Holographic diagnosis method for fast moving consumer goods brands based on deep mining

Abstract

The invention discloses a holographic diagnosis method for fast moving consumer goods brands based on deep mining, and relates to the technical field of big data. In order to solve the problem that brand cultivation and evaluation mechanisms of enterprises are imperfect, the adopted scheme comprises the steps that sales data of different fast moving consumer goods brands are collected, index data are extracted from the sales data, and a brand comprehensive competitiveness evaluation index system containing first-level indexes and second-level indexes is constructed; based on the evaluation index system, in combination with the positive and negative correlation between the secondary indexes and competitiveness, performing standardized conversion and interval processing on the secondary indexes, then calculating the weights of the secondary indexes, further outputting the scores of the primary indexes, calculating the weights of the primary indexes, and outputting the comprehensive competitiveness score of a certain fast moving consumer goods brand; and based on the score, dividing different price section thresholds and competitive power research and judgment are realized, competitive product positioning is performed on a single fast moving consumer goods brand, and comparative analysis of the single fast moving consumer goods brand and competitive products is realized. The system and the method are used for systematically managing fast moving consumer goods brands.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a holographic diagnosis method for fast-moving consumer goods brands based on deep mining. Background Art

[0002] With increasingly fierce competition in the fast-moving consumer goods (FMCG) market and the diversification and personalization of consumer demands, brand management is shifting from traditional experience-driven to data-driven. Particularly in the context of digital transformation, retail companies are placing higher demands on the efficiency of brand health assessment, market performance diagnosis, and problem identification. As a key brand management tool, holographic diagnostics has been gradually adopted within the industry.

[0003] Currently, both domestic and international research and practice in the field of holographic diagnosis of fast-moving consumer goods (FMCG) brands are underway to varying degrees. Foreign institutions such as Nielsen, Interbrand, and BASES utilize advanced technologies such as big data, artificial intelligence, and neuroscience, combined with multi-dimensional indicator systems to assess brand value and analyze consumer behavior. These institutions possess strong data integration and model-building capabilities. Domestically, leveraging the big data resources of e-commerce platforms and internet companies, they have developed data analysis tools such as Alibaba's "Business Advisor," achieving significant results in brand operations monitoring and market trend forecasting. The industry is evolving toward data-driven, intelligent, and systematic brand diagnosis, but it still faces numerous challenges, particularly in the dynamic responsiveness of diagnostic models, business adaptability, and interpretability of problems.

[0004] The technical problems existing in the prior art are as follows: 1. Lack of a systematic diagnostic framework. Existing technologies often focus on analyzing data from a single dimension or a specific segment, such as sales data, consumer preferences, and brand communication effectiveness. They fail to form a systematic diagnostic mechanism covering the entire chain, from procurement to sales and consumption, making it difficult to fully reflect a brand's overall competitiveness.

[0005] 2. Irrational weight allocation and poor business interpretability. Some diagnostic methods use subjective weighting methods (such as AHP), which are heavily influenced by expert experience and lack objective evidence. Others rely solely on statistical algorithms (such as principal component analysis and entropy), which, while objective, fail to reflect business logic. This results in model weight allocation that lacks business interpretability and is difficult to guide specific business actions.

[0006] 3. Unclear identification of weaknesses makes diagnosis difficult to implement. Existing diagnostic tools often remain at the level of "discovering problems" and lack a mechanism to drill down to the root causes. They are unable to accurately identify specific secondary indicators or even operational levels, thus limiting the application of diagnostic results in actual marketing, resource allocation, and other scenarios.

[0007] The root causes of these problems are: on the one hand, the design of traditional diagnostic models lacks comprehensive consideration of the perspectives of multiple stakeholders (suppliers, retailers, and consumers); on the other hand, advanced intelligent algorithms and business experience are not fully integrated into the model construction process, resulting in inaccurate and impractical diagnostic results. Summary of the Invention

[0008] In order to accurately evaluate the performance of fast-moving consumer goods, diagnose problems in the brand development process, and solve the problem of imperfect brand cultivation and evaluation mechanisms of enterprises, the present invention provides a holographic diagnosis method for fast-moving consumer goods brands based on deep mining.

[0009] The present invention provides a holographic diagnosis method for fast-moving consumer goods brands based on deep mining, and the technical solutions adopted to solve the above technical problems are as follows: A holographic diagnosis method for fast-moving consumer goods brands based on deep mining, comprising the following steps: S1. For different FMCG brands, collect sales information, store sales data, consumer purchase data, and store purchase order data from the company's cities and regions, extract indicator data from them, and summarize and calculate them by month, price segment, and brand dimension; S2. Based on the extracted indicator data, construct a comprehensive brand competitiveness evaluation indicator system consisting of primary indicators and secondary indicators, wherein a primary indicator contains at least one secondary indicator, and a secondary indicator can be subordinate to at most one primary indicator; S3. Based on the comprehensive brand competitiveness evaluation index system and the positive and negative correlations between secondary indicators and the comprehensive competitiveness of FMCG brands, each secondary indicator is standardized and intervalized, ultimately achieving dimensional unification of all secondary indicators, laying the foundation for subsequent quantitative evaluation of comprehensive competitiveness. S4. Based on the data processed in step S3, the weights of the secondary indicators are calculated using the CRITIC algorithm; S5. Perform a weighted operation based on the data processed in step S3 and the weight of the secondary indicator calculated in step S4, and output the score of the primary indicator to which it belongs; S6. Based on the scores of the first-level indicators, the weights of the first-level indicators are calculated by combining the CRITIC algorithm with the AHP algorithm. The first-level indicator scores are then weighted and summarized to output the comprehensive competitiveness score of a FMCG brand. S7. Based on the comprehensive competitiveness score of a FMCG brand, a Gaussian model is used to divide the thresholds of different price segments, thereby further analyzing the competitiveness of the FMCG brand. S8. Based on the competitiveness assessment results of different FMCG brands, position individual FMCG brands as competitors, conduct comparative analysis between individual FMCG brands and their competitors, identify the development shortcomings of FMCG brands, and anchor the focus of FMCG brands.

[0010] Optional, the first-level indicators involved include consumption depth and breadth, consumer loyalty, sales growth, market contribution and customer recognition; Secondary indicators include market penetration rate, per capita sales, per capita sales, month-on-month increase in the number of purchasers, repurchase rate, purchase frequency, churn rate, number of main purchasers, year-on-year growth rate, month-on-month growth rate, average monthly growth rate, sales share, gross profit contribution rate, market share, purchase volume, and purchase area; Among them, market penetration rate, per capita sales and per capita sales belong to the depth and breadth of consumption, the month-on-month number of buyers, repurchase rate, purchase frequency, churn rate and number of main buyers belong to consumer loyalty, the year-on-year growth rate, month-on-month growth rate and average monthly growth rate belong to sales growth, the proportion of sales revenue, gross profit contribution rate and market share belong to market contribution, and the purchase volume and purchase scope belong to customer recognition.

[0011] Preferably, the fifteen secondary indicators involved, including market penetration rate, per capita sales, per capita sales, month-on-month increase in the number of purchasers, repurchase rate, purchase frequency, number of main purchasers, year-on-year growth rate, month-on-month growth rate, average monthly growth rate, sales share, gross profit contribution rate, market share, procurement volume and procurement area, are all positively correlated with the comprehensive competitiveness of FMCG brands; There is a negative correlation between churn rate and the overall competitiveness of FMCG brands.

[0012] Optionally, in step S3, when there is a positive correlation between the secondary indicators and the comprehensive competitiveness of the FMCG brand, the formula for standardizing each secondary indicator is as follows: ; When there is a negative correlation between the secondary indicators and the comprehensive competitiveness of FMCG brands, the formula for standardizing each secondary indicator is as follows: ; Where, represents the original data value of the i-th FMCG brand on the j-th secondary indicator; represents the minimum value of the original data of all FMCG brands on the jth secondary indicator; It represents the maximum value of the original data of all FMCG brands on the jth secondary indicator; It represents the result of the standardized transformation of the j-th secondary indicator of the i-th FMCG brand, and its value range is [0,1]; The formula for interval processing of the secondary indicators after standardization conversion is as follows: ; Where, It represents the result of the standardized transformation of the j-th secondary indicator of the i-th FMCG brand, and its value range is [0,1]; It represents the final score of the j-th secondary indicator of the i-th fast-moving consumer goods brand after normalization and interval processing, and its value range is [50,100].

[0013] Further optionally, step S4 specifically includes: S4.1. For any FMCG brand, calculate the standard deviation of its j-th secondary indicator. , measures the comparative strength of a single secondary indicator; S4.2. Calculate the correlation coefficient between any two secondary indicators , construct the correlation coefficient matrix R to measure the correlation between the secondary indicators; S4.3. Calculate the conflict C between any two secondary indicators, C = 1- ; S4.4. Calculate the weight of the j-th secondary indicator by combining contrast intensity and conflict : ; In the formula, n represents the number of secondary indicators; It represents the correlation coefficient between the j-th secondary indicator and the k-th secondary indicator, and both j and k take values from 1 to n; represents the sum of the conflicts between the j-th secondary indicator and all secondary indicators; S4.5. Weight of the jth secondary indicator Normalize and get the final weight .

[0014] Optionally, step S5 is performed to calculate the score of the Jth first-level indicator for the i-th FMCG brand using the following formula: : ; In the formula, n represents the number of secondary indicators contained in the current primary indicator J; Represents the normalized weight value of the j-th secondary indicator, with a value range of [0,1]; It represents the final score of the j-th secondary indicator of the i-th fast-moving consumer goods brand after normalization and interval processing, and its value range is [50,100].

[0015] Further optionally, step S6 specifically includes: S6.1. For the i-th FMCG brand, based on its J-th primary indicator score , perform the following operations to output the weight of its J-th first-level indicator : S6.1.1. Calculate the standard deviation of the Jth first-level index , measures the comparative strength of a single first-level indicator; S6.1.2. Calculate the correlation coefficient between any two primary indicators , construct the correlation coefficient matrix R to measure the correlation between the secondary indicators; S6.1.3. Calculate the conflict C between any two first-level indicators, C = 1- ; S6.1.4. Calculate the weight of the Jth first-level indicator by combining contrast intensity and conflict. : ; Where N represents the number of first-level indicators; It represents the correlation coefficient between the Jth first-level indicator and the Kth first-level indicator, and both J and K take values from 1 to N; It represents the sum of the conflicts between the J-th first-level indicator and all first-level indicators; S6.1.5. Weight of the Jth first-level indicator Normalize and get the final weight ; S6.2. Based on the Jth primary indicator score of the i-th FMCG brand , use AHP algorithm to output the weight of the J-th first-level indicator : First, collect the importance rankings of each first-level indicator from business experts to generate a judgment matrix. Then, use the sum-product method to calculate the maximum eigenvalue and corresponding eigenvector of the judgment matrix. Finally, perform a consistency test on the judgment matrix and normalize the eigenvector to generate weights. ; S6.3. Weight of the Jth first-level indicator output in step S6.1 and the weight of the Jth first-level indicator output in step S6.2 Average weighting to generate the final weight of the J-th first-level indicator , ; S6.4. Final weight based on the Jth first-level indicator , the score of the J-th first-level indicator Perform weighted aggregation and output the comprehensive competitiveness score of fast-moving consumer goods brands.

[0016] Preferably, step S6.4 is executed, and the comprehensive competitiveness score of the i-th FMCG brand is output using the following formula: : ; Where N represents the number of first-level indicators; It represents the final weight of the i-th FMCG brand in the J-th first-level indicator, It represents the score of the i-th FMCG brand under the J-th first-level indicator.

[0017] Further optionally, step S7 specifically includes: S7.1. Calculate the average comprehensive competitiveness scores of FMCG brands in different price segments ; S7.2. Calculate the standard deviation of the comprehensive competitiveness scores of FMCG brands in different price segments ; S7.3, set the threshold range (50, )、[ , ]and[ , 100), conduct competitiveness assessment of fast-moving consumer goods brands in different price segments, and obtain corresponding assessment results of three types: emerging products, potential products, and leading products.

[0018] Further optionally, step S8 specifically includes: S8.1. Output brand research and assessment results for target FMCG brands that require diagnosis; S8.2. Brands with the same research and judgment results as the target FMCG brand in the same price segment are defined as competitors; S8.3. Compare and analyze the primary indicators of the target FMCG brand and competitors to identify the development shortcomings of the target FMCG brand, and further explore and identify the shortcomings of the secondary indicators.

[0019] The holographic diagnosis method of fast-moving consumer goods brands based on deep mining of the present invention has the following beneficial effects compared with the existing technology: 1. Based on the goal of holographic diagnosis of FMCG brands, this invention integrates business data from the entire chain of procurement, sales, and consumption to construct a comprehensive brand competitiveness evaluation index system consisting of primary and secondary indicators. A reasonable algorithm is used to calculate the weights of indicators at different levels. Weighted calculations are used to generate comprehensive competitiveness scores for FMCG brands. A Gaussian model is used for brand analysis and judgment. Competitive product positioning is performed, and a comparative analysis of target FMCG brands and competing products is completed. This quantifies the comprehensive performance of all FMCG brands, facilitating the systematic management and guidance of FMCG brands. 2. The present invention adopts differentiated algorithms to calculate indicator weights for indicators at different levels. The secondary indicator weights are realized by using a fully automated CRITIC algorithm, while the primary indicator weights are realized by combining the AHP algorithm with CRITIC based on the experience of business experts. This makes the weight calculation method more rational and more business-interpretable. 3. The present invention achieves targeted comparative analysis between target FMCG brands and competing products by locating competing products. By comparing and analyzing the target FMCG brands and competing products based on primary indicators, the weak links are identified. The secondary indicators under the primary indicators are then analyzed to identify specific problematic indicators, thereby providing more targeted guidance for business actions, enabling brand cultivation, and improving brand marketing efficiency. 4. In terms of brand diagnosis, the present invention forms a closed-loop brand health assessment and problem diagnosis system from macro to micro, which can improve the systematic and scientific nature of brand management; in practical application, it can truly realize the refined brand management of "problems can be located and improvements have directions", and improve brand operation efficiency and market responsiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Attachment Figure 1 is a flow chart of a method according to an embodiment of the present invention; Attachment Figure 2 This is a schematic diagram of the distribution of consumer competitiveness of different fast-moving consumer goods brands assumed in the embodiment of the present invention; Attachment Figure 3 4 is a schematic diagram of comparative analysis between brand 4 assumed in the embodiment of the present invention and its competitors. DETAILED DESCRIPTION

[0021] In order to make the technical solution, the technical problems solved and the technical effects of the present invention more clear, the technical solution of the present invention is clearly and completely described below in conjunction with specific embodiments.

[0022] Example: Refer to the attached Figure 1 This embodiment proposes a holographic diagnosis method for fast-moving consumer goods brands based on deep mining, which includes the following steps: S1. For different FMCG brands, collect sales information, store sales data, consumer purchase data, and store purchase order data in the city and region of the enterprise, extract indicator data from them, and summarize and calculate them by month, price segment, and brand dimension.

[0023] During the specific implementation, various data including month (MONTH), brand (GODSNAME), price range (PRICE), sales (SALEMNY), gross profit (PROFITMNY), number of consumers purchasing (CSQT), number of consumers purchasing (CSNUM), purchase quantity (INQT), number of purchases (INNUM) and so on are collected.

[0024] S2. Based on the extracted indicator data, they are classified into primary indicators and secondary indicators according to discussions among business experts. Then, a brand comprehensive competitiveness evaluation indicator system consisting of primary indicators and secondary indicators is constructed. A primary indicator contains at least one secondary indicator, and a secondary indicator can at most be subordinate to the same primary indicator.

[0025] During the specific implementation, based on the extracted indicator data, it is classified into five categories of first-level indicators and sixteen second-level indicators according to discussions by business experts.

[0026] The first-level indicators include five categories: consumption depth and breadth, consumer loyalty, sales growth, market contribution and customer recognition.

[0027] Secondary indicators include market penetration rate, per capita sales, per capita sales, month-on-month increase in the number of purchasers, repurchase rate, purchase frequency, churn rate, number of main purchasers, year-on-year growth rate, month-on-month growth rate, average monthly growth rate, sales share, gross profit contribution rate, market share, purchase volume and purchase area.

[0028] Among them, market penetration rate, per capita sales and per capita sales belong to the depth and breadth of consumption, the month-on-month number of buyers, repurchase rate, purchase frequency, churn rate and number of main buyers belong to consumer loyalty, the year-on-year growth rate, month-on-month growth rate and average monthly growth rate belong to sales growth, the proportion of sales revenue, gross profit contribution rate and market share belong to market contribution, and the purchase volume and purchase scope belong to customer recognition.

[0029] The fifteen secondary indicators, namely market penetration rate, per capita sales, per capita sales, month-on-month growth in the number of purchasers, repurchase rate, purchase frequency, number of main purchasers, year-on-year growth rate, month-on-month growth rate, average monthly growth rate, sales share, gross profit contribution rate, market share, purchase volume and purchase area, are all positively correlated with the overall competitiveness of FMCG brands. There is a negative correlation between churn rate and the overall competitiveness of FMCG brands.

[0030] It should be added that market penetration refers to the ratio of the number of consumers who actually purchase a FMCG brand in the target market to the total number of potential consumers in that market, reflecting the popularity of the FMCG brand in the market. Per capita sales refers to the average sales amount per buyer of a FMCG brand during a set period. It is calculated as total sales divided by the number of buyers and reflects the contribution of a single consumer to sales performance. Average sales per person refers to the average number of times each buyer purchases a FMCG brand during a set period. The calculation formula is total number of purchases divided by the number of buyers, reflecting the consumer's purchase frequency. The month-on-month change in the number of buyers refers to the change in the number of buyers in this period compared to the number of buyers in the previous period. It is usually expressed as a percentage and is calculated as (number of buyers in this period - number of buyers in the previous period) ÷ number of buyers in the previous period × 100%. It is used to observe the increase or decrease trend of the number of buyers in the short term. The repurchase rate refers to the proportion of repeat customers who purchase a particular FMCG brand again over a set period of time. It is calculated as the number of repeat customers divided by the total number of customers × 100% and reflects customer recognition and loyalty to the product or service. Purchase frequency refers to the total number of orders placed by consumers for a particular FMCG brand within a set period, reflecting the frequency of consumer demand for the FMCG brand. Churn rate refers to the ratio of customers who stop purchasing a particular FMCG brand to the total number of original customers within a set period. It is calculated as the number of churned customers in this period divided by the total number of customers in the previous period. It is used to measure customer retention. The number of churned customers in this period is the number of consumers who purchased a particular FMCG brand in the previous period but did not purchase it in the current period. Main buyers refer to the number of key, core purchasing groups among customers who purchase a particular FMCG brand. These groups are typically those with high purchase volume or frequency, and play a major role in supporting product sales. Year-on-year growth rate refers to the percentage increase in sales during a certain period this year compared to the same period last year. It is calculated as (sales during a certain period this year - sales during the same period last year) ÷ sales during the same period last year × 100%. This is used to eliminate the impact of cyclical factors such as seasonality and to observe long-term growth trends. Month-over-month growth rate refers to the percentage increase in sales between the current period and the previous period. It is calculated as (current period sales - previous period sales) ÷ previous period sales × 100% and is used to reflect the rate of change in sales over the short term. Average monthly growth rate refers to the average monthly growth rate of monthly sales within a set period. It is calculated by averaging the year-on-year growth rates of each month and is used to measure the stable growth of indicators within a set period. Sales share refers to the proportion of a particular FMCG brand's sales to the total sales of similar FMCG brands. The calculation formula is: sales of a particular FMCG brand / total sales of similar FMCG brands × 100%, reflecting the FMCG brand's contribution to the sales of similar FMCG brands. Gross profit contribution rate refers to the proportion of a particular FMCG brand's gross profit in the total gross profit of similar FMCG brands in the market. The calculation formula is: gross profit of a particular FMCG brand / total gross profit of similar FMCG brands in the market × 100%. It reflects the contribution of the FMCG brand to the profits of similar FMCG brands. Market share refers to the proportion of a FMCG brand's sales volume in the total sales volume of similar FMCG brands in the market, reflecting the brand's competitive position in the market. Purchase volume refers to the total amount of a particular FMCG brand purchased by a retailer within a set period, usually expressed in units (e.g., pieces, tons, etc.) to reflect the scale of purchases; Purchasing volume refers to the total number of times all retailers purchase a certain FMCG brand within a set date, reflecting the retailers' recognition of the FMCG brand.

[0031] S3. Based on the comprehensive brand competitiveness evaluation index system, combined with the positive and negative correlation between the secondary indicators and the comprehensive competitiveness of fast-moving consumer goods brands, each secondary indicator is standardized and intervalized, ultimately achieving dimensional unification of all secondary indicators, laying the foundation for subsequent quantitative evaluation of comprehensive competitiveness.

[0032] When there is a positive correlation between the secondary indicators and the comprehensive competitiveness of FMCG brands, the formula for standardizing each secondary indicator is as follows: ; When there is a negative correlation between the secondary indicators and the comprehensive competitiveness of FMCG brands, the formula for standardizing each secondary indicator is as follows: ; Where, represents the original data value of the i-th FMCG brand on the j-th secondary indicator; represents the minimum value of the original data of all FMCG brands on the jth secondary indicator; It represents the maximum value of the original data of all FMCG brands on the jth secondary indicator; It represents the result of the standardized transformation of the j-th secondary indicator of the i-th FMCG brand, and its value range is [0,1]; The formula for interval processing of the secondary indicators after standardization conversion is as follows: ; Where, It represents the result of the standardized transformation of the j-th secondary indicator of the i-th FMCG brand, and its value range is [0,1]; It represents the final score of the j-th secondary indicator of the i-th fast-moving consumer goods brand after normalization and interval processing, and its value range is [50,100].

[0033] S4. Based on the data processed in step S3, the CRITIC algorithm is used to calculate the weights of the secondary indicators. This process specifically includes: S4.1. For any FMCG brand, calculate the standard deviation of its j-th secondary indicator. , measures the comparative strength of a single secondary indicator; S4.2. Use Pearson correlation coefficient to calculate the correlation coefficient between any two secondary indicators , construct the correlation coefficient matrix R to measure the correlation between the secondary indicators; S4.3. Calculate the conflict C between any two secondary indicators, C = 1- ; S4.4. Calculate the weight of the j-th secondary indicator by combining contrast intensity and conflict : ; In the formula, n represents the number of secondary indicators; It represents the correlation coefficient between the j-th secondary indicator and the k-th secondary indicator, and both j and k take values from 1 to n; represents the sum of the conflicts between the j-th secondary indicator and all secondary indicators; S4.5. Weight of the jth secondary indicator Normalize and get the final weight .

[0034] It should be added that CRITIC stands for CriteriaImportanceThroughIntercriteriaCorrelation, which means in Chinese a weight determination method based on the correlation between indicators. It is an objective weighting method that calculates weights by analyzing the comparative strength of indicators (the degree of data fluctuation) and the conflict between indicators (the size of the correlation) to avoid interference from subjective factors.

[0035] S5: Based on the data processed in step S3 and the weights of the secondary indicators calculated in step S4, a weighted operation is performed to output the scores of the primary indicators to which they belong. This step specifically includes: For the i-th FMCG brand, use the following formula to calculate the score of its J-th first-level indicator: : ; In the formula, n represents the number of secondary indicators contained in the current primary indicator J; Represents the normalized weight value of the j-th secondary indicator, with a value range of [0,1]; It represents the final score of the j-th secondary indicator of the i-th fast-moving consumer goods brand after normalization and interval processing, and its value range is [50,100].

[0036] S6. Based on the scores of the first-level indicators, the CRITIC algorithm is combined with the AHP algorithm to calculate the weights of the first-level indicators. The first-level indicator scores are weighted and summarized to output the comprehensive competitiveness score of a FMCG brand. This process specifically includes: S6.1. For the i-th FMCG brand, based on its J-th primary indicator score , perform the following operations to output the weight of its J-th first-level indicator : S6.1.1. Calculate the standard deviation of the Jth first-level index , measures the comparative strength of a single first-level indicator; S6.1.2. Calculate the correlation coefficient between any two primary indicators , construct the correlation coefficient matrix R to measure the correlation between the secondary indicators; S6.1.3. Calculate the conflict C between any two first-level indicators, C = 1- ; S6.1.4. Calculate the weight of the Jth first-level indicator by combining contrast intensity and conflict. : ; Where N represents the number of first-level indicators; It represents the correlation coefficient between the Jth first-level indicator and the Kth first-level indicator, and both J and K take values from 1 to N; It represents the sum of the conflicts between the J-th first-level indicator and all first-level indicators; S6.1.5. Weight of the Jth first-level indicator Normalize and get the final weight ; S6.2. Based on the Jth primary indicator score of the i-th FMCG brand , use AHP algorithm to output the weight of the J-th first-level indicator : First, collect the importance rankings of each first-level indicator from business experts to generate a judgment matrix. Then, use the sum-product method to calculate the maximum eigenvalue and corresponding eigenvector of the judgment matrix. Finally, perform a consistency test on the judgment matrix and normalize the eigenvector to generate weights. ; S6.3. Weight of the Jth first-level indicator output in step S6.1 and the weight of the Jth first-level indicator output in step S6.2 Average weighting to generate the final weight of the J-th first-level indicator , ; S6.4. Final weight based on the Jth first-level indicator , the score of the J-th first-level indicator Perform weighted aggregation and use the following formula to output the comprehensive competitiveness score of the i-th FMCG brand : ; Where N represents the number of first-level indicators; It represents the final weight of the i-th FMCG brand in the J-th first-level indicator, It represents the score of the i-th FMCG brand under the J-th first-level indicator.

[0037] It should be added that AHP (Analytic Hierarchy Process) is a weight determination method that combines subjective judgment with mathematical analysis, by converting experts' qualitative judgment on the importance of indicators into quantitative weights.

[0038] S7. Based on the comprehensive competitiveness score of a FMCG brand, a Gaussian model is used to define thresholds for different price segments, thereby further evaluating the competitiveness of the FMCG brand. Specifically, the following are included: S7.1. Calculate the average comprehensive competitiveness scores of FMCG brands in different price segments ; S7.2. Calculate the standard deviation of the comprehensive competitiveness scores of FMCG brands in different price segments ; S7.3, set the threshold range (50, )、[ , ]and[ , 100), conduct competitiveness assessment of fast-moving consumer goods brands in different price segments, and obtain corresponding assessment results of three types: emerging products, potential products, and leading products.

[0039] S8. Based on the competitiveness analysis of different FMCG brands, position each FMCG brand against its competitors and conduct comparative analysis between the brand and its competitors to identify the brand's developmental shortcomings and focus on its strengths. This process specifically includes: S8.1. Output brand research and assessment results for target FMCG brands that require diagnosis; S8.2. Brands with the same research and judgment results as the target FMCG brand in the same price segment are defined as competitors; S8.3. Compare and analyze the primary indicators of the target FMCG brand and competitors to identify the development shortcomings of the target FMCG brand, and further explore and identify the shortcomings of the secondary indicators.

[0040] Taking a specific fast-moving consumer goods brand A (such as Head & Shoulders shampoo) as an example, perform the above steps in sequence.

[0041] Assume that after executing the above steps S1-S4, the final weights of all secondary indicators of FMCG brand A are calculated, as shown in Table 1 below.

[0042] Table 1: Final weights of all secondary indicators for FMCG brand A

[0043] Continuing with step S5, the scores of the primary indicators for the secondary indicators of FMCG brand A are output. Continuing with step S6, the weights of all primary indicators for FMCG brand A are calculated, and the weighted primary indicator scores are aggregated to output the overall competitiveness score of FMCG brand A. This is shown in Table 2 below.

[0044] Table 2: Primary indicator scores, weights, and comprehensive competitiveness scores of FMCG brand A

[0045] Continuing with step S7, it is assumed that the competitiveness of fast-moving consumer goods brands in different price segments (specifically including 11 price segments) is evaluated. The evaluation results are shown in Table 3 below.

[0046] Table 3: Thresholds and analysis results for different price segments

[0047] Continue to execute step S8, refer to the attached Figure 2 Assume that FMCG brand A is in the 5th price segment, which has 5 leading brands, 18 potential brands, and 2 emerging brands. Assume that brand 4 is the target FMCG brand (FMCG brand A) and its competitors are brand 1, brand 2, and brand 3. Compare brand 4 with one of its competitors (such as brand 1) and identify its development shortcomings, such as Figure 3 As shown in Table 4, Brand 4 has obvious advantages in sales growth, but has obvious shortcomings in purchase frequency, repeat purchases, and the number of main customers. Targeted brand cultivation activities can be organized to address these shortcomings and increase consumer loyalty to the brand.

[0048] Table 4 Comparison results between target FMCG brands and competing products

[0049] In summary, the holographic diagnostic method for FMCG brands based on deep mining proposed in the present invention can quantify the comprehensive performance of all FMCG brands, rationalize the calculation method of indicator weights, and make it more business-interpretable, thereby realizing targeted comparative analysis between target FMCG brands and competing products, thereby improving brand marketing efficiency.

[0050] The above specific examples are used to illustrate the principles and implementation methods of the present invention in detail. These examples are only used to help understand the core technical content of the present invention. Based on the above specific embodiments of the present invention, any improvements and modifications made by those skilled in the art without departing from the principles of the present invention should fall within the scope of patent protection of the present invention.

Claims

1. A holographic diagnosis method for fast-moving consumer goods brands based on deep mining, characterized by: The steps include: S1. For different FMCG brands, collect sales information, store sales data, consumer purchase data, and store purchase order data from the company's cities and regions, extract indicator data from them, and summarize and calculate them by month, price segment, and brand dimension; S2. Based on the extracted indicator data, construct a comprehensive brand competitiveness evaluation indicator system consisting of primary indicators and secondary indicators, wherein a primary indicator contains at least one secondary indicator, and a secondary indicator can be subordinate to at most one primary indicator; S3. Based on the comprehensive brand competitiveness evaluation index system and the positive and negative correlations between secondary indicators and the comprehensive competitiveness of FMCG brands, each secondary indicator is standardized and intervalized, ultimately achieving dimensional unification of all secondary indicators, laying the foundation for subsequent quantitative evaluation of comprehensive competitiveness. S4. Based on the data processed in step S3, the weights of the secondary indicators are calculated using the CRITIC algorithm; S5. Perform a weighted operation based on the data processed in step S3 and the weight of the secondary indicator calculated in step S4, and output the score of the primary indicator to which it belongs; S6. Based on the scores of the first-level indicators, the weights of the first-level indicators are calculated by combining the CRITIC algorithm with the AHP algorithm. The first-level indicator scores are then weighted and summarized to output the comprehensive competitiveness score of a FMCG brand. S7. Based on the comprehensive competitiveness score of a FMCG brand, a Gaussian model is used to divide the thresholds of different price segments to evaluate the competitiveness of the FMCG brand. S8. Based on the competitiveness assessment results of different FMCG brands, position individual FMCG brands as competitors, conduct comparative analysis between individual FMCG brands and their competitors, identify the development shortcomings of FMCG brands, and anchor the focus of FMCG brands.

2. The holographic diagnosis method for fast-moving consumer goods brands based on deep mining according to claim 1 is characterized in that: The first-level indicators include five categories: consumption depth and breadth, consumer loyalty, sales growth, market contribution and customer recognition; Secondary indicators include market penetration rate, per capita sales, per capita sales, month-on-month increase in the number of purchasers, repurchase rate, purchase frequency, churn rate, number of main purchasers, year-on-year growth rate, month-on-month growth rate, average monthly growth rate, sales share, gross profit contribution rate, market share, purchase volume, and purchase area; Among them, market penetration rate, per capita sales and per capita sales belong to the depth and breadth of consumption, the month-on-month number of buyers, repurchase rate, purchase frequency, churn rate and number of main buyers belong to consumer loyalty, the year-on-year growth rate, month-on-month growth rate and average monthly growth rate belong to sales growth, the proportion of sales revenue, gross profit contribution rate and market share belong to market contribution, and the purchase volume and purchase scope belong to customer recognition.

3. The holographic diagnosis method for fast-moving consumer goods brands based on deep mining according to claim 2 is characterized in that: The fifteen secondary indicators, namely market penetration rate, per capita sales, per capita sales, month-on-month growth in the number of purchasers, repurchase rate, purchase frequency, number of main purchasers, year-on-year growth rate, month-on-month growth rate, average monthly growth rate, sales share, gross profit contribution rate, market share, purchase volume and purchase area, are all positively correlated with the overall competitiveness of FMCG brands. There is a negative correlation between churn rate and the overall competitiveness of FMCG brands.

4. The holographic diagnosis method for fast-moving consumer goods brands based on deep mining according to claim 3 is characterized in that: Execute step S3. When the secondary indicators are positively correlated with the comprehensive competitiveness of FMCG brands, the formula for standardizing each secondary indicator is as follows: ； When there is a negative correlation between the secondary indicators and the comprehensive competitiveness of FMCG brands, the formula for standardizing each secondary indicator is as follows: ； Where, represents the original data value of the i-th FMCG brand on the j-th secondary indicator; represents the minimum value of the original data of all FMCG brands on the jth secondary indicator; It represents the maximum value of the original data of all FMCG brands on the jth secondary indicator; It represents the result of the standardized transformation of the j-th secondary indicator of the i-th FMCG brand, and its value range is [0,1]; The formula for interval processing of the secondary indicators after standardization conversion is as follows: ； Where, It represents the result of the standardized transformation of the j-th secondary indicator of the i-th FMCG brand, and its value range is [0,1]; It represents the final score of the j-th secondary indicator of the i-th fast-moving consumer goods brand after normalization and interval processing, and its value range is [50,100].

5. The holographic diagnosis method for fast-moving consumer goods brands based on deep mining according to claim 4 is characterized in that: The step S4 specifically includes: S4.

1. For any FMCG brand, calculate the standard deviation of its j-th secondary indicator. , measures the comparative strength of a single secondary indicator; S4.

2. Calculate the correlation coefficient between any two secondary indicators , construct the correlation coefficient matrix R to measure the correlation between the secondary indicators; S4.

3. Calculate the conflict C between any two secondary indicators, C = 1- ; S4.

4. Calculate the weight of the j-th secondary indicator by combining contrast intensity and conflict : ； In the formula, n represents the number of secondary indicators; It represents the correlation coefficient between the j-th secondary indicator and the k-th secondary indicator, and both j and k take values from 1 to n; represents the sum of the conflicts between the j-th secondary indicator and all secondary indicators; S4.

5. Weight of the jth secondary indicator Normalize and get the final weight .

6. The holographic diagnosis method for fast-moving consumer goods brands based on deep mining according to claim 5 is characterized in that: Execute step S5 and calculate the score of the Jth first-level indicator for the i-th FMCG brand using the following formula: : ； In the formula, n represents the number of secondary indicators contained in the current primary indicator J; Represents the normalized weight value of the j-th secondary indicator, with a value range of [0,1]; It represents the final score of the j-th secondary indicator of the i-th fast-moving consumer goods brand after normalization and interval processing, and its value range is [50,100].

7. The holographic diagnosis method for fast-moving consumer goods brands based on deep mining according to claim 6 is characterized in that: The step S6 specifically includes: S6.

1. For the i-th FMCG brand, based on its J-th primary indicator score , perform the following operations to output the weight of its J-th first-level indicator : S6.1.

1. Calculate the standard deviation of the Jth first-level index , measures the comparative strength of a single first-level indicator; S6.1.

2. Calculate the correlation coefficient between any two primary indicators , construct the correlation coefficient matrix R to measure the correlation between the secondary indicators; S6.1.

3. Calculate the conflict C between any two first-level indicators, C = 1- ; S6.1.

4. Calculate the weight of the Jth first-level indicator by combining contrast intensity and conflict. : ； Where N represents the number of first-level indicators; It represents the correlation coefficient between the Jth first-level indicator and the Kth first-level indicator, and both J and K take values from 1 to N; It represents the sum of the conflicts between the J-th first-level indicator and all first-level indicators; S6.1.

5. Weight of the Jth first-level indicator Normalize and get the final weight ; S6.

2. Based on the Jth primary indicator score of the i-th FMCG brand , use AHP algorithm to output the weight of the J-th first-level indicator : First, collect the importance rankings of each first-level indicator from business experts to generate a judgment matrix. Then, use the sum-product method to calculate the maximum eigenvalue and corresponding eigenvector of the judgment matrix. Finally, perform a consistency test on the judgment matrix and normalize the eigenvector to generate weights. ; S6.

3. Weight of the Jth first-level indicator output in step S6.1 and the weight of the Jth first-level indicator output in step S6.2 Average weighting to generate the final weight of the J-th first-level indicator , ; S6.

4. Final weight based on the Jth first-level indicator , the score of the J-th first-level indicator Perform weighted aggregation and output the comprehensive competitiveness score of fast-moving consumer goods brands.

8. The holographic diagnosis method for fast-moving consumer goods brands based on deep mining according to claim 7 is characterized in that: Execute step S6.4 and use the following formula to output the comprehensive competitiveness score of the i-th FMCG brand: : ； Where N represents the number of first-level indicators; It represents the final weight of the i-th FMCG brand in the J-th first-level indicator, It represents the score of the i-th FMCG brand under the J-th first-level indicator.

9. The holographic diagnosis method for fast-moving consumer goods brands based on deep mining according to claim 7 is characterized in that: The step S7 specifically includes: S7.

1. Calculate the average comprehensive competitiveness scores of FMCG brands in different price segments ; S7.

2. Calculate the standard deviation of the comprehensive competitiveness scores of FMCG brands in different price segments ; S7.3, set the threshold range (50, )、[ , ]and[ , 100), conduct competitiveness assessment of fast-moving consumer goods brands in different price segments, and obtain corresponding assessment results of three types: emerging products, potential products, and leading products.

10. The holographic diagnosis method for fast-moving consumer goods brands based on deep mining according to claim 9 is characterized in that: The step S8 specifically includes: S8.

1. Output brand research and assessment results for target FMCG brands that require diagnosis; S8.

2. Brands with the same research and judgment results as the target FMCG brand in the same price segment are defined as competitors; S8.

3. Compare and analyze the primary indicators of the target FMCG brand and competitors to identify the development shortcomings of the target FMCG brand, and further explore and identify the shortcomings of the secondary indicators.

Images