiring related parameters of each video frame image in each advertisement short video to be evaluated, and processing to obtain parameter influence weight indexes of each video frame image in each advertisement short video to be evaluated.
In this embodiment, the specific detailed steps corresponding to the step S3 include:
dividing each advertisement short video to be evaluated into each video frame image according to the video playing sequence, obtaining related parameters of each video frame image in each advertisement short video to be evaluated, wherein the related parameters comprise resolution, frame rate, pixels and definition, and dividing each advertisement short video to be evaluated into each video frame imageResolution, frame rate, pixels and sharpness of the video frame image are labeled w, respectively 1 b ij 、w 2 b ij 、w 3 b ij 、w 4 b ij J=1, 2,..m, j is denoted as the j-th video frame image;
analyzing parameter influence weight index of each video frame image in each advertisement short video to be evaluatedWherein lambda is 1 、λ 2 、λ 3 、λ 4 Respectively expressed as weight influence factors corresponding to preset image resolution, image frame rate, image pixels and image definition, and lambda 1 +λ 2 +λ 3 +λ 4 =1,w 1 b Label (C) 、w 2 b Label (C) 、w 3 b Label (C) 、w 4 b Label (C) Respectively representing the standard resolution, the standard frame rate, the standard pixel and the standard definition corresponding to the preset video frame image.
S4, video frame image clipping fluency analysis: and acquiring video time points corresponding to the video frame images in the advertisement short videos to be evaluated, and comparing and analyzing clipping fluency weight indexes of the video frame images in the advertisement short videos to be evaluated.
In this embodiment, in step S4, the clipping fluency weight index of each video frame image in each advertisement short video to be evaluated is compared and analyzed in the specific analysis manner:
acquiring video time points corresponding to video frame images in the advertisement short videos to be evaluated, and marking the video time points corresponding to the video frame images in the advertisement short videos to be evaluated as t i b j ;
Substituting video time points corresponding to video frame images in the advertisement short videos to be evaluated into a formulaObtaining the editing fluency weight index ++ ++of each video frame image in each advertisement short video to be evaluated>η 1 、η 2 Respectively expressed as preset clip fluency influencing factors, t i b j+1 The video time point, t, corresponding to the (j+1) th video frame image in the ith advertisement short video to be evaluated is represented as i b j-1 The video time point corresponding to the j-1 th video frame image in the ith advertisement short video to be evaluated is shown as delta t Allow for Represented as a preset allowable point-in-time error value between video frame images.
S5, analyzing the video content playing influence coefficient: and analyzing video content playing influence coefficients of the advertisement short videos to be evaluated according to the parameter influence weight indexes and the editing fluency weight indexes of the video frame images in the advertisement short videos to be evaluated.
In this embodiment, the specific detailed steps corresponding to the step S5 include:
the parameter influence weight index epsilon b 'of each video frame image in each advertisement short video to be evaluated' ij And clipping fluency weight index of each video frame image in each advertisement short video to be evaluatedSubstitution formulaObtaining video content playing influence coefficients xi of each advertisement short video to be evaluated 2 a i Where m is expressed as the number of divided video frame images, β 1 、β 2 Respectively expressed as preset video content playing influence factors, and beta 1 +β 2 =1。
S6, video frame image contrast processing: and extracting preset product display images corresponding to the advertisement short videos to be evaluated, comparing and screening the matching quantity of video frame images in the advertisement short videos to be evaluated, and analyzing the product display image matching coefficients of the advertisement short videos to be evaluated.
In this embodiment, in the step S6, the product display image matching coefficients of each advertisement short video to be evaluated are analyzed, and the specific analysis method is as follows:
comparing each video frame image in each short advertisement video to be evaluated with a preset product display image corresponding to the short advertisement video to be evaluated, if the preset product display image corresponding to the short advertisement video to be evaluated appears in a certain video frame image in a certain short advertisement video to be evaluated, matching the video frame image in the short advertisement video to be evaluated with the corresponding preset product display image, counting the matching number of the video frame images in each short advertisement video to be evaluated, and marking the matching number of the video frame images in each short advertisement video to be evaluated as za i ;
Analyzing product display image matching coefficients of advertisement short videos to be evaluatedWherein delta is expressed as a preset product display image matching influence factor, z Presetting Expressed as a preset video frame image matching number threshold, e is expressed as a constant.
S7, evaluating the production quality of the advertisement short video: and evaluating the comprehensive production quality coefficient of each advertisement short video to be evaluated, comparing the comprehensive production quality coefficient with a preset advertisement short video production quality coefficient threshold value, and carrying out corresponding processing according to a comparison result.
In this embodiment, the evaluating the comprehensive production quality coefficient of each advertisement short video to be evaluated in step S7 includes:
the method comprises the steps of conforming a theme coefficient xi of the video line information of the film head in each advertisement short video to be evaluated 1 a i Video content playing influence coefficient xi of each advertisement short video to be evaluated 2 a i And product display image matching coefficients xi of each advertisement short video to be evaluated 3 a i Substituting advertisement short video production quality evaluation formula psi i =γ 1 *ξ 1 a i +γ 2 *ξ 2 a i +γ 3 *ξ 3 a i Obtaining the comprehensive production quality coefficient psi of each advertisement short video to be evaluated i Wherein gamma is 1 、γ 2 、γ 3 Respectively expressed as preset advertisement shortVideo production quality influencing factor, and gamma 1 +γ 2 +γ 3 =1。
In one possible design, the step S7 performs corresponding processing according to the comparison result, including:
comparing the comprehensive production quality coefficient of each advertisement short video to be evaluated with a preset advertisement short video production quality coefficient threshold, if the comprehensive production quality coefficient of a certain advertisement short video to be evaluated is larger than or equal to the preset advertisement short video production quality coefficient threshold, indicating that the production quality evaluation of the advertisement short video to be evaluated is qualified, and if the comprehensive production quality coefficient of the advertisement short video to be evaluated is smaller than the preset advertisement short video production quality coefficient threshold, indicating that the production quality evaluation of the advertisement short video to be evaluated is unqualified, carrying out production evaluation on the advertisement short video to be evaluated again.
It is to be noted that the method analyzes the video content playing influence coefficient of each advertisement short video to be evaluated by acquiring the relevant parameters and video time points of each video frame image in each advertisement short video to be evaluated, combines the matching quantity of the video frame images in each advertisement short video to be evaluated, evaluates the comprehensive manufacturing quality coefficient of each advertisement short video to be evaluated, and carries out corresponding processing after comparative analysis, thereby realizing comprehensive evaluation according to the multidimensional quality influence factors of the advertisement short videos, breaking the problem that the existing method has certain limitation, further effectively guaranteeing the reliability and the accuracy of the manufacturing quality evaluation result of the advertisement short videos, ensuring the expected throwing effect of the advertisement short videos in the later period, and simultaneously avoiding the manufacturing economic cost, the throwing economic cost and the time cost loss of the advertisement short videos of enterprises to a certain extent.
In a second aspect, the invention also provides an advertisement short video quality evaluation system based on big data analysis, which comprises an advertisement short video head video acquisition module, a head video line information comparison analysis module, an advertisement short video planning database, a video frame image related parameter processing module, a video frame image clipping fluency analysis module, a video content playing influence coefficient analysis module, a video frame image comparison processing module and an advertisement short video production quality evaluation module;
the advertisement short video film head video acquisition module is connected with the film head video line information comparison analysis module, the film head video line information comparison analysis module is respectively connected with the advertisement short video planning database and the advertisement short video production quality evaluation module, the video frame image editing fluency analysis module is respectively connected with the video frame image related parameter processing module and the video content playing influence coefficient analysis module, the video content playing influence coefficient analysis module is respectively connected with the video frame image related parameter processing module and the advertisement short video production quality evaluation module, and the video frame image comparison processing module is respectively connected with the advertisement short video planning database, the video frame image related parameter processing module and the advertisement short video production quality evaluation module;
the advertisement short video title video acquisition module is used for acquiring title videos in the advertisement short videos to be evaluated according to the playing time of the advertisement short videos to be evaluated;
the film head video line information comparison and analysis module is used for extracting film head video line information in each advertisement short video to be evaluated, comparing the film head video line information with preset planning subject information of each advertisement short video to be evaluated, and analyzing the consistent subject coefficients of the film head video line information in each advertisement short video to be evaluated;
the advertisement short video planning database is used for storing preset planning subject information and preset product display images of advertisement short videos to be evaluated;
the video frame image related parameter processing module is used for dividing each advertisement short video to be evaluated into each video frame image, acquiring related parameters of each video frame image in each advertisement short video to be evaluated, and processing to obtain parameter influence weight indexes of each video frame image in each advertisement short video to be evaluated;
the video frame image clipping fluency analysis module is used for obtaining video time points corresponding to the video frame images in the advertisement short videos to be evaluated, and comparing and analyzing clipping fluency weight indexes of the video frame images in the advertisement short videos to be evaluated;
the video content playing influence coefficient analysis module is used for analyzing the video content playing influence coefficient of each advertisement short video to be evaluated according to the parameter influence weight index and the editing fluency weight index of each video frame image in each advertisement short video to be evaluated;
the video frame image comparison processing module is used for extracting preset product display images corresponding to the advertisement short videos to be evaluated, comparing and screening the matching quantity of the video frame images in the advertisement short videos to be evaluated, and analyzing the product display image matching coefficients of the advertisement short videos to be evaluated;
the advertisement short video production quality evaluation module is used for evaluating the comprehensive production quality coefficient of each advertisement short video to be evaluated, comparing the comprehensive production quality coefficient with a preset advertisement short video production quality coefficient threshold value, and carrying out corresponding processing according to the comparison result.
In a third aspect, the present invention further provides a storage medium, where the storage medium is burned with a computer program, and the computer program implements the advertisement short video quality evaluation method based on big data analysis according to the present invention when running in a memory of a server.
The foregoing is merely illustrative and explanatory of the principles of the invention, as various modifications and additions may be made to the specific embodiments described, or similar thereto, by those skilled in the art, without departing from the principles of the invention or beyond the scope of the appended claims.
Claims (6)
1. The advertisement short video quality evaluation method based on big data analysis is characterized by comprising the following steps:
s1, acquiring advertisement short video film head video: acquiring a video of a film head in each advertisement short video to be evaluated according to the playing time of each advertisement short video to be evaluated;
s2, comparing and analyzing the video speech information of the film head: extracting the video line information of the head of each advertisement short video to be evaluated, comparing the video line information with the preset planning subject information of each advertisement short video to be evaluated, and analyzing the coincidence subject coefficient of the video line information of the head of each advertisement short video to be evaluated;
in the step S2, the analyzing the topic factor of the video line information of the film head in each advertisement short video to be evaluated specifically includes:
extracting the line information of the head video in each short advertisement video to be evaluated, extracting the preset planning subject information of each short advertisement video to be evaluated in an advertisement short video planning database, comparing the line information of the head video in each short advertisement video to be evaluated with the preset planning subject information of the corresponding short advertisement video to be evaluated, obtaining the coincidence degree of the line information of the head video in each short advertisement video to be evaluated and the corresponding preset planning subject information, and marking the coincidence degree of the line information of the head video in each short advertisement video to be evaluated and the corresponding preset planning subject information as thetaa i ;
Analyzing the topic coefficient of the video line information of the film head in each advertisement short video to be evaluatedWherein mu θ Expressed as an impact index corresponding to a preset compliance, θ Standard of The standard coincidence degree threshold value of the preset short video line information and the planning subject information is represented;
s3, processing relevant parameters of the video frame image: dividing each advertisement short video to be evaluated into each video frame image, obtaining relevant parameters of each video frame image in each advertisement short video to be evaluated, and processing to obtain parameter influence weight indexes of each video frame image in each advertisement short video to be evaluated;
s4, video frame image clipping fluency analysis: acquiring video time points corresponding to video frame images in the advertisement short videos to be evaluated, and comparing and analyzing clipping fluency weight indexes of the video frame images in the advertisement short videos to be evaluated;
s5, analyzing the video content playing influence coefficient: analyzing video content playing influence coefficients of the advertisement short videos to be evaluated according to parameter influence weight indexes and editing fluency weight indexes of video frame images in the advertisement short videos to be evaluated;
the specific detailed steps corresponding to the step S5 include:
the parameter influence weight index epsilon b 'of each video frame image in each advertisement short video to be evaluated' ij And clipping fluency weight index of each video frame image in each advertisement short video to be evaluatedSubstitution formulaObtaining video content playing influence coefficients xi of each advertisement short video to be evaluated 2 a i Where m is expressed as the number of divided video frame images, β 1 、β 2 Respectively expressed as preset video content playing influence factors, and beta 1 +β 2 =1;
S6, video frame image contrast processing: extracting preset product display images corresponding to the advertisement short videos to be evaluated, comparing and screening the matching number of video frame images in the advertisement short videos to be evaluated, and analyzing the product display image matching coefficients of the advertisement short videos to be evaluated;
in the step S6, the matching coefficients of the product display images of the advertisement short videos to be evaluated are analyzed, and the specific analysis mode is as follows:
comparing each video frame image in each short advertisement video to be evaluated with a preset product display image corresponding to the short advertisement video to be evaluated, if the preset product display image corresponding to the short advertisement video to be evaluated appears in a certain video frame image in a certain short advertisement video to be evaluated, matching the video frame image in the short advertisement video to be evaluated with the corresponding preset product display image, counting the matching number of the video frame images in each short advertisement video to be evaluated, and marking the matching number of the video frame images in each short advertisement video to be evaluated as za i ;
Analyzing product display image matching coefficients of advertisement short videos to be evaluatedWherein the method comprises the steps ofDelta is expressed as a preset product display image matching influence factor, z Presetting A preset video frame image matching quantity threshold value is represented, and e is represented as a constant;
s7, evaluating the production quality of the advertisement short video: evaluating the comprehensive production quality coefficient of each advertisement short video to be evaluated, comparing the comprehensive production quality coefficient with a preset advertisement short video production quality coefficient threshold value, and carrying out corresponding processing according to a comparison result;
in the step S7, the evaluating the comprehensive production quality coefficient of each advertisement short video to be evaluated includes:
the method comprises the steps of conforming a theme coefficient xi of the video line information of the film head in each advertisement short video to be evaluated 1 a i Video content playing influence coefficient xi of each advertisement short video to be evaluated 2 a i And product display image matching coefficients xi of each advertisement short video to be evaluated 3 a i Substituting advertisement short video production quality evaluation formula psi i =γ 1 *ξ 1 a i +γ 2 *ξ 2 a i +γ 3 *ξ 3 a i Obtaining the comprehensive production quality coefficient psi of each advertisement short video to be evaluated i Wherein gamma is 1 、γ 2 、γ 3 Respectively expressed as preset advertisement short video production quality influencing factors, and gamma 1 +γ 2 +γ 3 =1。
2. The advertisement short video quality evaluation method based on big data analysis according to claim 1, wherein: the specific steps corresponding to the step S1 are as follows:
sequentially numbering the advertisement short videos to be evaluated according to the production time sequence, wherein the numbers of the advertisement short videos to be evaluated are 1,2, i, n;
acquiring the playing time length of each advertisement short video to be evaluated, and analyzing the time length of the head of each advertisement short video to be evaluated based on the preset time length of the head of each advertisement short video;
obtaining the video of the title of each short video of the advertisement to be evaluated according to the duration of the title of each short video of the advertisement to be evaluated, and putting each short video of the advertisement to be evaluatedThe video mark of the head of the evaluation advertisement short video is a i I=1, 2..n, i represents the i-th ad short video to be rated.
3. The advertisement short video quality evaluation method based on big data analysis according to claim 1, wherein: the specific detailed steps corresponding to the step S3 include:
dividing each advertisement short video to be evaluated into each video frame image in sequence according to the video playing sequence, obtaining related parameters of each video frame image in each advertisement short video to be evaluated, wherein the related parameters comprise resolution, frame rate, pixels and definition, and respectively marking the resolution, frame rate, pixels and definition of each video frame image in each advertisement short video to be evaluated as w 1 b ij 、w 2 b ij 、w 3 b ij 、w 4 b ij J=1, 2,..m, j is denoted as the j-th video frame image;
analyzing parameter influence weight index of each video frame image in each advertisement short video to be evaluated
Wherein lambda is 1 、λ 2 、λ 3 、λ 4 Respectively expressed as weight influence factors corresponding to preset image resolution, image frame rate, image pixels and image definition, and lambda 1 +λ 2 +λ 3 +λ 4 =1,w 1 b Label (C) 、w 2 b Label (C) 、w 3 b Label (C) 、w 4 b Label (C) Respectively representing the standard resolution, the standard frame rate, the standard pixel and the standard definition corresponding to the preset video frame image.
4. The advertisement short video quality evaluation method based on big data analysis according to claim 1, wherein: in the step S4, the clipping fluency weight index of each video frame image in each advertisement short video to be evaluated is compared and analyzed, and the specific analysis mode is as follows:
acquiring video time points corresponding to video frame images in the advertisement short videos to be evaluated, and marking the video time points corresponding to the video frame images in the advertisement short videos to be evaluated as t i b j ;
Substituting video time points corresponding to video frame images in the advertisement short videos to be evaluated into a formulaObtaining the editing fluency weight index ++ ++of each video frame image in each advertisement short video to be evaluated>η 1 、η 2 Respectively expressed as preset clip fluency influencing factors, t i b j+1 The video time point, t, corresponding to the (j+1) th video frame image in the ith advertisement short video to be evaluated is represented as i b j-1 The video time point corresponding to the j-1 th video frame image in the ith advertisement short video to be evaluated is shown as delta t Allow for Represented as a preset allowable point-in-time error value between video frame images.
5. An advertisement short video quality evaluation system based on big data analysis for performing the advertisement short video quality evaluation method based on big data analysis according to any one of claims 1 to 4, comprising:
the advertisement short video film head video acquisition module: the method comprises the steps of obtaining a video of a film head in each advertisement short video to be evaluated according to the playing time of each advertisement short video to be evaluated;
the film head video speech information comparison and analysis module: the method comprises the steps of extracting the video line information of the head of each advertisement short video to be evaluated, comparing the video line information with the preset planning subject information of each advertisement short video to be evaluated, and analyzing the coincidence subject coefficient of the video line information of the head of each advertisement short video to be evaluated;
advertisement short video plan database: the method comprises the steps of storing preset planning subject information and preset product display images of advertisement short videos to be evaluated;
the video frame image related parameter processing module: the method comprises the steps of dividing each advertisement short video to be evaluated into each video frame image, obtaining relevant parameters of each video frame image in each advertisement short video to be evaluated, and processing to obtain parameter influence weight indexes of each video frame image in each advertisement short video to be evaluated;
and the video frame image clipping fluency analysis module is used for: the method comprises the steps of obtaining video time points corresponding to video frame images in each advertisement short video to be evaluated, and comparing and analyzing clipping fluency weight indexes of the video frame images in each advertisement short video to be evaluated;
video content playing influence coefficient analysis module: the method comprises the steps of analyzing video content playing influence coefficients of advertisement short videos to be evaluated according to parameter influence weight indexes and editing fluency weight indexes of video frame images in the advertisement short videos to be evaluated;
the video frame image contrast processing module: the method comprises the steps of extracting preset product display images corresponding to advertisement short videos to be evaluated, comparing and screening the matching quantity of video frame images in the advertisement short videos to be evaluated, and analyzing the product display image matching coefficient of the advertisement short videos to be evaluated;
the advertisement short video production quality evaluation module: the method is used for evaluating the comprehensive production quality coefficient of each advertisement short video to be evaluated, comparing the comprehensive production quality coefficient with a preset advertisement short video production quality coefficient threshold value, and carrying out corresponding processing according to a comparison result.
6. A storage medium, characterized by: the storage medium is burnt with a computer program, and the computer program realizes the advertisement short video quality evaluation method based on big data analysis according to any one of the claims 1-4 when running in the memory of the server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210287821.2A CN114639051B (en) | 2022-03-22 | 2022-03-22 | Advertisement short video quality evaluation method, system and storage medium based on big data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210287821.2A CN114639051B (en) | 2022-03-22 | 2022-03-22 | Advertisement short video quality evaluation method, system and storage medium based on big data analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114639051A CN114639051A (en) | 2022-06-17 |
CN114639051B true CN114639051B (en) | 2023-07-21 |
Family
ID=81950631
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210287821.2A Active CN114639051B (en) | 2022-03-22 | 2022-03-22 | Advertisement short video quality evaluation method, system and storage medium based on big data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114639051B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115065865A (en) * | 2022-06-23 | 2022-09-16 | 北京奇艺世纪科技有限公司 | Video synthesis method and device, electronic equipment and storage medium |
CN116320218B (en) * | 2023-05-24 | 2023-08-29 | 深圳金智凌轩视讯技术有限公司 | Multipath video synthesis analysis processing management system based on embedded computer platform |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113327135A (en) * | 2021-06-18 | 2021-08-31 | 武汉埸葵电子商务有限公司 | Video advertisement playing analysis management method and system and advertisement analysis management cloud platform |
CN113506124A (en) * | 2021-06-21 | 2021-10-15 | 安徽西柚酷媒信息科技有限公司 | Method for evaluating media advertisement putting effect in intelligent business district |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112767313A (en) * | 2020-12-31 | 2021-05-07 | 广州方硅信息技术有限公司 | Video quality evaluation method and device and electronic equipment |
CN113191811B (en) * | 2021-05-10 | 2022-07-01 | 北京顶当互动科技有限公司 | Intelligent advertisement pushing method and device and computer readable storage medium |
CN113204709A (en) * | 2021-05-29 | 2021-08-03 | 武汉申子仟电子商务有限公司 | Short video search matching recommendation method and system based on multidimensional data depth comparison analysis and computer storage medium |
CN113327140B (en) * | 2021-08-02 | 2021-10-29 | 深圳小蝉文化传媒股份有限公司 | Video advertisement putting effect intelligent analysis management system based on big data analysis |
-
2022
- 2022-03-22 CN CN202210287821.2A patent/CN114639051B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113327135A (en) * | 2021-06-18 | 2021-08-31 | 武汉埸葵电子商务有限公司 | Video advertisement playing analysis management method and system and advertisement analysis management cloud platform |
CN113506124A (en) * | 2021-06-21 | 2021-10-15 | 安徽西柚酷媒信息科技有限公司 | Method for evaluating media advertisement putting effect in intelligent business district |
Also Published As
Publication number | Publication date |
---|---|
CN114639051A (en) | 2022-06-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114639051B (en) | Advertisement short video quality evaluation method, system and storage medium based on big data analysis | |
CN111683209B (en) | Mixed-cut video generation method and device, electronic equipment and computer-readable storage medium | |
US8180667B1 (en) | Rewarding creative use of product placements in user-contributed videos | |
US9044183B1 (en) | Intra-video ratings | |
Deldjoo et al. | Audio-visual encoding of multimedia content for enhancing movie recommendations | |
CN110390033B (en) | Training method and device for image classification model, electronic equipment and storage medium | |
DE102017005963A1 (en) | Providing relevant video scenes in response to a video search query | |
US8189963B2 (en) | Matching advertisements to visual media objects | |
US20050160113A1 (en) | Time-based media navigation system | |
US20120030711A1 (en) | Method or system to predict media content preferences | |
CN112910961B (en) | Method and system for automatically evaluating video quality of network course | |
CN111984824A (en) | Multi-mode-based video recommendation method | |
US20140172857A1 (en) | Formation of topic profiles for prediction of topic interest groups | |
Katyal et al. | Trademark Search, Artificial Intelligence, and the Role of the Private Sector | |
US20190007735A1 (en) | Content utilization paramerization | |
CN111107444A (en) | User comment generation method, electronic device and storage medium | |
Napontun et al. | Identifying Factors Influencing Consumers Not to Skip TrueView Advertising on YouTube | |
CN110958472A (en) | Video click rate rating prediction method and device, electronic equipment and storage medium | |
CN112995690A (en) | Live content item identification method and device, electronic equipment and readable storage medium | |
CN115964560B (en) | Information recommendation method and equipment based on multi-mode pre-training model | |
US20200218740A1 (en) | Data prioritization through relationship analysis mapping | |
CN111143688B (en) | Evaluation method and system based on mobile news client | |
CN112884866A (en) | Coloring method, device, equipment and storage medium for black and white video | |
Joly et al. | INRIA-IMEDIA TRECVID 2008: Video Copy Detection. | |
CN111813996A (en) | Video searching method based on sampling parallelism of single frame and continuous multi-frame |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20230630 Address after: Room 101 and 102, Floor 1, Building 12, No. 1777, Hualong Road, Huaxin Town, Qingpu District, Shanghai, 200000 Applicant after: Shanghai Funeng Information Technology Co.,Ltd. Address before: 430074 No. 9, liufangyuan South Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province Applicant before: Wuhan Yuanchun Media Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |