CN106600091A - Program evaluation system and program evaluation method based on entropy method - Google Patents
Program evaluation system and program evaluation method based on entropy method Download PDFInfo
- Publication number
- CN106600091A CN106600091A CN201510675147.5A CN201510675147A CN106600091A CN 106600091 A CN106600091 A CN 106600091A CN 201510675147 A CN201510675147 A CN 201510675147A CN 106600091 A CN106600091 A CN 106600091A
- Authority
- CN
- China
- Prior art keywords
- program
- index
- evaluation
- data
- entropy
- 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
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Abstract
The invention provides a program evaluation system and a program evaluation method based on an entropy method. The program evaluation system comprises an input unit, which is used to input to-be-evaluated programs and evaluation indexes; an initial data matrix constructing unit, which is used to acquire original data and the evaluation indexes to form an initial data matrix; a data non-negative processing unit, which is used for the non-negative processing of the data; a data proportion matrix constructing unit, which is formed by the proportions of the indexes occupied by the various programs under conditions of all of indexes; a program evaluation model constructing unit, which is used to calculate program evaluation index weights according to an entropy and a diversity factor of a single index calculated by the data proportion matrix; a program comprehensive evaluation unit, which is used to acquire the comprehensive evaluation values of the various programs according to the televiewing information and the program evaluation index weights of the to-be-evaluated programs to acquire the comprehensive elevation values of the various programs. Objective decisions are fully reflected, and the scientific empowerment of the evaluation indexes is realized, and therefore deviations caused by human factors are prevented, and the accuracy of the program evaluation is improved.
Description
Technical field
The present invention relates to field of broadcast televisions, more specifically, is related to a kind of program evaluation based on Information Entropy
System and method.
Background technology
In field of broadcast televisions, the usual preference using multiple metrics evaluation users to program, to evaluation index
The assignment of weight is an important step of multiobjective decision-making.The weight of index is referred to and is marked in evaluation procedure
The reflection of different significance levels, is that a kind of subjectivity of index relative importance in decision-making (or assessment) problem is commented
Valency and the comprehensive measurement for objectively responding.Whether reasonable the assignment of weight is, and the scientific rationality of evaluation result is risen
Vital effect；If the weight of a certain factor changes, it will affect whole evaluation result.Cause
This, the assignment of weight must accomplish science and objective, and this requires to seek suitable Weight Determination.
At present the domestic and international determination method with regard to evaluation index weight coefficient has many kinds, according to calculating weight coefficient
When initial data source and calculating process difference, these methods can substantially divide subjective weighting method and objective
The big class of enabling legislation two.Subjective weights Evaluation Method takes qualitatively method, rule of thumb carries out subjectivity by expert and sentences
It is disconnected and obtain flexible strategy, comprehensive assessment, such as analytic hierarchy process (AHP), expert survey, mould are then carried out to index again
Paste analytic process, binomial coefficient method etc., wherein, analytic hierarchy process (AHP) is the most method used in practical application,
It by challenge stratification, by qualitative question quantification.Objective Weight assessment rule is ground according to historical data
The dependency relation or index studied carefully between index carries out comprehensive assessment with the relation of assessment result, mainly there is entropy
The methods such as value method, PCA, average variance method, VC Method, wherein, Information Entropy it is more,
The data that this enabling legislation is used are decision matrixs, determined by attribute weight reflect property value from
Scattered degree.Subjective weighting method can embody the micro-judgment of policymaker, and the relative importance of attribute is general not
The general knowledge of people can be violated.But its randomness is larger, accuracy of determination and less reliable.Objective weighted model
There is entitled objective criterion, using certain mathematical model, by the weight coefficient for calculating attribute.
It has the disadvantage to ignore the subjective preference informations such as the Subjective Knowledge of policymaker and experience, it sometimes appear that weight
The irrational phenomenon of coefficient.
The content of the invention
In view of the above problems, it is an object of the invention to provide a kind of reflection objective making decision, realizes that TV programme are commented
The entitled program evaluation system of valency index science and method.
The present invention provides a kind of program evaluation system based on Information Entropy, including：Input block, for being input into
Program to be evaluated and evaluation index；Primary data matrix construction unit, to input block input programme information and
Evaluation index, according to program audience information initial matrix is constructed,X=
(Xij)m×n, 0≤i≤m, wherein 0≤j≤n, XijFor the numerical value of i-th program, j-th index；Data
Nonnegative number processing unit, if there is negative in data, needs to carry out nonnegative number process to data, for more
Big better index and the smaller the better index, with different formula to XijCarry out nonnegative numberization process to obtain
X’ij, ask during entropy logarithm meaningless in order to avoid asking, need to carry out data translation, make 0≤X 'ij≤1；Number
According to proportion matrix construction unit, P=(Pij)m×n, PijThe index is accounted for for i-th program under jth item index
Proportion；Program evaluation model construction unit, according to the entropy e of data proportion matrix calculus single indexjAnd difference
Different coefficient gj, so as to calculate program evaluation criterion weight Wj；Program overall merit unit, according to section to be evaluated
Purpose audience information and program evaluation criterion weight obtain the comprehensive evaluation value S of each programi。
According to another aspect of the present invention, there is provided a kind of program evaluation methodology based on Information Entropy, including：
Select program to be evaluated and evaluation index；Build primary data matrix；The process of primary data matrix nonnegative numberization,
Respective formula is selected to carry out nonnegative number process for different types of index；Data proportion matrix is built, is obtained
Obtain the proportion that each program under all indexs accounts for the index；Program evaluation model is built, according to data proportion matrix
The entropy and coefficient of variation of single index are calculated, so as to calculate program evaluation criterion weight；According to section to be evaluated
Purpose audience information and program evaluation criterion weight obtain the comprehensive evaluation value of each program.
Program evaluation system of the present invention and method are realized carries out Objective Weight using Information Entropy, realizes
The science of TV programme evaluation index assigns power, improves the accuracy and reliability of program evaluation.
Description of the drawings
By reference to the explanation below in conjunction with accompanying drawing and the content of claims, and with to the present invention
Be more fully understood from, the present invention other purposes and result will be more apparent and should be readily appreciated that.In the accompanying drawings：
Fig. 1 is composition block diagram of the present invention based on the program evaluation system of Information Entropy；
Fig. 2 is flow chart of the present invention based on the program evaluation methodology of Information Entropy；
Fig. 3 is the flow chart of data nonnegative number processing method of the present invention；
Fig. 4 is the flow chart of program evaluation model construction method of the present invention；
In all of the figs identical label indicates similar or corresponding feature or function.
Specific embodiment
In the following description, for purposes of illustration, in order to provide to the comprehensive of one or more embodiments
Understand, elaborate many details.It may be evident, however, that can also be in the feelings without these details
These embodiments are realized under condition.The specific embodiment of the present invention is described in detail below with reference to accompanying drawing.
The specific embodiment of the present invention is described in detail below with reference to accompanying drawing.
Fig. 1 is composition block diagram of the present invention based on the program evaluation system of Information Entropy, as shown in figure 1, this
Inventing the program evaluation system includes：
Input block 110, for selecting program to be evaluated and evaluation index, for example, input block 110 can
Think touch screen, computer, keyboard, mouse etc., show that program to be evaluated and evaluation index are selected for user thereon
Select, user can select m program to be evaluated, be designated as M={ M1, M2..., Mm, n evaluation index,
It is designated as I={ I1, I2..., In}。
Primary data matrix construction unit 120, the evaluation index to the input of input block 110, according to program
Correspondence rating index construction primary data matrix X=(Xij)m×n, as the 1st evaluation of the 1st program refers to
Mark audience ratings is 0.92, then X11=0.92.
Data nonnegative number processing unit 130, is carried out at nonnegative number to primary data matrix construction unit 120
Reason, for the index being the bigger the better, is processed with below equation：I=1,2 ..., n；J=1,2 ..., m
For the smaller the better index, processed with below equation：I=1,2 ..., n；J=1,2 ..., m
Wherein, 0≤X 'ij≤1。
Data proportion matrix construction unit 140, uses formulaJ=1,2 ... m build data ratio
Weight matrix P=(Pij)m×n, PijFor the proportion that i-th program under jth item index accounts for the index.
Program evaluation model construction unit 150, first according to data proportion matrix and formulaThe entropy of single index is calculated, according to formula gj=1-ejCalculate individual event to refer to
Target coefficient of variation, finally according to formulaCalculate program evaluation criterion weight.
Program overall merit unit 160, the audience information, program evaluation criterion weight according to program to be evaluated
W and program evaluation of estimate computing formulaObtain the comprehensive evaluation value and program row of each program
Sequence.
The program evaluation model of above-mentioned program evaluation system is to carry out Objective Weight, body to program evaluation index
Science decision is showed, reached carries out the entitled purpose of science for broadcast TV program index system.
Fig. 2 is flow chart of the present invention based on the program evaluation methodology of Information Entropy, as shown in Fig. 2 this
The bright program evaluation methodology includes：
First, in step S210, program to be evaluated and evaluation index are selected；
In step S220, primary data matrix is built, according to program correspondence rating index construction initial number
According to matrix X=(Xij)m×n。
In step S230, nonnegative number process is carried out to primary data matrix, according to index trend not
Together, different process formula, concrete application process are selected to describe in figure 3.
In step S240, data proportion matrix P=(P are constructedij)m×n, PijFor under jth item index
I-th program accounts for the proportion of the index；
In step s 250, program evaluation model is constructed, according to data proportion matrix calculus single index
Entropy and coefficient of variation, so as to calculate program evaluation criterion weight, specific operation process will in the diagram
Description.
In step S260, obtained respectively according to the audience information and program evaluation criterion weight of program to be evaluated
The comprehensive evaluation value of program and program sort.
Fig. 3 is that the present invention carries out the flow chart of nonnegative number process, the process side to primary data matrix
Method step：
First, in step S310, judge the demand of program index, be to be the bigger the better, it is still more little more
It is good；
In step s 320, it is the bigger the better if having selected index in step S310, then by formula
(1) process.If it is the smaller the better that index is have selected in step S310, then by formula (2) process.
Fig. 4 is the flow chart of program evaluation model construction method of the present invention, as shown in figure 4, the program
Evaluation model construction method includes：
First, in step S410, the entropy of jth item index is calculated
Wherein k ＞ 0,1n are natural logrithm, ej≥0.Constant k is relevant with sample number m in formula, general orderThen 0≤ej≤1；
In the step s 420, the coefficient of variation g of jth item index is calculatedj, for jth item index, index
Value X 'ijDifference it is bigger, to program evaluate effect it is bigger, entropy ejLess, coefficient of variation calculates public
Formula：gj=1-ej, then：gjBigger index is more important；
In step S430, jth item program evaluation criterion weight is calculatedJ=1,2 ... m.
In sum, it has been described by way of example with reference to according to program evaluation system proposed by the present invention
System and method.It will be understood by those skilled in the art, however, that the system that the invention described above is proposed and
Method, can be making various improvement on the basis of without departing from present invention.Therefore, guarantor of the invention
Shield scope should be determined by the content of appending claims.
Claims (7)
1. a kind of program evaluation system based on Information Entropy, including：
Input block, for being input into program to be evaluated and evaluation index；
Primary data matrix construction unit, to input block programme information and evaluation index are input into, and according to program audience information initial matrix is constructed,X=(Xij)m × n, X ∈ R, 0≤i≤m, 0≤j≤n, wherein XijFor the numerical value of i-th program, j-th index；
Data nonnegative number processing unit, if there is negative in data, needs to carry out nonnegative number process to data, for the index being the bigger the better and the smaller the better index, with different formula to XijCarry out nonnegative numberization process and obtain X 'ij, ask during entropy logarithm meaningless in order to avoid asking, need to carry out data translation, make 0≤X 'ij≤1；
Data proportion matrix construction unit, P=(Pij)m × n, PijFor the proportion that i-th program under jth item index accounts for the index；
Program evaluation model construction unit, according to the entropy and coefficient of variation of data proportion matrix calculus single index, so as to calculate program evaluation criterion weight；
Program overall merit unit, according to the audience information and program evaluation criterion weight of program to be evaluated the comprehensive evaluation value of each program is obtained.
2. program evaluation system according to claim 1, wherein, the program evaluation model construction unit includes：
Single index entropy computing unit, calculates the entropy of indices.
Single index coefficient of variation computing unit, calculates the coefficient of variation of indices, and the bigger index of coefficient of variation is more important.
Program evaluation criterion weight computing unit, calculates every program evaluation criterion weight.
3. a kind of program evaluation methodology based on Information Entropy, including：
Select program to be evaluated and evaluation index；
Primary data matrix is built, corresponding program and evaluation index matrix are built according to programme information；
The process of data nonnegative numberization, makes program index value be standardized in certain numerical range；
Data proportion matrix is built, the proportion that each program under all indexs accounts for the index is calculated；
Program evaluation model is built, according to the entropy and coefficient of variation of data proportion matrix calculus single index so as to calculating program evaluation criterion weight；
Program overall merit, according to the audience information and program evaluation criterion weight of program to be evaluated the comprehensive evaluation value of each program is obtained.
4. program evaluation methodology according to claim 3, wherein, the data nonnegative numberization is processed to be included：For the index being the bigger the better, processed with below equation：
For the smaller the better index, processed with below equation：
Wherein, 0≤X 'ij≤1。
5. program evaluation methodology according to claim 3, wherein, the structure data proportion matrix P=(Pij)m × n, PijFor the proportion that i-th program under jth item index accounts for the index, it is calculated by below equation
6. program evaluation methodology according to claim 3, wherein, the structure program evaluation model includes：
Single index entropy computing unit, calculates the entropy e of jth item indexj,Wherein k ＞ 0, ln are natural logrithm, ej≥0.Constant k is relevant with sample number m in formula, general orderThen 0≤ej≤1。
Single index coefficient of variation computing unit, calculates the coefficient of variation g of jth item indexj, for jth item index, desired value X 'ijDifference it is bigger, to program evaluate effect it is bigger, entropy ejIt is less, coefficient of variation computing formula：gj=1-ej, 0≤gj≤ 1：gjBigger index is more important.
Program evaluation criterion weight computing unit, calculates jth item program evaluation criterion weight Wj,
7. program evaluation methodology according to claim 3, wherein, the comprehensive evaluation value S for calculating programi, according to the audience information and program evaluation criterion weight of program to be evaluated, it is calculated by below equation：
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510675147.5A CN106600091A (en) | 2015-10-16 | 2015-10-16 | Program evaluation system and program evaluation method based on entropy method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510675147.5A CN106600091A (en) | 2015-10-16 | 2015-10-16 | Program evaluation system and program evaluation method based on entropy method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106600091A true CN106600091A (en) | 2017-04-26 |
Family
ID=58554022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510675147.5A Pending CN106600091A (en) | 2015-10-16 | 2015-10-16 | Program evaluation system and program evaluation method based on entropy method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106600091A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784519A (en) * | 2017-10-13 | 2018-03-09 | 厦门集微科技有限公司 | A kind of advertising results appraisal procedure and server |
| CN110414047A (en) * | 2019-06-24 | 2019-11-05 | 南方电网调峰调频发电有限公司信息通信分公司 | A method of it is evaluated for telecommunication transmission equipment health status |
| CN110516923A (en) * | 2019-08-06 | 2019-11-29 | 中交信息技术国家工程实验室有限公司 | A kind of car networking synthetical information evaluating method |
| CN113034058A (en) * | 2021-05-10 | 2021-06-25 | 南京百伦斯智能科技有限公司 | Teaching evaluation method and system based on education data mining and analysis |
| CN114662193A (en) * | 2022-03-22 | 2022-06-24 | 常州工学院 | Deceleration strip vibration energy recovery performance evaluation method based on multi-source data fusion |
-
2015
- 2015-10-16 CN CN201510675147.5A patent/CN106600091A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784519A (en) * | 2017-10-13 | 2018-03-09 | 厦门集微科技有限公司 | A kind of advertising results appraisal procedure and server |
| CN110414047A (en) * | 2019-06-24 | 2019-11-05 | 南方电网调峰调频发电有限公司信息通信分公司 | A method of it is evaluated for telecommunication transmission equipment health status |
| CN110516923A (en) * | 2019-08-06 | 2019-11-29 | 中交信息技术国家工程实验室有限公司 | A kind of car networking synthetical information evaluating method |
| CN110516923B (en) * | 2019-08-06 | 2022-04-05 | 中交信息技术国家工程实验室有限公司 | Internet of vehicles information comprehensive evaluation method |
| CN113034058A (en) * | 2021-05-10 | 2021-06-25 | 南京百伦斯智能科技有限公司 | Teaching evaluation method and system based on education data mining and analysis |
| CN114662193A (en) * | 2022-03-22 | 2022-06-24 | 常州工学院 | Deceleration strip vibration energy recovery performance evaluation method based on multi-source data fusion |
| CN114662193B (en) * | 2022-03-22 | 2023-10-13 | 常州工学院 | Deceleration strip vibration energy recovery performance evaluation method based on multi-source data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106600091A (en) | Program evaluation system and program evaluation method based on entropy method | |
| Azzeh et al. | Analogy-based software effort estimation using Fuzzy numbers | |
| Yue | Approach to group decision making based on determining the weights of experts by using projection method | |
| CN111291266A (en) | Artificial intelligence based recommendation method and device, electronic equipment and storage medium | |
| CN106611099A (en) | Program evaluation system and method based on analytic hierarchy process | |
| CN104809235B (en) | A kind of program evaluation system and method | |
| CN108537600A (en) | A kind of electricity market postitallation evaluation method and computing device | |
| Ruan et al. | Relief supplies allocation and optimization by interval and fuzzy number approaches | |
| WO2021180249A1 (en) | Occupation recommendation method and apparatus, and device and medium | |
| CN105512465B (en) | Based on the cloud platform safety quantitative estimation method for improving VIKOR methods | |
| CN109862431B (en) | MCL-HCF algorithm-based television program mixed recommendation method | |
| Smucker et al. | Modeling user variance in time-biased gain | |
| CN112396211B (en) | Data prediction method, device, equipment and computer storage medium | |
| Dias et al. | On generating utility functions in stochastic multicriteria acceptability analysis | |
| Izadikhah | Using the Hamming distance to extend TOPSIS in a fuzzy environment | |
| Alves et al. | The strength of social coding collaboration on github | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| CN115238167A (en) | Power consumer refined portrait and management method considering load and social information | |
| Minku et al. | Clustering dycom: An online cross-company software effort estimation study | |
| CN113191828B (en) | User electricity price value grade label construction method, device, equipment and medium | |
| CN105303194B (en) | A kind of power grid index system method for building up, device and computing device | |
| CN106611098A (en) | Program evaluation system and method based on variable coefficient method | |
| Petrova | Using the analytic hierarchy process for LMS selection | |
| Guan et al. | Preference of online users and personalized recommendations | |
| Shi et al. | Long-term effects of user preference-oriented recommendation method on the evolution of online system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170426 |
|
| WD01 | Invention patent application deemed withdrawn after publication |