CN107665373A - A kind of box office receipts Forecasting Methodology of mixed model - Google Patents

A kind of box office receipts Forecasting Methodology of mixed model Download PDF

Info

Publication number
CN107665373A
CN107665373A CN201610613047.4A CN201610613047A CN107665373A CN 107665373 A CN107665373 A CN 107665373A CN 201610613047 A CN201610613047 A CN 201610613047A CN 107665373 A CN107665373 A CN 107665373A
Authority
CN
China
Prior art keywords
box office
film
prediction
model
receipts
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.)
Withdrawn
Application number
CN201610613047.4A
Other languages
Chinese (zh)
Inventor
曲德君
李进岭
曹大军
杨爽
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.)
Shanghai Xinfeifan E-Commerce Co Ltd
Original Assignee
Shanghai Xinfeifan E-Commerce 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 Shanghai Xinfeifan E-Commerce Co Ltd filed Critical Shanghai Xinfeifan E-Commerce Co Ltd
Priority to CN201610613047.4A priority Critical patent/CN107665373A/en
Publication of CN107665373A publication Critical patent/CN107665373A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"

Abstract

The present invention proposes a kind of box office receipts Forecasting Methodology of mixed model, and for being predicted to film V box office to obtain the final box office receipts prediction result F of the film V, methods described comprises the following steps：Step A：N box office receipts forecast model M is established according to the different characteristic of the film Vn；Step B：According to the n box office receipts forecast model MnCalculate respectively and obtain n box office receipts prediction result Rn；Step C：To the n box office receipts prediction result RnCarry out fusion calculation and obtain the final box office receipts prediction result F.The above-mentioned box office receipts Forecasting Methodology of the present invention, multiple box office receipts forecast models are subjected to fusion calculation, the rate of accuracy reached of prediction result can be caused to more than 60%, than the accuracy rate lifting more than 20% of the box office prediction result of Individual forecast model.And the present invention is not only able to provide the value of box office prediction, and the section of box office prediction can also be provided.

Description

A kind of box office receipts Forecasting Methodology of mixed model
Technical field
The present invention relates to a kind of box office receipts Forecasting Methodology, to predict that the box office of certain film is sold before motion picture projection Sell, so as to provide reference for the waiting of film and screening, the basis of decision-making is provided for the profit maximization of cinemas.
Background technology
Existing recurrence is usually using relatively broad Forecasting Methodology, for box office receipts prediction, is returned using linear The scheme that may be used is returned to be returned using volumes of searches, click volume, the sentiment analysis of user, vertical media information etc. as linear nothing but The characteristic dimension returned.For example, in a kind of box office receipts prediction of typical linear model, films types, film point can be chosen Level, story familiarity, product state, star's appeal, director's appeal, production cost, propaganda strength index etc. are used as parameter, often Individual parameter is multiplied by the box office receipts summed after corresponding weight coefficient needed for acquisition
It is above-mentioned that box office is returned using single linear model, spy of its accuracy returned by simulation in itself Point, linear model always easily cause the higher of low box office prediction, and high box office is predicted lower, and is susceptible to film spy The influence of example, accuracy be not high.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of box office receipts Forecasting Methodology of mixed model, to reduce or keep away The problem of exempting to be formerly mentioned.
In order to solve the above technical problems, the present invention proposes a kind of box office receipts Forecasting Methodology of mixed model, use It is predicted in the box office to a film V to obtain the final box office receipts prediction result F of the film V, methods described bag Include following steps：Step A：N box office receipts forecast model M is established according to the different characteristic of the film Vn；Step B：Foundation The n box office receipts forecast model MnCalculate respectively and obtain n box office receipts prediction result Rn；Step C：To the n film Box office prediction result RnCarry out fusion calculation and obtain the final box office receipts prediction result F.
Preferably, the fusion calculation in the step C obtains the final box office receipts prediction result F including as follows Step：By the n box office receipts prediction result RnIt is added again divided by n, so as to obtain the final box office receipts prediction result F。
Preferably, the fusion calculation in the step C comprises the following steps：The n box office receipts are predicted and tied Fruit RnA corresponding model coefficient F is multiplied by respectivelynThen it is added, so as to obtain the final box office receipts prediction result F.
Preferably, the model coefficient FnCalculate and obtain as follows：Using the true ticket of film at least known to n portions Room result substitutes into the step described in claim 3 and obtains the equation group being made up of n equation, calculates the equation group and obtains institute State model coefficient Fn。
Preferably, the n is equal to 3, the n box office receipts forecast model MnRespectively type prediction model M1, section is pre- Survey model M2And all forecast model M3。
Preferably, the type prediction model M1The type prediction model M of the film V is predicted as follows1 Corresponding prediction result：For with the film V types identical film, establish a linear equation, the linear equation The type prediction model M is multiplied by by the box office maximum of the true box office result of the same type of known film at least i portions1Institute Corresponding box office normalizing index is to obtain the type prediction model M of the film V1Corresponding prediction result；Wherein, institute State type prediction model M1The known numeric value S of i feature of the corresponding box office normalizing index equal to the film ViIt is multiplied by respectively One corresponding characteristic constant KiThen it is added and obtains；Wherein, the characteristic constant KiObtain as follows：By it is above-mentioned extremely The true box office result of few i category type identical films, substitute into abovementioned steps and obtain the equation group being made up of i equation, calculate The equation group obtains the type prediction model M1In the characteristic constant KiNumerical value.
Preferably, the interval prediction model M2The interval prediction model M of the film V is predicted as follows2 Corresponding prediction result：Box office receipts are divided into multiple continuous segments, each segment includes a section Minimum value and a section maximum；Calculating is averaged with the true box office result of film known to the film V type identicals Value；The box office average value is fallen into some described segment, i.e., the described film V interval prediction model M2It is corresponding Prediction result be equal to the segment the section minimum value and the section maximum average value.
Preferably, all forecast model M3All forecast model M of the film V are predicted as follows3 Corresponding prediction result：For all types of films, establish a linear equation, the linear equation by least j portions Know that the box office maximum of the true box office result of film is multiplied by all forecast model M3Corresponding box office normalizing index with Obtain all forecast model M of the film V3Corresponding prediction result；Wherein, all forecast model M3Institute is right The known numeric value T of j feature of the box office normalizing index answered equal to the film VjA corresponding characteristic constant Z is multiplied by respectivelyj Then it is added and obtains；Wherein, the characteristic constant ZjObtain as follows：By the true box office of above-mentioned at least j portions film As a result, abovementioned steps are substituted into and obtains the equation group being made up of j equation, calculated the equation group and obtain all forecast models M3In the characteristic constant ZjNumerical value.
Preferably, the different characteristic of the film V includes the feature that its concrete numerical value can be known by internet.
The above-mentioned box office receipts Forecasting Methodology of the present invention, multiple box office receipts forecast models are subjected to fusion calculation, can be with So that the rate of accuracy reached of prediction result, to more than 60%, the accuracy rate than the box office prediction result of Individual forecast model lifts 20% More than.And the present invention is not only able to provide the value of box office prediction, and the section of box office prediction can also be provided.
Embodiment
Technical characteristic, purpose and the effect of the present invention are described in further detail below by specific embodiment.
For the single linear forecast model accuracy described in background section it is not high the defects of, the invention provides one The box office receipts Forecasting Methodology of kind of mixed model, for being predicted to film V box office to obtain the film V most Whole box office receipts prediction result F, methods described comprise the following steps：
Step A：N box office receipts forecast model M is established according to the different characteristic of the film Vn.For example, the difference Feature can include the feature that its concrete numerical value can be known by internet, for example, searchable index, the scoring of bean cotyledon film, beans Valve film is wanted to see that number, the scoring of Wanda's film, Wanda's film are wanted to see number, director's popularity, performer's popularity etc..Certainly, Obtained it will be appreciated by those skilled in the art that above-mentioned known features can also inquire about from existing known cinemas database, such as It can be obtained from Wanda's cinemas database.Certainly, this step and prior art fundamental difference be just employ first it is a variety of Different box office receipts forecast models, rather than like the prior art using Individual forecast model.
Step B：According to the n box office receipts forecast model MnIt is more excellent that n box office receipts invention of acquisition is calculated respectively Different forecast model in the 3 of choosing.
First, the type prediction model M1The type prediction model M of the film V is predicted as follows1Institute Corresponding prediction result：For with the film V types identical film, establish a linear equation, the linear equation by The box office maximum of at least true box office result of the same type of known film in i portions is multiplied by the type prediction model M1Institute is right The box office normalizing index answered is to obtain the type prediction model M of the film V1Corresponding prediction result.
In above-mentioned steps, the linear equation of a corresponding the type can be formed for the film of each particular type, Such as can be directed to action movie establish one be used for predict linear equation, can also establish one for predicting for romance movie Linear equation.The process of type prediction is, when given movie samples (film types is known), according to known film class Type, the model of corresponding film types is selected, the feature of this movie samples is then predicted box office with model, therefore In type prediction model, each film types has a forecast model.
The above-mentioned type forecast model M1In the i spy of the corresponding box office normalizing index used equal to the film V The known numeric value S of signiA corresponding characteristic constant K is multiplied by respectivelyiThen it is added and obtains.
For example, for film《It is one step away》, its type is action movie, then with type prediction model M1Predict the film When box office, first using the linear equation corresponding to action movie, the film that sheet type is acted in the linear equation uses one The action movie stored in individual available sample, such as Wanda's cinemas database is 400,000,000 as sample, the wherein maximum of box office result Member, this 400000000 yuan box office normalizing indexes needed to be multiplied by corresponding to action movie type movie, so as to correct acquisition prediction result.
Wherein, the box office normalizing index corresponding to action movie type movie is averagely obtained by multiple characteristic weighings, Such as its concrete numerical value can be obtained by internet checking as follows for the numerical value of the multiple feature：
Searchable index=0.81, bean cotyledon film scoring=0.17, bean cotyledon film are wanted to see number=0.59, the scoring of Wanda's film =0.12, Wanda's film is wanted to see number=0.29, director popularity=0.78, performer popularity=0.39.
Then, the box office normalizing index=0.81 (K corresponding to action movie type movie1) * 0.81 (searchable index)+0.46 (K2) * 0.17 (scoring of bean cotyledon film)+0.29 (K3) * 0.59 (bean cotyledon film is wanted to see number)+0.23 (K4) * 0.12 (Wanda's film Scoring)+0.21 (K5) * 0.29 (Wanda's film is wanted to see number)+0.34 (K6) * 0.78 (director's popularity)+0.19 (K7)*0.39 (performer's popularity)=3.7
Then action movie《It is one step away》Prediction box office result under this forecast model is multiplied by 400,000,000 equal to 3.7 and is equal to 14.8 hundred million.
Wherein, the characteristic constant KiObtain as follows：By the true of above-mentioned at least i categories type identical film Box office result, substitute into abovementioned steps and obtain the equation group being made up of i equation, calculate the equation group and obtain the type prediction Model M1In the characteristic constant KiNumerical value.Certainly, likewise, this calculation procedure is actually also a kind of reverse evaluation Method, i.e., in the case of known to equation equation, in order to obtain characteristic constant KiConcrete numerical value, can be by the true of known film Box office result substitutes into equation equation to obtain the weight coefficient in equation.Certainly, it will be appreciated by those skilled in the art that due to etc. Formula equation includes i characteristic constant Ki, therefore at least need i equation composition equation group can just solve it is every in equation equation One unknown model coefficient.Likewise, if it is known that the sample of film is sufficiently large, i are greater than, then can use mathematics Method further obtains more accurate characteristic constant KiConcrete numerical value.
Secondly, the interval prediction model M2The interval prediction mould of the film V can be predicted as follows Type M2Corresponding prediction result：Box office receipts are divided into multiple continuous segments, each segment includes one Section minimum value and a section maximum；Calculating and the true box office result of film known to the film V type identicals Average value；The box office average value is fallen into some described segment, i.e., the described film V interval prediction model M2Institute Corresponding prediction result is equal to the section minimum value of the segment and the average value of the section maximum.
The interval prediction model M2Equally it is that film has been divided into multiple types, can basis for each type Box office demarcation interval section, certainly, it will be appreciated by those skilled in the art that Type division is more accurate, then the result predicted is more accurate.Example Such as, the section at box office can be divided according to 2013 and the box office receipts data distribution of 2 years 2014, such as：[0- 5000000], [5,000,000-1,000 ten thousand], [10,000,000-2,000 ten thousand], [20,000,000-3,000 ten thousand] ... [100,000,000-2 hundred million] ... etc..Area Between represent in forecast model is to predict the film in which box office segment, and foregoing type prediction model and aftermentioned All forecast models it is different, the box office result predicted in type prediction model and all forecast models is one Specific numerical value.
Equally to act the film of sheet type《It is one step away》Exemplified by, the box office of the film of the type obtained by its classification Segment is [800,000,000-10 hundred million], then according to interval prediction model M2The box office result of prediction is 800,000,000 and 1,000,000,000 average value, is 900000000.
Finally, all forecast model M3All forecast model M of the film V are predicted as follows3Institute Corresponding prediction result：For all types of films, a linear equation is established, the linear equation is as known at least j portions The box office maximum of the true box office result of film is multiplied by all forecast model M3Corresponding box office normalizing index is to obtain Obtain all forecast model M of the film V3Corresponding prediction result.
The above-mentioned steps of all forecast models seem much like with type prediction model, and different places is all pre- Survey model no longer classified types, that is, be all predicted for all types of films using a linear equation.
Similar type forecast model, all forecast model M3Corresponding box office normalizing index is equal to the film V J feature known numeric value TjA corresponding characteristic constant Z is multiplied by respectivelyjThen it is added and obtains.
Or with film《It is one step away》Exemplified by, in the case where not differentiating between films types, such as Wanda's cinemas database All films of middle storage are 800,000,000 yuan as sample, the wherein maximum of box office result, and this 800,000,000 yuan need to be multiplied by all films Corresponding box office normalizing index, so as to correct acquisition prediction result.
Wherein, the box office normalizing index corresponding to all films is averagely obtained by multiple characteristic weighings, such as institute State concrete numerical value that the numerical value of multiple features is obtained by internet checking as hereinbefore：
Searchable index=0.81, bean cotyledon film scoring=0.17, bean cotyledon film are wanted to see number=0.59, the scoring of Wanda's film =0.12, Wanda's film is wanted to see number=0.29, director popularity=0.78, performer popularity=0.39.Use herein Feature quantity as hereinbefore, then j=i now.
Then, the box office normalizing index=0.21 (T corresponding to all films1) * 0.81 (searchable index)+0.36 (T2)*0.17 (scoring of bean cotyledon film)+0.49 (T3) * 0.59 (bean cotyledon film is wanted to see number)+0.13 (T4) * 0.12 (scoring of Wanda's film)+ 0.31(T5) * 0.29 (Wanda's film is wanted to see number)+0.14 (T6) * 0.78 (director's popularity)+0.09 (T7) * 0.39 (performer people Gas index)=1.4
Then film《It is one step away》Prediction box office result under this forecast model is multiplied by 800,000,000 equal to 1.4 and is equal to 11.2 hundred million.
Wherein, the characteristic constant ZjObtain as follows：By the true box office result of above-mentioned at least j portions film, Substitute into abovementioned steps and obtain the equation group being made up of j equation, calculate the equation group and obtain all forecast model M3In The characteristic constant ZjNumerical value.Certainly, likewise, this calculation procedure is actually also a kind of reverse evaluation method, that is, exist In the case of equation equation is known, in order to obtain characteristic constant ZjConcrete numerical value, the true box office of known film can be tied Fruit substitutes into equation equation to obtain the weight coefficient in equation.Certainly, it will be appreciated by those skilled in the art that due to equation equation Include j characteristic constant Zj, therefore at least need j equation composition equation group can just solve in equation equation each not The model coefficient known.Likewise, if it is known that the sample of film is sufficiently large, j are greater than, then can be entered using mathematical method One step obtains more accurate characteristic constant ZjConcrete numerical value.
Forecast model different in 3 is introduced and then has returned to step C, to this 3 film that forecast model obtains in 3 Box office prediction result carries out fusion calculation, is calculated for example with the simple method of average：
For example, foregoing film《It is one step away》Final box office receipts prediction result F=(14.8+9+11.2)/3=11.6 Hundred million.
By actual measuring and calculating, the present invention compares for the prediction result of box office receipts with actual box office result, of the invention Above-mentioned box office receipts Forecasting Methodology, multiple box office receipts forecast models are subjected to fusion calculation, the standard of prediction result can be caused True rate reaches more than 60%, than the accuracy rate lifting more than 20% of the box office prediction result of Individual forecast model.And the present invention It is not only able to provide the value of box office prediction, and the section of box office prediction can also be provided.
It will be appreciated by those skilled in the art that although the present invention is described in the way of multiple embodiments, It is that not each embodiment only includes an independent technical scheme.So narration is used for the purpose of for the sake of understanding in specification, The skilled in the art should refer to the specification as a whole is understood, and by technical scheme involved in each embodiment The modes of different embodiments can be mutually combined into understand protection scope of the present invention by regarding as.
The schematical embodiment of the present invention is the foregoing is only, is not limited to the scope of the present invention.It is any Those skilled in the art, equivalent variations, modification and the combination made on the premise of the design of the present invention and principle is not departed from, The scope of protection of the invention all should be belonged to.

Claims (9)

  1. A kind of 1. box office receipts Forecasting Methodology of mixed model, for being predicted film V box office with described in acquisition Film V final box office receipts prediction result F, methods described comprise the following steps：
    Step A：N box office receipts forecast model M is established according to the different characteristic of the film Vn；
    Step B：According to the n box office receipts forecast model MnCalculate respectively and obtain n box office receipts prediction result Rn；
    Step C：To the n box office receipts prediction result RnCarry out fusion calculation and obtain the final box office receipts prediction result F。
  2. 2. the method as described in claim 1, it is characterised in that the fusion calculation in the step C obtains described final Box office receipts prediction result F comprises the following steps：By the n box office receipts prediction result RnIt is added again divided by n, so as to obtain The final box office receipts prediction result F.
  3. 3. the method as described in claim 1, it is characterised in that the fusion calculation in the step C comprises the following steps： By the n box office receipts prediction result RnA corresponding model coefficient F is multiplied by respectivelynThen be added, so as to obtain it is described most Whole box office receipts prediction result F.
  4. 4. method as claimed in claim 3, it is characterised in that the model coefficient FnCalculate and obtain as follows：Using The true box office result of film substitutes into the equation for obtaining in the step described in claim 3 and being made up of n equation at least known to n portions Group, calculate the equation group and obtain the model coefficient Fn。
  5. 5. the method as described in claim 1, it is characterised in that the n is equal to 3, the n box office receipts forecast model MnPoint Wei not type prediction model M1, interval prediction model M2And all forecast model M3。
  6. 6. method as claimed in claim 5, it is characterised in that the type prediction model M1As follows described in prediction The film V type prediction model M1Corresponding prediction result：
    For with the film V types identical film, establish a linear equation, the linear equation is same by least i portions The box office maximum of the true box office result of the known film of type is multiplied by the type prediction model M1Corresponding box office is returned One index is to obtain the type prediction model M of the film V1Corresponding prediction result；
    Wherein, the type prediction model M1The datum of i feature of the corresponding box office normalizing index equal to the film V Value SiA corresponding characteristic constant K is multiplied by respectivelyiThen it is added and obtains；
    Wherein, the characteristic constant KiObtain as follows：By the true box office of above-mentioned at least i categories type identical film As a result, abovementioned steps are substituted into and obtains the equation group being made up of i equation, calculated the equation group and obtain the type prediction model M1In the characteristic constant KiNumerical value.
  7. 7. method as claimed in claim 5, it is characterised in that the interval prediction model M2As follows described in prediction The film V interval prediction model M2Corresponding prediction result：
    Box office receipts are divided into multiple continuous segments, each segment includes a section minimum value and an area Between maximum；
    Calculating and the average value of the true box office result of film known to the film V type identicals；
    The box office average value is fallen into some described segment, i.e., the described film V interval prediction model M2It is corresponding Prediction result be equal to the segment the section minimum value and the section maximum average value.
  8. 8. method as claimed in claim 5, it is characterised in that all forecast model M3As follows described in prediction Film V all forecast model M3Corresponding prediction result：
    For all types of films, a linear equation, the true ticket of linear equation film as known at least j portions are established The box office maximum of room result is multiplied by all forecast model M3Corresponding box office normalizing index is to obtain the film V's All forecast model M3Corresponding prediction result；
    Wherein, all forecast model M3The datum of j feature of the corresponding box office normalizing index equal to the film V Value TjA corresponding characteristic constant Z is multiplied by respectivelyjThen it is added and obtains；
    Wherein, the characteristic constant ZjObtain as follows：By the true box office result of above-mentioned at least j portions film, before substitution State step and obtain the equation group being made up of j equation, calculate the equation group and obtain all forecast model M3In it is described Characteristic constant ZjNumerical value.
  9. 9. the method as described in one of claim 1-8, it is characterised in that the different characteristic of the film V includes can be by mutual The feature of its concrete numerical value is known in networking.
CN201610613047.4A 2016-07-29 2016-07-29 A kind of box office receipts Forecasting Methodology of mixed model Withdrawn CN107665373A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610613047.4A CN107665373A (en) 2016-07-29 2016-07-29 A kind of box office receipts Forecasting Methodology of mixed model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610613047.4A CN107665373A (en) 2016-07-29 2016-07-29 A kind of box office receipts Forecasting Methodology of mixed model

Publications (1)

Publication Number Publication Date
CN107665373A true CN107665373A (en) 2018-02-06

Family

ID=61115754

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610613047.4A Withdrawn CN107665373A (en) 2016-07-29 2016-07-29 A kind of box office receipts Forecasting Methodology of mixed model

Country Status (1)

Country Link
CN (1) CN107665373A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109087146A (en) * 2018-08-15 2018-12-25 深圳快购科技有限公司 The prediction technique and system of movie theatre box-office income
CN109191165A (en) * 2018-07-12 2019-01-11 北京猫眼文化传媒有限公司 A kind of box office forward prediction method and device
CN109559163A (en) * 2018-11-16 2019-04-02 广州麦优网络科技有限公司 A kind of model building method and sales forecasting method based on machine learning
US11704495B2 (en) 2019-05-20 2023-07-18 Sony Group Corporation Prediction of film success-quotient

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109191165A (en) * 2018-07-12 2019-01-11 北京猫眼文化传媒有限公司 A kind of box office forward prediction method and device
CN109087146A (en) * 2018-08-15 2018-12-25 深圳快购科技有限公司 The prediction technique and system of movie theatre box-office income
CN109559163A (en) * 2018-11-16 2019-04-02 广州麦优网络科技有限公司 A kind of model building method and sales forecasting method based on machine learning
US11704495B2 (en) 2019-05-20 2023-07-18 Sony Group Corporation Prediction of film success-quotient

Similar Documents

Publication Publication Date Title
CN107665373A (en) A kind of box office receipts Forecasting Methodology of mixed model
CN106596450B (en) Incremental method based on infrared spectrum analysis material component content
CN106651519A (en) Method and system for personalized recommendation based on label information
CN103955714A (en) Navy detection model construction method and system and navy detection method
CN108682003B (en) Product quality detection method
CN108830492B (en) Method for determining spot-check merchants based on big data
CN108647818A (en) A kind of method and device of prediction enterprise concerning taxes risk
CN112308316A (en) Crime number prediction method based on linear regression algorithm
Simonton Predicting presidential performance in the United States: Equation replication on recent survey results
CN107832982A (en) One kind fits trip's index calculation method based on big data tourism trip assessment models region
CN103646165A (en) Method for quantitatively judging yellow water quality
CN110046789A (en) A kind of automatic generation method and system of students' information quality assessment paper
CN109406898A (en) A method of fusion multi-characteristicquantity quantity comprehensive assessment paper oil insulation degree of aging
CN110472363B (en) Surrounding rock deformation grade prediction method and system suitable for high-speed railway tunnel
CN107180293A (en) A kind of horizontal assay method of geologic assessment towards exploration targets
Li et al. Big data oriented macro-quality index based on customer satisfaction index and PLS-SEM for manufacturing industry
CN108920428B (en) Fuzzy distance discrimination method based on joint fuzzy expansion principle
CN110186533A (en) A kind of short-term tide prediction method in high-precision river mouth
CN110942830A (en) Background management system for psychological evaluation
CN106951462A (en) A kind of film based on Time Trust similarities recommends method
RU2470352C1 (en) Statistical process control method (versions)
CN108960954A (en) A kind of content recommendation method and recommender system based on user group behavior feedback
Isakson Valuation analysis of commercial real estate using the nearest neighbors appraisal technique
Retno et al. The Validity of Internal Support and Facilitating Content on Sustainable Green Building Management in Indonesia
Sunderman et al. Valuation of land using regression analysis

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20180206

WW01 Invention patent application withdrawn after publication