Bee product sales big data analysis management and control system

Abstract

The invention discloses a big data analysis and management and control system for bee product sales, and relates to the technical field of data analysis, the big data analysis and management and control system for bee product sales clusters customers according to characteristics such as purchase behaviors and preferences through a clustering algorithm, in the specific clustering process, key characteristics are selected and standardized, and then the key characteristics are selected; and gradually combining similar clusters by adopting a hierarchical clustering algorithm to finally obtain a clear customer clustering result, ensuring the effectiveness of the clustering, mining an association relationship among different products in bee product sales data through an association rule mining algorithm, and finding out a product combination which is frequently purchased together by calculating indexes such as support degree and confidence, so as to achieve the purpose of improving the quality of the bee product sales data. A basis is provided for product collocation recommendation of enterprises, so that the sales conversion rate is improved, bee product enterprises can be helped to better understand market demands and customer behaviors, sales strategies are optimized, sales efficiency and benefits are improved, and the method has important practical application value.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a bee product sales big data analysis and management system. Background Art

[0002] Honey is a supersaturated solution of nectar and sugar collected and brewed by bees. It is rich in various nutrients such as vitamins, amino acids, phenolic acids and minerals required by the human body. It has high nutritional value and outstanding medical effects. As a nutritious and delicious pure natural substance, it has been highly favored by consumers. The broad market demand has led to the rapid development of the bee product processing industry. Large-scale industrial production models have been developed and established in the fields of honey filtration, concentration, purification, packaging and other deep processing.

[0003] However, in the process of bee product marketing, it is particularly important to judge the current market demand and the possible future demand. Of course, the impact of inventory on bee product marketing is also very important. Good marketing control is the result of cooperation among many departments. Therefore, big data analysis can be used to replace some subjective factors in data analysis operations to avoid some subjective errors. Being closer to market regulation can increase corporate revenue while also enhancing consumers' purchasing desire. Summary of the invention

[0004] The purpose of the present invention is to provide a bee product sales big data analysis and management system to solve the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above-mentioned purpose, the present invention provides the following technical solutions: a bee product sales big data analysis and control system, including a data acquisition module, a data storage module, a data analysis module, a sales control module and a user interaction module:

[0006] The data collection module is used to collect various data related to bee product sales, such as sales order data, customer information data, etc.;

[0007] The data storage module stores the collected data for subsequent analysis and use;

[0008] The data analysis module performs in-depth analysis on the stored data to mine valuable information, including sales trends and customer preferences. The data analysis module clusters customers in the bee product sales data according to their purchasing behavior and preferences, and is also used to evaluate the quality of the clustering results;

[0009] The sales control module controls the sales of bee products based on the analysis results and optimizes the sales strategy;

[0010] The user interaction module provides an interface for users to interact with the system, allowing users to view analysis results and participate in sales management and control decisions.

[0011] Furthermore, the data collection module collects data from online e-commerce platforms and offline store sales data. At the same time, the data collection module also has data cleaning and preprocessing functions to remove noise data and invalid data. Through a variety of data collection methods and data cleaning preprocessing, it provides a reliable data foundation for subsequent data analysis and sales control.

[0012] Furthermore, the data analysis module clusters the customers in the bee product sales data according to their purchasing behavior and preferences, and the specific calculation formula is:

[0013] d{ij}=*sqrt{*sum{k=1}^{n}(x{ik}-y{jk})^2}

[0014] Where di{ij} represents the distance between customer i and customer j, x{ik} represents the value of customer i on feature k, y{jk} represents the value of customer j on feature k, and n is the number of features. By calculating the distance between customers, customers with close distances are clustered into one category.

[0015] Furthermore, before clustering, the data analysis module:

[0016] Firstly, the features in the sales data are selected and extracted, wherein the feature selection includes selecting features closely related to the customer's purchasing behavior and preference, and the feature extraction includes extracting the types of bee products purchased, the purchase frequency, and the purchase amount;

[0017] Then, these features are standardized to make them comparable between different features. The specific calculation formula is:

[0018] x{ik}′=frac{x{ik}-muk}{sigmak}

[0019] Where x{ik}′ represents the standardized eigenvalue, muk is the mean of feature k, and sigmak is the standard deviation of feature k.

[0020] In the clustering process, a hierarchical clustering algorithm is used to gradually merge or split the data into different levels to finally form a clustering result. The hierarchical clustering algorithm is specifically divided into two modes: agglomerative hierarchical clustering and divisive hierarchical clustering. The agglomerative hierarchical clustering starts with each data point as a separate cluster and gradually merges similar clusters. The divisive hierarchical clustering starts with all data points as a cluster and gradually splits into smaller clusters. The specific calculation formula of the agglomerative hierarchical clustering algorithm is:

[0021] d{ij}^l=*frac{1}{2}(d{ij}^{l-1}+d{i′j′}^{l-1})

[0022] Where d{ij}^l represents the distance between customer i and customer j at the lth level, d{ij}^{l-1} represents the distance between customer i and customer j at the l-1th level, and d{i′j′}^{l-1} represents the distance between the two merged clusters at the l-1th level.

[0023] Furthermore, a density-based clustering algorithm is used in the clustering process. The density-based clustering algorithm performs clustering according to the density of data points, divides the area with higher density into a cluster, and divides the area with lower density into a cluster or a noise point. The specific calculation formula is:

[0024] Neighborhood radius = epsilon

[0025] Minimum number of neighbor points = MinPts

[0026] For a data point p, if the number of points in its neighborhood is greater than or equal to MinPts, then p is a core point; if p is in the neighborhood of a core point, then p is a density-reachable point; otherwise, p is a noise point.

[0027] Furthermore, the data analysis module evaluates the quality of the clustering results by using the silhouette coefficient, which is a value between -1 and 1. The specific calculation formula is:

[0028] a(i)=*frac{1}{mi-1}*sum{j*neqi}*min(d{ij}, d{ik})

[0029] b(i)=*frac{1}{m-mi}*sum{j*inC*setminusi}d{ij}

[0030] s(i)=*frac{b(i)-a(i)}{*max(a(i),b(i)))

[0031] Where a(i) represents the average distance between sample i and other samples in its cluster, b(i) represents the average distance between sample i and samples in other clusters, mi is the number of samples in the cluster where sample i is located, m is the total number of samples, and C is the set of all clusters.

[0032] Furthermore, the mining algorithm in the data analysis module is also used to mine the association relationship between different products in the bee product sales data, and the specific steps include:

[0033] S1, collecting bee product sales data through a data collection algorithm, and preliminarily classifying and marking the collected data, wherein the bee product sales data includes sales records of honey, sales records of propolis, and sales records of bee pollen, covering different sales channels, different sales time periods, and corresponding customer information;

[0034] S2, data preprocessing stage, data cleaning, removal of noise data, duplicate data and outliers, and normalization and standardization of data, so that sales data of different products can be compared on the same scale;

[0035] S3, mining association relationships: based on the clustering algorithm in the data analysis module, different bee products are clustered according to the characteristics of sales data;

[0036] S4, evaluate the commercial value of the relationship between different products, including the following steps:

[0037] S41, Sales Growth Potential Assessment: Assess sales growth potential by comparing the sales growth rate of a portfolio of related products over different time periods with the sales growth rate of a single product;

[0038] S42, Customer Loyalty Improvement Assessment: Customer loyalty is measured by the frequency and proportion of customers repeatedly purchasing related products;

[0039] S43, Market expansion opportunity assessment: Determine the sales and potential of related products in different market segments through market research and data analysis. Study the performance of related products in different market segments or customer groups and assess their market expansion opportunities.

[0040] Compared with the prior art, the present invention provides a bee product sales big data analysis and management system. By clustering customers according to characteristics such as purchasing behavior and preferences through a clustering algorithm, enterprises can better understand the characteristics and needs of different customer groups. In the specific clustering process, key features are first selected and standardized, and then a hierarchical clustering algorithm is used to gradually merge similar clusters to finally obtain a clear customer clustering result. The quality of the clustering result can be evaluated by the silhouette coefficient to ensure the effectiveness of the clustering. At the same time, the association relationship between different products in the bee product sales data is mined through an association rule mining algorithm. By calculating indicators such as support and confidence, product combinations that are often purchased together are found, providing a basis for the company's product pairing recommendations, thereby improving sales conversion rate. It can help bee product companies better understand market demand and customer behavior, optimize sales strategies, and improve sales efficiency and benefits. It has important practical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0042] Figure 1 A system structure block diagram provided for an embodiment of the present invention;

[0043] Figure 2 A system block diagram of a data analysis module for performing association analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0045] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0046] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0047] Example embodiments will be described more fully below with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, the purpose of providing these embodiments is to make the present disclosure thorough and complete and to enable those skilled in the art to fully understand the scope of the present disclosure.

[0048] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0049] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0050] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded.

[0051] The embodiments described herein may be described with reference to plan views and / or cross-sectional views by means of idealized schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings have schematic properties, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the elements, but are not intended to be limiting.

[0052] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.

[0053] See also Figure 1 , a bee product sales big data analysis and management system, including a data acquisition module, a data storage module, a data analysis module, a sales management module and a user interaction module:

[0054] The data collection module is used to collect various data related to bee product sales, such as sales order data, customer information data, etc.;

[0055] The data storage module stores the collected data for subsequent analysis and use;

[0056] The data analysis module conducts in-depth analysis on the stored data to mine valuable information, including sales trends and customer preferences. The data analysis module clusters the customers in the bee product sales data according to their purchasing behavior and preferences. The data analysis module is also used to evaluate the quality of the clustering results.

[0057] The sales control module controls the sales of bee products based on the analysis results and optimizes the sales strategy;

[0058] The user interaction module provides an interface for users to interact with the system, allowing users to view analysis results and participate in sales management and decision-making. Through the collaborative work of various modules, the system realizes comprehensive big data analysis and effective management and control of bee product sales.

[0059] The data collection module collects data from online e-commerce platforms and offline store sales data to ensure that the collected data is comprehensive and accurate. At the same time, the data collection module also has data cleaning and preprocessing functions to remove noise data and invalid data and improve data quality. Through a variety of data collection methods and data cleaning preprocessing, a reliable data foundation is provided for subsequent data analysis and sales control.

[0060] The data collection module collects data related to bee product sales in a variety of ways, including order data and customer evaluation data from online e-commerce platforms, sales data from offline stores, customer information data, etc. These data are cleaned and preprocessed to remove noise and invalid data, ensuring data quality and accuracy.

[0061] The data storage module stores the collected data and uses distributed database technology to efficiently store and manage large-scale sales data. The data analysis module uses various data analysis algorithms to conduct in-depth analysis of the stored data and mine valuable information.

[0062] Clustering algorithms are an important part of data analysis. By clustering customers according to characteristics such as purchasing behavior and preferences, companies can better understand the characteristics and needs of different customer groups. For example, in the specific clustering process, key features are first selected and standardized, and then a hierarchical clustering algorithm is used to gradually merge similar clusters to finally obtain clear customer clustering results. The density-based clustering algorithm (DBSCAN) can better handle noisy data and irregularly shaped clusters. The silhouette coefficient can be used to evaluate the quality of clustering results and ensure the effectiveness of clustering.

[0063] The association rule mining algorithm is used to mine the associations between different products in the bee product sales data. By calculating indicators such as support and confidence, it finds out the product combinations that are often purchased together, providing a basis for the company's product pairing recommendations, thereby improving sales conversion rates.

[0064] The sales control module monitors and controls the sales of bee products in real time based on the results of data analysis. For example, it adjusts product inventory and formulates personalized promotion strategies according to the needs of different customer groups. The user interaction module provides a friendly interface that allows users to easily view analysis results and participate in sales control decisions, improving the ease of use of the system and user satisfaction.

[0065] The data analysis module clusters the customers in the bee product sales data according to their purchasing behavior and preferences. The specific calculation formula is:

[0066] d{ij}=*sqrt{*sum{k=1}^{n}(x{ik}-y{jk})^2}

[0067] Where di{ij} represents the distance between customer i and customer j, x{ik} represents the value of customer i on feature k, y{jk} represents the value of customer j on feature k, and n is the number of features. By calculating the distance between customers, customers with close distances are clustered into one category. This clustering algorithm can help companies better understand the characteristics and needs of different customer groups and provide a basis for precision marketing.

[0068] Before clustering, the data analysis module:

[0069] First, the features in the sales data are selected and extracted. Feature selection includes selecting features that are closely related to customer purchasing behavior and preferences, and feature extraction includes extracting the types of bee products purchased, purchase frequency, and purchase amount.

[0070] Then, these features are standardized to make them comparable between different features. The specific calculation formula is:

[0071] x{ik}′=frac{x{ik}-muk}{sigmak}

[0072] Where x{ik}′ represents the standardized feature value, muk is the mean of feature k, and sigmak is the standard deviation of feature k. Through standardization, the dimensional differences between different features can be eliminated and the accuracy of clustering can be improved.

[0073] In the clustering process, a hierarchical clustering algorithm is used to gradually merge or split the data into different levels to finally form a clustering result. The hierarchical clustering algorithm is specifically divided into two methods: agglomerative hierarchical clustering and divisive hierarchical clustering. Agglomerative hierarchical clustering starts with each data point as a separate cluster and gradually merges similar clusters. Divisive hierarchical clustering starts with all data points as a cluster and gradually splits them into smaller clusters. The specific calculation formula of the agglomerative hierarchical clustering algorithm is:

[0074] d{ij}^l=*frac{1}{2}((d{ij}^{l-1}+d{i′j′}^{l-1})

[0075] Where d{ij}^l represents the distance between customer i and customer j at level l, d{ij}^{l-1} represents the distance between customer i and customer j at level l-1, and d{i′j′}^{l-1} represents the distance between two merged clusters at level l-1. By continuously merging similar clusters, we can finally get the clustering result.

[0076] In order to improve the efficiency and accuracy of clustering during the clustering process, a density-based clustering algorithm is used. The density-based clustering algorithm clusters according to the density of data points, divides the area with higher density into a cluster, and the area with lower density is treated as a cluster or noise point. The specific calculation formula is:

[0077] Neighborhood radius = epsilon

[0078] Minimum number of neighbor points = MinPts

[0079] For a data point p, if the number of points in its neighborhood is greater than or equal to MinPts, then p is a core point; if p is in the neighborhood of a core point, then p is a density-reachable point; otherwise, p is a noise point. The density-based clustering algorithm can better handle noisy data and irregularly shaped clusters.

[0080] The data analysis module evaluates the quality of clustering results using the silhouette coefficient, which is a value between -1 and 1 and is used to measure the compactness and separation of clusters. The specific calculation formula is:

[0081] a((i)=*frac{1}{mi-1}*Sum{j*neqi}*min(d{ij},d{ik})

[0082] b(i)=*frac{1}{m-mi}*sum{j*inC*setminusi}d{ij}

[0083] s(i)=*frac{b(i)-a(i)}{*max(a(i),b(i))}

[0084] Where a(i) represents the average distance between sample i and other samples in its cluster, b(i) represents the average distance between sample i and samples in other clusters, mi represents the number of samples in the cluster where sample i is located, m represents the total number of samples, and C represents the set of all clusters. The closer the silhouette coefficient is to 1, the better the clustering effect is; the closer it is to -1, the worse the clustering effect is.

[0085] See Figure 2As shown, the mining algorithm in the data analysis module is also used to mine the association relationship between different products in the bee product sales data. The specific steps include:

[0086] S1, collect bee product sales data through data collection algorithms, and preliminarily classify and mark the collected data, so that different types of bee products can be analyzed more accurately during the mining process. The bee product sales data includes sales records of honey, propolis, and bee pollen, covering different sales channels (online e-commerce platforms, offline physical stores, etc.), different sales time periods (day, week, month, season, etc.) and corresponding customer information;

[0087] S2, data preprocessing stage, data cleaning, removal of noise data, duplicate data and outliers. For example, the incorrect price or quantity information that may appear in some sales records is corrected to ensure the quality of the data, and the data is normalized and standardized so that the sales data of different products can be compared on the same scale to avoid the impact of data magnitude differences on the mining of associations:

[0088] S3, mining association relationships: based on the clustering algorithm in the data analysis module, different bee products are clustered according to the characteristics of sales data;

[0089] S4, evaluate the commercial value of the relationship between different products, including the following steps:

[0090] S41, Sales growth potential assessment: Evaluate sales growth potential by comparing the sales growth rate of the associated product portfolio in different time periods with the sales growth rate of individual products; analyze the sales growth trend of the associated product portfolio. If it is found that the association of certain bee products with other products leads to significantly higher sales growth than when these products are sold separately, then this association has a higher sales growth potential. For example, propolis, which originally had poor sales, saw rapid overall sales growth after being sold in association with honey, indicating that the association between the two is of great value in promoting sales.

[0091] S42, Customer Loyalty Improvement Evaluation: Measure customer loyalty by the frequency and proportion of customers repeatedly purchasing related products; observe whether the purchase of related products can increase customer loyalty. If customers are more inclined to purchase other related products at the same time after purchasing a bee product, it means that this association helps to improve customer loyalty. For example, customers who buy honey are more likely to continue to buy propolis, which shows that the association between honey and propolis has a positive impact on customer loyalty.

[0092] S43, Market expansion opportunity assessment: Determine the sales situation and potential of related products in different market segments through market research and data analysis. Study the performance of related products in different market segments or customer groups and evaluate their market expansion opportunities. If some related products show strong associations in specific customer groups or market segments, but not in other groups, then these specific markets can be expanded. For example, the associated sales of honey and royal jelly are very good in the middle-aged and elderly customer groups, but not in the young customer groups, which provides a basis for expansion in the middle-aged and elderly market.

[0093] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A bee product sales big data analysis and management system, characterized by: Including data collection module, data storage module, data analysis module, sales control module and user interaction module: The data collection module is used to collect various data related to bee product sales, such as sales order data, customer information data, etc.; The data storage module stores the collected data for subsequent analysis and use; The data analysis module performs in-depth analysis on the stored data to mine valuable information, including sales trends and customer preferences. The data analysis module clusters customers in the bee product sales data according to their purchasing behavior and preferences, and is also used to evaluate the quality of the clustering results; The sales control module controls the sales of bee products based on the analysis results and optimizes the sales strategy; The user interaction module provides an interface for users to interact with the system, allowing users to view analysis results and participate in sales management and control decisions.

2. A bee product sales big data analysis and management system according to claim 1, characterized in that: The data collection module collects data from online e-commerce platforms and offline store sales data. At the same time, the data collection module also has data cleaning and preprocessing functions to remove noise data and invalid data. Through a variety of data collection methods and data cleaning preprocessing, it provides a reliable data foundation for subsequent data analysis and sales control.

3. The bee product sales big data analysis and management system according to claim 1, characterized in that: The data analysis module clusters the customers in the bee product sales data according to their purchasing behavior and preferences. The specific calculation formula is: d{ij}=*sqrt{*sum{k=1}∧{n}(x{ik}-y{jk})∧2} Where di{ij} represents the distance between customer i and customer j, x{ik} represents the value of customer i on feature k, y{jk} represents the value of customer j on feature k, and n is the number of features. By calculating the distance between customers, customers with close distances are clustered into one category.

4. The bee product sales big data analysis and management system according to claim 1, characterized in that: Before clustering, the data analysis module: Firstly, the features in the sales data are selected and extracted, wherein the feature selection includes selecting features closely related to the customer's purchasing behavior and preference, and the feature extraction includes extracting the types of bee products purchased, the purchase frequency, and the purchase amount; Then, these features are standardized to make them comparable between different features. The specific calculation formula is: x{ik}′=frac{x{ik}-muk}{sigmak} Where x{ik}′ represents the standardized eigenvalue, muk is the mean of feature k, and sigmak is the standard deviation of feature k; In the clustering process, a hierarchical clustering algorithm is used to gradually merge or split the data into different levels to finally form a clustering result. The hierarchical clustering algorithm is specifically divided into two modes: agglomerative hierarchical clustering and divisive hierarchical clustering. The agglomerative hierarchical clustering starts with each data point as a separate cluster and gradually merges similar clusters. The divisive hierarchical clustering starts with all data points as a cluster and gradually splits into smaller clusters. The specific calculation formula of the agglomerative hierarchical clustering algorithm is: d{ij}∧1=*frac{1}{2}(d{ij}∧{l-1}+d{i′j′}∧{l-1}) Where d{ij}∧l represents the distance between customer i and customer j at the first level, d{ij}∧{l-1} represents the distance between customer i and customer j at the l-1 level, and d{i′j′}∧{l-1} represents the distance between the two merged clusters at the l-1 level.

5. A bee product sales big data analysis and management system according to claim 4, characterized in that: The clustering process adopts a density-based clustering algorithm. The density-based clustering algorithm performs clustering according to the density of data points, divides the area with higher density into a cluster, and divides the area with lower density into a cluster or noise point. The specific calculation formula is: Neighborhood radius = epsilon Minimum number of neighbor points = MinPts For a data point p, if the number of points in its neighborhood is greater than or equal to MinPts, then p is a core point; if p is in the neighborhood of a core point, then p is a density-reachable point; otherwise, p is a noise point.

6. A bee product sales big data analysis and management system according to claim 5, characterized in that: The data analysis module evaluates the quality of the clustering results by using the silhouette coefficient, which is a value between -1 and 1. The specific calculation formula is: a(i)=*frac{1}{mi-1}*sum{j*neqi}*min(d{ij}, d{ik}) b(i)=*frac{1}{m-mi}*sum{j*inC*setminusi}d{ij} s(i)=*frac{b(i)-a(i)}{*max(a(i),b(i))} Where a(i) represents the average distance between sample i and other samples in its cluster, b(i) represents the average distance between sample i and samples in other clusters, mi is the number of samples in the cluster where sample i is located, m is the total number of samples, and C is the set of all clusters.

7. A bee product sales big data analysis and management system according to claim 6, characterized in that: The mining algorithm in the data analysis module is also used to mine the association relationship between different products in the bee product sales data. The specific steps include: S1, collect bee product sales data through data collection algorithm, and preliminarily classify and mark the collected data, the bee product sales data includes honey sales records, propolis sales records, bee pollen sales records, covering different sales channels, different sales time periods and corresponding customer information - S2, data preprocessing stage, data cleaning, removal of noise data, duplicate data and outliers, and normalization and standardization of data, so that sales data of different products can be compared on the same scale; S3, mining association relationships: based on the clustering algorithm in the data analysis module, different bee products are clustered according to the characteristics of sales data; S4, evaluate the commercial value of the relationship between different products, including the following steps: S41, Sales Growth Potential Assessment: Assess sales growth potential by comparing the sales growth rate of a portfolio of related products over different time periods with the sales growth rate of a single product; S42, Customer Loyalty Improvement Assessment: Customer loyalty is measured by the frequency and proportion of customers repeatedly purchasing related products; S43, Market expansion opportunity assessment: Determine the sales status and potential of related products in different market segments through market research and data analysis, study the performance of related products in different market segments or customer groups, and evaluate their opportunities for market expansion.

Images