CN107368965A - A kind of script data processing method, device and apply its computer equipment - Google Patents

A kind of script data processing method, device and apply its computer equipment Download PDF

Info

Publication number
CN107368965A
CN107368965A CN201710586732.7A CN201710586732A CN107368965A CN 107368965 A CN107368965 A CN 107368965A CN 201710586732 A CN201710586732 A CN 201710586732A CN 107368965 A CN107368965 A CN 107368965A
Authority
CN
China
Prior art keywords
drama
personage
play
script data
story
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.)
Pending
Application number
CN201710586732.7A
Other languages
Chinese (zh)
Inventor
苏宁军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Fire Technology Co Ltd
Original Assignee
Hangzhou Fire Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Fire Technology Co Ltd filed Critical Hangzhou Fire Technology Co Ltd
Priority to CN201710586732.7A priority Critical patent/CN107368965A/en
Publication of CN107368965A publication Critical patent/CN107368965A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/205Parsing

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a kind of script data processing method, device and its computer equipment is applied, wherein, this method includes:Reception includes drama content and the script data with drama relevant information;Structure elucidation is carried out to drama content according to the database pre-seted;Quality analysis is carried out to script data according to database and to the result that drama content structure parses;And the result of script data quality analysis with being contrasted to the result of predetermined drama quality analysis, and will be assessed script data according to comparing result.By the invention it is possible to the quality of video display drama is carried out it is objective efficiently judge, and then suggestions on Optimization can be provided.

Description

A kind of script data processing method, device and apply its computer equipment
Technical field
The present invention relates to big data process field, and in particular to a kind of script data processing method, device and application its Computer equipment.
Background technology
Success of the video display drama to film and television project plays vital effect, so-called drama be one it is acute this, good play Originally be successful half, and the drama of difference, no matter behind director, how outstanding performer is with making the video display for being also difficult to turn into Works.Therefore, at the initial stage planned in a film and television project, the analysis and evaluation to drama is very important, in drama stage handle It is good to close, to the investment risk of film and television project just can be earlier obtain management and control, the cost paid is evaded to project risk also can be minimum. However, traditional drama is assessed mainly by artificial experience, the requirement to evaluator is higher, and the workload of assessment is also bigger, effect Rate is also than relatively low, and due to the subjectivity of evaluator, it is difficult to obtains objective consistent assessment result.
The content of the invention
In view of this, the invention provides a kind of script data processing method, device and apply its computer equipment, with Solves the above-mentioned at least one problem referred to.
According to an aspect of the present invention, there is provided a kind of script data processing method, this method include:Receive drama number According to, wherein, script data includes drama content and the information related to drama;According to the database pre-seted to drama content Carry out structure elucidation;Quality analysis is carried out to script data according to database and to the result that drama content structure parses;With And by the result of script data quality analysis with being contrasted to the result of predetermined drama quality analysis, and according to comparing result Script data is assessed.
According to another aspect of the present invention, there is provided a kind of script data processing unit, the device include:Script data connects Module is received, for receiving script data, wherein, script data includes drama content and the information related to drama;Structure solution Module is analysed, for carrying out structure elucidation to drama content according to the database pre-seted;Quality analysis module, for according to data Storehouse and to drama content structure parsing result to script data carry out quality analysis;And evaluation module, for will be to play The result of notebook data quality analysis to the result of predetermined drama quality analysis with contrasting, and according to comparing result to drama number According to being assessed.
According to the further aspect of the present invention, there is provided a kind of computer equipment, including memory, processor and be stored in Above-mentioned method is realized on reservoir and the computer program that can run on a processor, during the computing device computer program.
According to another aspect of the invention, there is provided a kind of computer-readable recording medium, the computer-readable storage medium Matter is stored with the computer program for performing upper method.
By technical scheme provided by the invention, the quality of video display drama can be carried out it is objective efficiently judge, and then Suggestions on Optimization can be provided.
Brief description of the drawings
By the description to the embodiment of the present invention referring to the drawings, above-mentioned and other purpose of the invention, feature and Advantage will be apparent from, in the accompanying drawings:
Fig. 1 is the structured flowchart of script data processing unit according to embodiments of the present invention;
Fig. 2 is the structured flowchart of script data processing system according to embodiments of the present invention;
Fig. 3 is the structured flowchart of structure elucidation module according to embodiments of the present invention;
Fig. 4 is the structured flowchart of quality analysis module according to embodiments of the present invention;
Fig. 5 is another structured flowchart of quality analysis module according to embodiments of the present invention;
Fig. 6 is the flow chart of script data processing method according to embodiments of the present invention.
Embodiment
Below based on embodiment, present invention is described, but the present invention is not restricted to these embodiments.
In embodiments of the present invention, there is provided a kind of script data processing unit.Fig. 1 is the structural representation of the device, As shown in figure 1, the device includes:Script data receiving module 101, structure elucidation module 102, quality analysis module 103 and Evaluation module 104.
In the apparatus, script data receiving module 101, which receives, includes drama content and the information related to drama Script data, structure elucidation module 102 carry out structure elucidation, quality analysis module according to the database pre-seted to drama content 103 carry out quality analysis according to database and to the result that drama content structure parses to script data, and evaluation module 104 will To the result of script data quality analysis with being contrasted to the result of predetermined drama quality analysis, and according to comparing result to play Notebook data is assessed.
The device can be parsed to video display drama, analyzed and assessed, compared to existing based on the database pre-seted There is technology, the quality progress that the device can be to video display drama is objective efficiently to be judged, and then can provide suggestions on Optimization.
The above-mentioned database pre-seted, required information data is analyzed to drama parsing, drama support is provided.The database It can include:Movie and television play information bank, movie and television play rating box office information bank, video display audience information storehouse, IP information banks, video display implantation Advertising message storehouse, drama knowledge base etc..Wherein, drama knowledge base includes again:Video display type information storehouse, key word information storehouse, field Institute information base, stage property information bank, action emotion information storehouse, character relation information bank etc..
Fig. 2 is system architecture diagram according to embodiments of the present invention.
As shown in Fig. 2 script data receiving module 101 receives the drama information related to drama, such as playwright, screenwriter, acute name, class Type, person names etc..
Structure elucidation module 102, using Text Mining Technologies such as text retrieval, text classifications, in movie data storehouse 105 Under the support of drama knowledge base, realize to drama diversity, branch scape, divide the message structure of the dimensions such as personage to dissolve analysis, be drama Analysis and evaluation carry out analysis material structuring prepare.
Quality analysis module 103, the drama analysis and assessment scheme based on the embodiment of the present invention, pass through the data analysis of correlation Algorithm, realize playwright, screenwriter's capability analysis, the analysis of drama subject matter, story of a play or opera analysis and personage's analytic function.
Evaluation module 104, based on the analysis result of quality analysis module 103, every key element that drama is assessed is carried out certainly Dynamic marking, realize that subitem is assessed, and comprehensive assessment is carried out on the basis of subitem is assessed, while propose recommendation on improvement.In addition, also may be used To realize suggestion of being selected the role to play, product placement suggestion, drama assessment report is ultimately produced.
Structure elucidation module 102 and quality analysis module 103 is described in detail respectively below in conjunction with Fig. 3, Fig. 4.
As shown in figure 3, the structure elucidation module 102 includes:Content structure analyzing sub-module 1021, personage's analyzing sub-module 1022nd, scene analyzing sub-module 1023 and stage property analyzing sub-module 1024.
Content structure analyzing sub-module 1021, for the information related to content structure in drama knowledge base to collection Number, the scene often concentrated and plot development clue etc. are parsed.
Specifically, how many collection of the parsing of content structure analyzing sub-module 1021 drama, often collects how many individual scenes, each scene How many descriptive text;The how many story lines in longitudinal direction point, laterally divide how many individual developing stage.Pass through text matches statistic algorithm base Marked in diversity number and diversity scene, realize diversity, divide scene statistics, it is crucial based on the description of story summary and story key plot Word and search realizes clue analytic statistics.
Personage's analyzing sub-module 1022, for the information related to personage in database to character relation, personage Feature, personage's interaction and personage's dialogue etc. are parsed.
Specifically, personage's analyzing sub-module 1022 is retouched based on character relation, person character trait in drama knowledge base dictionary The keyword of correlation is stated, retrieval drama parses character relation and character features.Using data visualization demonstration tool, based on people Thing relation decomposing goes out character relation collection of illustrative plates, and character features keyword cloud atlas is parsed based on character features.Personage's analyzing sub-module 1022 personage by occurring in Same Scene simultaneously, parsing personage interactive before relation and the frequency, can be connected with lines The each two personage of interactive relationship is connected to, the thickness of lines represents the frequency of interaction, can so draw out the mutual cardon of personage Spectrum.Personage's analyzing sub-module 1022 is also based on person names and punctuation mark, parses dialogue, the language length of each personage Degree, word feature and language feature etc., Algorithm of documents categorization can also be used to carry out contingency table to language of characters characteristic key words Know.
Scene analyzing sub-module 1023, for the information related to scene in database to the field in drama content Scape is parsed.
Scene analyzing sub-module 1023 can realize the mark to following scene description type by Text Mining Technology:
Scene type includes:Conflict play, action play, emotion play, love scene, laugh at choose theatrical programme, mystery play etc.;
Scene plot point includes:Home court play, interlude play, the small upset of the story of a play or opera and the big upset of the story of a play or opera;
Scene time includes:Day and night;
Scene occasion includes:Indoor and outdoor and all kinds of places;
Leading role's situation includes:Favourable circumstance and adverse circumstance.
Based on the analysis result of scene analyzing sub-module 1023, the appearance accounting statistics to all kinds of scenes can be achieved.
In practical operation, the Algorithm of documents categorization of text mining can be used to realize scene classification.In drama knowledge base Middle structure and the dictionary of scene associated description keyword, mainly comprising occur in each scene action, the related key such as mood Word.Based on the dictionary, vector space model (VSM) algorithm, or the Algorithm of documents categorization such as Bayes's textual classification model can be used Realize and the intelligent classification of scene is identified.
Stage property analyzing sub-module 1024, for the information related to stage property in database to the road in drama content Tool is parsed.
Specifically, stage property analyzing sub-module 1024 is based on keyword related to stage property in drama knowledge base dictionary, inspection The type of animal occurred in all kinds of articles (including vehicle) type, and play occurred in rope drama.
As described above, keyword dictionary of the structure elucidation module 102 based on drama knowledge base, utilizes text retrieval, text The text mining algorithmic techniques such as classification realize the parsing to drama, and are realized based on the structured content after parsing to drama key element Statistics, to facilitate follow-up drama to analyze.
Fig. 4 is the structured flowchart of above-mentioned quality analysis module 103.As shown in figure 4, the quality analysis module 103 includes:Compile Acute capability analysis submodule 1031, drama subject matter analysis submodule 1032, story of a play or opera analysis submodule 1033 and personage analyze son Module 1034.
Write a play capability analysis submodule 1031, for the works quantity in database with playwright, screenwriter, make quality and The related information of works type is analyzed playwright, screenwriter's ability.
Playwright, screenwriter's capability analysis submodule 1031 realizes that the analysis of qualifications and record of service, ability to drama playwright, screenwriter judges.Because there is experience The relative works for being easier to have created of playwright, screenwriter, therefore it can be drama assessment that history of writing a play, which completes the quantity of works and quality, One of reference factor.
In specific implementation process, playwright, screenwriter's ability can be analyzed by equation below:
BScore=min { 0.5 × N, 1.5 }+(6/ar × 0.5+rtr × 0.5)+min { ct × 0.5,1 }
Wherein, N represents the works quantity that playwright, screenwriter has created and broadcasted, and can be obtained by often increasing by one by 0.5 point, but highest 1.5 is divided; Ar represents average viewership or the box office of playwright, screenwriter's works, and normalization is divided into 6 levels, and highest is the 1st grade;Rtr represents to compile Audience ratings or box office variation tendency of the play product in predetermined period (for example, in two years recently), when trend is rises, rtr =1, when trend is declines, rtr=-1;Ct represents the quantity acute with drama same type that playwright, screenwriter has created and broadcasted, min { } Expression takes minimum Value Operations.
Drama subject matter analyze submodule 1032, in database with drama subject matter type, drama theme and The related information of target audience is analyzed drama subject matter.
Specifically, drama subject matter analysis submodule 1032 is mainly from the side such as the subject matter type of drama, name, theme, audient The market acceptance of surface analysis drama, because being adapted to the drama of the market demand to be only possible to the rating having had and box office.
By percent saturation of market, market acceptance two indices, to judge the acceptance of subject matter type and theme market.City Field saturation degree represents same type, with the acute market volume variation tendency of theme, such as higher in decline explanation percent saturation of market;Market Acceptance, it can judge by the nearest same type in market, with the acute rating of theme or box office situation, such as rating or box office situation Preferably, illustrate that market acceptance is higher.Same type play can be retrieved by the classification of type of play in movie and television play information bank.Same theme Play can be identified by the text mining of subject key words, and text similarity algorithm.More commonly used text similarity is calculated Method is that cosine similarity (cosine) compares, and is calculated by the way that the subject key words of two dramas are formed vector.
Subject matter is such as adapted according to existing IP (such as well-known novel) is acute, then obtains extra bonus point;The target audience of subject matter Clearly, extra bonus point can also be obtained with target audience crowd's interest registration height.
In concrete operations, drama subject matter is analyzed by equation below:
TScore=(6/ar1 × 0.5+tr1 × 0.5+tr2 × 0.5)+
(6/ar2×0.5+tr3×0.5+tr4×0.5)+ip+nAu×cAu
Wherein, ar1 represents to represent with average viewership or box office of the drama subject matter same type play in predetermined period, ar2 With drama subject matter with average viewership of the theme play in predetermined period or box office, tr1 represents same type play in predetermined period Number change trend, tr2 represents rating or box office variation tendency of the same type play in predetermined period, and tr3 represents same theme The acute number change trend in predetermined period, tr4 represent the rating or box office variation tendency with theme play in predetermined period, Ip represents the Intrusion Index of the former novel (IP) of reorganization, and nAu represents the scale of target audience, and cAu represents the weight with target audience It is right.Here can be recently in two years in predetermined period.
The story of a play or opera analyzes submodule 1033, for the parsing knot according to content structure analyzing sub-module and scene analyzing sub-module Fruit is to analysis is carried out as follows:Story of a play or opera contradiction, story of a play or opera emotional experience, the attraction of story of a play or opera mystery, story of a play or opera humour, the story of a play or opera are tortuous Property, story of a play or opera reasonability and the rationally distributed property of plot.Wherein:
Story of a play or opera contradiction is analyzed according to story of a play or opera contradiction conspicuousness p1 and story of a play or opera contradiction balance expansion d1, Wherein, story of a play or opera contradiction conspicuousness p1 reflects the scene number accounting of contradiction play, and story of a play or opera contradiction balance expansion d1 is anti- Balance of the contradiction play in each collection distribution is reflected;
Story of a play or opera emotional experience is analyzed according to the rich p2 of story of a play or opera emotional experience and story of a play or opera affective development balance d2, Wherein, the rich p2 of story of a play or opera emotional experience reflects the scene number accounting of emotion love scene, and story of a play or opera affective development balance d2 is anti- Balance of the emotion love scene in each collection distribution is reflected;
Rich p3 and story of a play or opera affective development balance d3 is set to attract to analyze to story of a play or opera mystery according to story of a play or opera mystery, Wherein, story of a play or opera mystery sets rich p3 to reflect the scene number accounting that mystery is played, and story of a play or opera mystery balance expansion d3 is reflected Balance of the mystery play in each collection distribution;
Story of a play or opera tortuosity is analyzed according to the small rollover number m1 of the story of a play or opera and the story of a play or opera big rollover number m2;Specifically, root Story of a play or opera tortuosity is analyzed according to m1, m2 and m1/m2;
Story of a play or opera reasonability is analyzed according to home court play quantity z1 and interlude play quantity z2;Specifically, according to z1, z2 with And z2/z1 analyzes story of a play or opera reasonability;
Sent out according to collection number js, average scene number cj, average each scene number of words zs, story line quantity xs, the story of often collecting Exhibition stage quantity jd property rationally distributed to plot is analyzed.
In specific implementation process, logistic regression (Logistic Regression, LR) model algorithm can be used, with Historical play scenario information, rating or box office data etc. are used as training sample, draw assessment models, and progress is analyzed to the story of a play or opera of drama Assess.For example, the story of a play or opera can be analyzed by equation below:
SScore=θ1×p1+θ2×d1+θ3×p2+θ4×d2+θ5×p3+θ6×d3+θ7×p4+θ8×m1+θ9×m2+ θ10×m1/m2+θ11×z1+θ12×z2+θ13×z2/z1+θ14×js+θ15×cj+θ16×zs+θ17×xs+θ18× jd,
Wherein, θnRepresent weight coefficient, can be obtained by Algorithm for Training, concrete numerical value can according to practical operation and It is fixed,
P1=scene types are identified as scene number/total scene number of " conflict play, action play ",
There is collection number/always collect number in the scene that d1=scene types are identified as " conflict play, action play ",
P2=scene types are identified as scene number/total scene number of " emotion play, love scene ",
There is collection number/always collect number in the scene that d2=scene types are identified as " emotion play, love scene ",
P3=scene types are identified as scene number/total scene number of " mystery play ",
There is collection number/always collect number in the scene that d3=scene types are identified as " mystery play ",
P4=scene types are identified as scene number/total scene number of " laugh at and choose theatrical programme ".
Personage analyze submodule 1034, for according to the analysis result of personage's analyzing sub-module to analysis is carried out as follows:People Thing feature significance, personage's conflict and opposition conspicuousness, personage's emotional interaction are rich, personage's destiny integrality, personage's destiny are bent Folding endurance, character relation drama, personage's dialogue humour, personage's dialogue is classical, personage's dialogue is Politeness and personage be laid out close Rationality, wherein:
According to high priest's average characteristics word number c1, minor character's average characteristics word number c2 and character features word mean difference Heteromerism cd is analyzed character features conspicuousness sC1;
There is scene number simultaneously according to opposition personage to analyze personage's conflict and opposition conspicuousness sC2 with total scene number;
Occur scene number simultaneously according to emotion play opponent personage to carry out with total scene number sC3 rich to personage's emotional interaction Analysis;
Personage's destiny integrality sC4 is analyzed with always collecting several according to each personage appearance collection number;
Personage's destiny tortuosity sC5 is analyzed with favourable circumstance scene number according to adverse circumstance scene number;
Character relation drama sC6 is analyzed with total scene number according to personage's key reversal scene number;
According to making laughs, a dialogue number is analyzed personage's dialogue humour sC7 with total dialogue number;
Analyzed according to classical dialogue quotation number and total dialogue number sC8 classical to personage's dialogue;
Analyzed according to average dialogue length sC9 Politeness to personage's dialogue;
It is averaged according to high priest's number g1, minor character's number g2, the average starts t1 of high priest, number personage Starts t2, the average interactive number h2 property rationally distributed to personage of high priest average interactive number h1 and minor character are entered Row analysis.
Personage analyzes submodule 1034 and realizes that the fullness to characterization, the interactive excellent property with dialogue of personage etc. are carried out Assess.Parsing based on structure elucidation module 102 to character relation, character features, personage's interaction and personage's dialogue etc. is come real It is existing.
In practical operation, Logic Regression Models algorithm can be used, with historical play scenario information, rating or box office data Deng training sample is used as, assessment models are drawn.Personage's analysis to drama is assessed.For example, equation below pair can be passed through Personage is analyzed:
CScore=a1×sC1+a2×sC2+a3×sC3+a4×sC4+a5×sC5+a6×sC6+a7×sC7+
a8×sC8+a9×sC9+a10×g1+a11×g2+a12×t1+a13×t2+a14×h1+a15×h2
Wherein, αnRepresent weight coefficient, can be obtained by Algorithm for Training, concrete numerical value can according to practical operation and It is fixed,
SC1=1 × C1+0.5 × c2+0.5 × cd,
There is scene number/total scene number simultaneously in sC2=opposition personages,
There is scene number/total scene number simultaneously in sC3=emotions play opponent personage,
SC4=avg (each personage's appearance collection number/always collect number),
SC5=adverse circumstances scene number/favourable circumstance scene number,
SC6=personage's key reversal scene number/total scene number,
SC7=makes laughs a dialogue number/total dialogue number,
SC8=classics dialogue quotations number/total dialogue number,
The average dialogue length of sC9=.
In one embodiment, as shown in figure 5, quality analysis module 103 also includes business analysis submodule 1035, it is used for According to the structure elucidation result of drama content to commercially analyzing, and according to analysis result determine drama product placement chance with And the shooting difficulty of product placement.
Scene element parsing and stage property parsing of the business analysis submodule 1035 based on structure elucidation module 102 are realized to play This product placement chance, and the assessment of shooting degree-of-difficulty factor.
Product placement chance can be determined by equation below:
Sb=min { 0.5 × b, 2 }
Wherein, b represents the quantity of the merchandise classification keyword of the implantable advertisement retrieved in drama content.
Specifically, keyword can be described according to place, stage property, scene element etc. to be retrieved, often retrieving one can The merchandise classification keyword of product placement, then increase by 0.5 point, top score is 2 points.
Shooting degree-of-difficulty factor depend on to be related in scene description place, stage property, animal, action stunt, weather season Deng the difficulty of realization.For example, place is related to external or the Forbidden City etc. with being difficult to the shooting that obtains easily, stage property is related to the costs such as aircraft Higher article, animal such as lion etc., action stunt such as driving etc., weather pattern is more, seasonal time span is big etc., it can all increase bat Take the photograph difficulty.
The shooting degree-of-difficulty factor sn of product placement is determined by equation below:
Sn=max { -0.5 × n, -3 }
Wherein, n represents the quantity of the shooting difficulty factor keyword retrieved in drama content.Specifically, Ke Yigen According to place, stage property, animal, action stunt, weather the factor such as season retrieved, often retrieve a difficulty factor keyword Subtract 0.5 point, it is minimum to be scored at -3 points.
As described above, by above-mentioned quality analysis process, the subitem assessment to drama can be obtained.
Comprehensive analysis is every to assess score, using aggregative weighted algorithm, can obtain the comprehensive grading of drama:
AScore=β1×bScore+β2×tScore+β3×sScore+β4×cScore+β5×sb+β6×sn
Wherein, β n represent weight coefficient, can optimize to obtain by Algorithm for Training and artificial experience, concrete numerical value can root Depending on practical operation.
Evaluation module 104 every analytical conclusions can carry out data visualization displaying by more than, automatically generate picture and text analysis Report.
By the way that comprehensive grading, subitem scoring are contrasted with outstanding acute and similar outstanding acute each item rating respectively, obtain Go out the item that the drama score is relatively low, needs are perfect, and then propose the recommendation on improvement of drama.
For the drama after improvement, retouched by character features keyword, and character age, sex, occupation, identity etc. State, the similar role most matched can be found, and push away accordingly by text similar analysis mining algorithm in history movie and television play storehouse Recommend out the performer of suitable role.
Based on similar inventive concept, the embodiment of the present invention additionally provides a kind of script data processing method, can apply In above-mentioned script data processing unit.
Fig. 6 is the flow chart of script data processing method, as shown in fig. 6, this method includes:
Step 601, script data is received, the script data includes drama content and the information related to drama;
Step 602, structure elucidation is carried out to drama content according to the database pre-seted;
Step 603, quality analysis is carried out to script data according to database and to the result that drama content structure parses; And
Step 604, by the result of script data quality analysis with being contrasted to the result of predetermined drama quality analysis, And script data is assessed according to comparing result.
By the way that video display drama is parsed, analyzed and assessed, quality progress that can be to video display drama is objective efficiently Judge, and then provide suggestions on Optimization.
In step 602, structure elucidation being carried out to drama content can include to content structure, personage, scene and road Tool is parsed.
Wherein, carrying out parsing to content structure includes:The information related to content structure in database is to following At least one parsed:Collection number, the scene often concentrated and plot development clue;Carrying out parsing to personage includes:Root At least one of is parsed according to the information related to personage in database:Character relation, character features, personage are interactive And personage's dialogue.
In step 603, to script data carry out quality analysis can include to playwright, screenwriter ability, drama subject matter, the story of a play or opera with And personage is analyzed.Wherein:
(1) playwright, screenwriter's capability analysis
In database to the works quantity of playwright, screenwriter, make quality and the related information of works type to playwright, screenwriter's ability Analyzed.
In practical operation, playwright, screenwriter's ability can be analyzed by equation below:
BScore=min { 0.5 × N, 1.5 }+(6/ar × 0.5+rtr × 0.5)+min { ct × 0.5,1 }
Wherein, N represents the works quantity that playwright, screenwriter has created and broadcasted, and ar represents the average viewership of playwright, screenwriter's works, rtr tables Show rating variation tendency of playwright, screenwriter's works in predetermined period, when trend is rises, rtr=1, when trend is declines, rtr =-1, ct represents the quantity acute with drama same type that playwright, screenwriter has created and broadcasted, and min { } represents to take minimum Value Operations.
(2) drama subject matter is analyzed
The information related to drama subject matter type, drama theme and target audience in database is to drama subject matter Analyzed.
In practical operation, drama subject matter can be analyzed by equation below:
TScore=(6/ar1 × 0.5+tr1 × 0.5+tr2 × 0.5)+
(6/ar2×0.5+tr3×0.5+tr4×0.5)+ip+nAu×cAu
Wherein, ar1 is represented and average viewership of the drama subject matter same type play in predetermined period, ar2 expressions and drama Average viewership of the subject matter with theme play in predetermined period, tr1 represent that number change of the same type play in predetermined period becomes Gesture, tr2 represent rating variation tendency of the same type play in predetermined period, and tr3 represents the number with theme play in predetermined period Variation tendency is measured, tr4 represents the rating variation tendency with theme play in predetermined period, and ip represents that the former IP of reorganization influence refers to Number, nAu represent the scale of target audience, and cAu represents the registration with target audience.Here predetermined period can be nearest two Year.
(3) story of a play or opera is analyzed
According to the analysis result to content structure and scene to analysis is carried out as follows:Story of a play or opera contradiction, story of a play or opera emotion body Test, the attraction of story of a play or opera mystery, story of a play or opera humour, story of a play or opera tortuosity, story of a play or opera reasonability, the rationally distributed property of plot.
Wherein, story of a play or opera contradiction is carried out according to story of a play or opera contradiction conspicuousness p1 and story of a play or opera contradiction balance expansion d1 Analysis, is analyzed story of a play or opera emotional experience, root according to the rich p2 of story of a play or opera emotional experience and story of a play or opera affective development balance d2 Rich p3 and story of a play or opera affective development balance d3 is set to attract to analyze to story of a play or opera mystery according to story of a play or opera mystery, it is small according to the story of a play or opera Rollover number m1 and the big rollover number m2 of the story of a play or opera are analyzed story of a play or opera tortuosity, according to home court play quantity z1 and interlude play quantity Z2 is analyzed story of a play or opera reasonability, according to collection number js, average often collection scene number cj, average each scene number of words zs, story line Rope quantity xs, story developing stage quantity jd property rationally distributed to plot are analyzed.
In practical operation, the story of a play or opera can be analyzed by equation below:
SScore=θ1×p1+θ2×d1+θ3×p2+θ4×d2+θ5×p3+θ6×d3+θ7×p4+θ8×m1+θ9×m2+ θ10×m1/m2+θ11×z1+θ12×z2+θ13×z2/z1+θ14×js+θ15×cj+θ16×zs+θ17×xs+θ18× jd,
Wherein, θnRepresent weight coefficient, can be obtained by Algorithm for Training, concrete numerical value can according to practical operation and It is fixed;
P1 represents the story of a play or opera as the scene number of contradiction and the ratio of total scene number, and it is contradiction that d1, which is represented containing the story of a play or opera, The ratio of the collection number of scene and total collection number, p2 represent the story of a play or opera as the scene number of emotion and the ratio of total scene number, and d2 represents to contain The story of a play or opera represents the story of a play or opera for the scene number of mystery and the ratio of total scene number, d3 tables for the collection number and total ratio for collecting number, p3 of emotion Show that the ratio for the collection number and total collection number of mystery, p4 represent the story of a play or opera for the scene number of humour and the ratio of total scene number containing the story of a play or opera Value.
(4) personage analyzes
According to the analysis result to personage to analysis is carried out as follows:Character features conspicuousness, personage's conflict and opposition conspicuousness, Personage's emotional interaction is rich, personage's destiny integrality, personage's destiny tortuosity, character relation are dramatic, personage's dialogue humour Property, personage's dialogue is classical, personage's dialogue is Politeness and the rationally distributed property of personage.
Wherein, according to high priest's average characteristics word number c1, minor character's average characteristics word number c2 and character features word Mean difference heteromerism cd is analyzed character features conspicuousness sC1;Scene number e2 and total scene are occurred according to opposition personage simultaneously Number f is analyzed personage's conflict and opposition conspicuousness sC2;Scene number e3 and total scene are occurred according to emotion play opponent personage simultaneously Number f sC3s rich to personage's emotional interaction is analyzed;It is complete to personage's destiny according to each personage appearance collection number e4 and total collection number k Whole property sC4 is analyzed;Personage's destiny tortuosity sC5 is analyzed according to adverse circumstance scene number e5 and favourable circumstance scene number p;According to Personage's key reversal scene number e6 and total scene number f is analyzed character relation drama sC6;According to a dialogue number e7 that makes laughs Personage's dialogue humour sC7 is analyzed with total dialogue number g;According to classical dialogue quotation number e8 and total dialogue number g to personage The classical sC8 of dialogue is analyzed;Analyzed according to average dialogue length sC9 Politeness to personage's dialogue;According to main people Thing number g1, minor character's number g2, the average starts t1 of high priest, the average starts t2 of number personage, main people The average interactive number h2 property rationally distributed to personage of thing average interactive number h1 and minor character is analyzed.
In practical operation, personage can be analyzed by equation below:
CScore=a1×sC1+a2×sC2+a3×sC3+a4×sC4+a5×sC5+a6×sC6+a7×sC7+
a8×sC8+a9×sC9+a10×g1+a11×g2+a12×t1+a13×t2+a14×h1+a15×h2
Wherein, αnRepresent weight coefficient, can be obtained by Algorithm for Training, concrete numerical value can according to practical operation and It is fixed;
SC1=1 × c1+0.5 × c2+0.5 × cd, sC2=e2/f, sC3=e3/f, sC4=avg (e4/f), sC5= E5/p, sC6=e6/f, sC7=e7/g, sC8=e8/g, sC9 represent average dialogue length, and avg () represents to take averaging operation.
In one embodiment, step 603 to script data carry out quality analysis can also include:According to drama content Structure elucidation result to commercially analyzing;The bat of drama product placement chance and product placement is determined according to analysis result Take the photograph difficulty.
In practical operation, product placement chance sb can be determined by equation below:
Sb=min { 0.5 × b, 2 }
Wherein, b represents the quantity of the merchandise classification keyword of the implantable advertisement retrieved in drama content.
The shooting degree-of-difficulty factor sn of product placement can be determined by equation below:
Sn=max { -0.5 × n, -3 }
Wherein, n represents the quantity of the shooting difficulty factor keyword retrieved in drama content, and max { } represents to take most Big Value Operations.
It is similar to script data processing unit to solve the principle of problem due to this method, therefore the implementation of this method can be joined See the implementation of script data processing unit, repeat part and repeat no more.
The embodiment of the present invention additionally provides a kind of computer equipment, including memory, processor and storage are on a memory And the computer program that can be run on a processor, above-mentioned method is realized during the computing device computer program.
The embodiment of the present invention additionally provides a kind of computer-readable recording medium, and the computer-readable recording medium storage has Perform the computer program of the above method.
Compared to traditional artificial drama evaluation scheme, scheme provided in an embodiment of the present invention is based on big data technology and people Work intelligent algorithm, it is possible to achieve automatic parsing to video display drama, automatically analyze and automatic scoring, can be to video display drama Quality progress is objective efficiently to be judged, so as to provide suggestions on Optimization.
Obviously, it will be understood by those skilled in the art that above-mentioned each module of the invention or each step can be with general Computer system realizes that they can be concentrated on a single computer, or be distributed in the net that multiple computing devices are formed On network, alternatively, they can be realized with the program code that computer installation can perform, and be deposited so as to be stored in Performed in storage device by computing device, they are either fabricated to each integrated circuit modules respectively or by them Multiple modules or step are fabricated to single integrated circuit module to realize.So, the present invention is not restricted to any specific hardware With the combination of software.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for those skilled in the art For, the present invention can have various changes and change.All any modifications made within spirit and principles of the present invention, it is equal Replace, improve etc., it should be included in the scope of the protection.

Claims (10)

1. a kind of script data processing method, it is characterised in that methods described includes:
Script data is received, wherein, the script data includes drama content and the information related to drama;
Structure elucidation is carried out to the drama content according to the database pre-seted;
Quality analysis is carried out to the script data according to the database and to the result that the drama content structure parses; And
By to the result of the script data quality analysis with being contrasted to the result of predetermined drama quality analysis, and according to right The script data is assessed than result.
2. script data processing method according to claim 1, it is characterised in that structure solution is carried out to the drama content Analysis includes parsing at least one of:Content structure, personage, scene, stage property;
Wherein, carrying out parsing to the content structure includes:The information pair related to content structure in the database At least one of is parsed:Collection number, the scene often concentrated and plot development clue;
Carrying out parsing to the personage includes:The information related to personage in the database is entered at least one of Row parsing:Character relation, character features, personage's interaction and personage's dialogue.
3. script data processing method according to claim 2, it is characterised in that quality point is carried out to the script data Analysis includes analyzing at least one of:Playwright, screenwriter's ability, drama subject matter, the story of a play or opera and personage, wherein,
In the database to the works quantity of the playwright, screenwriter, make quality and the related information of works type to described Playwright, screenwriter's ability is analyzed,
The information related to drama subject matter type, drama theme and target audience in the database is to the drama Subject matter is analyzed,
The story of a play or opera is analyzed according to the content structure and the analysis result of the scene, the story of a play or opera is divided Analysis includes analyzing at least one of:Story of a play or opera contradiction, story of a play or opera emotional experience, the attraction of story of a play or opera mystery, story of a play or opera humour Property, story of a play or opera tortuosity, story of a play or opera reasonability, the rationally distributed property of plot,
The personage is analyzed according to the analysis result to the personage, analysis is carried out to the personage to be included to below extremely It is one of few to be analyzed:Character features conspicuousness, personage's conflict and opposition conspicuousness, personage's emotional interaction are rich, personage's destiny Integrality, personage's destiny tortuosity, character relation drama, personage's dialogue humour, personage's dialogue are classical, personage's dialogue essence Refining property and the rationally distributed property of personage.
4. script data processing method according to claim 3, it is characterised in that quality point is carried out to the script data Analysis also includes:
According to the structure elucidation result of the drama content to commercially analyzing;
Drama product placement chance and the shooting difficulty of the product placement are determined according to analysis result.
5. a kind of script data processing unit, it is characterised in that described device includes:
Script data receiving module, for receiving script data, wherein, the script data includes drama content and and drama Related information;
Structure elucidation module, for carrying out structure elucidation to the drama content according to the database pre-seted;
Quality analysis module, for according to the database and to the drama content structure parse result to the drama Data carry out quality analysis;And
Evaluation module, for by the result of the script data quality analysis and the result progress to predetermined drama quality analysis Contrast, and the script data is assessed according to comparing result.
6. script data processing unit according to claim 5, it is characterised in that the structure elucidation module includes:
Content structure analyzing sub-module, for the information related to content structure in the database to it is following at least it One is parsed:Collection number, the scene often concentrated and plot development clue;
Personage's analyzing sub-module, at least one of is solved for the information related to personage in the database Analysis:Character relation, character features, personage's interaction and personage's dialogue;
Scene analyzing sub-module, for the information related to scene in the database to the field in the drama content Scape is parsed;
Stage property analyzing sub-module, for the information related to stage property in the database to the road in the drama content Tool is parsed.
7. script data processing unit according to claim 6, it is characterised in that the quality analysis module includes:
Write a play capability analysis submodule, for the works quantity in the database with the playwright, screenwriter, make quality and The related information of works type is analyzed playwright, screenwriter's ability;
Drama subject matter analyze submodule, in the database with drama subject matter type, drama theme and target The related information of audient is analyzed the drama subject matter;
The story of a play or opera analyzes submodule, for the parsing knot according to the content structure analyzing sub-module and the scene analyzing sub-module Fruit is analyzed at least one of:Story of a play or opera contradiction, story of a play or opera emotional experience, the attraction of story of a play or opera mystery, story of a play or opera humour, play The rationally distributed property of feelings tortuosity, story of a play or opera reasonability, plot,
Personage analyzes submodule, for being divided according to the analysis result of personage's analyzing sub-module at least one of Analysis:Character features conspicuousness, personage's conflict and opposition conspicuousness, personage's emotional interaction are rich, personage's destiny integrality, Ren Wuming Transport tortuosity, character relation drama, personage's dialogue humour, personage's dialogue is classical, personage's dialogue is Politeness and personage's cloth Office's reasonability.
8. script data processing unit according to claim 7, it is characterised in that the quality analysis module also includes: Business analysis submodule, for being tied according to the structure elucidation result of the drama content to commercially analyzing, and according to analysis Fruit determines drama product placement chance and the shooting difficulty of the product placement.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can runs on a processor Computer program, it is characterised in that realized described in the computing device during computer program any in Claims 1-4 Method described in.
10. a kind of computer-readable recording medium, it is characterised in that the computer-readable recording medium storage has perform claim It is required that the computer program of method any one of 1 to 4.
CN201710586732.7A 2017-07-18 2017-07-18 A kind of script data processing method, device and apply its computer equipment Pending CN107368965A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710586732.7A CN107368965A (en) 2017-07-18 2017-07-18 A kind of script data processing method, device and apply its computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710586732.7A CN107368965A (en) 2017-07-18 2017-07-18 A kind of script data processing method, device and apply its computer equipment

Publications (1)

Publication Number Publication Date
CN107368965A true CN107368965A (en) 2017-11-21

Family

ID=60308137

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710586732.7A Pending CN107368965A (en) 2017-07-18 2017-07-18 A kind of script data processing method, device and apply its computer equipment

Country Status (1)

Country Link
CN (1) CN107368965A (en)

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107977360A (en) * 2017-11-27 2018-05-01 西安影视数据评估中心有限公司 The identification in personage camp and division methods in a kind of video display drama
CN107977359A (en) * 2017-11-27 2018-05-01 西安影视数据评估中心有限公司 A kind of extracting method of video display drama scene information
CN108549630A (en) * 2018-03-29 2018-09-18 西安影视数据评估中心有限公司 A kind of recognition methods of video display drama story overturning point
CN109272286A (en) * 2018-08-30 2019-01-25 中国传媒大学 It is a kind of towards SaaS multi-tenant using drama as the cloud film and television project management method and system of core
CN110414835A (en) * 2019-07-26 2019-11-05 北京小土科技有限公司 A kind of TV play drama quantitative evaluation system and method
CN110443482A (en) * 2019-07-26 2019-11-12 北京小土科技有限公司 A kind of screen play completeness quantitative evaluation system
CN110458428A (en) * 2019-07-26 2019-11-15 北京小土科技有限公司 A kind of excellent metrization assessment system of screen play
JP2019219830A (en) * 2018-06-18 2019-12-26 株式会社コミチ Emotion evaluation method
CN110909528A (en) * 2019-11-29 2020-03-24 北京奇艺世纪科技有限公司 Script analysis method, script display method, device and electronic equipment
CN111160586A (en) * 2019-11-25 2020-05-15 北京小土科技有限公司 Intelligent scheduling system and method for film and television
CN111291535A (en) * 2020-03-02 2020-06-16 北京奇艺世纪科技有限公司 Script processing method and device, electronic equipment and computer readable storage medium
CN113010709A (en) * 2021-03-25 2021-06-22 曹雪雅 Film and television scenario platform chance-passing quantitative evaluation system
CN113748439A (en) * 2019-05-20 2021-12-03 索尼集团公司 Prediction of successful quotient for motion pictures
CN117521628A (en) * 2023-11-20 2024-02-06 中诚华隆计算机技术有限公司 Script creation method, device, equipment and chip based on artificial intelligence
CN111291535B (en) * 2020-03-02 2024-06-11 北京奇艺世纪科技有限公司 Scenario processing method and device, electronic equipment and computer readable storage medium

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107977359B (en) * 2017-11-27 2021-03-30 西安影视数据评估中心有限公司 Method for extracting scene information of movie and television scenario
CN107977359A (en) * 2017-11-27 2018-05-01 西安影视数据评估中心有限公司 A kind of extracting method of video display drama scene information
CN107977360A (en) * 2017-11-27 2018-05-01 西安影视数据评估中心有限公司 The identification in personage camp and division methods in a kind of video display drama
CN107977360B (en) * 2017-11-27 2021-04-13 西安影视数据评估中心有限公司 Method for identifying and dividing character formation in movie and television script
CN108549630A (en) * 2018-03-29 2018-09-18 西安影视数据评估中心有限公司 A kind of recognition methods of video display drama story overturning point
CN108549630B (en) * 2018-03-29 2021-07-30 西安影视数据评估中心有限公司 Method for identifying turning points of film and television script stories
JP2019219830A (en) * 2018-06-18 2019-12-26 株式会社コミチ Emotion evaluation method
CN109272286A (en) * 2018-08-30 2019-01-25 中国传媒大学 It is a kind of towards SaaS multi-tenant using drama as the cloud film and television project management method and system of core
CN113748439B (en) * 2019-05-20 2024-03-12 索尼集团公司 Prediction of successful quotient of movies
CN113748439A (en) * 2019-05-20 2021-12-03 索尼集团公司 Prediction of successful quotient for motion pictures
CN110443482A (en) * 2019-07-26 2019-11-12 北京小土科技有限公司 A kind of screen play completeness quantitative evaluation system
CN110458428A (en) * 2019-07-26 2019-11-15 北京小土科技有限公司 A kind of excellent metrization assessment system of screen play
CN110414835A (en) * 2019-07-26 2019-11-05 北京小土科技有限公司 A kind of TV play drama quantitative evaluation system and method
CN111160586A (en) * 2019-11-25 2020-05-15 北京小土科技有限公司 Intelligent scheduling system and method for film and television
CN111160586B (en) * 2019-11-25 2024-05-10 北京小土科技有限公司 Intelligent video scheduling system and method
CN110909528A (en) * 2019-11-29 2020-03-24 北京奇艺世纪科技有限公司 Script analysis method, script display method, device and electronic equipment
CN111291535A (en) * 2020-03-02 2020-06-16 北京奇艺世纪科技有限公司 Script processing method and device, electronic equipment and computer readable storage medium
CN111291535B (en) * 2020-03-02 2024-06-11 北京奇艺世纪科技有限公司 Scenario processing method and device, electronic equipment and computer readable storage medium
CN113010709A (en) * 2021-03-25 2021-06-22 曹雪雅 Film and television scenario platform chance-passing quantitative evaluation system
CN117521628A (en) * 2023-11-20 2024-02-06 中诚华隆计算机技术有限公司 Script creation method, device, equipment and chip based on artificial intelligence
CN117521628B (en) * 2023-11-20 2024-05-28 中诚华隆计算机技术有限公司 Script creation method, device, equipment and chip based on artificial intelligence

Similar Documents

Publication Publication Date Title
CN107368965A (en) A kind of script data processing method, device and apply its computer equipment
Kim et al. Box office forecasting using machine learning algorithms based on SNS data
US7827054B2 (en) Online entertainment network for user-contributed content
CN101981563B (en) The method and apparatus for the related content shown is selected in conjunction with media
US8126763B2 (en) Automatic generation of trailers containing product placements
CN110222233B (en) Video recommendation method and device, server and storage medium
Bakker Building knowledge about the consumer: The emergence of market research in the motion picture industry
CN110474944B (en) Network information processing method, device and storage medium
JP5910316B2 (en) Information processing apparatus, information processing method, and program
CN112153426A (en) Content account management method and device, computer equipment and storage medium
CN113742567B (en) Recommendation method and device for multimedia resources, electronic equipment and storage medium
Arantes et al. Understanding video-ad consumption on YouTube: a measurement study on user behavior, popularity, and content properties
Liu et al. Building effective short video recommendation
CN111582975A (en) Artificial intelligence recommendation method and system based on combination of users, products and advertisements
JP2020107051A (en) Extraction system and program
CN109391829A (en) Video gets position analysis system, analysis method and storage media ready
CN111581435B (en) Video cover image generation method and device, electronic equipment and storage medium
WO2016125166A1 (en) Systems and methods for analyzing video and making recommendations
Knapp et al. Does 3D make sense for Hollywood? The economic implications of adding a third dimension to hedonic media products
CN114501105B (en) Video content generation method, device, equipment and storage medium
CN1996280A (en) Method for co-building search engine
KR20200110836A (en) System for providing contents agent service for talent sale based on multi-channel network
KR20190094541A (en) Advertisement recommendation apparatus and method based on comments
English Prestige, pleasure, and the data of cultural preference:“Quality Signals” in the age of superabundance
CN113450134A (en) Advertisement putting method, device, equipment and storage medium

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20171121

RJ01 Rejection of invention patent application after publication