Retail industry brand management method based on big data analysis

Abstract

The invention discloses a retail industry brand management method based on big data analysis, and relates to the field of brand management. The method comprises the following steps: acquiring commodity characteristic parameters and brand characteristic parameters of retail commodities in different periods, constructing a data sequence F and a data sequence B according to the acquired characteristic parameters, performing grey correlation analysis on the data sequence F and the data sequence B, and acquiring the grey correlation degree of the ith commodity characteristic parameter and the jth brand characteristic parameter; the influence degree of the commodity characteristic parameters on the brand characteristic parameters is judged by comparing the numerical values of the grey correlation degrees, a commodity characteristic parameter improvement strategy of the retail commodities is formulated according to the influence degree judgment result, and the factors and the degree of influence on the brand effect of the retail commodities are analyzed by adopting a big data technology. Therefore, the product features of the retail commodities are improved in a targeted manner, the quality of the commodities is improved, and the brand effect of the retail commodities of the enterprise in the consumer market is improved.

Description

Technical Field

[0001] The present invention relates to the field of brand management, and in particular to a retail brand management method based on big data analysis. Background Art

[0002] Brand is an intangible asset that gradually develops during the growth of an enterprise. It is also an important tool and means for an enterprise to improve its own value and seize or maintain its market share. Brand management strategy is an important part of the decision-making of an enterprise to operate its own products or services. It refers to the strategy of using brand trademarks in the most reasonable and effective way according to the enterprise's own business development status, market conditions and consumer psychology. In the retail industry, the impact of brand effect on enterprises is particularly obvious. Studies have shown that for retail products with good brand effect and high product satisfaction, customers have a higher frequency of repeat purchase behavior for products, which can bring continuous profits to enterprises and reduce marketing costs for enterprises.

[0003] With the continuous development of Internet technology, the rise of online shopping platforms has promoted the prosperity of the retail market. However, how to stand out from the increasing number of similar products and maintain or improve the brand effect of the company's retail products in the complex online market is a topic that many retailers pay close attention to. In reality, merchants usually use market research or questionnaires to collect consumers' opinions or suggestions on products, and use this as a goal to improve the products. However, this method is inefficient and has little effect. It is obviously unable to adapt to the current situation of the explosion of online shopping for retail products. To this end, we propose a retail brand management method based on big data analysis. Summary of the invention

[0004] The main purpose of the present invention is to provide a retail brand management method based on big data analysis, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] Retail brand management methods based on big data analysis include:

[0007] S1: Obtain commodity characteristic parameters and brand characteristic parameters of retail commodities in different periods;

[0008] S2: Construct data sequence F and data sequence B according to the acquired characteristic parameters, where F = {F1, F2, ..., F i}, B={B1,B2,...,B j}, F i Represented as the characteristic parameter data set of the i-th commodity; B j Represented as the j-th brand feature parameter dataset;

[0009] S3: Perform grey correlation analysis on data sequence F and data sequence B to obtain the grey correlation between the i-th commodity characteristic parameter and the j-th brand characteristic parameter. The specific process includes the following steps:

[0010] S31: The data values ​​f of the data sequence F are ik and data value b in data sequence B jk Perform standardization processing, the standardization processing formula is:

[0011]

[0012] In the formula, is the mean value of the characteristic parameter of the ith item in the data sequence E; is the mean value of the jth brand characteristic parameter in the data sequence F; λ1 and λ2 are the types of product characteristic parameters and brand characteristic parameters respectively; n is the data volume, and the standardized data f' is obtained. ik and b' jk , where f ik It is represented as the kth data value of the characteristic parameter of the i-th commodity in the data sequence F; b jk Represented as the kth data value of the jth brand feature parameter in data sequence B;

[0013] S32: Calculate the correlation coefficient between all data points in data sequence B and each commodity characteristic parameter. The calculation formula is:

[0014]

[0015] In the formula, r jk It is expressed as the correlation coefficient between the kth data value of the jth brand characteristic parameter in the data sequence B and the product characteristic parameter; ρ is a constant coefficient, and the value range of ρ is (0,1), usually ρ=0.5; Δ min and Δ max They are the minimum difference between the two levels and the maximum difference between the two levels of the standardized data of the brand characteristic parameters and the product characteristic parameters, and the calculation formulas are:

[0016] Δ min =min i (min k (|f' ik -b' jk |));

[0017] Δ max =max i (max k (|f' ik -b' jk |));

[0018] In the formula, min(min(·)) means first taking the minimum value of all factors in (·) and then taking the minimum value among all minimum values; max(max(·)) means first taking the maximum value of all factors in (·) and then taking the maximum value among all maximum values;

[0019] S33: According to the obtained correlation coefficient r jk , calculate the grey correlation R between the i-th commodity characteristic parameter and the j-th brand characteristic parameter ij , the calculation formula is:

[0020]

[0021] S4: By comparing the values ​​of the grey correlation degrees, the influence of the product characteristic parameters on the brand characteristic parameters is judged, wherein the influence of the product characteristic parameters on the brand characteristic parameters is proportional to the grey correlation value between the product characteristic parameters and the brand characteristic parameters;

[0022] S5: Based on the impact judgment results, formulate a strategy to improve the commodity characteristic parameters of retail commodities;

[0023] The method further comprises the following steps:

[0024] A quantitative evaluation model for the individual brand characteristics of the retail products to be analyzed is constructed, and the quantitative evaluation values ​​of the individual brand characteristics of the retail products to be analyzed in different periods are calculated according to the model, where the expression of the model is:

[0025]

[0026] In the formula, q jv It is represented as the quantitative evaluation value of the jth brand feature of the retail product to be analyzed in the vth period; It is represented as the sampling mean of the characteristic parameter of the ith item of the retail commodity to be analyzed in the vth period; is represented as the weight of the i-th product feature, and v=1,2,...,V;wherein, the weight of the feature of the i-th item The method for determining includes the following steps:

[0027] Get the grey correlation between the i-th commodity characteristic parameter and the j-th brand characteristic parameter of the retail commodity to be analyzed in the v-th period, denoted as

[0028] The obtained grey relational degree The values ​​are normalized, and the normalization formula is: in, is the normalized grey relational degree value;

[0029] The normalized grey relational value As the weight of the feature of the i-th product,

[0030] The method further comprises:

[0031] A quantitative evaluation model for the comprehensive brand characteristics of the retail products to be analyzed is constructed, and the quantitative evaluation values ​​of the comprehensive brand characteristics of the retail products to be analyzed in different periods are calculated according to the model, where the expression of the model is:

[0032]

[0033] In the formula, Q v It is expressed as the quantitative evaluation value of the comprehensive brand characteristics of the retail products to be analyzed in the vth period; is represented as the weight of the j-th brand feature, and

[0034] The present invention has the following beneficial effects:

[0035] Compared with the prior art, the technical solution of the present invention obtains commodity characteristic parameters and brand characteristic parameters of retail commodities in different periods, constructs data sequence F and data sequence B according to the obtained characteristic parameters, performs grey correlation analysis on data sequence F and data sequence B, obtains the grey correlation degree between the i-th commodity characteristic parameter and the j-th brand characteristic parameter, judges the influence degree of commodity characteristic parameters on brand characteristic parameters by comparing the numerical values ​​of each grey correlation degree, formulates commodity characteristic parameter improvement strategy for retail commodities according to the judgment result of the influence degree, adopts big data technology to analyze the factors and degree of influence on the brand effect of retail commodities, thereby improving the product characteristics of retail commodities in a targeted manner, which is beneficial to improving the quality of commodities and improving the brand effect of the enterprise's retail commodities in the consumer market, and provides a scientific management method for commodity brands in the retail industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flow chart of the retail brand management method based on big data analysis of the present invention;

[0037] Figure 2 Schematic diagram of the process for quantitative evaluation of brand effect value for this plan. DETAILED DESCRIPTION

[0038] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0039] Example 1

[0040] In this embodiment, a certain brand of retail food on an online shopping platform is taken as an example to illustrate this solution. Figure 1 As shown, the specific implementation process of the technical solution of the present invention includes the following steps:

[0041] Step 1: Obtain the commodity characteristic parameters and brand characteristic parameters of the retail food on the online shopping platform at different times through web crawler technology;

[0042] It should be noted that the commodity characteristic parameters of retail food include food sales parameters, sensory indicators, physical and chemical indicators and microbiological indicators, etc., which may be some quantitative indicators such as the selling price, quality grade, taste grade (sweetness / spiciness / saltiness, etc.), content of certain substances (additives / flavor seasonings, etc.) of the commodity; the brand characteristic parameters of retail food are parameter types that can reflect the brand effect of the retail food, for example, they may be the repurchase rate, favorable comment rate and sales volume of the commodity on the online shopping platform. When the repurchase rate, favorable comment rate and sales volume of such retail food are higher, it means that the brand effect of the commodity is better. Therefore, in this embodiment, we use the selling price, quality grade and taste grade of the commodity as the commodity characteristic parameters, wherein the quality grade is proportional to the product quality, and the repurchase rate, favorable comment rate and sales volume of the commodity on the online shopping platform are used as brand characteristic parameters for explanation;

[0043] Step 2: Construct data sequence F and data sequence B according to the acquired characteristic parameters, where F = {F1, F2, ..., F i}, B={B1,B2,...,B j}, F i Represented as the characteristic parameter data set of the i-th commodity; B j Represented as the j-th brand feature parameter dataset;

[0044] Step 3: Perform grey correlation analysis on data series F and data series B to obtain the grey correlation between the i-th commodity characteristic parameter and the j-th brand characteristic parameter. The specific process includes the following steps:

[0045] S31: The data values ​​f of the data sequence F are ik and data value b in data sequence B jk Perform standardization to obtain standardized data f' ik and b' jk , where f ik It is represented as the kth data value of the characteristic parameter of the i-th commodity in the data sequence F; b jk It is represented as the kth data value of the jth brand characteristic parameter in the data sequence B. The standardization formula is:

[0046]

[0047] In the formula, is the mean value of the characteristic parameter of the ith item in the data sequence E; is the mean value of the j-th brand characteristic parameter in the data sequence F; n is the data volume, λ1 and λ2 are the types of commodity characteristic parameters and brand characteristic parameters, respectively. In this embodiment, λ1=λ2=3, then the above formula is specifically:

[0048]

[0049] S32: Calculate the correlation coefficient between all data points in data sequence B and each commodity characteristic parameter. The calculation formula is:

[0050]

[0051] In the formula, r jk It is expressed as the correlation coefficient between the kth data value of the jth brand characteristic parameter in the data sequence B and the product characteristic parameter; ρ is a constant coefficient, and the value range of ρ is (0,1), usually ρ=0.5; Δ min and Δ max They are the minimum difference between the two levels and the maximum difference between the two levels of the standardized data of the brand characteristic parameters and the product characteristic parameters, and the calculation formulas are:

[0052] Δ min =min i (min k (|f' ik -b' jk |));

[0053] Δ max =max i (max k (|f' ik -b' jk |));

[0054] In the formula, min(min(·)) means first taking the minimum value of all factors in (·) and then taking the minimum value among all minimum values; max(max(·)) means first taking the maximum value of all factors in (·) and then taking the maximum value among all maximum values;

[0055] S33: According to the obtained correlation coefficient r jk , calculate the grey correlation R between the i-th commodity characteristic parameter and the j-th brand characteristic parameter ij , the calculation formula is:

[0056] Step 4: By comparing the values ​​of each grey correlation degree, the influence of the product characteristic parameters on the brand characteristic parameters is judged. It should be noted that the influence of the product characteristic parameters on the brand characteristic parameters is proportional to the grey correlation value between the product characteristic parameters and the brand characteristic parameters, that is, by obtaining the values ​​of each grey correlation degree, the types of product characteristic parameters that influence each brand characteristic parameter can be determined respectively;

[0057] Step 5: Based on the impact judgment results, formulate a strategy to improve the commodity characteristic parameters of retail commodities;

[0058] It should be noted that, for example, the types of product characteristic parameters that have the greatest impact on the favorable review rate calculated through the above steps are, from low to high, the product's selling price, quality grade, and taste grade. This means that the product's selling price has the greatest impact on the favorable review rate of the retail food on the online shopping platform, followed by the product's quality grade, and then the product's taste grade. If the company wants to increase the favorable review frequency of the retail product on the online shopping platform, it can first achieve this by adjusting the price, then by adjusting the quality grade in the product production process, and then by adjusting the taste grade in the product production process.

[0059] Through the above scheme, big data technology is used to analyze the factors and extent that affect the brand effect of retail products, so as to improve the product characteristics of retail products in a targeted manner, which is conducive to improving the quality of products and improving the brand effect of the company's retail products in the consumer market, and provides a scientific management method for retail product brands.

[0060] Example 2

[0061] In this embodiment, the brand effect value can be quantitatively evaluated through this solution. Taking a certain brand of retail food on an online shopping platform as an example, this solution is explained. Figure 2 As shown, the specific implementation process of the technical solution of the present invention includes the following steps:

[0062] Step 1: Obtain the commodity characteristic parameters and brand characteristic parameters of the retail food on the online shopping platform at different times through web crawler technology;

[0063] Step 2: Construct data sequence F and data sequence B according to the acquired characteristic parameters, where F = {F1, F2, ..., F i}, B={B1,B2,...,B j}, F i Represented as the characteristic parameter data set of the i-th commodity; B j Represented as the j-th brand feature parameter dataset;

[0064] Step 3: Perform grey correlation analysis on data series F and data series B to obtain the grey correlation between the i-th commodity characteristic parameter and the j-th brand characteristic parameter. The specific process includes the following steps:

[0065] S31: The data values ​​f of the data sequence F are ik and data value b in data sequence B jk Perform standardization to obtain standardized data f' ik and b' jk , where f ik It is represented as the kth data value of the characteristic parameter of the i-th commodity in the data sequence F; b jk It is represented as the kth data value of the jth brand characteristic parameter in the data sequence B. The standardization formula is:

[0066]

[0067] In the formula, is the mean value of the characteristic parameter of the ith item in the data sequence E; is the mean value of the j-th brand characteristic parameter in the data sequence F; n is the data volume, λ1 and λ2 are the types of product characteristic parameters and brand characteristic parameters respectively;

[0068] S32: Calculate the correlation coefficient between all data points in data sequence B and each commodity characteristic parameter. The calculation formula is:

[0069]

[0070] In the formula, r jk It is expressed as the correlation coefficient between the kth data value of the jth brand characteristic parameter in the data sequence B and the product characteristic parameter; ρ is a constant coefficient, and the value range of ρ is (0,1), usually ρ=0.5; Δ min and Δ max They are the minimum difference between the two levels and the maximum difference between the two levels of the standardized data of the brand characteristic parameters and the product characteristic parameters, and the calculation formulas are:

[0071] Δ min =min i (min k (|f' ik -b' jk |));

[0072] Δ max =max i (max k (|f' ik -b' jk |));

[0073] In the formula, min(min(·)) means first taking the minimum value of all factors in (·) and then taking the minimum value among all minimum values; max(max(·)) means first taking the maximum value of all factors in (·) and then taking the maximum value among all maximum values;

[0074] S33: According to the obtained correlation coefficient r jk , calculate the grey correlation R between the i-th commodity characteristic parameter and the j-th brand characteristic parameter ij , the calculation formula is:

[0075] Step 4: By comparing the values ​​of each grey correlation degree, the influence of the product characteristic parameters on the brand characteristic parameters is judged. It should be noted that the influence of the product characteristic parameters on the brand characteristic parameters is proportional to the grey correlation value between the product characteristic parameters and the brand characteristic parameters, that is, by obtaining the values ​​of each grey correlation degree, the types of product characteristic parameters that influence each brand characteristic parameter can be determined respectively;

[0076] Step 5: Construct a quantitative evaluation model for the comprehensive brand characteristics of the retail products to be analyzed, and calculate the quantitative evaluation values ​​of the comprehensive brand characteristics of the retail products to be analyzed in different periods according to the model, where the expression of the model is:

[0077]

[0078] In the formula, Q v It is expressed as the quantitative evaluation value of the comprehensive brand characteristics of the retail products to be analyzed in the vth period; is represented as the weight of the j-th brand feature, and

[0079] Among them, q jv It is expressed as the quantitative evaluation value of the j-th brand feature of the retail product to be analyzed in the v-th period, and the calculation formula is:

[0080]

[0081] In the formula, q jv It is represented as the quantitative evaluation value of the jth brand feature of the retail product to be analyzed in the vth period; It is represented as the sampling mean of the characteristic parameter of the ith item of the retail commodity to be analyzed in the vth period; is represented as the weight of the i-th product feature, and v=1,2,...,V;wherein, the weight of the feature of the i-th item The method for determining includes the following steps:

[0082] Get the grey correlation between the i-th commodity characteristic parameter and the j-th brand characteristic parameter of the retail commodity to be analyzed in the v-th period, denoted as

[0083] The obtained grey relational degree The values ​​are normalized, and the normalization formula is: in, is the normalized grey relational degree value;

[0084] The normalized grey relational value As the weight of the feature of the i-th product,

[0085] Through the above solution, the relevant data of retail goods are analyzed using big data technology, which can achieve a quantitative evaluation of the brand effect of retail goods, help to intuitively understand the sales of retail goods on online shopping platforms, and thus assist enterprises in modifying or formulating sales strategies.

[0086] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A retail brand management method based on big data analysis, characterized in that: include: S1: Obtain commodity characteristic parameters and brand characteristic parameters of retail commodities in different periods; S2: Construct data sequence F and data sequence B according to the acquired characteristic parameters, where F = {F1, F2, ..., F i }, B={B1,B2,...,B j }, F i Represented as the characteristic parameter data set of the i-th commodity; B j Represented as the j-th brand feature parameter dataset; S3: Perform grey correlation analysis on data series F and data series B to obtain the grey correlation degree between the i-th commodity characteristic parameter and the j-th brand characteristic parameter; S4: By comparing the values ​​of the grey correlation degrees, the influence of the product characteristic parameters on the brand characteristic parameters is judged; S5: Based on the impact determination results, formulate a strategy to improve the product characteristic parameters of retail products.

2. The retail brand management method based on big data analysis according to claim 1 is characterized in that: The specific process of step S3 includes the following steps: S31: The data values ​​f of the data sequence F are ik and data value b in data sequence B jk Perform standardization to obtain standardized data f' ik and b' jk , where f ik It is represented as the kth data value of the characteristic parameter of the i-th commodity in the data sequence F; b jk Represented as the kth data value of the jth brand feature parameter in data sequence B; S32: Calculate the correlation coefficient between all data points in data sequence B and each commodity characteristic parameter. The calculation formula is: In the formula, r jk It is expressed as the correlation coefficient between the kth data value of the jth brand characteristic parameter in the data sequence B and the product characteristic parameter; ρ is a constant coefficient, and the value range of ρ is (0,1), usually ρ=0.5; Δ min and Δ max They are the minimum difference between the two levels and the maximum difference between the two levels of the standardized data of the brand characteristic parameters and the product characteristic parameters, and the calculation formulas are: D min =min i (min) k (f' ik -b' jk )); Δ max =max i (max k (f' ik -b' jk )); In the formula, min(min(·)) means first taking the minimum value of all factors in (·) and then taking the minimum value among all minimum values; max(max(·)) means first taking the maximum value of all factors in (·) and then taking the maximum value among all maximum values; S33: According to the obtained correlation coefficient r jk , calculate the grey correlation R between the i-th commodity characteristic parameter and the j-th brand characteristic parameter ij , the calculation formula is:

3. The retail brand management method based on big data analysis according to claim 2 is characterized in that: In step S31, the normalization processing formula is: In the formula, is the mean value of the characteristic parameter of the ith item in the data sequence E; is the mean of the j-th brand characteristic parameter in the data sequence F; λ1 and λ2 are the types of product characteristic parameters and brand characteristic parameters respectively; n is the data volume.

4. The retail brand management method based on big data analysis according to claim 1 is characterized in that: The influence of product characteristic parameters on brand characteristic parameters is proportional to the grey correlation value between product characteristic parameters and brand characteristic parameters.

5. The retail brand management method based on big data analysis according to claim 1 is characterized in that: The method further comprises the following steps: A quantitative evaluation model for the individual brand characteristics of the retail products to be analyzed is constructed, and the quantitative evaluation values ​​of the individual brand characteristics of the retail products to be analyzed in different periods are calculated according to the model, where the expression of the model is: In the formula, q jv It is represented as the quantitative evaluation value of the jth brand feature of the retail product to be analyzed in the vth period; It is represented as the sampling mean of the characteristic parameter of the ith item of the retail commodity to be analyzed in the vth period; is represented as the weight of the i-th product feature, and 6. The retail brand management method based on big data analysis according to claim 5 is characterized in that: The weight of the i-th product feature The method for determining includes the following steps: Get the grey correlation between the i-th commodity characteristic parameter and the j-th brand characteristic parameter of the retail commodity to be analyzed in the v-th period, denoted as The obtained grey relational degree The values ​​are normalized, and the normalization formula is: in, is the normalized grey relational degree value; The normalized grey relational value As the weight of the feature of the i-th product, 7. The retail brand management method based on big data analysis according to claim 5 is characterized in that: The method further comprises: A quantitative evaluation model for the comprehensive brand characteristics of the retail products to be analyzed is constructed, and the quantitative evaluation values ​​of the comprehensive brand characteristics of the retail products to be analyzed in different periods are calculated according to the model, where the expression of the model is: In the formula, Q v It is expressed as the quantitative evaluation value of the comprehensive brand characteristics of the retail products to be analyzed in the vth period; is represented as the weight of the j-th brand feature, and

Images