CN111062548A - Enterprise decision-making auxiliary real-time data acquisition and evaluation method - Google Patents

Abstract

The invention relates to an enterprise decision-making auxiliary real-time data acquisition and evaluation method, which is a decision-making auxiliary analysis system provided by enterprises, wherein an evaluation object and an evaluation index of the evaluation system are selected by a user according to self requirements, index weight is determined by combining a subjective (G2 weighting method) mode and an objective (CRITIC weighting method), comprehensive score of the evaluation object is automatically calculated by a computer through a TOPSIS method, and results are automatically output, so that efficient, scientific and reliable analysis results are provided for enterprise decision makers.

Description

A real-time data collection and evaluation method for enterprise decision-making assistance

technical field

The invention belongs to the field of information, and in particular relates to a method for collecting and evaluating information data

Background technique

The invention provides an auxiliary decision-making analysis system for enterprises, the evaluation object and evaluation index of the evaluation system are selected by the user according to their own needs, and the index weight is combined in two ways: subjective (G2 weighting method) and objective (CRITIC weighting method). To determine, the comprehensive score of the evaluation object is automatically calculated by the computer through the TOPSIS method, and the results are automatically output, providing efficient, scientific and reliable analysis results for enterprise decision makers.

SUMMARY OF THE INVENTION

In order to help enterprises solve the problems of data acquisition difficulties and project evaluation being too subjective in the process of project evaluation, the present invention proposes a real-time data acquisition and evaluation method for enterprise decision-making assistance, which specifically includes:

A real-time data collection method for enterprise decision-making assistance, comprising manual selection of target enterprises, selection of evaluation indicators, data entry, data standardization, and computer collection of standardized data.

The data standardization refers to processing and processing the collected data according to a fixed format to form a unified specification, which is convenient for data comparison;

An evaluation method for enterprise decision assistance, comprising the following steps:

(1) Construction of initial decision matrix A and factor set U:

(2) Data standardization processing

(3) Weight determination

(4) Comprehensive score calculation

Specifically, the above steps are determined according to the following methods:

(1) Construction of initial decision matrix A and factor set U:

First, according to the evaluation object and the index system, construct a matrix with the evaluation index as the row and the evaluation object as the column. Suppose there are m evaluation objects x ₁ , x ₂ , x ₃ ...... x _m , Xi = {x ₁ , x ₂ , x ₃ ...... x _m }, _n evaluation indicators, y ₁ , y ₂ , y ₃ ...... y _n , Y _j = {y ₁ , y ₂ , y ₃ ...... y _n }, the value of the evaluation object X _i in the evaluation index Y _j is a _ij , and its evaluation value constitutes the initial decision matrix A=(a _ij ) _m×n (i=1,2,...,m; j=1,2,...,n).

Assuming that there are S first-level indicators in the evaluation system, the index system consists of S first-level indicators and j second-level indicators, then the total factor set U=(U ₁ ,U ₂ ,...,U _s ), the sub-target factor set U _k =(U _k1 ,U _k2 ,…,U _km )(k=1,2,…,s) composed of the second-level indicators corresponding to the first-level indicator k.

(2) Data standardization processing

进行标准化处理，标准化后的数据矩阵记为T＝(t_ij)_m×n(i＝1,2,…,m；j＝1,2,…,n)，其中t_ij具体计算公式为：Due to the different dimensions and orders of magnitude of the objects represented by each index, in order to facilitate quantitative calculation, it is necessary to analyze the original data matrix.

Carry out standardization processing, and the standardized data matrix is denoted as T=(t _ij ) _m×n (i=1,2,...,m; j=1,2,...,n), where the specific calculation formula of t _ij is:

Among them, the standardized processing formula (3) is used for the indicators of positive effect, and (4) is used otherwise.

(3) Weight determination

Use the G2 method to obtain the subjective weight of the index, and obtain the index weight set as W _ai =(W _a1 ,W _a2 ,...W _as ) according to the accurate assignment of _Rik .

The CRITIC method is used to determine the objective weight of each index, and the standardized index data is imported into the system. The system calculates the differences and conflicts of the selected indicators, and then obtains the amount of information contained in the index j. The greater the amount of information contained in the index, the correspondingly larger weight. The objective index weight (W _bj ) can be calculated by Expressed as

The importance of subjective weight obtained by expert evaluation and objective weight obtained by data calculation is consistent, so the comprehensive weight is the average of the two weights, and the comprehensive weight of index j can be expressed as

(4) Comprehensive score calculation

Based on the comprehensive weight W _j and the normalized data t _ij , the Euclidean distance (D ⁺ and D ⁻ , Equation 11 and Equation 12) between the evaluation object and the positive ideal solution and the negative ideal solution is calculated by using TOSIS, and the evaluation is obtained from this The overall score M of the subject (Equation 13).

Method 1: Select n indicators to be evaluated x ₁ , x ₂ , x ₃ ...... x _n , in the evaluation index set {x _i }={x ₁ , x ₂ , x ₃ ...... Select the least important and only one indicator from x _n } as a reference, and denote it as y _k , and re-mark each indicator as y ₁ , y ₂ , y ₃ ...... y _n , where n is the total number of indicators. {x _i }={x ₁ , x ₂ , x ₃ ...... x _n } and {y _i }={y ₁ , y ₂ , y ₃ ...... y _n } have one-to-one corresponding relationship. The relative importance _Rik is obtained by comparing the index y _i with the least important index _yk , where _Rik ≥1, _Rii =1, and the meaning of each value is shown in Table 1:

Table 1 Relative importance between evaluation indicators

1. The ratio of importance degree R _ik is the case of point assignment

Domain experts determine the least important index y _k as the only reference according to the relevant information, and then obtain the relative importance R _ik by comparing the index y _i with the least important index y _k , and then make a decision on the importance of the evaluation index. Rational judgment, the calculation method of _Rik is:

If the assignment of R _ik is accurate, the weight coefficient Wi of the indicator _i is:

2. The ratio of importance degree R _ik is the case of interval assignment

In some cases, when experts assign Ri _ik subjectively, due to lack of information, they are not sure to assign Ri _ik an exact value, but they are sure to give Ri _ik a range of values, but they cannot give up, that is, they cannot One and only one definite value is given to _Rik for sure, but a value range of _Rik is given with certainty. In this case, a G2 method with interval characteristics can be used. In this case, it is assumed that the designated expert gives an interval _Dik according to the ratio _Rik of the importance of the relevant information to the evaluation index.

A bounded closed set of real numbers [d ₁ , d ₂ ]=(x|d ₁ ≤x≤d ₂ , x∈R) is called a closed interval, and a closed interval can also be regarded as consisting of its endpoints d ₁ and d ₂ A pair of ordered numbers, called interval numbers, is usually denoted by D. For D=[d ₁ , d ₂ ], e(D)=d ₂ -d ₁ and n(D)=(d ₁ +d ₂ )/2 are called the interval width and interval midpoint of D, respectively.

为具有专家风险态度的区间映射函数，其中ε为风险态度因子，其取值范围为：-1/2≤ε≤1/2。对于保守型专家，取-1/2≤ε≤0；对于中立型专家，取ε＝0；对于风险型专家，取0≤ε≤1/2。对于指定的专家，ε为已知数。When n(D)=0, then D is a symmetric interval. For D ₁ =[d ₁₁ ,d ₂₁ ], D ₂ =[d ₁₂ ,d ₂₂ ], then D ₁ +D ₂ =[d ₁₁ +d ₁₂ ,d ₂₁ +d ₂₂ ] is specified. Often decisions are risky, called mapping

is an interval mapping function with expert risk attitude, where ε is the risk attitude factor, and its value range is: -1/2≤ε≤1/2. For conservative experts, take -1/2≤ε≤0; for neutral experts, take ε=0; for risk experts, take 0≤ε≤1/2. For the designated expert, ε is a known number.

Assume that experts give an interval number D _k to the ratio Ri _ik of the importance of the evaluation index y _i and the least important index y _k to a certain criterion according to the relevant information, that is, the value interval of Ri _ik is given:

R _ik = _ak ∈[d _1k ,d _2k ]=D _k ,k=1,2,...,m-1 (3)

Wherein, d _1k ≤d _2k , d _2m =d _1m =1

If the assignment of {D _k } is accurate, then

Method Two:

The CRITIC weighting method is used to objectively weight the indicators by calculating the difference and conflict between the evaluation indicators. Difference refers to the difference in the value of the same indicator between different samples, and is measured by the standard deviation coefficient (S _j ) on the basis of excluding the influence of dimensions; the conflict between indicators includes two aspects: size and direction , expressed by the correlation coefficient (R _pq ), if the two indicators have a strong positive correlation, it means that their conflict is low.

The standard deviation and correlation coefficient of the jth indicator are calculated as:

Among them, p and q represent the indicators, and R _pq represents the correlation coefficient sequence between the tracer p and the indicator q

R_ij是第j个指标与第i个指标的相关系数，同时说明对于绝对值相同的正相关与负相关，其指标间的冲突性是相同的。设C_j为第j个指标所包含的信息量，表示为The conflict between the jth indicator and other indicators can be quantified as

R _ij is the correlation coefficient between the j-th index and the i-th index, and it shows that for the positive correlation and negative correlation with the same absolute value, the conflict between the indicators is the same. Let C _j be the amount of information contained in the jth index, expressed as

The larger C _j is, the larger the amount of information contained in the j-th index is, and its weight is correspondingly larger, which is expressed as

Method 3:

Using the TOPSIS method, by calculating the distance between the index value and the positive ideal solution and the negative ideal solution, the relative closeness of each evaluation object to the optimal solution is obtained and sorted. The closer the evaluation object is to the ideal value, the higher the ranking. This method is not limited by the sample size, and can obtain reasonable evaluation results through simple calculation. It is a commonly used method in multi-objective decision analysis. For the data subjected to dimensionless normalization, the "positive ideal solution" is the maximum value in the standardized data of the evaluation object, and the "negative ideal solution" corresponds to the minimum value in the standardized data of the evaluation index. The positive ideal solution X ^{+ and} the negative ideal solution X- can be expressed as

The distance from the ideal value is calculated by using the weighted Euclidean distance, and the distances of the positive ideal solution and the negative ideal solution of the evaluation object are expressed as D ⁺ and D ^- respectively:

D ⁺ and D ^- evaluate the evaluation object from different angles. The smaller the D ⁺ is, the smaller the distance between the evaluation object and the optimal ideal solution is, that is, the evaluation object is in a relatively dominant position; the larger the D ^- is, the smaller the evaluation object is. The distance from the poor ideal solution is farther, and it also indicates that it is closer to the positive ideal solution, so D ⁺ and D ^- can be regarded as the same meaning. Combining the evaluation results of D ⁺ and D ^- , the closeness M ^* of the evaluation object and the optimal solution can be obtained, that is, the comprehensive score of the evaluation object:

The score of closeness M calculated by this method is between 0 and 1. It can be seen that the closer the score of the evaluation object is to 1, the smaller the distance between the evaluation object and the positive ideal solution, and it is in an advantageous position relative to other evaluation objects.

Claims (3)

1. An enterprise decision-making assisted real-time data acquisition method comprises the steps of manually selecting a target enterprise, selecting an evaluation index, inputting data, standardizing the data and collecting standardized data by a computer.

2. The data acquisition method of claim 1, wherein the data standardization means that the acquired data are processed and processed according to a fixed format to form a unified specification, so as to facilitate data comparison.

3. An enterprise decision-assisted evaluation method comprises the following steps:

(1) constructing an initial decision matrix A and a factor set U:

(2) data normalization process

(3) Weight determination

(4) Composite score calculation

The data standardization means that the dimension and magnitude of the object represented by each index are different, so that quantitative calculation is facilitated, and an original data matrix is subjected to

And (6) carrying out standardization treatment.