CN109636184A - A kind of appraisal procedure and system of the account assets of brand - Google Patents

Abstract

The invention relates to a method and system for evaluating account assets of a brand. The method includes: establishing an evaluation index system for account assets; acquiring the number of accounts and fans of all brands in a given industry whose bottom-level indexes of the evaluation index system are in a given industry; Calculate the incremental data of the number of accounts and fans; divide the incremental data into fuzzy intervals to establish the scoring standard of the evaluation index system; establish the weight of the indicators at all levels; use the multiply-add operator to calculate the membership vector of the indicators at all levels; according to the score Criteria, weights and membership degree vectors, and use the multiply-add operator to calculate the comprehensive score of the evaluation index system step by step. The technical solution provided by the invention comprehensively utilizes the analytic hierarchy process and the fuzzy comprehensive evaluation method, realizes the quantitative, objective and accurate evaluation of the account assets of the brand, and lays a solid foundation for the merchants to improve the brand marketing accuracy and the users to improve the brand consumption experience. The decision-making basis is established, the user satisfaction is high, and the experience is good.

Description

A method and system for evaluating account assets of a brand

technical field

The invention relates to the technical field of big data processing, and in particular to a method and system for evaluating brand account assets.

Background technique

With the rapid development of the Internet, the running trajectories of various brands on the Internet are increasing day by day, and the networked data information of each brand is also increasing massively. In today's big data era, this information can undoubtedly be used as the brand's intangible Internet digital assets.

But the sheer volume of digital information can be overwhelming for companies or consumers. Therefore, statistics, analysis and evaluation of digital information related to various brands have a good role in promoting the operation of the company and consumers' understanding of the company. By understanding their own Internet digital assets, companies can grasp their own brand strengths and weaknesses in time, maintain their strengths, make up for weaknesses, further improve their brand effects, and make more profits for the company; You can guide yourself to consume more scientifically and buy more ideal products or services.

From the perspective of brand value evaluation, a brand's Internet digital assets include: content assets, volume assets, and account assets. Among them, account assets refer to the number of user accounts and fans of a certain brand on Internet channels such as third-party social platforms, third-party search platforms, third-party live broadcast platforms, and third-party document platforms. To evaluate a brand's Internet digital assets, it must involve how to evaluate the brand's account assets.

At present, the most widely used comprehensive evaluation theory at home and abroad is the Analytic Hierarchy Process (AHP). The idea of AHP is to first decompose complex problems by establishing a clear hierarchical structure, secondly introduce measure theory, standardize human judgment with relative scale through comparison, and build a judgment matrix layer by layer, then solve the weight of the judgment matrix, and finally calculate The overall weight of the program. However, when the AHP method performs pairwise comparisons, if the information is incomplete, the judgment will be uncertain, resulting in a large deviation in the solution accuracy. Fuzzy Comprehensive Evaluation Method (FuzzyComprehensive Evaluation Method) is an analysis method based on fuzzy set theory, which quantitatively processes various fuzzy information in analysis and evaluation, and performs state judgment. The uncertainty of the original data or the ambiguity of the evaluation standard in the comprehensive evaluation is solved.

Fuzzy comprehensive evaluation is a comprehensive evaluation made by applying the principle of fuzzy transformation and considering various factors related to the evaluation object.

The basic principle is:

(1) Construct multiple membership functions according to the evaluation criteria,

(2) A fuzzy relationship matrix can be formed by evaluating the different degrees of corresponding indexes in each membership function (ie, different degrees of membership).

(3) Construct the weight coefficient matrix.

(4) The weight coefficient fuzzy matrix and the fuzzy relation matrix are processed by fuzzy operation, and finally the membership degree matrix of the comprehensive index for each evaluation level can be obtained.

Although the AHP theory and the fuzzy comprehensive evaluation theory in the prior art are well developed and applied in many fields, how to apply the AHP theory and the fuzzy comprehensive evaluation theory to the field of account asset evaluation to realize the evaluation of account assets is now There are technologies that have not yet been involved. This makes it impossible for brand users and brand merchants to quantitatively, objectively and accurately evaluate specific brands, resulting in low brand marketing accuracy for merchants and poor brand consumption experience for users.

SUMMARY OF THE INVENTION

In view of this, the purpose of the present invention is to overcome the deficiencies of the prior art, and to provide a method and system for evaluating the account assets of a brand, so as to solve the problem that the prior art cannot realize the evaluation of the account assets of the brand, resulting in the brand marketing of the merchant. The problem of low accuracy and poor brand consumption experience of users.

To achieve the above purpose, the present invention adopts the following technical solutions:

A method for evaluating brand account assets, including:

Step S1, establishing an evaluation index system of account assets;

Step S2, obtain the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation index system are in a given industry, and calculate the incremental data of the number of accounts and the number of fans respectively;

Step S3, performing fuzzy interval division on the incremental data, and establishing a scoring standard for the evaluation index system;

Step S4, using the analytic hierarchy process to establish the weights of the indicators at all levels;

Step S5, utilize multiplication and addition operator to calculate the membership degree vector of each level index;

Step S6: Calculate the comprehensive score of the evaluation index system step by step by using the multiplication and addition operator according to the scoring standard, the weight and the membership degree vector.

Preferably, the step S3 includes:

Step S31: Divide the incremental data into fuzzy intervals, and express the division result by a vector to obtain a fuzzy set vector (G ₁ , G ₂ . . . G _n ) corresponding to n score levels for any index, wherein , n≥1;

Step S32: Determine the representative value (g ₁ , _{g 2} . . . g _{n )} of the fuzzy set _vector (G ₁ , G ₂ . ...g _n ) as a scoring criterion for calculating indicator scores; or,

Determine g ₁ =C(G ₁ ),g ₂ =C(G ₂ )....g _n =C(G _n ) as the representative of the fuzzy set vector (G ₁ , G ₂ . .G _n ) value _{( g 1} , _{g 2 ......}

Among them, C(G _i ) represents the barycentric value or center value of G _i , and 1≤i≤n.

Preferably, the step S4 includes:

Step S41, issuing questionnaires to experts to count the judgment matrix of each expert regarding the importance of the two indicators in the evaluation indicator system, and the direct weight distribution of the two indicators;

Step S42, according to the credibility of the expert, weighted and summarized to obtain the weight distribution between the two indicators;

Step S43 , according to the credibility of the experts, weighting and summarizing the judgment matrix of three or more indicators, and calculating the weight distribution among the three or more indicators according to the analytic hierarchy process.

Preferably, the step S5 includes:

Step S51, standardize the incremental data of the number of accounts and the number of fans according to formula (1):

Among them, Δx ^* represents the incremental data after normalization processing, Δx represents the incremental data before normalization processing, minData represents the minimum value of the incremental data, and maxData represents the maximum value of the incremental data;

Step S52: Calculate Δx ^* according to formula (2) for the trapezoidal fuzzy set G _i =[a,b,c,d], the membership degree of 1≤i≤n Thus, the membership vector of the index corresponding to Δx ^* is obtained as:

in,

Wherein, a, b, c, d are the division points of each trapezoidal fuzzy set G _i obtained by dividing the incremental data into fuzzy intervals in the step S31;

Step S53, assuming that there are m next-level indicators under any of the intermediate-level indicators, the membership degree vector of the jth indicator of the m sub-level indicators is denoted as: The weight of the j-th indicator of the m next-level indicators is W _j , 1≤j≤m, then the membership degree vector of any indicator in the middle-level indicators is calculated according to formula (3):

Wherein, the middle-level indicators refer to indicators of other layers except the lowest-level indicators.

Preferably, the step S6 includes:

Step S61: Assume that the membership degree vector of any index in the intermediate level index is (a ₁ , a ₂ ....a _n ), wherein, The representative value of the corresponding fuzzy set vector (G ₁ , G ₂ ....G _n ) is (g ₁ , g ₂ ....g _n ), then the incremental score of this level of indicators is calculated according to formula (4). ΔS:

ΔS=a ₁ g ₁ +a ₂ g ₂ +.....a _n g _n (4),

Step S62, suppose that the evaluation index system has a total of y-level indicators, and any index in the middle-level index has m subordinate indicators, and calculates the comprehensive score of the evaluation index system according to formula (5):

in, Represents the current moment, the incremental score of the jth indicator of the xth level; W _xj represents the weight of the jth indicator of the xth level; represents the comprehensive score of the evaluation index system mentioned in the previous moment, Represents the comprehensive score of the evaluation index system at the current moment.

Preferably, the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation indicator system are obtained in a given industry are obtained by at least one of the following methods:

Crawler programs are provided from Internet scraping, manual entry, and third-party data platforms.

In addition, the present invention also proposes a brand account asset evaluation system, including:

The establishment unit is used to establish the evaluation index system of account assets;

Incremental data calculation unit, used to obtain the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation index system are in a given industry, and calculate the incremental data of the number of accounts and the number of fans;

a scoring standard establishing unit, configured to perform fuzzy interval division on the incremental data, and establish a scoring standard for the evaluation index system;

The weight establishment unit is used to establish the weights of indicators at all levels by using the AHP;

The membership degree calculation unit is used to calculate the membership degree vector of the indicators at all levels by using the multiply-add operator;

The comprehensive scoring unit is used to calculate the comprehensive score of the evaluation index system step by step by using the multiplication and addition operator according to the scoring standard, the weight and the membership degree vector.

Preferably, the scoring standard establishing unit includes:

A dividing unit, used for dividing the incremental data into fuzzy intervals, and expressing the dividing result as a vector to obtain a fuzzy set vector (G ₁ , G ₂ ....G _n ) corresponding to n scoring levels for any index , where n≥1;

A determination unit for determining the representative value (g ₁ , g ₂ ....g _{n )} of the fuzzy set _vector (G ₁ , G ₂ ...... ₂ ....g _n ) as the scoring criterion for calculating the indicator score; or,

Determine g ₁ =C(G ₁ ), _g2 =C(G ₂ )....g _n =C(G _n ) as the representative value of the fuzzy set vector (G ₁ , G ₂ . . . G _n ) _{( g 1} , _{g 2 ......}

Among them, C(G _i ) represents the barycentric value or center value of G _i , and 1≤i≤n.

Preferably, the weight establishing unit includes:

The statistical unit is used to issue questionnaires to experts to count the judgement matrix of the importance of each of the two indicators in the evaluation indicator system, and the direct weight distribution of the two indicators;

The weighting unit is used for weighting and summarizing the weight distribution between the two indicators according to the credibility of the experts;

It is also used to obtain a judgment matrix of three or more indicators by weighting and summarizing according to the credibility of experts, and calculate the weight distribution among three or more indicators according to the analytic hierarchy process.

Preferably, the incremental data calculation unit obtains the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation index system are in a given industry by at least one of the following methods:

Crawler programs are provided from Internet scraping, manual entry, and third-party data platforms.

The present invention adopts the above technical scheme, and at least has the following beneficial effects:

The technical solution provided by the present invention takes into account the vastness and complexity of the data information on the Internet and the mixing of true and false data, which will interfere with the evaluation results, and comprehensively utilizes the advantages of the analytic hierarchy process in assigning weights and the fuzzy comprehensive evaluation method in dealing with uncertainties. It has the advantages in nature, realizes the quantitative, objective and accurate evaluation of the brand's account assets, and provides a concrete data description of the value evaluation of the abstract account assets. Compared with the general weighted average model, it has stronger robustness. The stability and anti-interference ability have laid a decision-making basis for merchants to improve brand marketing accuracy and users to improve brand consumption experience, with high user satisfaction and good experience.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

FIG. 1 is a flowchart of a method for evaluating account assets of a brand according to an embodiment of the present invention;

2 is a schematic block diagram of calculating a comprehensive score of account assets according to an embodiment of the present invention;

FIG. 3 is a schematic block diagram of a system for evaluating account assets of a brand according to an embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described in detail below. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other implementations obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

The technical solutions of the present invention will be further described in detail below through the accompanying drawings and embodiments.

Referring to FIG. 1 , a method for evaluating brand account assets provided by an embodiment of the present invention includes:

Step S1, establishing an evaluation index system of account assets;

Step S2, obtain the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation index system are in a given industry, and calculate the incremental data of the number of accounts and the number of fans respectively;

Step S3, performing fuzzy interval division on the incremental data, and establishing a scoring standard for the evaluation index system;

Step S4, using the analytic hierarchy process to establish the weights of the indicators at all levels;

Step S5, utilize multiplication and addition operator to calculate the membership degree vector of each level index;

Step S6: Calculate the comprehensive score of the evaluation index system step by step by using the multiplication and addition operator according to the scoring standard, the weight and the membership degree vector.

The technical solution provided in this embodiment takes into account the vastness and complexity of data and information on the Internet and the mixing of true and false data, which will cause interference to the evaluation results, and comprehensively utilizes the advantages of the AHP in assigning weights and the fuzzy comprehensive evaluation method in dealing with different The advantage of certainty enables quantitative, objective and accurate evaluation of the brand's account assets, and provides a concrete data description of the value evaluation of the abstract account assets. Compared with the general weighted average model, it has stronger robustness. Robustness and anti-interference, laying a decision-making basis for merchants to improve brand marketing accuracy and users to improve brand consumption experience, with high user satisfaction and good experience.

It can be understood that, in specific practice, the evaluation index system of the account assets may include multi-level indicators, and each level of indicators may include multiple lower-level indicators in addition to the bottom-level indicators.

For ease of understanding, taking the evaluation index system of the account assets including three-level indicators as an example, Table 1 is used as an example to illustrate the following:

Table I

It should be noted that the above table is only an example for the convenience of explaining the evaluation index system of account assets mentioned in this embodiment, and does not mean that the evaluation index system of account assets mentioned in this embodiment is only as shown in Table 1. The indicator system shown does not mean that there are only these indicators shown in Table 1.

It can be understood that the evaluation index system of the account assets may only include first-level indicators, and may also include second-level indicators, third-level indicators, ... or more, and the number of subordinate indicators that each level of indicators may include may also be Set according to user needs.

Preferably, the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation indicator system are obtained in a given industry are obtained by at least one of the following methods:

Crawler programs are provided from Internet scraping, manual entry, and third-party data platforms.

It should be noted that, in the step S2, the number of accounts and the number of fans of all brands in a given industry for the bottom-level index of the evaluation index system is limited, because only the bottom-level index has the number of accounts and the number of fans, and the other levels. The indicator does not have the number of accounts and fans. The essence of the technical solution provided by this embodiment is that the lowest-level indicators calculate their respective membership degrees according to the incremental data of the number of accounts and the number of fans, and other layer indicators calculate their own indicator scores according to their own membership degrees and weights of the next layer indicators , and then accumulated layer by layer to obtain the final account asset score.

The incremental data for calculating the number of accounts and the number of fans in the step S2 is the prior art, for example, it is known that the number of accounts and the number of fans at the previous moment is N ₁ , and the number of accounts and the number of fans at the current moment is N ₂ , then at the current moment, the incremental data of the number of accounts and the number of fans Δx=N ₂ -N ₁ .

In order to facilitate the understanding of the account asset evaluation method provided in this embodiment, referring to FIG. 2 , it is assumed that the evaluation index system of account assets is three-level.

Step S2: For the three-level evaluation index system of account assets, first calculate the incremental data accounts of the number of accounts and the incremental data fans of the number of fans of the lowest index.

Step S3: Divide the incremental data into fuzzy intervals to establish a scoring standard for the evaluation index system.

Step S4, using AHP to establish the weights of indicators at all levels; for example, for the account asset module, the weight of the i-th indicator in the first-level indicator is W _s1i , and the weight of the i-th indicator in the first-level indicator is W s1i . The weight of the j second-level indicators is W _s2ij , and the weight of the k-th third-level indicator of the j-th second-level indicator of the i-th indicator in the first-level indicators is W _s3ijk .

Step S5, using the multiply-add operator to calculate the membership degree vectors of the indicators at all levels.

Step S6: Calculate the comprehensive score of the evaluation index system step by step by using the multiplication and addition operator according to the scoring standard, the weight and the membership degree vector.

Preferably, the step S3 includes:

Step S31: Divide the incremental data into fuzzy intervals, and express the division result by a vector to obtain a fuzzy set vector (G ₁ , G ₂ . . . G _n ) corresponding to n score levels for any index, wherein , n≥1;

Step S32: Determine the representative value (g ₁ , _{g 2} . . . g _{n )} of the fuzzy set _vector (G ₁ , G ₂ . ...g _n ) as a scoring criterion for calculating indicator scores; or,

Determine g ₁ =C(G ₁ ),g ₂ =C(G ₂ )....g _n =C(G _n ) as the representative of the fuzzy set vector (G ₁ , G ₂ . .G _n ) value _{( g 1} , _{g 2 ......}

Among them, C(G _i ) represents the barycentric value or center value of G _i , and 1≤i≤n.

For step S31, assuming that there are three scoring levels, the corresponding level term vectors can be expressed as (low, medium, high), and the corresponding fuzzy set vectors can be expressed as (G ₁ , G ₂ , G ₃ ).

In the step S31, the incremental data is divided into fuzzy intervals, and the specific implementation method is as follows:

Step S311 , set the total number of fuzzy sets numMF divided by the fuzzy interval, and calculate the number of points q=2*numMF-1.

Step S312, read the data Datas of the fuzzy interval to be divided, and calculate its minimum value minData and maximum value maxData;

It should be noted that: if the data is normalized, then minData=0, maxData=1;

The data Datas of the to-be-divided fuzzy interval is the incremental data.

Step S313, if Datas is an empty set or the data are all the same, at this time, the interval [0, 1] is equally divided into numNF trapezoidal fuzzy sets (Note: the data set is empty or the data are all the same, no matter what kind of interval is divided, the result is are the same, so a simple average division method is used):

(1) The parameters of the first trapezoidal fuzzy set are set to [0, 0, 1/q quantile, 2/q quantile];

(2) for k=1:q-3 do (parameter setting of trapezoidal fuzzy set in the middle);

[k/q quantile, (k+1)/q quantile, (k+2)/q quantile, (k+3)/q quantile];

(3) The parameters of the last trapezoidal fuzzy set are set to [(q-2)/q quantile, (q-1)/q quantile, 1, 1].

Step S314, if the number of different data in the Datas is less than or equal to the number of points q, then divide the interval into numNF triangular fuzzy sets on average (Note: due to less data, divide the interval into more detailed triangular fuzzy sets on average. ):

(1) The parameters of the first triangular fuzzy set are set to [minData, minData, minData, 1/(numMF-1) quantile];

(2) for j=0: numNF-3 do (parameter setting of trapezoidal fuzzy set in the middle)

[j/(numMF-1) quantile, (j+1)/(numMF-1) quantile, (j+1)/(numMF-1) quantile, (j+2)/(numMF -1)Quantile];

(3) The parameters of the last triangular fuzzy set are set to [(numMF-2)/(numMF-1) quantile, maxData, maxData, maxData].

Step S315, if the number of different data in Datas is greater than the number of points q, then set numMF trapezoidal fuzzy sets as follows:

t=0; (the indicator that controls the quantile, which is used to remove abnormally large or abnormally small values)

while t<=10 (up to the 10% quantile and above the 90% quantile, this magnitude can be adjusted by itself)

quantile=99; (the initial setting is the 99% quantile, that is, the values less than 1% quantile and greater than 99% quantile are eliminated)

low=(100-quantile-t*0.1)/100 quantile;

high=(quantile+t*0.1)/100 quantile; (set the new interval minimum value low and maximum value high)

if data between [low, high] > number of points q

(1) The parameters of the first trapezoidal fuzzy set are set to [low, low, 1/q quantile, 2/q quantile];

(2) for k=1:q-3 do (parameter setting of trapezoidal fuzzy set in the middle)

[k/q quantile, (k+1)/q quantile, (k+2)/q quantile, (k+3)/q quantile];

(3) The parameters of the last trapezoidal fuzzy set are set to [(q-2)/q quantile, (q-1)/q quantile, high, high];

else

t=t+1.

Preferably, the step S4 includes:

Step S41, issuing questionnaires to experts to count the judgment matrix of each expert regarding the importance of the two indicators in the evaluation indicator system, and the direct weight distribution of the two indicators;

Step S42, according to the credibility of the expert, weighted and summarized to obtain the weight distribution between the two indicators;

For ease of understanding, taking the evaluation index system of the account assets including three-level indicators as an example, Table 2 is used as an example to illustrate the following:

Table II

Table 2 is the weight data given by experts. Use these data to calculate the weight of the corresponding indicators. For example, the weights of the next-level indicators of the third-level indicator service account and subscription account are:

Authentication: Unauthenticated = 3/(3+7):3/(3+7)=0.3:0.7 (service number)

Authentication: Unauthenticated = 4/(4+5):5/(4+5)=0.44:0.56 (subscription number)

This also unifies the dimensions, satisfying the weight sum equal to 1.

Step S43 , according to the credibility of the experts, weighting and summarizing the judgment matrix of three or more indicators, and calculating the weight distribution among the three or more indicators according to the analytic hierarchy process.

Taking the evaluation index system shown in Table 2 above as an example, the judgment matrix of the three secondary indicators can be shown in Table 3 below:

Table 3

It should be noted that according to the AHP, assigning weights to indicators at all levels is the prior art, and the present application uses the prior art in the implementation scheme of weight assignment, which has been disclosed in the prior art, and is not discussed in this application. Repeat.

Preferably, the step S5 includes:

Step S51, standardize the incremental data of the number of accounts and the number of fans according to formula (1):

Among them, Δx ^* represents the incremental data after normalization processing, Δx represents the incremental data before normalization processing, minData represents the minimum value of the incremental data, and maxData represents the maximum value of the incremental data;

Step S52: Calculate Δx ^* according to formula (2) for the trapezoidal fuzzy set G _i =[a,b,c,d], the membership degree of 1≤i≤n Thus, the membership vector of the index corresponding to Δx ^* is obtained as:

in,

Wherein, a, b, c, d are the division points of each trapezoidal fuzzy set G _i obtained by dividing the incremental data into fuzzy intervals in the step S31;

Step S53, assuming that there are m next-level indicators under any of the intermediate-level indicators, the membership degree vector of the jth indicator of the m sub-level indicators is denoted as: The weight of the j-th indicator of the m next-level indicators is W _j , 1≤j≤m, then the membership degree vector of any indicator in the middle-level indicators is calculated according to formula (3):

Wherein, the middle-level indicators refer to indicators of other layers except the lowest-level indicators.

Preferably, the step S6 includes:

Step S61: Assume that the membership degree vector of any index in the intermediate level index is (a ₁ , a ₂ ....a _n ), wherein, The representative value of the corresponding fuzzy set vector (G ₁ , G ₂ ....G _n ) is (g ₁ , g ₂ ....g _n ), then the incremental score of this level of indicators is calculated according to formula (4). ΔS:

ΔS=a ₁ g ₁ +a ₂ g ₂ +.....a _n g _n (4),

Step S62, suppose that the evaluation index system has a total of y-level indicators, and any index in the middle-level index has m subordinate indicators, and calculates the comprehensive score of the evaluation index system according to formula (5):

in, Represents the current moment, the incremental score of the jth indicator of the xth level; W _xj represents the weight of the jth indicator of the xth level; represents the comprehensive score of the evaluation index system mentioned in the previous moment, Represents the comprehensive score of the evaluation index system at the current moment.

In addition, referring to FIG. 3 , the present invention also proposes a brand account asset evaluation system 100, including:

establishing unit 101 for establishing an evaluation index system of account assets;

Incremental data calculation unit 102, used to obtain the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation index system are in a given industry, and calculate the incremental data of the number of accounts and the number of fans respectively;

A scoring standard establishing unit 103, configured to perform fuzzy interval division on the incremental data, and establish a scoring standard for the evaluation index system;

The weight establishing unit 104 is used for establishing the weights of the indicators at all levels by using the AHP;

The membership degree calculation unit 105 is used to calculate the membership degree vector of the indicators at all levels by using the multiply-add operator;

The comprehensive scoring unit 106 is configured to calculate the comprehensive score of the evaluation index system step by step by using the multiplication and addition operator according to the scoring standard, the weight and the membership degree vector.

The technical solution provided in this embodiment takes into account the vastness and complexity of data and information on the Internet and the mixing of true and false data, which will cause interference to the evaluation results, and comprehensively utilizes the advantages of the AHP in assigning weights and the fuzzy comprehensive evaluation method in dealing with different The advantage of certainty enables quantitative, objective and accurate evaluation of the brand's account assets, and provides a concrete data description of the value evaluation of the abstract account assets. Compared with the general weighted average model, it has stronger robustness. Robustness and anti-interference, laying a decision-making basis for merchants to improve brand marketing accuracy and users to improve brand consumption experience, with high user satisfaction and good experience.

Preferably, the scoring standard establishing unit 103 includes:

A dividing unit, used for dividing the incremental data into fuzzy intervals, and expressing the dividing result as a vector to obtain a fuzzy set vector (G ₁ , G ₂ ....G _n ) corresponding to n scoring levels for any index , where n≥1;

A determination unit for determining the representative value (g ₁ , g ₂ ....g _{n )} of the fuzzy set _vector (G ₁ , G ₂ ...... ₂ ....g _n ) as the scoring criterion for calculating the indicator score; or,

Determine g ₁ =C(G ₁ ),g ₂ =C(G ₂ )....g _n =C(G _n ) as the representative of the fuzzy set vector (G ₁ , G ₂ . .G _n ) value _{( g 1} , _{g 2 ......}

Among them, C(G _i ) represents the barycentric value or center value of G _i , and 1≤i≤n.

Preferably, the weight establishing unit 104 includes:

The statistical unit is used to issue questionnaires to experts to count the judgement matrix of the importance of each of the two indicators in the evaluation indicator system, and the direct weight distribution of the two indicators;

The weighting unit is used for weighting and summarizing the weight distribution between the two indicators according to the credibility of the experts;

It is also used to obtain a judgment matrix of three or more indicators by weighting and summarizing according to the credibility of experts, and calculate the weight distribution among three or more indicators according to the analytic hierarchy process.

Preferably, the incremental data calculation unit 102 obtains the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation index system are in a given industry by at least one of the following methods:

Crawler programs are provided from Internet scraping, manual entry, and third-party data platforms.

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention. should be included within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims. The terms "first" and "second" are used for descriptive purposes only and should not be construed to indicate or imply relative importance. The term "plurality" refers to two or more, unless expressly limited otherwise.

Claims (10)

1. A method for evaluating the account assets of a brand, comprising: Step S1, establishing an evaluation index system of account assets; Step S2, obtain the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation index system are in a given industry, and calculate the incremental data of the number of accounts and the number of fans respectively; Step S3, performing fuzzy interval division on the incremental data, and establishing a scoring standard for the evaluation index system; Step S4, using the analytic hierarchy process to establish the weights of the indicators at all levels; Step S5, utilize multiplication and addition operator to calculate the membership degree vector of each level index; Step S6: Calculate the comprehensive score of the evaluation index system step by step by using the multiplication and addition operator according to the scoring standard, the weight and the membership degree vector. 2. The method according to claim 1, wherein the step S3 comprises: Step S31: Divide the incremental data into fuzzy intervals, and express the division result by a vector to obtain a fuzzy set vector (G ₁ , G ₂ . . . G _n ) corresponding to n score levels for any index, wherein , n≥1; Step S32: Determine the representative value (g ₁ , _{g 2} . . . g _{n )} of the fuzzy set _vector (G ₁ , G ₂ . ...g _n ) as a scoring criterion for calculating indicator scores; or, Determine g ₁ =C(G ₁ ),g ₂ =C(G ₂ )....g _n =C(G _n ) as the representative of the fuzzy set vector (G ₁ , G ₂ . .G _n ) value _{( g 1} , _{g 2 ......} Among them, C(G _i ) represents the barycentric value or center value of G _i , and 1≤i≤n. 3. The method according to claim 1, wherein the step S4 comprises: Step S41, issuing questionnaires to experts to count the judgment matrix of each expert regarding the importance of the two indicators in the evaluation indicator system, and the direct weight distribution of the two indicators; Step S42, according to the credibility of the expert, weighted and summarized to obtain the weight distribution between the two indicators; Step S43 , according to the credibility of the experts, weighting and summarizing the judgment matrix of three or more indicators, and calculating the weight distribution among the three or more indicators according to the analytic hierarchy process. 4. The method according to claim 2, wherein the step S5 comprises: Step S51, standardize the incremental data of the number of accounts and the number of fans according to formula (1): Among them, Δx ^* represents the incremental data after normalization processing, Δx represents the incremental data before normalization processing, minData represents the minimum value of the incremental data, and maxData represents the maximum value of the incremental data; Step S52: Calculate Δx ^* according to formula (2) for the trapezoidal fuzzy set G _i =[a,b,c,d], the membership degree of 1≤i≤n Thus, the membership vector of the index corresponding to Δx ^* is obtained as: in, Wherein, a, b, c, d are the division points of each trapezoidal fuzzy set G _i obtained by dividing the incremental data into fuzzy intervals in the step S31; Step S53, assuming that there are m next-level indicators under any of the intermediate-level indicators, the membership degree vector of the jth indicator of the m sub-level indicators is denoted as: The weight of the j-th indicator of the m next-level indicators is W _j , 1≤j≤m, then the membership degree vector of any indicator in the middle-level indicators is calculated according to formula (3): Wherein, the middle-level indicators refer to indicators of other layers except the lowest-level indicators. 5. The method according to claim 4, wherein the step S6 comprises: Step S61: Assume that the membership degree vector of any index in the intermediate level index is (a ₁ , a ₂ ....a _n ), wherein, 1≤i≤n, the representative value of the corresponding fuzzy set vector (G ₁ , G ₂ ....G _n ) is (g ₁ , g ₂ ....g _n ), then calculate the value according to formula (4). The incremental score ΔS of the level indicator: ΔS=a ₁ g ₁ +a ₂ g ₂ +.....a _n g _n (4), Step S62, suppose that the evaluation index system has a total of y-level indicators, and any index in the middle-level index has m subordinate indicators, and calculates the comprehensive score of the evaluation index system according to formula (5): in, Represents the current moment, the incremental score of the jth indicator of the xth level; W _xj represents the weight of the jth indicator of the xth level; represents the comprehensive score of the evaluation index system mentioned in the previous moment, Represents the comprehensive score of the evaluation index system at the current moment. 6. The method according to any one of claims 1 to 5, wherein the acquisition of the bottom-level index of the evaluation index system is the number of accounts and the number of fans of all brands in a given industry, by the following methods: at least one of: Crawler programs are provided from Internet scraping, manual entry, and third-party data platforms. 7. An evaluation system for brand account assets, comprising: The establishment unit is used to establish the evaluation index system of account assets; Incremental data calculation unit, used to obtain the number of accounts and the number of fans of all brands whose bottom-level indicators of the evaluation index system are in a given industry, and calculate the incremental data of the number of accounts and the number of fans; a scoring standard establishing unit, configured to perform fuzzy interval division on the incremental data, and establish a scoring standard for the evaluation index system; The weight establishment unit is used to establish the weights of indicators at all levels by using the AHP; The membership degree calculation unit is used to calculate the membership degree vector of the indicators at all levels by using the multiply-add operator; The comprehensive scoring unit is used to calculate the comprehensive score of the evaluation index system step by step by using the multiplication and addition operator according to the scoring standard, the weight and the membership degree vector. 8. The system according to claim 7, wherein the scoring standard establishing unit comprises: A dividing unit, used for dividing the incremental data into fuzzy intervals, and expressing the dividing result as a vector to obtain a fuzzy set vector (G ₁ , G ₂ ....G _n ) corresponding to n scoring levels for any index , where n≥1; A determination unit for determining the representative value (g ₁ , g ₂ ....g _{n )} of the fuzzy set _vector (G ₁ , G ₂ ...... ₂ ....g _n ) as the scoring criterion for calculating the indicator score; or, Determine g ₁ =C(G ₁ ),g ₂ =C(G ₂ )....g _n =C(G _n ) as the representative of the fuzzy set vector (G ₁ , G ₂ . .G _n ) value _{( g 1} , _{g 2 ......} Among them, C(G _i ) represents the barycentric value or center value of G _i , and 1≤i≤n. 9. The system according to claim 7, wherein the weight establishing unit comprises: The statistical unit is used to issue questionnaires to experts to count the judgment matrix of the importance of each of the two indicators in the evaluation indicator system, and the direct weight distribution of the two indicators; The weighting unit is used for weighting and summarizing the weight distribution between the two indicators according to the credibility of the experts; It is also used to obtain a judgment matrix of three or more indicators by weighting and summarizing according to the credibility of experts, and calculate the weight distribution among three or more indicators according to the analytic hierarchy process. 10. The system according to any one of claims 7 to 9, wherein the incremental data calculation unit obtains the lowest-level index of the evaluation index system in at least one of the following manners in a given industry The number of accounts and fans of all brands of : Crawler programs are provided from Internet scraping, manual entry, and third-party data platforms.