Customer management method suitable for business operation support system

Abstract

The invention discloses a customer management method suitable for a business operation support system, and relates to the technical field of customer management, and the method comprises the steps: carrying out the calculation and analysis according to the number characteristic coefficients corresponding to different association levels, combining the order data, ordering times and cooperation duration of each customer, and obtaining an important index corresponding to each customer, dividing the clients into high-association-level clients, middle-association-level clients and low-association-level clients according to the association coefficients and the importance indexes corresponding to the clients; according to the method and the system, a clearer customer classification basis is provided for an enterprise through refined division of the customer association levels, so that a more accurate and effective management strategy can be implemented for customers of different association levels, more resources and energy are put into high-value customers, and the pertinence and effectiveness of customer management are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of customer management, and in particular to a customer management method applicable to a business operation support system. Background Art

[0002] In the current highly competitive business environment, effective customer management has become the key for enterprises to gain competitive advantage. The core of customer relationship management is to enhance the interaction between enterprises and customers by understanding and influencing customer behavior. Effective practice requires the integration of people, processes and technology to provide timely and personalized services.

[0003] However, the existing customer management methods lack a fine division of customer association levels, which makes it impossible to accurately identify the importance and business dependence of different customers to the enterprise. There is a lack of in-depth analysis of the changing trend of the number of customers. There is no comprehensive consideration of multiple factors such as customer order data, number of orders, and length of cooperation to evaluate the customer's value, resulting in incomplete and inaccurate customer value assessment. Based on this, a customer management method suitable for business operation support systems is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a customer management method suitable for a business operation support system, which solves the technical problems that the existing customer management methods lack a fine division of customer association levels, resulting in the inability to accurately identify the importance and business dependence of different customers to the enterprise, and lack of in-depth analysis of the changing trend of the number of customers.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A customer management method applicable to a business operation support system comprises the following steps: Step 1: Obtain the customer’s order characteristics, order quantity, cooperation duration, and company data; Step 2: Analyze the customer's order characteristics, order quantity, cooperation duration, and company data, and obtain the corresponding correlation coefficient for each customer based on the analysis results; Step 3: Classify the relevance level of each customer according to the relevance coefficient corresponding to each customer; Step 4: Analyze the number of customers corresponding to each association level in each year within the preset period n, and obtain the characteristic coefficient corresponding to the analysis of customers at each association level, where n is a positive integer, n≥1; Step 5: Based on the quantitative characteristic coefficients corresponding to different correlation levels, combined with each customer's order data, order times and cooperation duration, calculate and analyze to obtain the important index corresponding to each customer; Step 6: According to the correlation coefficient and importance index corresponding to each customer, the customers are divided into high-correlation level customers, medium-correlation level customers and low-correlation level customers.

[0006] As a further solution of the present invention: the specific method of obtaining the correlation coefficient corresponding to each customer is: The company data of the company within the preset period of n years is marked as A, and the order characteristics and cooperation duration BAi and BBi corresponding to each customer within the preset period of n years are obtained. The ratio between the order characteristics of each customer within the preset period of n years and the company data of the company is defined as the company characteristic proportion Ci corresponding to each customer. The ratio between the cooperation duration of each customer within the preset period of n years and the preset period n is defined as the cooperation proportion Di corresponding to each customer. The sum of the products of each customer's company characteristic proportion Ci and the cooperation proportion Di with the preset parameter coefficients θ1 and θ2 is defined as the correlation coefficient Ei corresponding to each customer, where i refers to different customers, i is a positive integer, i=1, 2, ..., a, a is the corresponding number of customers, a≥1, 1=θ1+θ2 and θ1>θ2.

[0007] As a further solution of the present invention: according to the correlation coefficients corresponding to the respective customers, the specific manner of dividing the correlation levels of the respective customers is as follows: The association level when the value of the association coefficient Ei is greater than the limit value Q2 is marked as level one, the association level when the value of the association coefficient Ei is less than or equal to the limit value Q2 and greater than or equal to the limit value Q1 is marked as level two, and the association level when the value of the association coefficient Ei is less than the limit value Q1 is marked as level three. Q1 and Q2 are both preset limit values, Q2>Q1.

[0008] As a further solution of the present invention, the specific method of obtaining the characteristic coefficients corresponding to the customers at each association level is as follows: S1: Obtain the number of customers LAn corresponding to the first-level association level in each year within the preset period n, take the preset period n as the horizontal coordinate, take the number of customers LAn corresponding to the first-level association level in each year within the preset period n as the vertical coordinate, establish a customer quantity change curve corresponding to the first-level association level, and analyze the coordinates of each node on the customer quantity change curve corresponding to the first-level association level to obtain the value of the quantity characteristic coefficient HA corresponding to the first-level association level; S2: The numerical value of the numerical characteristic coefficient HB and the numerical characteristic coefficient HC corresponding to the second-level correlation level and the third-level correlation level are obtained in the same manner as the numerical characteristic coefficient HA corresponding to the first-level correlation level in step S1.

[0009] As a further solution of the present invention, a specific method of establishing a customer quantity change curve corresponding to the first-level association level is as follows: In each data node, the preset number of years n is used as the horizontal axis value, and the number of customers LAn corresponding to each year within the preset number of years n is used as the vertical axis value. Each data node is connected to establish a customer quantity change curve corresponding to the first-level correlation level.

[0010] As a further solution of the present invention: the specific method of obtaining the numerical value of the quantitative characteristic coefficient HA corresponding to the first-level association level is: The ratio between the difference between the ordinate and the difference between the abscissa of each two adjacent data nodes on the customer quantity change curve corresponding to the first-level correlation level is defined as the quantity change coefficient Rh between each two adjacent data nodes on the customer quantity change curve, and the number of positive and negative values ​​Z+ and Z- in the quantity change coefficient Rh is obtained. When Z+ and Z- are both 0, the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level is marked as 0. When Z+ and Z- are both not 0, the absolute value K of the difference between Z+ and Z- is obtained. When K is greater than 0.2h, the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level is marked as 0. When K is less than or equal to 0.2h, the number of values ​​in the quantity change coefficient Rh that meet the preset screening conditions is analyzed, and then the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level is obtained, where h refers to the number of data change coefficients, h=n-1.

[0011] As a further solution of the present invention: the specific method of analyzing the number of values ​​in the quantity variation coefficient Rh that meet the preset screening conditions is: Obtain the number b of values ​​in the quantity change coefficient Rh that meet the preset screening condition: |Rh-Rp|≥Y1. When the number b is greater than the preset threshold value Y2, define the mean Rp of Rp as the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level. When the number b is less than the preset threshold value Y2, define the mean of the maximum and minimum values ​​in Rh as the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level, where Y1 is the preset value, Rp is the mean of Rh and h≥b≥1.

[0012] As a further solution of the present invention: the specific method of obtaining the important index corresponding to each customer is: For customers marked as first-level association level, the formula is: ; Calculate the importance index MAg corresponding to each first-level associated level customer; Wherein, LAg is the order data of customer g within the preset time length T, LBg is the number of orders of customer g within the preset time length T, LAg is the cooperation time of customer g within the preset time length T, LAmax, LBmax and LCmax are respectively the maximum values ​​of the order data, number of orders and cooperation time of all first-level associated level customers within the preset time length T, λ1, λ2 and λ3 are all preset weight coefficients, satisfying 1=λ1+λ2+λ3, and the same method as obtaining the important index MAg corresponding to each first-level associated level customer is adopted to analyze and obtain the important indexes MBg and MCg corresponding to each second-level associated level customer and the third-level associated level customer, wherein g refers to different customers corresponding to each level of association level, and g≥1.

[0013] As a further solution of the present invention, the specific method of classifying customers into high-association-level customers, medium-association-level customers and low-association-level customers is as follows: Preset importance index thresholds E1 and E2, and correlation coefficient thresholds D1 and D2, where E2>E1, D2>D1, and mark customers whose importance index is greater than E2 and whose correlation coefficient is greater than D2 as high-correlation customers; mark customers whose importance index is less than or equal to E2 and greater than or equal to E1, and whose correlation coefficient is less than or equal to D2 and greater than or equal to D1 as medium-correlation customers; and mark customers whose importance index is less than E1 or whose correlation coefficient is less than D1 as low-correlation customers.

[0014] Beneficial effects of the present invention: The present invention, by introducing the correlation coefficient and the important index, comprehensively considers multiple dimensions such as the customer's sales contribution, cooperation duration, order data, order times, etc., so as to more comprehensively evaluate the customer's true value and realize the refined division of customer association levels, which helps enterprises to more clearly identify which customers are the key support for their business development. By segmenting customers by association level, it provides enterprises with a clearer basis for customer classification, so that more accurate and effective management strategies can be implemented for customers of different association levels, and more resources and energy can be invested in high-value customers, thereby improving resource utilization efficiency and enhancing the pertinence and effectiveness of customer management strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] Figure 1 It is a schematic diagram of the framework structure of a customer management method applicable to a business operation support system of the present invention; Figure 2 It is a flow chart of the present invention for classifying customers into high-association-level customers, medium-association-level customers and low-association-level customers. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1: Please refer to Figure 1-Figure 2 As shown, the present invention is a customer management method applicable to a business operation support system, comprising the following steps: Step 1: Obtain the enterprise's customer cooperation data and company data from the database. The customer cooperation data includes the order characteristics, order quantity and cooperation duration of each customer; Step 2: Analyze the customer cooperation data to obtain the corresponding correlation coefficients for each customer. The specific method is as follows: The company data within the preset period of n years is obtained and marked as A, where n refers to the preset period, specifically the period of n years from the moment the data is obtained, and the moment the data is obtained is not included. Specifically, n is a positive integer, 3≥n≥1; Obtain the order characteristics and cooperation duration of each customer within the preset period of n years, and mark them as BAi and BBi, where i refers to different customers, i is a positive integer, i=1, 2, ..., a, a is the number of customers, a≥1; It should be noted that the cooperation duration refers to the time from the first order placed by each customer in the past n years to the acquisition of data; The ratio between the order characteristics of each customer within the preset period n and the company data of the company is defined as the company characteristic proportion Ci corresponding to each customer, that is, Ci=BAi / A. At the same time, the ratio between the cooperation duration of each customer within the preset period n and the preset period n is defined as the cooperation proportion Di corresponding to each customer. The sum of the products of the company characteristic proportion Ci and the cooperation proportion Di of each customer and the preset parameter coefficients θ1 and θ2 is defined as the correlation coefficient Ei corresponding to each customer, that is, Ei=Ci×θ1+Di×θ2, where θ1 and θ2 are both parameter coefficients. The specific values ​​are formulated by relevant personnel according to actual needs, satisfying 1=θ1+θ2 and θ1>θ2; Step 3: Analyze the correlation coefficients corresponding to each customer, and classify the correlation levels of each customer according to the analysis results. The specific method is as follows; Two limit values ​​Q1 and Q2 are preset, where Q2>Q1. The specific values ​​of the limit values ​​Q1 and Q2 are formulated by relevant personnel according to actual needs. The correlation level where the correlation coefficient Ei value is greater than the limit value Q2 is marked as level one, the correlation level where the correlation coefficient Ei value is less than or equal to the limit value Q2 and greater than or equal to the limit value Q1 is marked as level two, and the correlation level where the correlation coefficient Ei value is less than the limit value Q1 is marked as level three; It should be noted that the first-level correlation level is higher than the second-level correlation level, and the second-level correlation level is higher than the third-level correlation level. The higher the correlation level, the more important the corresponding level customer is to the enterprise, and the higher the enterprise's dependence on its business, and vice versa: Step 4: Obtain and analyze the number of customers corresponding to each association level each year within the preset period n, and obtain the characteristic coefficients corresponding to customers of each association level according to the analysis results, in the following specific manner; The number of customers corresponding to the first-level association level, the second-level association level and the third-level association level each year within the preset period of n years is marked as LAn, LBn and LCn respectively; S1: Obtain the number of customers LAn corresponding to the first-level association level in each year within the preset period n; The preset years n is used as the horizontal axis, and the number of customers LAn corresponding to the first-level association level in each of the preset years n is used as the vertical axis, and multiple data nodes corresponding to the first-level association level in the preset years n are obtained. In each data node, the preset years n is used as the horizontal axis value, and the number of customers LAn corresponding to the level in each of the preset years n is used as the vertical axis value. The coordinates of each data node are marked as Rn (n, LAn), and each data node is connected to obtain a customer quantity change curve corresponding to the first-level association level; According to the coordinates Rn (n, LAn) corresponding to each node on the customer quantity change curve corresponding to the first-level association level, the ratio between the ordinate difference and the abscissa difference of each two adjacent data nodes is defined as the quantity change coefficient Rh between each two adjacent data nodes on the customer quantity change curve, where h refers to the number of data change coefficients, h=n-1; Obtain the number of positive and negative values ​​in the coefficient of variation Rh and label them as Z respectively + and Z - , when Z + and Z - When both are 0, it means that the number of customers corresponding to the first-level correlation level does not change with the year, and the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level is marked as 0; When Z + and Z - When both are not 0, Z is obtained.+ and Z - The absolute value K of the difference between them is obtained. When K is greater than 0.2h, the value of the quantitative characteristic coefficient HA corresponding to the first-level association level is marked as 0. When K is less than or equal to 0.2h, the number of values ​​b in the quantitative change coefficient Rh that meet the preset screening condition: |Rh-Rp|≥Y1 is obtained, where Rp is the mean of Rh and h≥b≥1. The number b is compared with the preset threshold value Y2. When the number b is greater than the preset threshold value Y2, it means that the number of values ​​in Rh that meet the preset screening condition is large, and the mean Rp of Rh is representative. Then the mean Rp of Rp is defined as the value of the quantitative characteristic coefficient HA corresponding to the first-level association level. When the number b is less than the preset threshold value Y2, it means that the number of values ​​in Rh that meet the preset screening condition is small, and then the mean of the maximum and minimum values ​​in Rh is defined as the value of the quantitative characteristic coefficient HA corresponding to the first-level association level. That is, HA=(R min +R max ) / 2, where R max and R min They are the maximum and minimum values ​​in Rh, respectively. The specific values ​​of Y1 and Y2 are determined by relevant personnel according to actual needs; S2: In the same manner as the numerical value of the quantitative characteristic coefficient HA corresponding to the first-level association level obtained in step S1, the number of customers corresponding to the second-level association level and the third-level association level in each year within the preset period of n years is analyzed, thereby obtaining the specific numerical values ​​of the quantitative characteristic coefficients HB and HC corresponding to the second-level association level and the third-level association level respectively; Step 5: Based on the quantity characteristic coefficients corresponding to different correlation levels, combined with the order data, order times and cooperation duration of each customer within the preset time, calculate and analyze to obtain the important index corresponding to each customer. The specific method is as follows: For customers who are marked as Level 1 association level; By formula: ; Calculate the importance index MAg corresponding to each first-level associated level customer; Among them, LAg is the order data of customer g within the preset time length T, LBg is the number of orders of customer g within the preset time length T, LAg is the cooperation time of customer g within the preset time length T, LA max , LB max and LC maxThey are the maximum values ​​of order data, order times, and cooperation duration of all first-level associated customers within the preset time T. λ1, λ2, and λ3 are preset weight coefficients, which are set by relevant personnel according to actual conditions and satisfy 1=λ1+λ2+λ3, where g refers to different first-level associated customers, and g≥1; In the same way as obtaining the important index MAg corresponding to each first-level correlation level customer, the important indexes MBg and MCg corresponding to each second-level correlation level customer and the third-level correlation level customer are analyzed and obtained respectively; The higher the importance index of a customer, the greater its contribution to the enterprise's business and the higher the enterprise's dependence on it. Conversely, the lower the importance index of a customer, the less its contribution to the enterprise's business and the lower the enterprise's dependence on it. This helps enterprises to conduct more targeted customer management and resource allocation based on the importance index and improve overall business operation efficiency. The higher the importance index, the higher the value and importance of the customer to the enterprise. Enterprises can formulate corresponding customer management strategies based on the importance index, such as giving priority to meeting the needs of customers with high importance indexes, providing personalized services, and strengthening cooperative relations with these customers, so as to improve customer satisfaction and loyalty and promote the business development of the enterprise. It can comprehensively evaluate the value of customers to the enterprise, which helps enterprises identify which customers are truly high-value customers; Embodiment 2: As Embodiment 2 of the present invention, when the present application is specifically implemented, compared with Embodiment 1, the technical solution of this embodiment is different from that of Embodiment 1 only in that this embodiment further includes Step 6; Step 6: According to the correlation coefficient and importance index corresponding to each customer, the correlation level of each customer is subdivided into high correlation level customers, medium correlation level customers and low correlation level customers, so as to mark the correlation level of each customer. The specific method is as follows: Preset important index thresholds E1 and E2, and correlation coefficient thresholds D1 and D2, where E2>E1, D2>D1, and specific values ​​are formulated by relevant personnel based on actual needs; Customers with an importance index greater than E2 and a correlation coefficient greater than D2 are marked as high-correlation customers; Customers with an importance index less than or equal to E2 and greater than or equal to E1 and a correlation coefficient less than or equal to D2 and greater than or equal to D1 are marked as medium-level customers, and customers with an importance index less than E1 or a correlation coefficient less than D1 are marked as low-level customers; Based on the customer segmentation results, formulate targeted customer management strategies, such as providing personalized services and preferential policies for high-value customers, strengthening communication and interaction, and establishing long-term and stable cooperative relationships; for medium-value customers, pay attention to their demand changes, provide high-quality products and services, and promote the improvement of customer value; for low-value customers, optimize resource allocation, reduce service costs, and look for potential development opportunities; By introducing correlation coefficients and important indexes, the system comprehensively considers multiple dimensions such as customer sales contribution, cooperation duration, order data, order times, etc., so as to more comprehensively evaluate the true value of customers. By defining correlation coefficients and combining preset limit values, it realizes the refined division of customer correlation levels, which helps enterprises to more clearly identify which customers are the key support for their business development. By segmenting customers according to correlation levels, it provides enterprises with a clearer basis for customer classification, so that more accurate and effective management strategies can be implemented for customers of different correlation levels. Based on refined customer classification and value assessment, enterprises can reasonably allocate resources and invest more resources and energy in high-value customers, thereby improving resource utilization efficiency and enhancing the pertinence and effectiveness of customer management strategies, which brings remarkable good results to enterprises. By analyzing the changes in the number of customers and calculating the characteristic coefficients, it can better predict the development trend of customers, take corresponding measures in advance, avoid customer loss, and maintain the stability of the customer base.

[0019] Embodiment 3: As the embodiment 3 of the present invention, when this application is specifically implemented, compared with Embodiment 1 and Embodiment 2, the technical solution of this embodiment is to combine the solutions of the above-mentioned Embodiment 1 and Embodiment 2 for implementation.

[0020] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0021] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A customer management method applicable to a business operation support system, characterized in that: The following steps are involved: Step 1: Obtain the customer’s order characteristics, order quantity, cooperation duration, and company data; Step 2: Analyze the customer's order characteristics, order quantity, cooperation duration, and company data, and obtain the corresponding correlation coefficient for each customer based on the analysis results; Step 3: Classify the relevance level of each customer according to the relevance coefficient corresponding to each customer; Step 4: Analyze the number of customers corresponding to each association level in each year within the preset period n, and obtain the characteristic coefficient corresponding to the analysis of customers at each association level, where n is a positive integer, n≥1; Step 5: Based on the quantitative characteristic coefficients corresponding to different correlation levels, combined with each customer's order data, order times and cooperation duration, calculate and analyze to obtain the important index corresponding to each customer; Step 6: According to the correlation coefficient and importance index corresponding to each customer, the customers are divided into high-correlation level customers, medium-correlation level customers and low-correlation level customers.

2. A customer management method applicable to a business operation support system according to claim 1, characterized in that: The specific method of obtaining the correlation coefficient corresponding to each customer is: The company data of the company within the preset period of n years is marked as A, and the order characteristics and cooperation duration BAi and BBi corresponding to each customer within the preset period of n years are obtained. The ratio between the order characteristics of each customer within the preset period of n years and the company data of the company is defined as the company characteristic proportion Ci corresponding to each customer. The ratio between the cooperation duration of each customer within the preset period of n years and the preset period n is defined as the cooperation proportion Di corresponding to each customer. The sum of the products of each customer's company characteristic proportion Ci and the cooperation proportion Di with the preset parameter coefficients θ1 and θ2 is defined as the correlation coefficient Ei corresponding to each customer, where i refers to different customers, i is a positive integer, i=1, 2, ..., a, a is the corresponding number of customers, a≥1, 1=θ1+θ2 and θ1>θ2.

3. A customer management method applicable to a business operation support system according to claim 2, characterized in that: According to the correlation coefficients corresponding to each customer, the specific way to divide the correlation level of each customer is as follows: The association level when the value of the association coefficient Ei is greater than the limit value Q2 is marked as level one, the association level when the value of the association coefficient Ei is less than or equal to the limit value Q2 and greater than or equal to the limit value Q1 is marked as level two, and the association level when the value of the association coefficient Ei is less than the limit value Q1 is marked as level three. Q1 and Q2 are both preset limit values, Q2>Q1.

4. A customer management method applicable to a business operation support system according to claim 3, characterized in that: The specific method of obtaining the characteristic coefficients corresponding to customers of each association level is as follows: S1: Obtain the number of customers LAn corresponding to the first-level association level in each year within the preset period n, take the preset period n as the horizontal coordinate, take the number of customers LAn corresponding to the first-level association level in each year within the preset period n as the vertical coordinate, establish a customer quantity change curve corresponding to the first-level association level, and analyze the coordinates of each node on the customer quantity change curve corresponding to the first-level association level to obtain the value of the quantity characteristic coefficient HA corresponding to the first-level association level; S2: The numerical value of the numerical characteristic coefficient HB and the numerical characteristic coefficient HC corresponding to the second-level correlation level and the third-level correlation level are obtained in the same manner as the numerical characteristic coefficient HA corresponding to the first-level correlation level in step S1.

5. A customer management method applicable to a business operation support system according to claim 4, characterized in that: The specific method of establishing the customer quantity change curve corresponding to the first-level correlation level is: In each data node, the preset number of years n is used as the horizontal axis value, and the number of customers LAn corresponding to each year within the preset number of years n is used as the vertical axis value. Each data node is connected to establish a customer quantity change curve corresponding to the first-level correlation level.

6. A customer management method applicable to a business operation support system according to claim 5, characterized in that: The specific method of obtaining the numerical characteristic coefficient HA value corresponding to the first-level association level is: The ratio between the difference between the ordinate and the abscissa of each two adjacent data nodes on the customer quantity change curve corresponding to the first-level correlation level is defined as the quantity change coefficient Rh between each two adjacent data nodes on the customer quantity change curve, and the number Z of positive and negative values ​​in the quantity change coefficient Rh is obtained. + and Z - , when Z + and Z - When both are 0, the value of the quantitative characteristic coefficient HA corresponding to the first-level association level is marked as 0. + and Z - When both are not 0, Z is obtained. + and Z - The absolute value K of the difference between them, when K is greater than 0.2h, the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level is marked as 0, when K is less than or equal to 0.2h, the number of values ​​in the quantity change coefficient Rh that meet the preset screening conditions is analyzed, and then the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level is obtained, where h refers to the number of data change coefficients, h=n-1.

7. A customer management method applicable to a business operation support system according to claim 6, characterized in that: The specific method for analyzing the number of values ​​in the quantity variation coefficient Rh that meet the preset screening conditions is as follows: Obtain the number b of values ​​in the quantity change coefficient Rh that meet the preset screening condition: |Rh-Rp|≥Y1. When the number b is greater than the preset threshold value Y2, define the mean Rp of Rp as the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level. When the number b is less than the preset threshold value Y2, define the mean of the maximum and minimum values ​​in Rh as the value of the quantity characteristic coefficient HA corresponding to the first-level correlation level, where Y1 is the preset value, Rp is the mean of Rh and h≥b≥1.

8. A customer management method applicable to a business operation support system according to claim 7, characterized in that: The specific method of obtaining the important indexes corresponding to each customer is as follows: For customers marked as first-level association level, the formula is: ； Calculate the importance index MAg corresponding to each first-level associated level customer; Among them, LAg is the order data of customer g within the preset time length T, LBg is the number of orders of customer g within the preset time length T, LAg is the cooperation time of customer g within the preset time length T, LA max , LB max and LC max are respectively the maximum values ​​of order data, order times and cooperation duration of all first-level association level customers within the preset time T; λ1, λ2 and λ3 are preset weight coefficients, satisfying 1=λ1+λ2+λ3. The same method as that of obtaining the important index MAg corresponding to each first-level association level customer is adopted to analyze and obtain the important indexes MBg and MCg corresponding to each second-level association level customer and the third-level association level customer, where g refers to different customers corresponding to each level of association level, and g≥1.

9. A customer management method applicable to a business operation support system according to claim 8, characterized in that: The specific method of classifying customers into high-relevance customers, medium-relevance customers and low-relevance customers is as follows: Preset importance index thresholds E1 and E2, and correlation coefficient thresholds D1 and D2, where E2>E1, D2>D1, and mark customers whose importance index is greater than E2 and whose correlation coefficient is greater than D2 as high-correlation customers; mark customers whose importance index is less than or equal to E2 and greater than or equal to E1, and whose correlation coefficient is less than or equal to D2 and greater than or equal to D1 as medium-correlation customers; and mark customers whose importance index is less than E1 or whose correlation coefficient is less than D1 as low-correlation customers.

Images